Upload folder using huggingface_hub

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: other
+base_model: NousResearch/Meta-Llama-3-8B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft
+
+This model is a fine-tuned version of [NousResearch/Meta-Llama-3-8B-Instruct](https://huggingface.co/NousResearch/Meta-Llama-3-8B-Instruct) on the identity and the labor20240807 datasets.
+It achieves the following results on the evaluation set:
+- Loss: 1.1235
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 12.0
+
+### Training results
+
+| Training Loss | Epoch   | Step | Validation Loss |
+|:-------------:|:-------:|:----:|:---------------:|
+| 0.9225        | 3.6331  | 1000 | 1.1293          |
+| 0.7145        | 7.2661  | 2000 | 1.1055          |
+| 0.6401        | 10.8992 | 3000 | 1.1234          |
+
+
+### Framework versions
+
+- Transformers 4.44.2
+- Pytorch 2.4.1+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 11.989100817438691,
+    "eval_loss": 1.1235156059265137,
+    "eval_runtime": 10.55,
+    "eval_samples_per_second": 23.223,
+    "eval_steps_per_second": 23.223,
+    "total_flos": 3.144153968877896e+17,
+    "train_loss": 0.880180758562955,
+    "train_runtime": 3585.8754,
+    "train_samples_per_second": 7.369,
+    "train_steps_per_second": 0.92
+}

checkpoint-3300/config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-3300/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

checkpoint-3300/model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce8310054018ee51b78299d3d660d133731acacca439d5c43ac36a22021a4a1
+size 4976698672

checkpoint-3300/model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f6cbceea7eee5ecca69f4e97863818b1850d40e1c0b9d27f0a13af55ed0380
+size 4999802720

checkpoint-3300/model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3154807ed0c4bf3fcc841323e69c082c60b8e1d12779c1e8d363dc8eb986519
+size 4915916176

checkpoint-3300/model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa64f16e7b8a8f83d11ef628f49a1d6986b67729c41b08bd03a8e5788a215fd6
+size 1168138808

checkpoint-3300/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-3300/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043bb3427e47a8e55c513c150c7b0ff4c9a1f5266a54719c93ba405940876832
+size 1744904195

checkpoint-3300/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5328f04f222a66b45931d6bc246721e0747decf9d78d167903d0547a248f78f0
+size 14244

checkpoint-3300/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b5ce95da8b1f2b5b24d133763d92b0b36b11c87b0d99042ec4fafad2db811c4c
+size 1064

checkpoint-3300/special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-3300/tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-3300/trainer_state.json

@@ -0,0 +1,2367 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.989100817438691,
+  "eval_steps": 1000,
+  "global_step": 3300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03633060853769301,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.0303030303030305e-07,
+      "loss": 2.0607,
+      "step": 10
+    },
+    {
+      "epoch": 0.07266121707538602,
+      "grad_norm": 5.90625,
+      "learning_rate": 6.060606060606061e-07,
+      "loss": 2.033,
+      "step": 20
+    },
+    {
+      "epoch": 0.10899182561307902,
+      "grad_norm": 5.46875,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 2.0622,
+      "step": 30
+    },
+    {
+      "epoch": 0.14532243415077203,
+      "grad_norm": 4.96875,
+      "learning_rate": 1.2121212121212122e-06,
+      "loss": 1.9896,
+      "step": 40
+    },
+    {
+      "epoch": 0.18165304268846502,
+      "grad_norm": 15.625,
+      "learning_rate": 1.5151515151515152e-06,
+      "loss": 1.9998,
+      "step": 50
+    },
+    {
+      "epoch": 0.21798365122615804,
+      "grad_norm": 18.0,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.9608,
+      "step": 60
+    },
+    {
+      "epoch": 0.254314259763851,
+      "grad_norm": 15.625,
+      "learning_rate": 2.1212121212121216e-06,
+      "loss": 1.9272,
+      "step": 70
+    },
+    {
+      "epoch": 0.29064486830154407,
+      "grad_norm": 15.5625,
+      "learning_rate": 2.4242424242424244e-06,
+      "loss": 1.9031,
+      "step": 80
+    },
+    {
+      "epoch": 0.32697547683923706,
+      "grad_norm": 14.1875,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.8012,
+      "step": 90
+    },
+    {
+      "epoch": 0.36330608537693004,
+      "grad_norm": 3.421875,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 1.7756,
+      "step": 100
+    },
+    {
+      "epoch": 0.3996366939146231,
+      "grad_norm": 3.09375,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.6836,
+      "step": 110
+    },
+    {
+      "epoch": 0.4359673024523161,
+      "grad_norm": 2.46875,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.7013,
+      "step": 120
+    },
+    {
+      "epoch": 0.47229791099000906,
+      "grad_norm": 2.859375,
+      "learning_rate": 3.93939393939394e-06,
+      "loss": 1.6328,
+      "step": 130
+    },
+    {
+      "epoch": 0.508628519527702,
+      "grad_norm": 2.6875,
+      "learning_rate": 4.242424242424243e-06,
+      "loss": 1.6888,
+      "step": 140
+    },
+    {
+      "epoch": 0.5449591280653951,
+      "grad_norm": 2.828125,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.6583,
+      "step": 150
+    },
+    {
+      "epoch": 0.5812897366030881,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.848484848484849e-06,
+      "loss": 1.5485,
+      "step": 160
+    },
+    {
+      "epoch": 0.6176203451407811,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.151515151515152e-06,
+      "loss": 1.5464,
+      "step": 170
+    },
+    {
+      "epoch": 0.6539509536784741,
+      "grad_norm": 2.25,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.5506,
+      "step": 180
+    },
+    {
+      "epoch": 0.6902815622161671,
+      "grad_norm": 2.4375,
+      "learning_rate": 5.7575757575757586e-06,
+      "loss": 1.5301,
+      "step": 190
+    },
+    {
+      "epoch": 0.7266121707538601,
+      "grad_norm": 2.4375,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 1.5116,
+      "step": 200
+    },
+    {
+      "epoch": 0.7629427792915532,
+      "grad_norm": 2.609375,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 1.4874,
+      "step": 210
+    },
+    {
+      "epoch": 0.7992733878292462,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5056,
+      "step": 220
+    },
+    {
+      "epoch": 0.8356039963669392,
+      "grad_norm": 2.21875,
+      "learning_rate": 6.969696969696971e-06,
+      "loss": 1.5036,
+      "step": 230
+    },
+    {
+      "epoch": 0.8719346049046321,
+      "grad_norm": 2.359375,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.4625,
+      "step": 240
+    },
+    {
+      "epoch": 0.9082652134423251,
+      "grad_norm": 1.921875,
+      "learning_rate": 7.5757575757575764e-06,
+      "loss": 1.4439,
+      "step": 250
+    },
+    {
+      "epoch": 0.9445958219800181,
+      "grad_norm": 2.265625,
+      "learning_rate": 7.87878787878788e-06,
+      "loss": 1.4025,
+      "step": 260
+    },
+    {
+      "epoch": 0.9809264305177112,
+      "grad_norm": 2.609375,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 1.4267,
+      "step": 270
+    },
+    {
+      "epoch": 1.017257039055404,
+      "grad_norm": 1.84375,
+      "learning_rate": 8.484848484848486e-06,
+      "loss": 1.3484,
+      "step": 280
+    },
+    {
+      "epoch": 1.0535876475930972,
+      "grad_norm": 2.0,
+      "learning_rate": 8.787878787878788e-06,
+      "loss": 1.3809,
+      "step": 290
+    },
+    {
+      "epoch": 1.0899182561307903,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.3901,
+      "step": 300
+    },
+    {
+      "epoch": 1.1262488646684832,
+      "grad_norm": 1.8984375,
+      "learning_rate": 9.393939393939396e-06,
+      "loss": 1.3203,
+      "step": 310
+    },
+    {
+      "epoch": 1.1625794732061763,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.696969696969698e-06,
+      "loss": 1.3295,
+      "step": 320
+    },
+    {
+      "epoch": 1.1989100817438691,
+      "grad_norm": 1.9140625,
+      "learning_rate": 1e-05,
+      "loss": 1.3936,
+      "step": 330
+    },
+    {
+      "epoch": 1.2352406902815622,
+      "grad_norm": 2.5,
+      "learning_rate": 9.999720280459576e-06,
+      "loss": 1.3483,
+      "step": 340
+    },
+    {
+      "epoch": 1.2715712988192553,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.99888115313551e-06,
+      "loss": 1.3384,
+      "step": 350
+    },
+    {
+      "epoch": 1.3079019073569482,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.997482711915926e-06,
+      "loss": 1.2888,
+      "step": 360
+    },
+    {
+      "epoch": 1.344232515894641,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.99552511326936e-06,
+      "loss": 1.3144,
+      "step": 370
+    },
+    {
+      "epoch": 1.3805631244323342,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.993008576227248e-06,
+      "loss": 1.2905,
+      "step": 380
+    },
+    {
+      "epoch": 1.4168937329700273,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.989933382359423e-06,
+      "loss": 1.2816,
+      "step": 390
+    },
+    {
+      "epoch": 1.4532243415077202,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.986299875742612e-06,
+      "loss": 1.3315,
+      "step": 400
+    },
+    {
+      "epoch": 1.4895549500454133,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.982108462921938e-06,
+      "loss": 1.2984,
+      "step": 410
+    },
+    {
+      "epoch": 1.5258855585831061,
+      "grad_norm": 2.765625,
+      "learning_rate": 9.977359612865424e-06,
+      "loss": 1.2677,
+      "step": 420
+    },
+    {
+      "epoch": 1.5622161671207992,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.972053856911534e-06,
+      "loss": 1.3098,
+      "step": 430
+    },
+    {
+      "epoch": 1.5985467756584923,
+      "grad_norm": 1.84375,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 1.3503,
+      "step": 440
+    },
+    {
+      "epoch": 1.6348773841961854,
+      "grad_norm": 2.609375,
+      "learning_rate": 9.959774064153977e-06,
+      "loss": 1.3301,
+      "step": 450
+    },
+    {
+      "epoch": 1.6712079927338783,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.952801401309504e-06,
+      "loss": 1.2454,
+      "step": 460
+    },
+    {
+      "epoch": 1.7075386012715712,
+      "grad_norm": 1.8515625,
+      "learning_rate": 9.945274580332316e-06,
+      "loss": 1.239,
+      "step": 470
+    },
+    {
+      "epoch": 1.7438692098092643,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.937194443381972e-06,
+      "loss": 1.2823,
+      "step": 480
+    },
+    {
+      "epoch": 1.7801998183469574,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.928561894527354e-06,
+      "loss": 1.2774,
+      "step": 490
+    },
+    {
+      "epoch": 1.8165304268846503,
+      "grad_norm": 2.15625,
+      "learning_rate": 9.919377899645497e-06,
+      "loss": 1.2215,
+      "step": 500
+    },
+    {
+      "epoch": 1.8528610354223434,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.909643486313533e-06,
+      "loss": 1.2509,
+      "step": 510
+    },
+    {
+      "epoch": 1.8891916439600362,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.899359743693715e-06,
+      "loss": 1.2656,
+      "step": 520
+    },
+    {
+      "epoch": 1.9255222524977293,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.888527822411543e-06,
+      "loss": 1.186,
+      "step": 530
+    },
+    {
+      "epoch": 1.9618528610354224,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.877148934427037e-06,
+      "loss": 1.2468,
+      "step": 540
+    },
+    {
+      "epoch": 1.9981834695731153,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 1.2471,
+      "step": 550
+    },
+    {
+      "epoch": 2.034514078110808,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.85275541204318e-06,
+      "loss": 1.1688,
+      "step": 560
+    },
+    {
+      "epoch": 2.0708446866485013,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.839743506981783e-06,
+      "loss": 1.1216,
+      "step": 570
+    },
+    {
+      "epoch": 2.1071752951861944,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.826190093588564e-06,
+      "loss": 1.1333,
+      "step": 580
+    },
+    {
+      "epoch": 2.1435059037238875,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.812096688325354e-06,
+      "loss": 1.1148,
+      "step": 590
+    },
+    {
+      "epoch": 2.1798365122615806,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 1.1331,
+      "step": 600
+    },
+    {
+      "epoch": 2.2161671207992732,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.78229626995238e-06,
+      "loss": 1.1931,
+      "step": 610
+    },
+    {
+      "epoch": 2.2524977293369663,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.766592591146353e-06,
+      "loss": 1.146,
+      "step": 620
+    },
+    {
+      "epoch": 2.2888283378746594,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.750355588704728e-06,
+      "loss": 1.1397,
+      "step": 630
+    },
+    {
+      "epoch": 2.3251589464123525,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.733587079350254e-06,
+      "loss": 1.0941,
+      "step": 640
+    },
+    {
+      "epoch": 2.3614895549500456,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.716288939274818e-06,
+      "loss": 1.101,
+      "step": 650
+    },
+    {
+      "epoch": 2.3978201634877383,
+      "grad_norm": 2.703125,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 1.0632,
+      "step": 660
+    },
+    {
+      "epoch": 2.4341507720254314,
+      "grad_norm": 2.5625,
+      "learning_rate": 9.680111567808212e-06,
+      "loss": 1.1315,
+      "step": 670
+    },
+    {
+      "epoch": 2.4704813805631245,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.66123638422413e-06,
+      "loss": 1.0989,
+      "step": 680
+    },
+    {
+      "epoch": 2.5068119891008176,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.641839665080363e-06,
+      "loss": 1.0829,
+      "step": 690
+    },
+    {
+      "epoch": 2.5431425976385107,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.621923580633462e-06,
+      "loss": 1.1155,
+      "step": 700
+    },
+    {
+      "epoch": 2.5794732061762033,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.601490359250616e-06,
+      "loss": 1.1248,
+      "step": 710
+    },
+    {
+      "epoch": 2.6158038147138964,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.580542287160348e-06,
+      "loss": 1.1391,
+      "step": 720
+    },
+    {
+      "epoch": 2.6521344232515895,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.559081708196696e-06,
+      "loss": 1.0538,
+      "step": 730
+    },
+    {
+      "epoch": 2.688465031789282,
+      "grad_norm": 1.953125,
+      "learning_rate": 9.537111023536973e-06,
+      "loss": 1.055,
+      "step": 740
+    },
+    {
+      "epoch": 2.7247956403269757,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.514632691433108e-06,
+      "loss": 1.1769,
+      "step": 750
+    },
+    {
+      "epoch": 2.7611262488646684,
+      "grad_norm": 2.609375,
+      "learning_rate": 9.491649226936586e-06,
+      "loss": 1.0949,
+      "step": 760
+    },
+    {
+      "epoch": 2.7974568574023615,
+      "grad_norm": 1.9609375,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 1.1308,
+      "step": 770
+    },
+    {
+      "epoch": 2.8337874659400546,
+      "grad_norm": 1.953125,
+      "learning_rate": 9.444177243274619e-06,
+      "loss": 1.1283,
+      "step": 780
+    },
+    {
+      "epoch": 2.8701180744777472,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.419694035645753e-06,
+      "loss": 1.0907,
+      "step": 790
+    },
+    {
+      "epoch": 2.9064486830154403,
+      "grad_norm": 1.5,
+      "learning_rate": 9.394716318103098e-06,
+      "loss": 1.1043,
+      "step": 800
+    },
+    {
+      "epoch": 2.9427792915531334,
+      "grad_norm": 2.3125,
+      "learning_rate": 9.369246885348926e-06,
+      "loss": 1.0676,
+      "step": 810
+    },
+    {
+      "epoch": 2.9791099000908265,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.343288587102444e-06,
+      "loss": 1.0642,
+      "step": 820
+    },
+    {
+      "epoch": 3.0154405086285196,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.316844327780955e-06,
+      "loss": 1.0437,
+      "step": 830
+    },
+    {
+      "epoch": 3.0517711171662127,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.289917066174887e-06,
+      "loss": 0.9874,
+      "step": 840
+    },
+    {
+      "epoch": 3.0881017257039054,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.262509815116732e-06,
+      "loss": 0.9582,
+      "step": 850
+    },
+    {
+      "epoch": 3.1244323342415985,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.234625641143962e-06,
+      "loss": 0.9471,
+      "step": 860
+    },
+    {
+      "epoch": 3.1607629427792916,
+      "grad_norm": 2.015625,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 0.9424,
+      "step": 870
+    },
+    {
+      "epoch": 3.1970935513169847,
+      "grad_norm": 1.625,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.972,
+      "step": 880
+    },
+    {
+      "epoch": 3.2334241598546773,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.148143045440181e-06,
+      "loss": 0.9729,
+      "step": 890
+    },
+    {
+      "epoch": 3.2697547683923704,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.118382907149164e-06,
+      "loss": 0.9558,
+      "step": 900
+    },
+    {
+      "epoch": 3.3060853769300635,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.088161971988517e-06,
+      "loss": 0.9518,
+      "step": 910
+    },
+    {
+      "epoch": 3.3424159854677566,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.057483621312671e-06,
+      "loss": 0.9694,
+      "step": 920
+    },
+    {
+      "epoch": 3.3787465940054497,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.026351287655294e-06,
+      "loss": 0.9457,
+      "step": 930
+    },
+    {
+      "epoch": 3.4150772025431424,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.994768454345207e-06,
+      "loss": 0.9585,
+      "step": 940
+    },
+    {
+      "epoch": 3.4514078110808355,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.96273865511666e-06,
+      "loss": 0.9479,
+      "step": 950
+    },
+    {
+      "epoch": 3.4877384196185286,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.930265473713939e-06,
+      "loss": 0.9105,
+      "step": 960
+    },
+    {
+      "epoch": 3.5240690281562217,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.897352543490396e-06,
+      "loss": 0.9795,
+      "step": 970
+    },
+    {
+      "epoch": 3.560399636693915,
+      "grad_norm": 1.21875,
+      "learning_rate": 8.864003547001916e-06,
+      "loss": 0.9403,
+      "step": 980
+    },
+    {
+      "epoch": 3.5967302452316074,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.925,
+      "step": 990
+    },
+    {
+      "epoch": 3.6330608537693005,
+      "grad_norm": 1.25,
+      "learning_rate": 8.796012328988716e-06,
+      "loss": 0.9225,
+      "step": 1000
+    },
+    {
+      "epoch": 3.6330608537693005,
+      "eval_loss": 1.1292678117752075,
+      "eval_runtime": 10.2075,
+      "eval_samples_per_second": 24.002,
+      "eval_steps_per_second": 24.002,
+      "step": 1000
+    },
+    {
+      "epoch": 3.6693914623069936,
+      "grad_norm": 1.171875,
+      "learning_rate": 8.7613777148529e-06,
+      "loss": 0.9778,
+      "step": 1010
+    },
+    {
+      "epoch": 3.7057220708446867,
+      "grad_norm": 1.234375,
+      "learning_rate": 8.726322248378775e-06,
+      "loss": 0.8997,
+      "step": 1020
+    },
+    {
+      "epoch": 3.74205267938238,
+      "grad_norm": 1.1328125,
+      "learning_rate": 8.690849851845933e-06,
+      "loss": 0.9874,
+      "step": 1030
+    },
+    {
+      "epoch": 3.7783832879200725,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.65496449418336e-06,
+      "loss": 0.9101,
+      "step": 1040
+    },
+    {
+      "epoch": 3.8147138964577656,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.9101,
+      "step": 1050
+    },
+    {
+      "epoch": 3.8510445049954587,
+      "grad_norm": 1.25,
+      "learning_rate": 8.581971001762287e-06,
+      "loss": 0.9549,
+      "step": 1060
+    },
+    {
+      "epoch": 3.887375113533152,
+      "grad_norm": 1.375,
+      "learning_rate": 8.54487103408625e-06,
+      "loss": 0.9486,
+      "step": 1070
+    },
+    {
+      "epoch": 3.923705722070845,
+      "grad_norm": 1.1953125,
+      "learning_rate": 8.507374438531606e-06,
+      "loss": 0.9476,
+      "step": 1080
+    },
+    {
+      "epoch": 3.9600363306085375,
+      "grad_norm": 1.2421875,
+      "learning_rate": 8.469485410510545e-06,
+      "loss": 0.9283,
+      "step": 1090
+    },
+    {
+      "epoch": 3.9963669391462306,
+      "grad_norm": 1.2109375,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.9616,
+      "step": 1100
+    },
+    {
+      "epoch": 4.032697547683924,
+      "grad_norm": 1.5,
+      "learning_rate": 8.392547057785662e-06,
+      "loss": 0.8816,
+      "step": 1110
+    },
+    {
+      "epoch": 4.069028156221616,
+      "grad_norm": 1.0546875,
+      "learning_rate": 8.353506341546106e-06,
+      "loss": 0.8704,
+      "step": 1120
+    },
+    {
+      "epoch": 4.10535876475931,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.314090408805481e-06,
+      "loss": 0.8515,
+      "step": 1130
+    },
+    {
+      "epoch": 4.141689373297003,
+      "grad_norm": 1.125,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 0.7986,
+      "step": 1140
+    },
+    {
+      "epoch": 4.178019981834696,
+      "grad_norm": 0.9765625,
+      "learning_rate": 8.234150575960288e-06,
+      "loss": 0.859,
+      "step": 1150
+    },
+    {
+      "epoch": 4.214350590372389,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.193635620149041e-06,
+      "loss": 0.8537,
+      "step": 1160
+    },
+    {
+      "epoch": 4.2506811989100814,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.152763335422612e-06,
+      "loss": 0.8513,
+      "step": 1170
+    },
+    {
+      "epoch": 4.287011807447775,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.111538294891684e-06,
+      "loss": 0.8318,
+      "step": 1180
+    },
+    {
+      "epoch": 4.323342415985468,
+      "grad_norm": 1.03125,
+      "learning_rate": 8.06996511113601e-06,
+      "loss": 0.846,
+      "step": 1190
+    },
+    {
+      "epoch": 4.359673024523161,
+      "grad_norm": 1.0,
+      "learning_rate": 8.028048435688333e-06,
+      "loss": 0.8667,
+      "step": 1200
+    },
+    {
+      "epoch": 4.396003633060854,
+      "grad_norm": 0.9921875,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.8715,
+      "step": 1210
+    },
+    {
+      "epoch": 4.4323342415985465,
+      "grad_norm": 0.9296875,
+      "learning_rate": 7.943203407485864e-06,
+      "loss": 0.848,
+      "step": 1220
+    },
+    {
+      "epoch": 4.46866485013624,
+      "grad_norm": 0.94921875,
+      "learning_rate": 7.900284547855992e-06,
+      "loss": 0.8859,
+      "step": 1230
+    },
+    {
+      "epoch": 4.504995458673933,
+      "grad_norm": 0.98046875,
+      "learning_rate": 7.857041181721788e-06,
+      "loss": 0.8575,
+      "step": 1240
+    },
+    {
+      "epoch": 4.541326067211626,
+      "grad_norm": 0.94140625,
+      "learning_rate": 7.813478147489052e-06,
+      "loss": 0.8496,
+      "step": 1250
+    },
+    {
+      "epoch": 4.577656675749319,
+      "grad_norm": 0.92578125,
+      "learning_rate": 7.769600319330553e-06,
+      "loss": 0.8166,
+      "step": 1260
+    },
+    {
+      "epoch": 4.6139872842870115,
+      "grad_norm": 1.15625,
+      "learning_rate": 7.725412606640658e-06,
+      "loss": 0.8191,
+      "step": 1270
+    },
+    {
+      "epoch": 4.650317892824705,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.680919953486047e-06,
+      "loss": 0.833,
+      "step": 1280
+    },
+    {
+      "epoch": 4.686648501362398,
+      "grad_norm": 1.0390625,
+      "learning_rate": 7.636127338052513e-06,
+      "loss": 0.839,
+      "step": 1290
+    },
+    {
+      "epoch": 4.722979109900091,
+      "grad_norm": 1.2421875,
+      "learning_rate": 7.5910397720879785e-06,
+      "loss": 0.807,
+      "step": 1300
+    },
+    {
+      "epoch": 4.759309718437784,
+      "grad_norm": 0.984375,
+      "learning_rate": 7.545662300341736e-06,
+      "loss": 0.8215,
+      "step": 1310
+    },
+    {
+      "epoch": 4.795640326975477,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8584,
+      "step": 1320
+    },
+    {
+      "epoch": 4.83197093551317,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.454057980117842e-06,
+      "loss": 0.7955,
+      "step": 1330
+    },
+    {
+      "epoch": 4.868301544050863,
+      "grad_norm": 1.140625,
+      "learning_rate": 7.407841381047533e-06,
+      "loss": 0.8482,
+      "step": 1340
+    },
+    {
+      "epoch": 4.904632152588556,
+      "grad_norm": 1.234375,
+      "learning_rate": 7.361355373863415e-06,
+      "loss": 0.8457,
+      "step": 1350
+    },
+    {
+      "epoch": 4.940962761126249,
+      "grad_norm": 0.91796875,
+      "learning_rate": 7.314605159783313e-06,
+      "loss": 0.8705,
+      "step": 1360
+    },
+    {
+      "epoch": 4.977293369663942,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.2675959695865896e-06,
+      "loss": 0.829,
+      "step": 1370
+    },
+    {
+      "epoch": 5.013623978201635,
+      "grad_norm": 0.9375,
+      "learning_rate": 7.2203330630288714e-06,
+      "loss": 0.8391,
+      "step": 1380
+    },
+    {
+      "epoch": 5.049954586739328,
+      "grad_norm": 0.9921875,
+      "learning_rate": 7.172821728253563e-06,
+      "loss": 0.7915,
+      "step": 1390
+    },
+    {
+      "epoch": 5.0862851952770205,
+      "grad_norm": 1.1171875,
+      "learning_rate": 7.1250672812001505e-06,
+      "loss": 0.8199,
+      "step": 1400
+    },
+    {
+      "epoch": 5.122615803814714,
+      "grad_norm": 1.0,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 0.8065,
+      "step": 1410
+    },
+    {
+      "epoch": 5.158946412352407,
+      "grad_norm": 1.2578125,
+      "learning_rate": 7.02885044942567e-06,
+      "loss": 0.8098,
+      "step": 1420
+    },
+    {
+      "epoch": 5.1952770208901,
+      "grad_norm": 1.0625,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.7675,
+      "step": 1430
+    },
+    {
+      "epoch": 5.231607629427793,
+      "grad_norm": 1.125,
+      "learning_rate": 6.931725628465643e-06,
+      "loss": 0.7747,
+      "step": 1440
+    },
+    {
+      "epoch": 5.2679382379654855,
+      "grad_norm": 1.375,
+      "learning_rate": 6.882836290173493e-06,
+      "loss": 0.7623,
+      "step": 1450
+    },
+    {
+      "epoch": 5.304268846503179,
+      "grad_norm": 1.2109375,
+      "learning_rate": 6.833736285440632e-06,
+      "loss": 0.8113,
+      "step": 1460
+    },
+    {
+      "epoch": 5.340599455040872,
+      "grad_norm": 1.3359375,
+      "learning_rate": 6.78443110795936e-06,
+      "loss": 0.8411,
+      "step": 1470
+    },
+    {
+      "epoch": 5.376930063578565,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.734926274378313e-06,
+      "loss": 0.7592,
+      "step": 1480
+    },
+    {
+      "epoch": 5.413260672116258,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.685227323685209e-06,
+      "loss": 0.7776,
+      "step": 1490
+    },
+    {
+      "epoch": 5.449591280653951,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.7727,
+      "step": 1500
+    },
+    {
+      "epoch": 5.485921889191644,
+      "grad_norm": 1.40625,
+      "learning_rate": 6.5852693348882345e-06,
+      "loss": 0.7539,
+      "step": 1510
+    },
+    {
+      "epoch": 5.522252497729337,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.535021480865439e-06,
+      "loss": 0.8292,
+      "step": 1520
+    },
+    {
+      "epoch": 5.55858310626703,
+      "grad_norm": 1.8359375,
+      "learning_rate": 6.484601876641375e-06,
+      "loss": 0.7463,
+      "step": 1530
+    },
+    {
+      "epoch": 5.594913714804723,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.7744,
+      "step": 1540
+    },
+    {
+      "epoch": 5.631244323342416,
+      "grad_norm": 2.578125,
+      "learning_rate": 6.383270001532636e-06,
+      "loss": 0.7868,
+      "step": 1550
+    },
+    {
+      "epoch": 5.667574931880109,
+      "grad_norm": 2.65625,
+      "learning_rate": 6.332369068450175e-06,
+      "loss": 0.7485,
+      "step": 1560
+    },
+    {
+      "epoch": 5.703905540417802,
+      "grad_norm": 2.34375,
+      "learning_rate": 6.2813190595023135e-06,
+      "loss": 0.7783,
+      "step": 1570
+    },
+    {
+      "epoch": 5.740236148955495,
+      "grad_norm": 2.40625,
+      "learning_rate": 6.230125686563068e-06,
+      "loss": 0.7769,
+      "step": 1580
+    },
+    {
+      "epoch": 5.776566757493188,
+      "grad_norm": 2.390625,
+      "learning_rate": 6.178794677547138e-06,
+      "loss": 0.7977,
+      "step": 1590
+    },
+    {
+      "epoch": 5.812897366030881,
+      "grad_norm": 3.65625,
+      "learning_rate": 6.127331775769023e-06,
+      "loss": 0.8101,
+      "step": 1600
+    },
+    {
+      "epoch": 5.849227974568574,
+      "grad_norm": 5.4375,
+      "learning_rate": 6.07574273930042e-06,
+      "loss": 0.8397,
+      "step": 1610
+    },
+    {
+      "epoch": 5.885558583106267,
+      "grad_norm": 4.78125,
+      "learning_rate": 6.024033340325954e-06,
+      "loss": 0.8191,
+      "step": 1620
+    },
+    {
+      "epoch": 5.9218891916439595,
+      "grad_norm": 4.625,
+      "learning_rate": 5.972209364497355e-06,
+      "loss": 0.7843,
+      "step": 1630
+    },
+    {
+      "epoch": 5.958219800181653,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.920276610286102e-06,
+      "loss": 0.8099,
+      "step": 1640
+    },
+    {
+      "epoch": 5.994550408719346,
+      "grad_norm": 10.875,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.8025,
+      "step": 1650
+    },
+    {
+      "epoch": 6.030881017257039,
+      "grad_norm": 10.25,
+      "learning_rate": 5.816108020806297e-06,
+      "loss": 0.7426,
+      "step": 1660
+    },
+    {
+      "epoch": 6.067211625794732,
+      "grad_norm": 9.8125,
+      "learning_rate": 5.763883840733736e-06,
+      "loss": 0.7439,
+      "step": 1670
+    },
+    {
+      "epoch": 6.1035422343324255,
+      "grad_norm": 8.4375,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 0.7617,
+      "step": 1680
+    },
+    {
+      "epoch": 6.139872842870118,
+      "grad_norm": 8.4375,
+      "learning_rate": 5.659184925516802e-06,
+      "loss": 0.7333,
+      "step": 1690
+    },
+    {
+      "epoch": 6.176203451407811,
+      "grad_norm": 2.453125,
+      "learning_rate": 5.60672190490541e-06,
+      "loss": 0.7747,
+      "step": 1700
+    },
+    {
+      "epoch": 6.212534059945504,
+      "grad_norm": 2.5625,
+      "learning_rate": 5.5541909995050554e-06,
+      "loss": 0.7469,
+      "step": 1710
+    },
+    {
+      "epoch": 6.248864668483197,
+      "grad_norm": 3.015625,
+      "learning_rate": 5.5015980868840254e-06,
+      "loss": 0.7507,
+      "step": 1720
+    },
+    {
+      "epoch": 6.28519527702089,
+      "grad_norm": 2.546875,
+      "learning_rate": 5.448949051548459e-06,
+      "loss": 0.7774,
+      "step": 1730
+    },
+    {
+      "epoch": 6.321525885558583,
+      "grad_norm": 2.921875,
+      "learning_rate": 5.396249784283943e-06,
+      "loss": 0.773,
+      "step": 1740
+    },
+    {
+      "epoch": 6.357856494096276,
+      "grad_norm": 2.21875,
+      "learning_rate": 5.343506181496405e-06,
+      "loss": 0.7333,
+      "step": 1750
+    },
+    {
+      "epoch": 6.394187102633969,
+      "grad_norm": 2.28125,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.7352,
+      "step": 1760
+    },
+    {
+      "epoch": 6.430517711171662,
+      "grad_norm": 2.3125,
+      "learning_rate": 5.237909579118713e-06,
+      "loss": 0.68,
+      "step": 1770
+    },
+    {
+      "epoch": 6.466848319709355,
+      "grad_norm": 2.296875,
+      "learning_rate": 5.185068394501791e-06,
+      "loss": 0.7279,
+      "step": 1780
+    },
+    {
+      "epoch": 6.503178928247048,
+      "grad_norm": 2.53125,
+      "learning_rate": 5.132206502986368e-06,
+      "loss": 0.7547,
+      "step": 1790
+    },
+    {
+      "epoch": 6.539509536784741,
+      "grad_norm": 2.421875,
+      "learning_rate": 5.07932981917404e-06,
+      "loss": 0.7015,
+      "step": 1800
+    },
+    {
+      "epoch": 6.575840145322434,
+      "grad_norm": 2.4375,
+      "learning_rate": 5.026444259321489e-06,
+      "loss": 0.7614,
+      "step": 1810
+    },
+    {
+      "epoch": 6.612170753860127,
+      "grad_norm": 2.171875,
+      "learning_rate": 4.973555740678512e-06,
+      "loss": 0.7953,
+      "step": 1820
+    },
+    {
+      "epoch": 6.64850136239782,
+      "grad_norm": 2.40625,
+      "learning_rate": 4.9206701808259605e-06,
+      "loss": 0.736,
+      "step": 1830
+    },
+    {
+      "epoch": 6.684831970935513,
+      "grad_norm": 2.28125,
+      "learning_rate": 4.867793497013634e-06,
+      "loss": 0.7502,
+      "step": 1840
+    },
+    {
+      "epoch": 6.721162579473206,
+      "grad_norm": 2.390625,
+      "learning_rate": 4.81493160549821e-06,
+      "loss": 0.7496,
+      "step": 1850
+    },
+    {
+      "epoch": 6.7574931880108995,
+      "grad_norm": 2.359375,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.7888,
+      "step": 1860
+    },
+    {
+      "epoch": 6.793823796548592,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.7238,
+      "step": 1870
+    },
+    {
+      "epoch": 6.830154405086285,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.6564938185035954e-06,
+      "loss": 0.7484,
+      "step": 1880
+    },
+    {
+      "epoch": 6.866485013623978,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.603750215716057e-06,
+      "loss": 0.7835,
+      "step": 1890
+    },
+    {
+      "epoch": 6.902815622161671,
+      "grad_norm": 2.53125,
+      "learning_rate": 4.551050948451542e-06,
+      "loss": 0.6878,
+      "step": 1900
+    },
+    {
+      "epoch": 6.9391462306993645,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.498401913115975e-06,
+      "loss": 0.7528,
+      "step": 1910
+    },
+    {
+      "epoch": 6.975476839237057,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.445809000494945e-06,
+      "loss": 0.7486,
+      "step": 1920
+    },
+    {
+      "epoch": 7.01180744777475,
+      "grad_norm": 2.15625,
+      "learning_rate": 4.393278095094591e-06,
+      "loss": 0.7948,
+      "step": 1930
+    },
+    {
+      "epoch": 7.048138056312443,
+      "grad_norm": 2.03125,
+      "learning_rate": 4.340815074483199e-06,
+      "loss": 0.6872,
+      "step": 1940
+    },
+    {
+      "epoch": 7.084468664850136,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.7289,
+      "step": 1950
+    },
+    {
+      "epoch": 7.12079927338783,
+      "grad_norm": 2.15625,
+      "learning_rate": 4.2361161592662655e-06,
+      "loss": 0.612,
+      "step": 1960
+    },
+    {
+      "epoch": 7.157129881925522,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.183891979193703e-06,
+      "loss": 0.7135,
+      "step": 1970
+    },
+    {
+      "epoch": 7.193460490463215,
+      "grad_norm": 2.28125,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.6932,
+      "step": 1980
+    },
+    {
+      "epoch": 7.229791099000908,
+      "grad_norm": 1.9453125,
+      "learning_rate": 4.079723389713899e-06,
+      "loss": 0.705,
+      "step": 1990
+    },
+    {
+      "epoch": 7.266121707538601,
+      "grad_norm": 2.09375,
+      "learning_rate": 4.027790635502646e-06,
+      "loss": 0.7145,
+      "step": 2000
+    },
+    {
+      "epoch": 7.266121707538601,
+      "eval_loss": 1.1055254936218262,
+      "eval_runtime": 10.2576,
+      "eval_samples_per_second": 23.885,
+      "eval_steps_per_second": 23.885,
+      "step": 2000
+    },
+    {
+      "epoch": 7.302452316076295,
+      "grad_norm": 1.921875,
+      "learning_rate": 3.975966659674048e-06,
+      "loss": 0.6724,
+      "step": 2010
+    },
+    {
+      "epoch": 7.338782924613987,
+      "grad_norm": 2.3125,
+      "learning_rate": 3.924257260699583e-06,
+      "loss": 0.6468,
+      "step": 2020
+    },
+    {
+      "epoch": 7.37511353315168,
+      "grad_norm": 2.140625,
+      "learning_rate": 3.872668224230979e-06,
+      "loss": 0.6792,
+      "step": 2030
+    },
+    {
+      "epoch": 7.4114441416893735,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.821205322452863e-06,
+      "loss": 0.723,
+      "step": 2040
+    },
+    {
+      "epoch": 7.447774750227066,
+      "grad_norm": 1.984375,
+      "learning_rate": 3.769874313436933e-06,
+      "loss": 0.6608,
+      "step": 2050
+    },
+    {
+      "epoch": 7.48410535876476,
+      "grad_norm": 2.21875,
+      "learning_rate": 3.7186809404976877e-06,
+      "loss": 0.6679,
+      "step": 2060
+    },
+    {
+      "epoch": 7.520435967302452,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.667630931549826e-06,
+      "loss": 0.6944,
+      "step": 2070
+    },
+    {
+      "epoch": 7.556766575840145,
+      "grad_norm": 2.15625,
+      "learning_rate": 3.6167299984673655e-06,
+      "loss": 0.7172,
+      "step": 2080
+    },
+    {
+      "epoch": 7.5930971843778385,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.7029,
+      "step": 2090
+    },
+    {
+      "epoch": 7.629427792915531,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.5153981233586277e-06,
+      "loss": 0.6549,
+      "step": 2100
+    },
+    {
+      "epoch": 7.665758401453225,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.4649785191345613e-06,
+      "loss": 0.7342,
+      "step": 2110
+    },
+    {
+      "epoch": 7.702089009990917,
+      "grad_norm": 2.09375,
+      "learning_rate": 3.4147306651117663e-06,
+      "loss": 0.6246,
+      "step": 2120
+    },
+    {
+      "epoch": 7.73841961852861,
+      "grad_norm": 1.90625,
+      "learning_rate": 3.3646601834128924e-06,
+      "loss": 0.6587,
+      "step": 2130
+    },
+    {
+      "epoch": 7.774750227066304,
+      "grad_norm": 1.953125,
+      "learning_rate": 3.3147726763147913e-06,
+      "loss": 0.6682,
+      "step": 2140
+    },
+    {
+      "epoch": 7.811080835603996,
+      "grad_norm": 2.421875,
+      "learning_rate": 3.2650737256216885e-06,
+      "loss": 0.6854,
+      "step": 2150
+    },
+    {
+      "epoch": 7.84741144414169,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.2155688920406415e-06,
+      "loss": 0.6908,
+      "step": 2160
+    },
+    {
+      "epoch": 7.883742052679382,
+      "grad_norm": 2.046875,
+      "learning_rate": 3.16626371455937e-06,
+      "loss": 0.6875,
+      "step": 2170
+    },
+    {
+      "epoch": 7.920072661217075,
+      "grad_norm": 2.28125,
+      "learning_rate": 3.1171637098265063e-06,
+      "loss": 0.6732,
+      "step": 2180
+    },
+    {
+      "epoch": 7.956403269754769,
+      "grad_norm": 1.9765625,
+      "learning_rate": 3.0682743715343565e-06,
+      "loss": 0.742,
+      "step": 2190
+    },
+    {
+      "epoch": 7.992733878292461,
+      "grad_norm": 2.796875,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.6791,
+      "step": 2200
+    },
+    {
+      "epoch": 8.029064486830155,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.9711495505743317e-06,
+      "loss": 0.654,
+      "step": 2210
+    },
+    {
+      "epoch": 8.065395095367847,
+      "grad_norm": 2.0,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 0.705,
+      "step": 2220
+    },
+    {
+      "epoch": 8.10172570390554,
+      "grad_norm": 2.0,
+      "learning_rate": 2.8749327187998516e-06,
+      "loss": 0.6067,
+      "step": 2230
+    },
+    {
+      "epoch": 8.138056312443233,
+      "grad_norm": 2.03125,
+      "learning_rate": 2.8271782717464413e-06,
+      "loss": 0.6043,
+      "step": 2240
+    },
+    {
+      "epoch": 8.174386920980927,
+      "grad_norm": 1.6875,
+      "learning_rate": 2.7796669369711294e-06,
+      "loss": 0.6292,
+      "step": 2250
+    },
+    {
+      "epoch": 8.21071752951862,
+      "grad_norm": 2.0625,
+      "learning_rate": 2.7324040304134125e-06,
+      "loss": 0.6041,
+      "step": 2260
+    },
+    {
+      "epoch": 8.247048138056313,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.685394840216688e-06,
+      "loss": 0.6222,
+      "step": 2270
+    },
+    {
+      "epoch": 8.283378746594005,
+      "grad_norm": 2.046875,
+      "learning_rate": 2.6386446261365874e-06,
+      "loss": 0.6586,
+      "step": 2280
+    },
+    {
+      "epoch": 8.319709355131698,
+      "grad_norm": 2.015625,
+      "learning_rate": 2.5921586189524694e-06,
+      "loss": 0.6612,
+      "step": 2290
+    },
+    {
+      "epoch": 8.356039963669392,
+      "grad_norm": 2.0,
+      "learning_rate": 2.5459420198821604e-06,
+      "loss": 0.6693,
+      "step": 2300
+    },
+    {
+      "epoch": 8.392370572207085,
+      "grad_norm": 2.125,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.6244,
+      "step": 2310
+    },
+    {
+      "epoch": 8.428701180744778,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.454337699658267e-06,
+      "loss": 0.6312,
+      "step": 2320
+    },
+    {
+      "epoch": 8.46503178928247,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.4089602279120224e-06,
+      "loss": 0.6729,
+      "step": 2330
+    },
+    {
+      "epoch": 8.501362397820163,
+      "grad_norm": 1.8125,
+      "learning_rate": 2.363872661947488e-06,
+      "loss": 0.6276,
+      "step": 2340
+    },
+    {
+      "epoch": 8.537693006357856,
+      "grad_norm": 1.90625,
+      "learning_rate": 2.319080046513954e-06,
+      "loss": 0.6292,
+      "step": 2350
+    },
+    {
+      "epoch": 8.57402361489555,
+      "grad_norm": 2.125,
+      "learning_rate": 2.274587393359342e-06,
+      "loss": 0.6593,
+      "step": 2360
+    },
+    {
+      "epoch": 8.610354223433243,
+      "grad_norm": 1.875,
+      "learning_rate": 2.230399680669449e-06,
+      "loss": 0.6302,
+      "step": 2370
+    },
+    {
+      "epoch": 8.646684831970935,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.1865218525109496e-06,
+      "loss": 0.6481,
+      "step": 2380
+    },
+    {
+      "epoch": 8.683015440508628,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.1429588182782147e-06,
+      "loss": 0.6175,
+      "step": 2390
+    },
+    {
+      "epoch": 8.719346049046322,
+      "grad_norm": 1.953125,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.6144,
+      "step": 2400
+    },
+    {
+      "epoch": 8.755676657584015,
+      "grad_norm": 1.6875,
+      "learning_rate": 2.0567965925141366e-06,
+      "loss": 0.6572,
+      "step": 2410
+    },
+    {
+      "epoch": 8.792007266121708,
+      "grad_norm": 1.890625,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.654,
+      "step": 2420
+    },
+    {
+      "epoch": 8.8283378746594,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.971951564311668e-06,
+      "loss": 0.621,
+      "step": 2430
+    },
+    {
+      "epoch": 8.864668483197093,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.9300348888639915e-06,
+      "loss": 0.62,
+      "step": 2440
+    },
+    {
+      "epoch": 8.900999091734786,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.8884617051083183e-06,
+      "loss": 0.5858,
+      "step": 2450
+    },
+    {
+      "epoch": 8.93732970027248,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.8472366645773892e-06,
+      "loss": 0.6467,
+      "step": 2460
+    },
+    {
+      "epoch": 8.973660308810173,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.8063643798509594e-06,
+      "loss": 0.6138,
+      "step": 2470
+    },
+    {
+      "epoch": 9.009990917347865,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.7658494240397127e-06,
+      "loss": 0.6388,
+      "step": 2480
+    },
+    {
+      "epoch": 9.046321525885558,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 0.5733,
+      "step": 2490
+    },
+    {
+      "epoch": 9.082652134423252,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.68590959119452e-06,
+      "loss": 0.6066,
+      "step": 2500
+    },
+    {
+      "epoch": 9.118982742960945,
+      "grad_norm": 1.2890625,
+      "learning_rate": 1.646493658453896e-06,
+      "loss": 0.5849,
+      "step": 2510
+    },
+    {
+      "epoch": 9.155313351498638,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.6074529422143398e-06,
+      "loss": 0.6136,
+      "step": 2520
+    },
+    {
+      "epoch": 9.19164396003633,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.5891,
+      "step": 2530
+    },
+    {
+      "epoch": 9.227974568574023,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.5305145894894547e-06,
+      "loss": 0.6065,
+      "step": 2540
+    },
+    {
+      "epoch": 9.264305177111716,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.4926255614683931e-06,
+      "loss": 0.5854,
+      "step": 2550
+    },
+    {
+      "epoch": 9.30063578564941,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.4551289659137497e-06,
+      "loss": 0.6023,
+      "step": 2560
+    },
+    {
+      "epoch": 9.336966394187103,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.4180289982377138e-06,
+      "loss": 0.6052,
+      "step": 2570
+    },
+    {
+      "epoch": 9.373297002724795,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.3813298094746491e-06,
+      "loss": 0.5806,
+      "step": 2580
+    },
+    {
+      "epoch": 9.409627611262488,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.345035505816642e-06,
+      "loss": 0.6058,
+      "step": 2590
+    },
+    {
+      "epoch": 9.44595821980018,
+      "grad_norm": 1.3671875,
+      "learning_rate": 1.3091501481540676e-06,
+      "loss": 0.6339,
+      "step": 2600
+    },
+    {
+      "epoch": 9.482288828337875,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2736777516212267e-06,
+      "loss": 0.6058,
+      "step": 2610
+    },
+    {
+      "epoch": 9.518619436875568,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.238622285147103e-06,
+      "loss": 0.6186,
+      "step": 2620
+    },
+    {
+      "epoch": 9.55495004541326,
+      "grad_norm": 1.3203125,
+      "learning_rate": 1.2039876710112847e-06,
+      "loss": 0.5913,
+      "step": 2630
+    },
+    {
+      "epoch": 9.591280653950953,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.663,
+      "step": 2640
+    },
+    {
+      "epoch": 9.627611262488646,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.135996452998085e-06,
+      "loss": 0.6278,
+      "step": 2650
+    },
+    {
+      "epoch": 9.66394187102634,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.1026474565096068e-06,
+      "loss": 0.6074,
+      "step": 2660
+    },
+    {
+      "epoch": 9.700272479564033,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.0697345262860638e-06,
+      "loss": 0.6545,
+      "step": 2670
+    },
+    {
+      "epoch": 9.736603088101726,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.0372613448833429e-06,
+      "loss": 0.6141,
+      "step": 2680
+    },
+    {
+      "epoch": 9.772933696639418,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.0052315456547934e-06,
+      "loss": 0.5699,
+      "step": 2690
+    },
+    {
+      "epoch": 9.809264305177111,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.73648712344707e-07,
+      "loss": 0.579,
+      "step": 2700
+    },
+    {
+      "epoch": 9.845594913714805,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.425163786873292e-07,
+      "loss": 0.61,
+      "step": 2710
+    },
+    {
+      "epoch": 9.881925522252498,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.118380280114858e-07,
+      "loss": 0.6106,
+      "step": 2720
+    },
+    {
+      "epoch": 9.91825613079019,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.816170928508367e-07,
+      "loss": 0.6066,
+      "step": 2730
+    },
+    {
+      "epoch": 9.954586739327883,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.518569545598198e-07,
+      "loss": 0.6094,
+      "step": 2740
+    },
+    {
+      "epoch": 9.990917347865576,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.6383,
+      "step": 2750
+    },
+    {
+      "epoch": 10.02724795640327,
+      "grad_norm": 1.203125,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.6017,
+      "step": 2760
+    },
+    {
+      "epoch": 10.063578564940963,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.653743588560387e-07,
+      "loss": 0.6005,
+      "step": 2770
+    },
+    {
+      "epoch": 10.099909173478656,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.374901848832683e-07,
+      "loss": 0.647,
+      "step": 2780
+    },
+    {
+      "epoch": 10.136239782016348,
+      "grad_norm": 1.0625,
+      "learning_rate": 7.100829338251147e-07,
+      "loss": 0.5894,
+      "step": 2790
+    },
+    {
+      "epoch": 10.172570390554041,
+      "grad_norm": 0.953125,
+      "learning_rate": 6.831556722190453e-07,
+      "loss": 0.6075,
+      "step": 2800
+    },
+    {
+      "epoch": 10.208900999091735,
+      "grad_norm": 0.97265625,
+      "learning_rate": 6.567114128975571e-07,
+      "loss": 0.5531,
+      "step": 2810
+    },
+    {
+      "epoch": 10.245231607629428,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.307531146510754e-07,
+      "loss": 0.6052,
+      "step": 2820
+    },
+    {
+      "epoch": 10.28156221616712,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.052836818969027e-07,
+      "loss": 0.5833,
+      "step": 2830
+    },
+    {
+      "epoch": 10.317892824704813,
+      "grad_norm": 1.1484375,
+      "learning_rate": 5.803059643542491e-07,
+      "loss": 0.5934,
+      "step": 2840
+    },
+    {
+      "epoch": 10.354223433242506,
+      "grad_norm": 0.9609375,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.5931,
+      "step": 2850
+    },
+    {
+      "epoch": 10.3905540417802,
+      "grad_norm": 1.15625,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.6253,
+      "step": 2860
+    },
+    {
+      "epoch": 10.426884650317893,
+      "grad_norm": 1.0390625,
+      "learning_rate": 5.083507730634152e-07,
+      "loss": 0.61,
+      "step": 2870
+    },
+    {
+      "epoch": 10.463215258855586,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.853673085668947e-07,
+      "loss": 0.6329,
+      "step": 2880
+    },
+    {
+      "epoch": 10.499545867393278,
+      "grad_norm": 0.96484375,
+      "learning_rate": 4.628889764630279e-07,
+      "loss": 0.5733,
+      "step": 2890
+    },
+    {
+      "epoch": 10.535876475930971,
+      "grad_norm": 1.0,
+      "learning_rate": 4.4091829180330503e-07,
+      "loss": 0.5922,
+      "step": 2900
+    },
+    {
+      "epoch": 10.572207084468666,
+      "grad_norm": 1.0078125,
+      "learning_rate": 4.194577128396521e-07,
+      "loss": 0.5843,
+      "step": 2910
+    },
+    {
+      "epoch": 10.608537693006358,
+      "grad_norm": 1.0546875,
+      "learning_rate": 3.985096407493838e-07,
+      "loss": 0.6028,
+      "step": 2920
+    },
+    {
+      "epoch": 10.64486830154405,
+      "grad_norm": 0.984375,
+      "learning_rate": 3.7807641936653984e-07,
+      "loss": 0.5767,
+      "step": 2930
+    },
+    {
+      "epoch": 10.681198910081743,
+      "grad_norm": 1.0625,
+      "learning_rate": 3.581603349196372e-07,
+      "loss": 0.6062,
+      "step": 2940
+    },
+    {
+      "epoch": 10.717529518619436,
+      "grad_norm": 1.0,
+      "learning_rate": 3.3876361577587115e-07,
+      "loss": 0.5978,
+      "step": 2950
+    },
+    {
+      "epoch": 10.75386012715713,
+      "grad_norm": 1.046875,
+      "learning_rate": 3.1988843219178776e-07,
+      "loss": 0.5984,
+      "step": 2960
+    },
+    {
+      "epoch": 10.790190735694823,
+      "grad_norm": 1.1953125,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.5761,
+      "step": 2970
+    },
+    {
+      "epoch": 10.826521344232516,
+      "grad_norm": 1.0078125,
+      "learning_rate": 2.8371106072518194e-07,
+      "loss": 0.5988,
+      "step": 2980
+    },
+    {
+      "epoch": 10.862851952770209,
+      "grad_norm": 1.015625,
+      "learning_rate": 2.664129206497479e-07,
+      "loss": 0.593,
+      "step": 2990
+    },
+    {
+      "epoch": 10.899182561307901,
+      "grad_norm": 1.125,
+      "learning_rate": 2.4964441129527337e-07,
+      "loss": 0.6401,
+      "step": 3000
+    },
+    {
+      "epoch": 10.899182561307901,
+      "eval_loss": 1.12338387966156,
+      "eval_runtime": 10.3307,
+      "eval_samples_per_second": 23.716,
+      "eval_steps_per_second": 23.716,
+      "step": 3000
+    },
+    {
+      "epoch": 10.935513169845596,
+      "grad_norm": 0.921875,
+      "learning_rate": 2.3340740885364922e-07,
+      "loss": 0.5798,
+      "step": 3010
+    },
+    {
+      "epoch": 10.971843778383288,
+      "grad_norm": 1.0546875,
+      "learning_rate": 2.1770373004762035e-07,
+      "loss": 0.5684,
+      "step": 3020
+    },
+    {
+      "epoch": 11.008174386920981,
+      "grad_norm": 1.171875,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 0.619,
+      "step": 3030
+    },
+    {
+      "epoch": 11.044504995458674,
+      "grad_norm": 1.125,
+      "learning_rate": 1.8790331167464758e-07,
+      "loss": 0.5739,
+      "step": 3040
+    },
+    {
+      "epoch": 11.080835603996366,
+      "grad_norm": 1.140625,
+      "learning_rate": 1.738099064114368e-07,
+      "loss": 0.6039,
+      "step": 3050
+    },
+    {
+      "epoch": 11.11716621253406,
+      "grad_norm": 1.3359375,
+      "learning_rate": 1.6025649301821877e-07,
+      "loss": 0.6057,
+      "step": 3060
+    },
+    {
+      "epoch": 11.153496821071753,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.4724458795681962e-07,
+      "loss": 0.5966,
+      "step": 3070
+    },
+    {
+      "epoch": 11.189827429609446,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.5987,
+      "step": 3080
+    },
+    {
+      "epoch": 11.226158038147139,
+      "grad_norm": 1.1796875,
+      "learning_rate": 1.2285106557296479e-07,
+      "loss": 0.614,
+      "step": 3090
+    },
+    {
+      "epoch": 11.262488646684831,
+      "grad_norm": 1.25,
+      "learning_rate": 1.1147217758845752e-07,
+      "loss": 0.5854,
+      "step": 3100
+    },
+    {
+      "epoch": 11.298819255222526,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.0064025630628583e-07,
+      "loss": 0.5866,
+      "step": 3110
+    },
+    {
+      "epoch": 11.335149863760218,
+      "grad_norm": 1.25,
+      "learning_rate": 9.035651368646647e-08,
+      "loss": 0.6412,
+      "step": 3120
+    },
+    {
+      "epoch": 11.371480472297911,
+      "grad_norm": 1.203125,
+      "learning_rate": 8.06221003545038e-08,
+      "loss": 0.5935,
+      "step": 3130
+    },
+    {
+      "epoch": 11.407811080835604,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.143810547264762e-08,
+      "loss": 0.6097,
+      "step": 3140
+    },
+    {
+      "epoch": 11.444141689373296,
+      "grad_norm": 2.1875,
+      "learning_rate": 6.280555661802857e-08,
+      "loss": 0.5737,
+      "step": 3150
+    },
+    {
+      "epoch": 11.48047229791099,
+      "grad_norm": 2.09375,
+      "learning_rate": 5.472541966768552e-08,
+      "loss": 0.5908,
+      "step": 3160
+    },
+    {
+      "epoch": 11.516802906448683,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.719859869049659e-08,
+      "loss": 0.5884,
+      "step": 3170
+    },
+    {
+      "epoch": 11.553133514986376,
+      "grad_norm": 2.125,
+      "learning_rate": 4.02259358460233e-08,
+      "loss": 0.6072,
+      "step": 3180
+    },
+    {
+      "epoch": 11.589464123524069,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.6049,
+      "step": 3190
+    },
+    {
+      "epoch": 11.625794732061761,
+      "grad_norm": 3.734375,
+      "learning_rate": 2.7946143088466437e-08,
+      "loss": 0.6021,
+      "step": 3200
+    },
+    {
+      "epoch": 11.662125340599456,
+      "grad_norm": 4.34375,
+      "learning_rate": 2.264038713457706e-08,
+      "loss": 0.6059,
+      "step": 3210
+    },
+    {
+      "epoch": 11.698455949137148,
+      "grad_norm": 3.9375,
+      "learning_rate": 1.789153707806357e-08,
+      "loss": 0.601,
+      "step": 3220
+    },
+    {
+      "epoch": 11.734786557674841,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.3700124257388092e-08,
+      "loss": 0.5657,
+      "step": 3230
+    },
+    {
+      "epoch": 11.771117166212534,
+      "grad_norm": 4.25,
+      "learning_rate": 1.006661764057837e-08,
+      "loss": 0.6255,
+      "step": 3240
+    },
+    {
+      "epoch": 11.807447774750226,
+      "grad_norm": 7.65625,
+      "learning_rate": 6.991423772753636e-09,
+      "loss": 0.6209,
+      "step": 3250
+    },
+    {
+      "epoch": 11.84377838328792,
+      "grad_norm": 7.90625,
+      "learning_rate": 4.474886730641004e-09,
+      "loss": 0.6111,
+      "step": 3260
+    },
+    {
+      "epoch": 11.880108991825614,
+      "grad_norm": 8.5625,
+      "learning_rate": 2.5172880840745873e-09,
+      "loss": 0.6328,
+      "step": 3270
+    },
+    {
+      "epoch": 11.916439600363306,
+      "grad_norm": 8.375,
+      "learning_rate": 1.118846864490708e-09,
+      "loss": 0.5511,
+      "step": 3280
+    },
+    {
+      "epoch": 11.952770208900999,
+      "grad_norm": 8.4375,
+      "learning_rate": 2.797195404247166e-10,
+      "loss": 0.5795,
+      "step": 3290
+    },
+    {
+      "epoch": 11.989100817438691,
+      "grad_norm": 2.59375,
+      "learning_rate": 0.0,
+      "loss": 0.5714,
+      "step": 3300
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.144153968877896e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-3300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf2707d2b44041692fc48569fafa359449408ba1404e7dcad3487b612ff0546
+size 5304

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "NousResearch/Meta-Llama-3-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128009,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.2",
+  "use_cache": false,
+  "vocab_size": 128256
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 11.989100817438691,
+    "eval_loss": 1.1235156059265137,
+    "eval_runtime": 10.55,
+    "eval_samples_per_second": 23.223,
+    "eval_steps_per_second": 23.223
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128009
+  ],
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.44.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ce8310054018ee51b78299d3d660d133731acacca439d5c43ac36a22021a4a1
+size 4976698672

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34f6cbceea7eee5ecca69f4e97863818b1850d40e1c0b9d27f0a13af55ed0380
+size 4999802720

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a3154807ed0c4bf3fcc841323e69c082c60b8e1d12779c1e8d363dc8eb986519
+size 4915916176

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa64f16e7b8a8f83d11ef628f49a1d6986b67729c41b08bd03a8e5788a215fd6
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

runs/Oct02_02-27-38_e931142f9336/events.out.tfevents.1727836076.e931142f9336.19435.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:48879a6ab9a0ab4e4a2968bdb1444ea6b4bff1e885ce0f94c14fefb4031b06cd
+size 75915

runs/Oct02_02-27-38_e931142f9336/events.out.tfevents.1727839739.e931142f9336.19435.1

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7b81eed1526244c954003cadc9f998e250dcfce08a44a0bc8bbe9ecbeb096ab1
+size 359

special_tokens_map.json

@@ -0,0 +1,17 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer_config.json

@@ -0,0 +1,2065 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_248|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_249|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_250|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{% set loop_messages = messages %}{% for message in loop_messages %}{% set content = '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] | trim + '<|eot_id|>' %}{% if loop.index0 == 0 %}{% set content = bos_token + content %}{% endif %}{{ content }}{% endfor %}{% if add_generation_prompt %}{{ '<|start_header_id|>assistant<|end_header_id|>\n\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 11.989100817438691,
+    "total_flos": 3.144153968877896e+17,
+    "train_loss": 0.880180758562955,
+    "train_runtime": 3585.8754,
+    "train_samples_per_second": 7.369,
+    "train_steps_per_second": 0.92
+}

trainer_log.jsonl

@@ -0,0 +1,334 @@
+{"current_steps": 10, "total_steps": 3300, "loss": 2.0607, "learning_rate": 3.0303030303030305e-07, "epoch": 0.03633060853769301, "percentage": 0.3, "elapsed_time": "0:00:16", "remaining_time": "1:29:41"}
+{"current_steps": 20, "total_steps": 3300, "loss": 2.033, "learning_rate": 6.060606060606061e-07, "epoch": 0.07266121707538602, "percentage": 0.61, "elapsed_time": "0:00:31", "remaining_time": "1:26:41"}
+{"current_steps": 30, "total_steps": 3300, "loss": 2.0622, "learning_rate": 9.090909090909091e-07, "epoch": 0.10899182561307902, "percentage": 0.91, "elapsed_time": "0:00:47", "remaining_time": "1:25:32"}
+{"current_steps": 40, "total_steps": 3300, "loss": 1.9896, "learning_rate": 1.2121212121212122e-06, "epoch": 0.14532243415077203, "percentage": 1.21, "elapsed_time": "0:01:02", "remaining_time": "1:24:23"}
+{"current_steps": 50, "total_steps": 3300, "loss": 1.9998, "learning_rate": 1.5151515151515152e-06, "epoch": 0.18165304268846502, "percentage": 1.52, "elapsed_time": "0:01:17", "remaining_time": "1:24:21"}
+{"current_steps": 60, "total_steps": 3300, "loss": 1.9608, "learning_rate": 1.8181818181818183e-06, "epoch": 0.21798365122615804, "percentage": 1.82, "elapsed_time": "0:01:32", "remaining_time": "1:23:28"}
+{"current_steps": 70, "total_steps": 3300, "loss": 1.9272, "learning_rate": 2.1212121212121216e-06, "epoch": 0.254314259763851, "percentage": 2.12, "elapsed_time": "0:01:47", "remaining_time": "1:22:51"}
+{"current_steps": 80, "total_steps": 3300, "loss": 1.9031, "learning_rate": 2.4242424242424244e-06, "epoch": 0.29064486830154407, "percentage": 2.42, "elapsed_time": "0:02:02", "remaining_time": "1:22:12"}
+{"current_steps": 90, "total_steps": 3300, "loss": 1.8012, "learning_rate": 2.7272727272727272e-06, "epoch": 0.32697547683923706, "percentage": 2.73, "elapsed_time": "0:02:17", "remaining_time": "1:21:44"}
+{"current_steps": 100, "total_steps": 3300, "loss": 1.7756, "learning_rate": 3.0303030303030305e-06, "epoch": 0.36330608537693004, "percentage": 3.03, "elapsed_time": "0:02:32", "remaining_time": "1:21:30"}
+{"current_steps": 110, "total_steps": 3300, "loss": 1.6836, "learning_rate": 3.3333333333333333e-06, "epoch": 0.3996366939146231, "percentage": 3.33, "elapsed_time": "0:02:47", "remaining_time": "1:20:51"}
+{"current_steps": 120, "total_steps": 3300, "loss": 1.7013, "learning_rate": 3.6363636363636366e-06, "epoch": 0.4359673024523161, "percentage": 3.64, "elapsed_time": "0:03:01", "remaining_time": "1:20:22"}
+{"current_steps": 130, "total_steps": 3300, "loss": 1.6328, "learning_rate": 3.93939393939394e-06, "epoch": 0.47229791099000906, "percentage": 3.94, "elapsed_time": "0:03:16", "remaining_time": "1:19:49"}
+{"current_steps": 140, "total_steps": 3300, "loss": 1.6888, "learning_rate": 4.242424242424243e-06, "epoch": 0.508628519527702, "percentage": 4.24, "elapsed_time": "0:03:31", "remaining_time": "1:19:24"}
+{"current_steps": 150, "total_steps": 3300, "loss": 1.6583, "learning_rate": 4.5454545454545455e-06, "epoch": 0.5449591280653951, "percentage": 4.55, "elapsed_time": "0:03:45", "remaining_time": "1:19:05"}
+{"current_steps": 160, "total_steps": 3300, "loss": 1.5485, "learning_rate": 4.848484848484849e-06, "epoch": 0.5812897366030881, "percentage": 4.85, "elapsed_time": "0:04:00", "remaining_time": "1:18:37"}
+{"current_steps": 170, "total_steps": 3300, "loss": 1.5464, "learning_rate": 5.151515151515152e-06, "epoch": 0.6176203451407811, "percentage": 5.15, "elapsed_time": "0:04:14", "remaining_time": "1:18:06"}
+{"current_steps": 180, "total_steps": 3300, "loss": 1.5506, "learning_rate": 5.4545454545454545e-06, "epoch": 0.6539509536784741, "percentage": 5.45, "elapsed_time": "0:04:28", "remaining_time": "1:17:42"}
+{"current_steps": 190, "total_steps": 3300, "loss": 1.5301, "learning_rate": 5.7575757575757586e-06, "epoch": 0.6902815622161671, "percentage": 5.76, "elapsed_time": "0:04:43", "remaining_time": "1:17:18"}
+{"current_steps": 200, "total_steps": 3300, "loss": 1.5116, "learning_rate": 6.060606060606061e-06, "epoch": 0.7266121707538601, "percentage": 6.06, "elapsed_time": "0:04:58", "remaining_time": "1:16:59"}
+{"current_steps": 210, "total_steps": 3300, "loss": 1.4874, "learning_rate": 6.363636363636364e-06, "epoch": 0.7629427792915532, "percentage": 6.36, "elapsed_time": "0:05:12", "remaining_time": "1:16:30"}
+{"current_steps": 220, "total_steps": 3300, "loss": 1.5056, "learning_rate": 6.666666666666667e-06, "epoch": 0.7992733878292462, "percentage": 6.67, "elapsed_time": "0:05:25", "remaining_time": "1:16:00"}
+{"current_steps": 230, "total_steps": 3300, "loss": 1.5036, "learning_rate": 6.969696969696971e-06, "epoch": 0.8356039963669392, "percentage": 6.97, "elapsed_time": "0:05:39", "remaining_time": "1:15:36"}
+{"current_steps": 240, "total_steps": 3300, "loss": 1.4625, "learning_rate": 7.272727272727273e-06, "epoch": 0.8719346049046321, "percentage": 7.27, "elapsed_time": "0:05:53", "remaining_time": "1:15:09"}
+{"current_steps": 250, "total_steps": 3300, "loss": 1.4439, "learning_rate": 7.5757575757575764e-06, "epoch": 0.9082652134423251, "percentage": 7.58, "elapsed_time": "0:06:08", "remaining_time": "1:14:50"}
+{"current_steps": 260, "total_steps": 3300, "loss": 1.4025, "learning_rate": 7.87878787878788e-06, "epoch": 0.9445958219800181, "percentage": 7.88, "elapsed_time": "0:06:21", "remaining_time": "1:14:23"}
+{"current_steps": 270, "total_steps": 3300, "loss": 1.4267, "learning_rate": 8.181818181818183e-06, "epoch": 0.9809264305177112, "percentage": 8.18, "elapsed_time": "0:06:35", "remaining_time": "1:13:56"}
+{"current_steps": 280, "total_steps": 3300, "loss": 1.3484, "learning_rate": 8.484848484848486e-06, "epoch": 1.017257039055404, "percentage": 8.48, "elapsed_time": "0:06:49", "remaining_time": "1:13:31"}
+{"current_steps": 290, "total_steps": 3300, "loss": 1.3809, "learning_rate": 8.787878787878788e-06, "epoch": 1.0535876475930972, "percentage": 8.79, "elapsed_time": "0:07:02", "remaining_time": "1:13:04"}
+{"current_steps": 300, "total_steps": 3300, "loss": 1.3901, "learning_rate": 9.090909090909091e-06, "epoch": 1.0899182561307903, "percentage": 9.09, "elapsed_time": "0:07:16", "remaining_time": "1:12:44"}
+{"current_steps": 310, "total_steps": 3300, "loss": 1.3203, "learning_rate": 9.393939393939396e-06, "epoch": 1.1262488646684832, "percentage": 9.39, "elapsed_time": "0:07:29", "remaining_time": "1:12:16"}
+{"current_steps": 320, "total_steps": 3300, "loss": 1.3295, "learning_rate": 9.696969696969698e-06, "epoch": 1.1625794732061763, "percentage": 9.7, "elapsed_time": "0:07:42", "remaining_time": "1:11:51"}
+{"current_steps": 330, "total_steps": 3300, "loss": 1.3936, "learning_rate": 1e-05, "epoch": 1.1989100817438691, "percentage": 10.0, "elapsed_time": "0:07:56", "remaining_time": "1:11:27"}
+{"current_steps": 340, "total_steps": 3300, "loss": 1.3483, "learning_rate": 9.999720280459576e-06, "epoch": 1.2352406902815622, "percentage": 10.3, "elapsed_time": "0:08:09", "remaining_time": "1:11:01"}
+{"current_steps": 350, "total_steps": 3300, "loss": 1.3384, "learning_rate": 9.99888115313551e-06, "epoch": 1.2715712988192553, "percentage": 10.61, "elapsed_time": "0:08:23", "remaining_time": "1:10:41"}
+{"current_steps": 360, "total_steps": 3300, "loss": 1.2888, "learning_rate": 9.997482711915926e-06, "epoch": 1.3079019073569482, "percentage": 10.91, "elapsed_time": "0:08:35", "remaining_time": "1:10:13"}
+{"current_steps": 370, "total_steps": 3300, "loss": 1.3144, "learning_rate": 9.99552511326936e-06, "epoch": 1.344232515894641, "percentage": 11.21, "elapsed_time": "0:08:49", "remaining_time": "1:09:49"}
+{"current_steps": 380, "total_steps": 3300, "loss": 1.2905, "learning_rate": 9.993008576227248e-06, "epoch": 1.3805631244323342, "percentage": 11.52, "elapsed_time": "0:09:02", "remaining_time": "1:09:25"}
+{"current_steps": 390, "total_steps": 3300, "loss": 1.2816, "learning_rate": 9.989933382359423e-06, "epoch": 1.4168937329700273, "percentage": 11.82, "elapsed_time": "0:09:14", "remaining_time": "1:09:00"}
+{"current_steps": 400, "total_steps": 3300, "loss": 1.3315, "learning_rate": 9.986299875742612e-06, "epoch": 1.4532243415077202, "percentage": 12.12, "elapsed_time": "0:09:28", "remaining_time": "1:08:40"}
+{"current_steps": 410, "total_steps": 3300, "loss": 1.2984, "learning_rate": 9.982108462921938e-06, "epoch": 1.4895549500454133, "percentage": 12.42, "elapsed_time": "0:09:40", "remaining_time": "1:08:14"}
+{"current_steps": 420, "total_steps": 3300, "loss": 1.2677, "learning_rate": 9.977359612865424e-06, "epoch": 1.5258855585831061, "percentage": 12.73, "elapsed_time": "0:09:53", "remaining_time": "1:07:50"}
+{"current_steps": 430, "total_steps": 3300, "loss": 1.3098, "learning_rate": 9.972053856911534e-06, "epoch": 1.5622161671207992, "percentage": 13.03, "elapsed_time": "0:10:06", "remaining_time": "1:07:27"}
+{"current_steps": 440, "total_steps": 3300, "loss": 1.3503, "learning_rate": 9.966191788709716e-06, "epoch": 1.5985467756584923, "percentage": 13.33, "elapsed_time": "0:10:18", "remaining_time": "1:07:02"}
+{"current_steps": 450, "total_steps": 3300, "loss": 1.3301, "learning_rate": 9.959774064153977e-06, "epoch": 1.6348773841961854, "percentage": 13.64, "elapsed_time": "0:10:32", "remaining_time": "1:06:42"}
+{"current_steps": 460, "total_steps": 3300, "loss": 1.2454, "learning_rate": 9.952801401309504e-06, "epoch": 1.6712079927338783, "percentage": 13.94, "elapsed_time": "0:10:44", "remaining_time": "1:06:18"}
+{"current_steps": 470, "total_steps": 3300, "loss": 1.239, "learning_rate": 9.945274580332316e-06, "epoch": 1.7075386012715712, "percentage": 14.24, "elapsed_time": "0:10:56", "remaining_time": "1:05:55"}
+{"current_steps": 480, "total_steps": 3300, "loss": 1.2823, "learning_rate": 9.937194443381972e-06, "epoch": 1.7438692098092643, "percentage": 14.55, "elapsed_time": "0:11:09", "remaining_time": "1:05:32"}
+{"current_steps": 490, "total_steps": 3300, "loss": 1.2774, "learning_rate": 9.928561894527354e-06, "epoch": 1.7801998183469574, "percentage": 14.85, "elapsed_time": "0:11:21", "remaining_time": "1:05:07"}
+{"current_steps": 500, "total_steps": 3300, "loss": 1.2215, "learning_rate": 9.919377899645497e-06, "epoch": 1.8165304268846503, "percentage": 15.15, "elapsed_time": "0:11:34", "remaining_time": "1:04:48"}
+{"current_steps": 510, "total_steps": 3300, "loss": 1.2509, "learning_rate": 9.909643486313533e-06, "epoch": 1.8528610354223434, "percentage": 15.45, "elapsed_time": "0:11:46", "remaining_time": "1:04:24"}
+{"current_steps": 520, "total_steps": 3300, "loss": 1.2656, "learning_rate": 9.899359743693715e-06, "epoch": 1.8891916439600362, "percentage": 15.76, "elapsed_time": "0:11:58", "remaining_time": "1:04:00"}
+{"current_steps": 530, "total_steps": 3300, "loss": 1.186, "learning_rate": 9.888527822411543e-06, "epoch": 1.9255222524977293, "percentage": 16.06, "elapsed_time": "0:12:10", "remaining_time": "1:03:37"}
+{"current_steps": 540, "total_steps": 3300, "loss": 1.2468, "learning_rate": 9.877148934427037e-06, "epoch": 1.9618528610354224, "percentage": 16.36, "elapsed_time": "0:12:22", "remaining_time": "1:03:14"}
+{"current_steps": 550, "total_steps": 3300, "loss": 1.2471, "learning_rate": 9.86522435289912e-06, "epoch": 1.9981834695731153, "percentage": 16.67, "elapsed_time": "0:12:34", "remaining_time": "1:02:53"}
+{"current_steps": 560, "total_steps": 3300, "loss": 1.1688, "learning_rate": 9.85275541204318e-06, "epoch": 2.034514078110808, "percentage": 16.97, "elapsed_time": "0:12:46", "remaining_time": "1:02:31"}
+{"current_steps": 570, "total_steps": 3300, "loss": 1.1216, "learning_rate": 9.839743506981783e-06, "epoch": 2.0708446866485013, "percentage": 17.27, "elapsed_time": "0:12:58", "remaining_time": "1:02:06"}
+{"current_steps": 580, "total_steps": 3300, "loss": 1.1333, "learning_rate": 9.826190093588564e-06, "epoch": 2.1071752951861944, "percentage": 17.58, "elapsed_time": "0:13:09", "remaining_time": "1:01:44"}
+{"current_steps": 590, "total_steps": 3300, "loss": 1.1148, "learning_rate": 9.812096688325354e-06, "epoch": 2.1435059037238875, "percentage": 17.88, "elapsed_time": "0:13:21", "remaining_time": "1:01:22"}
+{"current_steps": 600, "total_steps": 3300, "loss": 1.1331, "learning_rate": 9.797464868072489e-06, "epoch": 2.1798365122615806, "percentage": 18.18, "elapsed_time": "0:13:33", "remaining_time": "1:01:01"}
+{"current_steps": 610, "total_steps": 3300, "loss": 1.1931, "learning_rate": 9.78229626995238e-06, "epoch": 2.2161671207992732, "percentage": 18.48, "elapsed_time": "0:13:45", "remaining_time": "1:00:39"}
+{"current_steps": 620, "total_steps": 3300, "loss": 1.146, "learning_rate": 9.766592591146353e-06, "epoch": 2.2524977293369663, "percentage": 18.79, "elapsed_time": "0:13:56", "remaining_time": "1:00:16"}
+{"current_steps": 630, "total_steps": 3300, "loss": 1.1397, "learning_rate": 9.750355588704728e-06, "epoch": 2.2888283378746594, "percentage": 19.09, "elapsed_time": "0:14:07", "remaining_time": "0:59:53"}
+{"current_steps": 640, "total_steps": 3300, "loss": 1.0941, "learning_rate": 9.733587079350254e-06, "epoch": 2.3251589464123525, "percentage": 19.39, "elapsed_time": "0:14:19", "remaining_time": "0:59:31"}
+{"current_steps": 650, "total_steps": 3300, "loss": 1.101, "learning_rate": 9.716288939274818e-06, "epoch": 2.3614895549500456, "percentage": 19.7, "elapsed_time": "0:14:31", "remaining_time": "0:59:11"}
+{"current_steps": 660, "total_steps": 3300, "loss": 1.0632, "learning_rate": 9.698463103929542e-06, "epoch": 2.3978201634877383, "percentage": 20.0, "elapsed_time": "0:14:42", "remaining_time": "0:58:48"}
+{"current_steps": 670, "total_steps": 3300, "loss": 1.1315, "learning_rate": 9.680111567808212e-06, "epoch": 2.4341507720254314, "percentage": 20.3, "elapsed_time": "0:14:53", "remaining_time": "0:58:26"}
+{"current_steps": 680, "total_steps": 3300, "loss": 1.0989, "learning_rate": 9.66123638422413e-06, "epoch": 2.4704813805631245, "percentage": 20.61, "elapsed_time": "0:15:04", "remaining_time": "0:58:04"}
+{"current_steps": 690, "total_steps": 3300, "loss": 1.0829, "learning_rate": 9.641839665080363e-06, "epoch": 2.5068119891008176, "percentage": 20.91, "elapsed_time": "0:15:15", "remaining_time": "0:57:42"}
+{"current_steps": 700, "total_steps": 3300, "loss": 1.1155, "learning_rate": 9.621923580633462e-06, "epoch": 2.5431425976385107, "percentage": 21.21, "elapsed_time": "0:15:26", "remaining_time": "0:57:22"}
+{"current_steps": 710, "total_steps": 3300, "loss": 1.1248, "learning_rate": 9.601490359250616e-06, "epoch": 2.5794732061762033, "percentage": 21.52, "elapsed_time": "0:15:37", "remaining_time": "0:56:59"}
+{"current_steps": 720, "total_steps": 3300, "loss": 1.1391, "learning_rate": 9.580542287160348e-06, "epoch": 2.6158038147138964, "percentage": 21.82, "elapsed_time": "0:15:48", "remaining_time": "0:56:37"}
+{"current_steps": 730, "total_steps": 3300, "loss": 1.0538, "learning_rate": 9.559081708196696e-06, "epoch": 2.6521344232515895, "percentage": 22.12, "elapsed_time": "0:15:59", "remaining_time": "0:56:16"}
+{"current_steps": 740, "total_steps": 3300, "loss": 1.055, "learning_rate": 9.537111023536973e-06, "epoch": 2.688465031789282, "percentage": 22.42, "elapsed_time": "0:16:09", "remaining_time": "0:55:55"}
+{"current_steps": 750, "total_steps": 3300, "loss": 1.1769, "learning_rate": 9.514632691433108e-06, "epoch": 2.7247956403269757, "percentage": 22.73, "elapsed_time": "0:16:21", "remaining_time": "0:55:35"}
+{"current_steps": 760, "total_steps": 3300, "loss": 1.0949, "learning_rate": 9.491649226936586e-06, "epoch": 2.7611262488646684, "percentage": 23.03, "elapsed_time": "0:16:31", "remaining_time": "0:55:14"}
+{"current_steps": 770, "total_steps": 3300, "loss": 1.1308, "learning_rate": 9.468163201617063e-06, "epoch": 2.7974568574023615, "percentage": 23.33, "elapsed_time": "0:16:42", "remaining_time": "0:54:53"}
+{"current_steps": 780, "total_steps": 3300, "loss": 1.1283, "learning_rate": 9.444177243274619e-06, "epoch": 2.8337874659400546, "percentage": 23.64, "elapsed_time": "0:16:52", "remaining_time": "0:54:31"}
+{"current_steps": 790, "total_steps": 3300, "loss": 1.0907, "learning_rate": 9.419694035645753e-06, "epoch": 2.8701180744777472, "percentage": 23.94, "elapsed_time": "0:17:03", "remaining_time": "0:54:11"}
+{"current_steps": 800, "total_steps": 3300, "loss": 1.1043, "learning_rate": 9.394716318103098e-06, "epoch": 2.9064486830154403, "percentage": 24.24, "elapsed_time": "0:17:14", "remaining_time": "0:53:51"}
+{"current_steps": 810, "total_steps": 3300, "loss": 1.0676, "learning_rate": 9.369246885348926e-06, "epoch": 2.9427792915531334, "percentage": 24.55, "elapsed_time": "0:17:24", "remaining_time": "0:53:29"}
+{"current_steps": 820, "total_steps": 3300, "loss": 1.0642, "learning_rate": 9.343288587102444e-06, "epoch": 2.9791099000908265, "percentage": 24.85, "elapsed_time": "0:17:34", "remaining_time": "0:53:08"}
+{"current_steps": 830, "total_steps": 3300, "loss": 1.0437, "learning_rate": 9.316844327780955e-06, "epoch": 3.0154405086285196, "percentage": 25.15, "elapsed_time": "0:17:44", "remaining_time": "0:52:47"}
+{"current_steps": 840, "total_steps": 3300, "loss": 0.9874, "learning_rate": 9.289917066174887e-06, "epoch": 3.0517711171662127, "percentage": 25.45, "elapsed_time": "0:17:54", "remaining_time": "0:52:26"}
+{"current_steps": 850, "total_steps": 3300, "loss": 0.9582, "learning_rate": 9.262509815116732e-06, "epoch": 3.0881017257039054, "percentage": 25.76, "elapsed_time": "0:18:04", "remaining_time": "0:52:07"}
+{"current_steps": 860, "total_steps": 3300, "loss": 0.9471, "learning_rate": 9.234625641143962e-06, "epoch": 3.1244323342415985, "percentage": 26.06, "elapsed_time": "0:18:14", "remaining_time": "0:51:46"}
+{"current_steps": 870, "total_steps": 3300, "loss": 0.9424, "learning_rate": 9.206267664155906e-06, "epoch": 3.1607629427792916, "percentage": 26.36, "elapsed_time": "0:18:24", "remaining_time": "0:51:24"}
+{"current_steps": 880, "total_steps": 3300, "loss": 0.972, "learning_rate": 9.177439057064684e-06, "epoch": 3.1970935513169847, "percentage": 26.67, "elapsed_time": "0:18:34", "remaining_time": "0:51:03"}
+{"current_steps": 890, "total_steps": 3300, "loss": 0.9729, "learning_rate": 9.148143045440181e-06, "epoch": 3.2334241598546773, "percentage": 26.97, "elapsed_time": "0:18:44", "remaining_time": "0:50:43"}
+{"current_steps": 900, "total_steps": 3300, "loss": 0.9558, "learning_rate": 9.118382907149164e-06, "epoch": 3.2697547683923704, "percentage": 27.27, "elapsed_time": "0:18:54", "remaining_time": "0:50:24"}
+{"current_steps": 910, "total_steps": 3300, "loss": 0.9518, "learning_rate": 9.088161971988517e-06, "epoch": 3.3060853769300635, "percentage": 27.58, "elapsed_time": "0:19:03", "remaining_time": "0:50:03"}
+{"current_steps": 920, "total_steps": 3300, "loss": 0.9694, "learning_rate": 9.057483621312671e-06, "epoch": 3.3424159854677566, "percentage": 27.88, "elapsed_time": "0:19:13", "remaining_time": "0:49:43"}
+{"current_steps": 930, "total_steps": 3300, "loss": 0.9457, "learning_rate": 9.026351287655294e-06, "epoch": 3.3787465940054497, "percentage": 28.18, "elapsed_time": "0:19:22", "remaining_time": "0:49:23"}
+{"current_steps": 940, "total_steps": 3300, "loss": 0.9585, "learning_rate": 8.994768454345207e-06, "epoch": 3.4150772025431424, "percentage": 28.48, "elapsed_time": "0:19:32", "remaining_time": "0:49:03"}
+{"current_steps": 950, "total_steps": 3300, "loss": 0.9479, "learning_rate": 8.96273865511666e-06, "epoch": 3.4514078110808355, "percentage": 28.79, "elapsed_time": "0:19:42", "remaining_time": "0:48:44"}
+{"current_steps": 960, "total_steps": 3300, "loss": 0.9105, "learning_rate": 8.930265473713939e-06, "epoch": 3.4877384196185286, "percentage": 29.09, "elapsed_time": "0:19:51", "remaining_time": "0:48:24"}
+{"current_steps": 970, "total_steps": 3300, "loss": 0.9795, "learning_rate": 8.897352543490396e-06, "epoch": 3.5240690281562217, "percentage": 29.39, "elapsed_time": "0:20:00", "remaining_time": "0:48:04"}
+{"current_steps": 980, "total_steps": 3300, "loss": 0.9403, "learning_rate": 8.864003547001916e-06, "epoch": 3.560399636693915, "percentage": 29.7, "elapsed_time": "0:20:10", "remaining_time": "0:47:44"}
+{"current_steps": 990, "total_steps": 3300, "loss": 0.925, "learning_rate": 8.83022221559489e-06, "epoch": 3.5967302452316074, "percentage": 30.0, "elapsed_time": "0:20:19", "remaining_time": "0:47:25"}
+{"current_steps": 1000, "total_steps": 3300, "loss": 0.9225, "learning_rate": 8.796012328988716e-06, "epoch": 3.6330608537693005, "percentage": 30.3, "elapsed_time": "0:20:29", "remaining_time": "0:47:06"}
+{"current_steps": 1000, "total_steps": 3300, "eval_loss": 1.1292678117752075, "epoch": 3.6330608537693005, "percentage": 30.3, "elapsed_time": "0:20:39", "remaining_time": "0:47:30"}
+{"current_steps": 1010, "total_steps": 3300, "loss": 0.9778, "learning_rate": 8.7613777148529e-06, "epoch": 3.6693914623069936, "percentage": 30.61, "elapsed_time": "0:20:48", "remaining_time": "0:47:10"}
+{"current_steps": 1020, "total_steps": 3300, "loss": 0.8997, "learning_rate": 8.726322248378775e-06, "epoch": 3.7057220708446867, "percentage": 30.91, "elapsed_time": "0:20:57", "remaining_time": "0:46:50"}
+{"current_steps": 1030, "total_steps": 3300, "loss": 0.9874, "learning_rate": 8.690849851845933e-06, "epoch": 3.74205267938238, "percentage": 31.21, "elapsed_time": "0:21:06", "remaining_time": "0:46:30"}
+{"current_steps": 1040, "total_steps": 3300, "loss": 0.9101, "learning_rate": 8.65496449418336e-06, "epoch": 3.7783832879200725, "percentage": 31.52, "elapsed_time": "0:21:14", "remaining_time": "0:46:10"}
+{"current_steps": 1050, "total_steps": 3300, "loss": 0.9101, "learning_rate": 8.61867019052535e-06, "epoch": 3.8147138964577656, "percentage": 31.82, "elapsed_time": "0:21:24", "remaining_time": "0:45:52"}
+{"current_steps": 1060, "total_steps": 3300, "loss": 0.9549, "learning_rate": 8.581971001762287e-06, "epoch": 3.8510445049954587, "percentage": 32.12, "elapsed_time": "0:21:32", "remaining_time": "0:45:32"}
+{"current_steps": 1070, "total_steps": 3300, "loss": 0.9486, "learning_rate": 8.54487103408625e-06, "epoch": 3.887375113533152, "percentage": 32.42, "elapsed_time": "0:21:41", "remaining_time": "0:45:11"}
+{"current_steps": 1080, "total_steps": 3300, "loss": 0.9476, "learning_rate": 8.507374438531606e-06, "epoch": 3.923705722070845, "percentage": 32.73, "elapsed_time": "0:21:49", "remaining_time": "0:44:52"}
+{"current_steps": 1090, "total_steps": 3300, "loss": 0.9283, "learning_rate": 8.469485410510545e-06, "epoch": 3.9600363306085375, "percentage": 33.03, "elapsed_time": "0:21:58", "remaining_time": "0:44:33"}
+{"current_steps": 1100, "total_steps": 3300, "loss": 0.9616, "learning_rate": 8.43120818934367e-06, "epoch": 3.9963669391462306, "percentage": 33.33, "elapsed_time": "0:22:07", "remaining_time": "0:44:14"}
+{"current_steps": 1110, "total_steps": 3300, "loss": 0.8816, "learning_rate": 8.392547057785662e-06, "epoch": 4.032697547683924, "percentage": 33.64, "elapsed_time": "0:22:15", "remaining_time": "0:43:54"}
+{"current_steps": 1120, "total_steps": 3300, "loss": 0.8704, "learning_rate": 8.353506341546106e-06, "epoch": 4.069028156221616, "percentage": 33.94, "elapsed_time": "0:22:23", "remaining_time": "0:43:35"}
+{"current_steps": 1130, "total_steps": 3300, "loss": 0.8515, "learning_rate": 8.314090408805481e-06, "epoch": 4.10535876475931, "percentage": 34.24, "elapsed_time": "0:22:32", "remaining_time": "0:43:17"}
+{"current_steps": 1140, "total_steps": 3300, "loss": 0.7986, "learning_rate": 8.274303669726427e-06, "epoch": 4.141689373297003, "percentage": 34.55, "elapsed_time": "0:22:40", "remaining_time": "0:42:58"}
+{"current_steps": 1150, "total_steps": 3300, "loss": 0.859, "learning_rate": 8.234150575960288e-06, "epoch": 4.178019981834696, "percentage": 34.85, "elapsed_time": "0:22:49", "remaining_time": "0:42:40"}
+{"current_steps": 1160, "total_steps": 3300, "loss": 0.8537, "learning_rate": 8.193635620149041e-06, "epoch": 4.214350590372389, "percentage": 35.15, "elapsed_time": "0:22:57", "remaining_time": "0:42:20"}
+{"current_steps": 1170, "total_steps": 3300, "loss": 0.8513, "learning_rate": 8.152763335422612e-06, "epoch": 4.2506811989100814, "percentage": 35.45, "elapsed_time": "0:23:05", "remaining_time": "0:42:01"}
+{"current_steps": 1180, "total_steps": 3300, "loss": 0.8318, "learning_rate": 8.111538294891684e-06, "epoch": 4.287011807447775, "percentage": 35.76, "elapsed_time": "0:23:13", "remaining_time": "0:41:42"}
+{"current_steps": 1190, "total_steps": 3300, "loss": 0.846, "learning_rate": 8.06996511113601e-06, "epoch": 4.323342415985468, "percentage": 36.06, "elapsed_time": "0:23:21", "remaining_time": "0:41:24"}
+{"current_steps": 1200, "total_steps": 3300, "loss": 0.8667, "learning_rate": 8.028048435688333e-06, "epoch": 4.359673024523161, "percentage": 36.36, "elapsed_time": "0:23:29", "remaining_time": "0:41:06"}
+{"current_steps": 1210, "total_steps": 3300, "loss": 0.8715, "learning_rate": 7.985792958513932e-06, "epoch": 4.396003633060854, "percentage": 36.67, "elapsed_time": "0:23:37", "remaining_time": "0:40:47"}
+{"current_steps": 1220, "total_steps": 3300, "loss": 0.848, "learning_rate": 7.943203407485864e-06, "epoch": 4.4323342415985465, "percentage": 36.97, "elapsed_time": "0:23:44", "remaining_time": "0:40:28"}
+{"current_steps": 1230, "total_steps": 3300, "loss": 0.8859, "learning_rate": 7.900284547855992e-06, "epoch": 4.46866485013624, "percentage": 37.27, "elapsed_time": "0:23:52", "remaining_time": "0:40:10"}
+{"current_steps": 1240, "total_steps": 3300, "loss": 0.8575, "learning_rate": 7.857041181721788e-06, "epoch": 4.504995458673933, "percentage": 37.58, "elapsed_time": "0:23:59", "remaining_time": "0:39:52"}
+{"current_steps": 1250, "total_steps": 3300, "loss": 0.8496, "learning_rate": 7.813478147489052e-06, "epoch": 4.541326067211626, "percentage": 37.88, "elapsed_time": "0:24:08", "remaining_time": "0:39:34"}
+{"current_steps": 1260, "total_steps": 3300, "loss": 0.8166, "learning_rate": 7.769600319330553e-06, "epoch": 4.577656675749319, "percentage": 38.18, "elapsed_time": "0:24:15", "remaining_time": "0:39:16"}
+{"current_steps": 1270, "total_steps": 3300, "loss": 0.8191, "learning_rate": 7.725412606640658e-06, "epoch": 4.6139872842870115, "percentage": 38.48, "elapsed_time": "0:24:22", "remaining_time": "0:38:57"}
+{"current_steps": 1280, "total_steps": 3300, "loss": 0.833, "learning_rate": 7.680919953486047e-06, "epoch": 4.650317892824705, "percentage": 38.79, "elapsed_time": "0:24:29", "remaining_time": "0:38:39"}
+{"current_steps": 1290, "total_steps": 3300, "loss": 0.839, "learning_rate": 7.636127338052513e-06, "epoch": 4.686648501362398, "percentage": 39.09, "elapsed_time": "0:24:37", "remaining_time": "0:38:21"}
+{"current_steps": 1300, "total_steps": 3300, "loss": 0.807, "learning_rate": 7.5910397720879785e-06, "epoch": 4.722979109900091, "percentage": 39.39, "elapsed_time": "0:24:44", "remaining_time": "0:38:04"}
+{"current_steps": 1310, "total_steps": 3300, "loss": 0.8215, "learning_rate": 7.545662300341736e-06, "epoch": 4.759309718437784, "percentage": 39.7, "elapsed_time": "0:24:51", "remaining_time": "0:37:46"}
+{"current_steps": 1320, "total_steps": 3300, "loss": 0.8584, "learning_rate": 7.500000000000001e-06, "epoch": 4.795640326975477, "percentage": 40.0, "elapsed_time": "0:24:58", "remaining_time": "0:37:28"}
+{"current_steps": 1330, "total_steps": 3300, "loss": 0.7955, "learning_rate": 7.454057980117842e-06, "epoch": 4.83197093551317, "percentage": 40.3, "elapsed_time": "0:25:05", "remaining_time": "0:37:10"}
+{"current_steps": 1340, "total_steps": 3300, "loss": 0.8482, "learning_rate": 7.407841381047533e-06, "epoch": 4.868301544050863, "percentage": 40.61, "elapsed_time": "0:25:12", "remaining_time": "0:36:52"}
+{"current_steps": 1350, "total_steps": 3300, "loss": 0.8457, "learning_rate": 7.361355373863415e-06, "epoch": 4.904632152588556, "percentage": 40.91, "elapsed_time": "0:25:20", "remaining_time": "0:36:35"}
+{"current_steps": 1360, "total_steps": 3300, "loss": 0.8705, "learning_rate": 7.314605159783313e-06, "epoch": 4.940962761126249, "percentage": 41.21, "elapsed_time": "0:25:26", "remaining_time": "0:36:17"}
+{"current_steps": 1370, "total_steps": 3300, "loss": 0.829, "learning_rate": 7.2675959695865896e-06, "epoch": 4.977293369663942, "percentage": 41.52, "elapsed_time": "0:25:33", "remaining_time": "0:36:00"}
+{"current_steps": 1380, "total_steps": 3300, "loss": 0.8391, "learning_rate": 7.2203330630288714e-06, "epoch": 5.013623978201635, "percentage": 41.82, "elapsed_time": "0:25:40", "remaining_time": "0:35:43"}
+{"current_steps": 1390, "total_steps": 3300, "loss": 0.7915, "learning_rate": 7.172821728253563e-06, "epoch": 5.049954586739328, "percentage": 42.12, "elapsed_time": "0:25:47", "remaining_time": "0:35:25"}
+{"current_steps": 1400, "total_steps": 3300, "loss": 0.8199, "learning_rate": 7.1250672812001505e-06, "epoch": 5.0862851952770205, "percentage": 42.42, "elapsed_time": "0:25:53", "remaining_time": "0:35:08"}
+{"current_steps": 1410, "total_steps": 3300, "loss": 0.8065, "learning_rate": 7.0770750650094335e-06, "epoch": 5.122615803814714, "percentage": 42.73, "elapsed_time": "0:26:00", "remaining_time": "0:34:51"}
+{"current_steps": 1420, "total_steps": 3300, "loss": 0.8098, "learning_rate": 7.02885044942567e-06, "epoch": 5.158946412352407, "percentage": 43.03, "elapsed_time": "0:26:06", "remaining_time": "0:34:34"}
+{"current_steps": 1430, "total_steps": 3300, "loss": 0.7675, "learning_rate": 6.980398830195785e-06, "epoch": 5.1952770208901, "percentage": 43.33, "elapsed_time": "0:26:13", "remaining_time": "0:34:17"}
+{"current_steps": 1440, "total_steps": 3300, "loss": 0.7747, "learning_rate": 6.931725628465643e-06, "epoch": 5.231607629427793, "percentage": 43.64, "elapsed_time": "0:26:19", "remaining_time": "0:34:00"}
+{"current_steps": 1450, "total_steps": 3300, "loss": 0.7623, "learning_rate": 6.882836290173493e-06, "epoch": 5.2679382379654855, "percentage": 43.94, "elapsed_time": "0:26:26", "remaining_time": "0:33:43"}
+{"current_steps": 1460, "total_steps": 3300, "loss": 0.8113, "learning_rate": 6.833736285440632e-06, "epoch": 5.304268846503179, "percentage": 44.24, "elapsed_time": "0:26:31", "remaining_time": "0:33:26"}
+{"current_steps": 1470, "total_steps": 3300, "loss": 0.8411, "learning_rate": 6.78443110795936e-06, "epoch": 5.340599455040872, "percentage": 44.55, "elapsed_time": "0:26:38", "remaining_time": "0:33:09"}
+{"current_steps": 1480, "total_steps": 3300, "loss": 0.7592, "learning_rate": 6.734926274378313e-06, "epoch": 5.376930063578565, "percentage": 44.85, "elapsed_time": "0:26:44", "remaining_time": "0:32:52"}
+{"current_steps": 1490, "total_steps": 3300, "loss": 0.7776, "learning_rate": 6.685227323685209e-06, "epoch": 5.413260672116258, "percentage": 45.15, "elapsed_time": "0:26:50", "remaining_time": "0:32:35"}
+{"current_steps": 1500, "total_steps": 3300, "loss": 0.7727, "learning_rate": 6.635339816587109e-06, "epoch": 5.449591280653951, "percentage": 45.45, "elapsed_time": "0:26:56", "remaining_time": "0:32:19"}
+{"current_steps": 1510, "total_steps": 3300, "loss": 0.7539, "learning_rate": 6.5852693348882345e-06, "epoch": 5.485921889191644, "percentage": 45.76, "elapsed_time": "0:27:02", "remaining_time": "0:32:02"}
+{"current_steps": 1520, "total_steps": 3300, "loss": 0.8292, "learning_rate": 6.535021480865439e-06, "epoch": 5.522252497729337, "percentage": 46.06, "elapsed_time": "0:27:07", "remaining_time": "0:31:46"}
+{"current_steps": 1530, "total_steps": 3300, "loss": 0.7463, "learning_rate": 6.484601876641375e-06, "epoch": 5.55858310626703, "percentage": 46.36, "elapsed_time": "0:27:13", "remaining_time": "0:31:29"}
+{"current_steps": 1540, "total_steps": 3300, "loss": 0.7744, "learning_rate": 6.434016163555452e-06, "epoch": 5.594913714804723, "percentage": 46.67, "elapsed_time": "0:27:19", "remaining_time": "0:31:13"}
+{"current_steps": 1550, "total_steps": 3300, "loss": 0.7868, "learning_rate": 6.383270001532636e-06, "epoch": 5.631244323342416, "percentage": 46.97, "elapsed_time": "0:27:25", "remaining_time": "0:30:57"}
+{"current_steps": 1560, "total_steps": 3300, "loss": 0.7485, "learning_rate": 6.332369068450175e-06, "epoch": 5.667574931880109, "percentage": 47.27, "elapsed_time": "0:27:30", "remaining_time": "0:30:41"}
+{"current_steps": 1570, "total_steps": 3300, "loss": 0.7783, "learning_rate": 6.2813190595023135e-06, "epoch": 5.703905540417802, "percentage": 47.58, "elapsed_time": "0:27:36", "remaining_time": "0:30:25"}
+{"current_steps": 1580, "total_steps": 3300, "loss": 0.7769, "learning_rate": 6.230125686563068e-06, "epoch": 5.740236148955495, "percentage": 47.88, "elapsed_time": "0:27:41", "remaining_time": "0:30:09"}
+{"current_steps": 1590, "total_steps": 3300, "loss": 0.7977, "learning_rate": 6.178794677547138e-06, "epoch": 5.776566757493188, "percentage": 48.18, "elapsed_time": "0:27:47", "remaining_time": "0:29:53"}
+{"current_steps": 1600, "total_steps": 3300, "loss": 0.8101, "learning_rate": 6.127331775769023e-06, "epoch": 5.812897366030881, "percentage": 48.48, "elapsed_time": "0:27:54", "remaining_time": "0:29:38"}
+{"current_steps": 1610, "total_steps": 3300, "loss": 0.8397, "learning_rate": 6.07574273930042e-06, "epoch": 5.849227974568574, "percentage": 48.79, "elapsed_time": "0:28:09", "remaining_time": "0:29:33"}
+{"current_steps": 1620, "total_steps": 3300, "loss": 0.8191, "learning_rate": 6.024033340325954e-06, "epoch": 5.885558583106267, "percentage": 49.09, "elapsed_time": "0:28:24", "remaining_time": "0:29:28"}
+{"current_steps": 1630, "total_steps": 3300, "loss": 0.7843, "learning_rate": 5.972209364497355e-06, "epoch": 5.9218891916439595, "percentage": 49.39, "elapsed_time": "0:28:40", "remaining_time": "0:29:22"}
+{"current_steps": 1640, "total_steps": 3300, "loss": 0.8099, "learning_rate": 5.920276610286102e-06, "epoch": 5.958219800181653, "percentage": 49.7, "elapsed_time": "0:28:55", "remaining_time": "0:29:16"}
+{"current_steps": 1650, "total_steps": 3300, "loss": 0.8025, "learning_rate": 5.8682408883346535e-06, "epoch": 5.994550408719346, "percentage": 50.0, "elapsed_time": "0:29:11", "remaining_time": "0:29:11"}
+{"current_steps": 1660, "total_steps": 3300, "loss": 0.7426, "learning_rate": 5.816108020806297e-06, "epoch": 6.030881017257039, "percentage": 50.3, "elapsed_time": "0:29:26", "remaining_time": "0:29:05"}
+{"current_steps": 1670, "total_steps": 3300, "loss": 0.7439, "learning_rate": 5.763883840733736e-06, "epoch": 6.067211625794732, "percentage": 50.61, "elapsed_time": "0:29:41", "remaining_time": "0:28:58"}
+{"current_steps": 1680, "total_steps": 3300, "loss": 0.7617, "learning_rate": 5.711574191366427e-06, "epoch": 6.1035422343324255, "percentage": 50.91, "elapsed_time": "0:29:56", "remaining_time": "0:28:52"}
+{"current_steps": 1690, "total_steps": 3300, "loss": 0.7333, "learning_rate": 5.659184925516802e-06, "epoch": 6.139872842870118, "percentage": 51.21, "elapsed_time": "0:30:11", "remaining_time": "0:28:46"}
+{"current_steps": 1700, "total_steps": 3300, "loss": 0.7747, "learning_rate": 5.60672190490541e-06, "epoch": 6.176203451407811, "percentage": 51.52, "elapsed_time": "0:30:27", "remaining_time": "0:28:39"}
+{"current_steps": 1710, "total_steps": 3300, "loss": 0.7469, "learning_rate": 5.5541909995050554e-06, "epoch": 6.212534059945504, "percentage": 51.82, "elapsed_time": "0:30:41", "remaining_time": "0:28:32"}
+{"current_steps": 1720, "total_steps": 3300, "loss": 0.7507, "learning_rate": 5.5015980868840254e-06, "epoch": 6.248864668483197, "percentage": 52.12, "elapsed_time": "0:30:56", "remaining_time": "0:28:25"}
+{"current_steps": 1730, "total_steps": 3300, "loss": 0.7774, "learning_rate": 5.448949051548459e-06, "epoch": 6.28519527702089, "percentage": 52.42, "elapsed_time": "0:31:11", "remaining_time": "0:28:18"}
+{"current_steps": 1740, "total_steps": 3300, "loss": 0.773, "learning_rate": 5.396249784283943e-06, "epoch": 6.321525885558583, "percentage": 52.73, "elapsed_time": "0:31:25", "remaining_time": "0:28:10"}
+{"current_steps": 1750, "total_steps": 3300, "loss": 0.7333, "learning_rate": 5.343506181496405e-06, "epoch": 6.357856494096276, "percentage": 53.03, "elapsed_time": "0:31:41", "remaining_time": "0:28:03"}
+{"current_steps": 1760, "total_steps": 3300, "loss": 0.7352, "learning_rate": 5.290724144552379e-06, "epoch": 6.394187102633969, "percentage": 53.33, "elapsed_time": "0:31:55", "remaining_time": "0:27:56"}
+{"current_steps": 1770, "total_steps": 3300, "loss": 0.68, "learning_rate": 5.237909579118713e-06, "epoch": 6.430517711171662, "percentage": 53.64, "elapsed_time": "0:32:09", "remaining_time": "0:27:48"}
+{"current_steps": 1780, "total_steps": 3300, "loss": 0.7279, "learning_rate": 5.185068394501791e-06, "epoch": 6.466848319709355, "percentage": 53.94, "elapsed_time": "0:32:24", "remaining_time": "0:27:40"}
+{"current_steps": 1790, "total_steps": 3300, "loss": 0.7547, "learning_rate": 5.132206502986368e-06, "epoch": 6.503178928247048, "percentage": 54.24, "elapsed_time": "0:32:38", "remaining_time": "0:27:31"}
+{"current_steps": 1800, "total_steps": 3300, "loss": 0.7015, "learning_rate": 5.07932981917404e-06, "epoch": 6.539509536784741, "percentage": 54.55, "elapsed_time": "0:32:52", "remaining_time": "0:27:24"}
+{"current_steps": 1810, "total_steps": 3300, "loss": 0.7614, "learning_rate": 5.026444259321489e-06, "epoch": 6.575840145322434, "percentage": 54.85, "elapsed_time": "0:33:06", "remaining_time": "0:27:15"}
+{"current_steps": 1820, "total_steps": 3300, "loss": 0.7953, "learning_rate": 4.973555740678512e-06, "epoch": 6.612170753860127, "percentage": 55.15, "elapsed_time": "0:33:21", "remaining_time": "0:27:07"}
+{"current_steps": 1830, "total_steps": 3300, "loss": 0.736, "learning_rate": 4.9206701808259605e-06, "epoch": 6.64850136239782, "percentage": 55.45, "elapsed_time": "0:33:35", "remaining_time": "0:26:58"}
+{"current_steps": 1840, "total_steps": 3300, "loss": 0.7502, "learning_rate": 4.867793497013634e-06, "epoch": 6.684831970935513, "percentage": 55.76, "elapsed_time": "0:33:49", "remaining_time": "0:26:50"}
+{"current_steps": 1850, "total_steps": 3300, "loss": 0.7496, "learning_rate": 4.81493160549821e-06, "epoch": 6.721162579473206, "percentage": 56.06, "elapsed_time": "0:34:03", "remaining_time": "0:26:42"}
+{"current_steps": 1860, "total_steps": 3300, "loss": 0.7888, "learning_rate": 4.762090420881289e-06, "epoch": 6.7574931880108995, "percentage": 56.36, "elapsed_time": "0:34:17", "remaining_time": "0:26:33"}
+{"current_steps": 1870, "total_steps": 3300, "loss": 0.7238, "learning_rate": 4.7092758554476215e-06, "epoch": 6.793823796548592, "percentage": 56.67, "elapsed_time": "0:34:31", "remaining_time": "0:26:24"}
+{"current_steps": 1880, "total_steps": 3300, "loss": 0.7484, "learning_rate": 4.6564938185035954e-06, "epoch": 6.830154405086285, "percentage": 56.97, "elapsed_time": "0:34:44", "remaining_time": "0:26:14"}
+{"current_steps": 1890, "total_steps": 3300, "loss": 0.7835, "learning_rate": 4.603750215716057e-06, "epoch": 6.866485013623978, "percentage": 57.27, "elapsed_time": "0:34:58", "remaining_time": "0:26:05"}
+{"current_steps": 1900, "total_steps": 3300, "loss": 0.6878, "learning_rate": 4.551050948451542e-06, "epoch": 6.902815622161671, "percentage": 57.58, "elapsed_time": "0:35:12", "remaining_time": "0:25:56"}
+{"current_steps": 1910, "total_steps": 3300, "loss": 0.7528, "learning_rate": 4.498401913115975e-06, "epoch": 6.9391462306993645, "percentage": 57.88, "elapsed_time": "0:35:25", "remaining_time": "0:25:47"}
+{"current_steps": 1920, "total_steps": 3300, "loss": 0.7486, "learning_rate": 4.445809000494945e-06, "epoch": 6.975476839237057, "percentage": 58.18, "elapsed_time": "0:35:39", "remaining_time": "0:25:37"}
+{"current_steps": 1930, "total_steps": 3300, "loss": 0.7948, "learning_rate": 4.393278095094591e-06, "epoch": 7.01180744777475, "percentage": 58.48, "elapsed_time": "0:35:52", "remaining_time": "0:25:28"}
+{"current_steps": 1940, "total_steps": 3300, "loss": 0.6872, "learning_rate": 4.340815074483199e-06, "epoch": 7.048138056312443, "percentage": 58.79, "elapsed_time": "0:36:06", "remaining_time": "0:25:18"}
+{"current_steps": 1950, "total_steps": 3300, "loss": 0.7289, "learning_rate": 4.2884258086335755e-06, "epoch": 7.084468664850136, "percentage": 59.09, "elapsed_time": "0:36:19", "remaining_time": "0:25:09"}
+{"current_steps": 1960, "total_steps": 3300, "loss": 0.612, "learning_rate": 4.2361161592662655e-06, "epoch": 7.12079927338783, "percentage": 59.39, "elapsed_time": "0:36:33", "remaining_time": "0:24:59"}
+{"current_steps": 1970, "total_steps": 3300, "loss": 0.7135, "learning_rate": 4.183891979193703e-06, "epoch": 7.157129881925522, "percentage": 59.7, "elapsed_time": "0:36:46", "remaining_time": "0:24:49"}
+{"current_steps": 1980, "total_steps": 3300, "loss": 0.6932, "learning_rate": 4.131759111665349e-06, "epoch": 7.193460490463215, "percentage": 60.0, "elapsed_time": "0:36:59", "remaining_time": "0:24:39"}
+{"current_steps": 1990, "total_steps": 3300, "loss": 0.705, "learning_rate": 4.079723389713899e-06, "epoch": 7.229791099000908, "percentage": 60.3, "elapsed_time": "0:37:12", "remaining_time": "0:24:29"}
+{"current_steps": 2000, "total_steps": 3300, "loss": 0.7145, "learning_rate": 4.027790635502646e-06, "epoch": 7.266121707538601, "percentage": 60.61, "elapsed_time": "0:37:25", "remaining_time": "0:24:19"}
+{"current_steps": 2000, "total_steps": 3300, "eval_loss": 1.1055254936218262, "epoch": 7.266121707538601, "percentage": 60.61, "elapsed_time": "0:37:35", "remaining_time": "0:24:26"}
+{"current_steps": 2010, "total_steps": 3300, "loss": 0.6724, "learning_rate": 3.975966659674048e-06, "epoch": 7.302452316076295, "percentage": 60.91, "elapsed_time": "0:37:48", "remaining_time": "0:24:15"}
+{"current_steps": 2020, "total_steps": 3300, "loss": 0.6468, "learning_rate": 3.924257260699583e-06, "epoch": 7.338782924613987, "percentage": 61.21, "elapsed_time": "0:38:00", "remaining_time": "0:24:05"}
+{"current_steps": 2030, "total_steps": 3300, "loss": 0.6792, "learning_rate": 3.872668224230979e-06, "epoch": 7.37511353315168, "percentage": 61.52, "elapsed_time": "0:38:13", "remaining_time": "0:23:54"}
+{"current_steps": 2040, "total_steps": 3300, "loss": 0.723, "learning_rate": 3.821205322452863e-06, "epoch": 7.4114441416893735, "percentage": 61.82, "elapsed_time": "0:38:26", "remaining_time": "0:23:44"}
+{"current_steps": 2050, "total_steps": 3300, "loss": 0.6608, "learning_rate": 3.769874313436933e-06, "epoch": 7.447774750227066, "percentage": 62.12, "elapsed_time": "0:38:39", "remaining_time": "0:23:34"}
+{"current_steps": 2060, "total_steps": 3300, "loss": 0.6679, "learning_rate": 3.7186809404976877e-06, "epoch": 7.48410535876476, "percentage": 62.42, "elapsed_time": "0:38:51", "remaining_time": "0:23:23"}
+{"current_steps": 2070, "total_steps": 3300, "loss": 0.6944, "learning_rate": 3.667630931549826e-06, "epoch": 7.520435967302452, "percentage": 62.73, "elapsed_time": "0:39:03", "remaining_time": "0:23:12"}
+{"current_steps": 2080, "total_steps": 3300, "loss": 0.7172, "learning_rate": 3.6167299984673655e-06, "epoch": 7.556766575840145, "percentage": 63.03, "elapsed_time": "0:39:16", "remaining_time": "0:23:02"}
+{"current_steps": 2090, "total_steps": 3300, "loss": 0.7029, "learning_rate": 3.5659838364445505e-06, "epoch": 7.5930971843778385, "percentage": 63.33, "elapsed_time": "0:39:28", "remaining_time": "0:22:51"}
+{"current_steps": 2100, "total_steps": 3300, "loss": 0.6549, "learning_rate": 3.5153981233586277e-06, "epoch": 7.629427792915531, "percentage": 63.64, "elapsed_time": "0:39:41", "remaining_time": "0:22:40"}
+{"current_steps": 2110, "total_steps": 3300, "loss": 0.7342, "learning_rate": 3.4649785191345613e-06, "epoch": 7.665758401453225, "percentage": 63.94, "elapsed_time": "0:39:53", "remaining_time": "0:22:29"}
+{"current_steps": 2120, "total_steps": 3300, "loss": 0.6246, "learning_rate": 3.4147306651117663e-06, "epoch": 7.702089009990917, "percentage": 64.24, "elapsed_time": "0:40:05", "remaining_time": "0:22:18"}
+{"current_steps": 2130, "total_steps": 3300, "loss": 0.6587, "learning_rate": 3.3646601834128924e-06, "epoch": 7.73841961852861, "percentage": 64.55, "elapsed_time": "0:40:17", "remaining_time": "0:22:07"}
+{"current_steps": 2140, "total_steps": 3300, "loss": 0.6682, "learning_rate": 3.3147726763147913e-06, "epoch": 7.774750227066304, "percentage": 64.85, "elapsed_time": "0:40:29", "remaining_time": "0:21:56"}
+{"current_steps": 2150, "total_steps": 3300, "loss": 0.6854, "learning_rate": 3.2650737256216885e-06, "epoch": 7.811080835603996, "percentage": 65.15, "elapsed_time": "0:40:41", "remaining_time": "0:21:46"}
+{"current_steps": 2160, "total_steps": 3300, "loss": 0.6908, "learning_rate": 3.2155688920406415e-06, "epoch": 7.84741144414169, "percentage": 65.45, "elapsed_time": "0:40:53", "remaining_time": "0:21:34"}
+{"current_steps": 2170, "total_steps": 3300, "loss": 0.6875, "learning_rate": 3.16626371455937e-06, "epoch": 7.883742052679382, "percentage": 65.76, "elapsed_time": "0:41:05", "remaining_time": "0:21:23"}
+{"current_steps": 2180, "total_steps": 3300, "loss": 0.6732, "learning_rate": 3.1171637098265063e-06, "epoch": 7.920072661217075, "percentage": 66.06, "elapsed_time": "0:41:16", "remaining_time": "0:21:12"}
+{"current_steps": 2190, "total_steps": 3300, "loss": 0.742, "learning_rate": 3.0682743715343565e-06, "epoch": 7.956403269754769, "percentage": 66.36, "elapsed_time": "0:41:28", "remaining_time": "0:21:01"}
+{"current_steps": 2200, "total_steps": 3300, "loss": 0.6791, "learning_rate": 3.019601169804216e-06, "epoch": 7.992733878292461, "percentage": 66.67, "elapsed_time": "0:41:40", "remaining_time": "0:20:50"}
+{"current_steps": 2210, "total_steps": 3300, "loss": 0.654, "learning_rate": 2.9711495505743317e-06, "epoch": 8.029064486830155, "percentage": 66.97, "elapsed_time": "0:41:51", "remaining_time": "0:20:38"}
+{"current_steps": 2220, "total_steps": 3300, "loss": 0.705, "learning_rate": 2.9229249349905686e-06, "epoch": 8.065395095367847, "percentage": 67.27, "elapsed_time": "0:42:03", "remaining_time": "0:20:27"}
+{"current_steps": 2230, "total_steps": 3300, "loss": 0.6067, "learning_rate": 2.8749327187998516e-06, "epoch": 8.10172570390554, "percentage": 67.58, "elapsed_time": "0:42:14", "remaining_time": "0:20:16"}
+{"current_steps": 2240, "total_steps": 3300, "loss": 0.6043, "learning_rate": 2.8271782717464413e-06, "epoch": 8.138056312443233, "percentage": 67.88, "elapsed_time": "0:42:26", "remaining_time": "0:20:04"}
+{"current_steps": 2250, "total_steps": 3300, "loss": 0.6292, "learning_rate": 2.7796669369711294e-06, "epoch": 8.174386920980927, "percentage": 68.18, "elapsed_time": "0:42:38", "remaining_time": "0:19:53"}
+{"current_steps": 2260, "total_steps": 3300, "loss": 0.6041, "learning_rate": 2.7324040304134125e-06, "epoch": 8.21071752951862, "percentage": 68.48, "elapsed_time": "0:42:49", "remaining_time": "0:19:42"}
+{"current_steps": 2270, "total_steps": 3300, "loss": 0.6222, "learning_rate": 2.685394840216688e-06, "epoch": 8.247048138056313, "percentage": 68.79, "elapsed_time": "0:43:00", "remaining_time": "0:19:30"}
+{"current_steps": 2280, "total_steps": 3300, "loss": 0.6586, "learning_rate": 2.6386446261365874e-06, "epoch": 8.283378746594005, "percentage": 69.09, "elapsed_time": "0:43:11", "remaining_time": "0:19:19"}
+{"current_steps": 2290, "total_steps": 3300, "loss": 0.6612, "learning_rate": 2.5921586189524694e-06, "epoch": 8.319709355131698, "percentage": 69.39, "elapsed_time": "0:43:22", "remaining_time": "0:19:07"}
+{"current_steps": 2300, "total_steps": 3300, "loss": 0.6693, "learning_rate": 2.5459420198821604e-06, "epoch": 8.356039963669392, "percentage": 69.7, "elapsed_time": "0:43:34", "remaining_time": "0:18:56"}
+{"current_steps": 2310, "total_steps": 3300, "loss": 0.6244, "learning_rate": 2.5000000000000015e-06, "epoch": 8.392370572207085, "percentage": 70.0, "elapsed_time": "0:43:45", "remaining_time": "0:18:45"}
+{"current_steps": 2320, "total_steps": 3300, "loss": 0.6312, "learning_rate": 2.454337699658267e-06, "epoch": 8.428701180744778, "percentage": 70.3, "elapsed_time": "0:43:55", "remaining_time": "0:18:33"}
+{"current_steps": 2330, "total_steps": 3300, "loss": 0.6729, "learning_rate": 2.4089602279120224e-06, "epoch": 8.46503178928247, "percentage": 70.61, "elapsed_time": "0:44:06", "remaining_time": "0:18:21"}
+{"current_steps": 2340, "total_steps": 3300, "loss": 0.6276, "learning_rate": 2.363872661947488e-06, "epoch": 8.501362397820163, "percentage": 70.91, "elapsed_time": "0:44:17", "remaining_time": "0:18:10"}
+{"current_steps": 2350, "total_steps": 3300, "loss": 0.6292, "learning_rate": 2.319080046513954e-06, "epoch": 8.537693006357856, "percentage": 71.21, "elapsed_time": "0:44:28", "remaining_time": "0:17:58"}
+{"current_steps": 2360, "total_steps": 3300, "loss": 0.6593, "learning_rate": 2.274587393359342e-06, "epoch": 8.57402361489555, "percentage": 71.52, "elapsed_time": "0:44:39", "remaining_time": "0:17:47"}
+{"current_steps": 2370, "total_steps": 3300, "loss": 0.6302, "learning_rate": 2.230399680669449e-06, "epoch": 8.610354223433243, "percentage": 71.82, "elapsed_time": "0:44:49", "remaining_time": "0:17:35"}
+{"current_steps": 2380, "total_steps": 3300, "loss": 0.6481, "learning_rate": 2.1865218525109496e-06, "epoch": 8.646684831970935, "percentage": 72.12, "elapsed_time": "0:45:00", "remaining_time": "0:17:23"}
+{"current_steps": 2390, "total_steps": 3300, "loss": 0.6175, "learning_rate": 2.1429588182782147e-06, "epoch": 8.683015440508628, "percentage": 72.42, "elapsed_time": "0:45:10", "remaining_time": "0:17:12"}
+{"current_steps": 2400, "total_steps": 3300, "loss": 0.6144, "learning_rate": 2.09971545214401e-06, "epoch": 8.719346049046322, "percentage": 72.73, "elapsed_time": "0:45:21", "remaining_time": "0:17:00"}
+{"current_steps": 2410, "total_steps": 3300, "loss": 0.6572, "learning_rate": 2.0567965925141366e-06, "epoch": 8.755676657584015, "percentage": 73.03, "elapsed_time": "0:45:31", "remaining_time": "0:16:48"}
+{"current_steps": 2420, "total_steps": 3300, "loss": 0.654, "learning_rate": 2.0142070414860704e-06, "epoch": 8.792007266121708, "percentage": 73.33, "elapsed_time": "0:45:41", "remaining_time": "0:16:37"}
+{"current_steps": 2430, "total_steps": 3300, "loss": 0.621, "learning_rate": 1.971951564311668e-06, "epoch": 8.8283378746594, "percentage": 73.64, "elapsed_time": "0:45:52", "remaining_time": "0:16:25"}
+{"current_steps": 2440, "total_steps": 3300, "loss": 0.62, "learning_rate": 1.9300348888639915e-06, "epoch": 8.864668483197093, "percentage": 73.94, "elapsed_time": "0:46:02", "remaining_time": "0:16:13"}
+{"current_steps": 2450, "total_steps": 3300, "loss": 0.5858, "learning_rate": 1.8884617051083183e-06, "epoch": 8.900999091734786, "percentage": 74.24, "elapsed_time": "0:46:13", "remaining_time": "0:16:02"}
+{"current_steps": 2460, "total_steps": 3300, "loss": 0.6467, "learning_rate": 1.8472366645773892e-06, "epoch": 8.93732970027248, "percentage": 74.55, "elapsed_time": "0:46:23", "remaining_time": "0:15:50"}
+{"current_steps": 2470, "total_steps": 3300, "loss": 0.6138, "learning_rate": 1.8063643798509594e-06, "epoch": 8.973660308810173, "percentage": 74.85, "elapsed_time": "0:46:33", "remaining_time": "0:15:38"}
+{"current_steps": 2480, "total_steps": 3300, "loss": 0.6388, "learning_rate": 1.7658494240397127e-06, "epoch": 9.009990917347865, "percentage": 75.15, "elapsed_time": "0:46:42", "remaining_time": "0:15:26"}
+{"current_steps": 2490, "total_steps": 3300, "loss": 0.5733, "learning_rate": 1.7256963302735752e-06, "epoch": 9.046321525885558, "percentage": 75.45, "elapsed_time": "0:46:52", "remaining_time": "0:15:14"}
+{"current_steps": 2500, "total_steps": 3300, "loss": 0.6066, "learning_rate": 1.68590959119452e-06, "epoch": 9.082652134423252, "percentage": 75.76, "elapsed_time": "0:47:03", "remaining_time": "0:15:03"}
+{"current_steps": 2510, "total_steps": 3300, "loss": 0.5849, "learning_rate": 1.646493658453896e-06, "epoch": 9.118982742960945, "percentage": 76.06, "elapsed_time": "0:47:12", "remaining_time": "0:14:51"}
+{"current_steps": 2520, "total_steps": 3300, "loss": 0.6136, "learning_rate": 1.6074529422143398e-06, "epoch": 9.155313351498638, "percentage": 76.36, "elapsed_time": "0:47:22", "remaining_time": "0:14:39"}
+{"current_steps": 2530, "total_steps": 3300, "loss": 0.5891, "learning_rate": 1.5687918106563326e-06, "epoch": 9.19164396003633, "percentage": 76.67, "elapsed_time": "0:47:31", "remaining_time": "0:14:27"}
+{"current_steps": 2540, "total_steps": 3300, "loss": 0.6065, "learning_rate": 1.5305145894894547e-06, "epoch": 9.227974568574023, "percentage": 76.97, "elapsed_time": "0:47:41", "remaining_time": "0:14:16"}
+{"current_steps": 2550, "total_steps": 3300, "loss": 0.5854, "learning_rate": 1.4926255614683931e-06, "epoch": 9.264305177111716, "percentage": 77.27, "elapsed_time": "0:47:51", "remaining_time": "0:14:04"}
+{"current_steps": 2560, "total_steps": 3300, "loss": 0.6023, "learning_rate": 1.4551289659137497e-06, "epoch": 9.30063578564941, "percentage": 77.58, "elapsed_time": "0:48:00", "remaining_time": "0:13:52"}
+{"current_steps": 2570, "total_steps": 3300, "loss": 0.6052, "learning_rate": 1.4180289982377138e-06, "epoch": 9.336966394187103, "percentage": 77.88, "elapsed_time": "0:48:09", "remaining_time": "0:13:40"}
+{"current_steps": 2580, "total_steps": 3300, "loss": 0.5806, "learning_rate": 1.3813298094746491e-06, "epoch": 9.373297002724795, "percentage": 78.18, "elapsed_time": "0:48:18", "remaining_time": "0:13:28"}
+{"current_steps": 2590, "total_steps": 3300, "loss": 0.6058, "learning_rate": 1.345035505816642e-06, "epoch": 9.409627611262488, "percentage": 78.48, "elapsed_time": "0:48:28", "remaining_time": "0:13:17"}
+{"current_steps": 2600, "total_steps": 3300, "loss": 0.6339, "learning_rate": 1.3091501481540676e-06, "epoch": 9.44595821980018, "percentage": 78.79, "elapsed_time": "0:48:37", "remaining_time": "0:13:05"}
+{"current_steps": 2610, "total_steps": 3300, "loss": 0.6058, "learning_rate": 1.2736777516212267e-06, "epoch": 9.482288828337875, "percentage": 79.09, "elapsed_time": "0:48:46", "remaining_time": "0:12:53"}
+{"current_steps": 2620, "total_steps": 3300, "loss": 0.6186, "learning_rate": 1.238622285147103e-06, "epoch": 9.518619436875568, "percentage": 79.39, "elapsed_time": "0:48:55", "remaining_time": "0:12:41"}
+{"current_steps": 2630, "total_steps": 3300, "loss": 0.5913, "learning_rate": 1.2039876710112847e-06, "epoch": 9.55495004541326, "percentage": 79.7, "elapsed_time": "0:49:04", "remaining_time": "0:12:30"}
+{"current_steps": 2640, "total_steps": 3300, "loss": 0.663, "learning_rate": 1.1697777844051105e-06, "epoch": 9.591280653950953, "percentage": 80.0, "elapsed_time": "0:49:13", "remaining_time": "0:12:18"}
+{"current_steps": 2650, "total_steps": 3300, "loss": 0.6278, "learning_rate": 1.135996452998085e-06, "epoch": 9.627611262488646, "percentage": 80.3, "elapsed_time": "0:49:22", "remaining_time": "0:12:06"}
+{"current_steps": 2660, "total_steps": 3300, "loss": 0.6074, "learning_rate": 1.1026474565096068e-06, "epoch": 9.66394187102634, "percentage": 80.61, "elapsed_time": "0:49:31", "remaining_time": "0:11:54"}
+{"current_steps": 2670, "total_steps": 3300, "loss": 0.6545, "learning_rate": 1.0697345262860638e-06, "epoch": 9.700272479564033, "percentage": 80.91, "elapsed_time": "0:49:40", "remaining_time": "0:11:43"}
+{"current_steps": 2680, "total_steps": 3300, "loss": 0.6141, "learning_rate": 1.0372613448833429e-06, "epoch": 9.736603088101726, "percentage": 81.21, "elapsed_time": "0:49:48", "remaining_time": "0:11:31"}
+{"current_steps": 2690, "total_steps": 3300, "loss": 0.5699, "learning_rate": 1.0052315456547934e-06, "epoch": 9.772933696639418, "percentage": 81.52, "elapsed_time": "0:49:57", "remaining_time": "0:11:19"}
+{"current_steps": 2700, "total_steps": 3300, "loss": 0.579, "learning_rate": 9.73648712344707e-07, "epoch": 9.809264305177111, "percentage": 81.82, "elapsed_time": "0:50:06", "remaining_time": "0:11:08"}
+{"current_steps": 2710, "total_steps": 3300, "loss": 0.61, "learning_rate": 9.425163786873292e-07, "epoch": 9.845594913714805, "percentage": 82.12, "elapsed_time": "0:50:14", "remaining_time": "0:10:56"}
+{"current_steps": 2720, "total_steps": 3300, "loss": 0.6106, "learning_rate": 9.118380280114858e-07, "epoch": 9.881925522252498, "percentage": 82.42, "elapsed_time": "0:50:22", "remaining_time": "0:10:44"}
+{"current_steps": 2730, "total_steps": 3300, "loss": 0.6066, "learning_rate": 8.816170928508367e-07, "epoch": 9.91825613079019, "percentage": 82.73, "elapsed_time": "0:50:31", "remaining_time": "0:10:32"}
+{"current_steps": 2740, "total_steps": 3300, "loss": 0.6094, "learning_rate": 8.518569545598198e-07, "epoch": 9.954586739327883, "percentage": 83.03, "elapsed_time": "0:50:39", "remaining_time": "0:10:21"}
+{"current_steps": 2750, "total_steps": 3300, "loss": 0.6383, "learning_rate": 8.225609429353187e-07, "epoch": 9.990917347865576, "percentage": 83.33, "elapsed_time": "0:50:48", "remaining_time": "0:10:09"}
+{"current_steps": 2760, "total_steps": 3300, "loss": 0.6017, "learning_rate": 7.937323358440935e-07, "epoch": 10.02724795640327, "percentage": 83.64, "elapsed_time": "0:50:56", "remaining_time": "0:09:57"}
+{"current_steps": 2770, "total_steps": 3300, "loss": 0.6005, "learning_rate": 7.653743588560387e-07, "epoch": 10.063578564940963, "percentage": 83.94, "elapsed_time": "0:51:04", "remaining_time": "0:09:46"}
+{"current_steps": 2780, "total_steps": 3300, "loss": 0.647, "learning_rate": 7.374901848832683e-07, "epoch": 10.099909173478656, "percentage": 84.24, "elapsed_time": "0:51:12", "remaining_time": "0:09:34"}
+{"current_steps": 2790, "total_steps": 3300, "loss": 0.5894, "learning_rate": 7.100829338251147e-07, "epoch": 10.136239782016348, "percentage": 84.55, "elapsed_time": "0:51:20", "remaining_time": "0:09:23"}
+{"current_steps": 2800, "total_steps": 3300, "loss": 0.6075, "learning_rate": 6.831556722190453e-07, "epoch": 10.172570390554041, "percentage": 84.85, "elapsed_time": "0:51:28", "remaining_time": "0:09:11"}
+{"current_steps": 2810, "total_steps": 3300, "loss": 0.5531, "learning_rate": 6.567114128975571e-07, "epoch": 10.208900999091735, "percentage": 85.15, "elapsed_time": "0:51:36", "remaining_time": "0:08:59"}
+{"current_steps": 2820, "total_steps": 3300, "loss": 0.6052, "learning_rate": 6.307531146510754e-07, "epoch": 10.245231607629428, "percentage": 85.45, "elapsed_time": "0:51:43", "remaining_time": "0:08:48"}
+{"current_steps": 2830, "total_steps": 3300, "loss": 0.5833, "learning_rate": 6.052836818969027e-07, "epoch": 10.28156221616712, "percentage": 85.76, "elapsed_time": "0:51:51", "remaining_time": "0:08:36"}
+{"current_steps": 2840, "total_steps": 3300, "loss": 0.5934, "learning_rate": 5.803059643542491e-07, "epoch": 10.317892824704813, "percentage": 86.06, "elapsed_time": "0:51:59", "remaining_time": "0:08:25"}
+{"current_steps": 2850, "total_steps": 3300, "loss": 0.5931, "learning_rate": 5.558227567253832e-07, "epoch": 10.354223433242506, "percentage": 86.36, "elapsed_time": "0:52:07", "remaining_time": "0:08:13"}
+{"current_steps": 2860, "total_steps": 3300, "loss": 0.6253, "learning_rate": 5.318367983829393e-07, "epoch": 10.3905540417802, "percentage": 86.67, "elapsed_time": "0:52:14", "remaining_time": "0:08:02"}
+{"current_steps": 2870, "total_steps": 3300, "loss": 0.61, "learning_rate": 5.083507730634152e-07, "epoch": 10.426884650317893, "percentage": 86.97, "elapsed_time": "0:52:21", "remaining_time": "0:07:50"}
+{"current_steps": 2880, "total_steps": 3300, "loss": 0.6329, "learning_rate": 4.853673085668947e-07, "epoch": 10.463215258855586, "percentage": 87.27, "elapsed_time": "0:52:29", "remaining_time": "0:07:39"}
+{"current_steps": 2890, "total_steps": 3300, "loss": 0.5733, "learning_rate": 4.628889764630279e-07, "epoch": 10.499545867393278, "percentage": 87.58, "elapsed_time": "0:52:36", "remaining_time": "0:07:27"}
+{"current_steps": 2900, "total_steps": 3300, "loss": 0.5922, "learning_rate": 4.4091829180330503e-07, "epoch": 10.535876475930971, "percentage": 87.88, "elapsed_time": "0:52:44", "remaining_time": "0:07:16"}
+{"current_steps": 2910, "total_steps": 3300, "loss": 0.5843, "learning_rate": 4.194577128396521e-07, "epoch": 10.572207084468666, "percentage": 88.18, "elapsed_time": "0:52:51", "remaining_time": "0:07:05"}
+{"current_steps": 2920, "total_steps": 3300, "loss": 0.6028, "learning_rate": 3.985096407493838e-07, "epoch": 10.608537693006358, "percentage": 88.48, "elapsed_time": "0:52:58", "remaining_time": "0:06:53"}
+{"current_steps": 2930, "total_steps": 3300, "loss": 0.5767, "learning_rate": 3.7807641936653984e-07, "epoch": 10.64486830154405, "percentage": 88.79, "elapsed_time": "0:53:05", "remaining_time": "0:06:42"}
+{"current_steps": 2940, "total_steps": 3300, "loss": 0.6062, "learning_rate": 3.581603349196372e-07, "epoch": 10.681198910081743, "percentage": 89.09, "elapsed_time": "0:53:11", "remaining_time": "0:06:30"}
+{"current_steps": 2950, "total_steps": 3300, "loss": 0.5978, "learning_rate": 3.3876361577587115e-07, "epoch": 10.717529518619436, "percentage": 89.39, "elapsed_time": "0:53:19", "remaining_time": "0:06:19"}
+{"current_steps": 2960, "total_steps": 3300, "loss": 0.5984, "learning_rate": 3.1988843219178776e-07, "epoch": 10.75386012715713, "percentage": 89.7, "elapsed_time": "0:53:26", "remaining_time": "0:06:08"}
+{"current_steps": 2970, "total_steps": 3300, "loss": 0.5761, "learning_rate": 3.015368960704584e-07, "epoch": 10.790190735694823, "percentage": 90.0, "elapsed_time": "0:53:32", "remaining_time": "0:05:56"}
+{"current_steps": 2980, "total_steps": 3300, "loss": 0.5988, "learning_rate": 2.8371106072518194e-07, "epoch": 10.826521344232516, "percentage": 90.3, "elapsed_time": "0:53:39", "remaining_time": "0:05:45"}
+{"current_steps": 2990, "total_steps": 3300, "loss": 0.593, "learning_rate": 2.664129206497479e-07, "epoch": 10.862851952770209, "percentage": 90.61, "elapsed_time": "0:53:45", "remaining_time": "0:05:34"}
+{"current_steps": 3000, "total_steps": 3300, "loss": 0.6401, "learning_rate": 2.4964441129527337e-07, "epoch": 10.899182561307901, "percentage": 90.91, "elapsed_time": "0:53:52", "remaining_time": "0:05:23"}
+{"current_steps": 3000, "total_steps": 3300, "eval_loss": 1.12338387966156, "epoch": 10.899182561307901, "percentage": 90.91, "elapsed_time": "0:54:03", "remaining_time": "0:05:24"}
+{"current_steps": 3010, "total_steps": 3300, "loss": 0.5798, "learning_rate": 2.3340740885364922e-07, "epoch": 10.935513169845596, "percentage": 91.21, "elapsed_time": "0:54:09", "remaining_time": "0:05:13"}
+{"current_steps": 3020, "total_steps": 3300, "loss": 0.5684, "learning_rate": 2.1770373004762035e-07, "epoch": 10.971843778383288, "percentage": 91.52, "elapsed_time": "0:54:15", "remaining_time": "0:05:01"}
+{"current_steps": 3030, "total_steps": 3300, "loss": 0.619, "learning_rate": 2.0253513192751374e-07, "epoch": 11.008174386920981, "percentage": 91.82, "elapsed_time": "0:54:22", "remaining_time": "0:04:50"}
+{"current_steps": 3040, "total_steps": 3300, "loss": 0.5739, "learning_rate": 1.8790331167464758e-07, "epoch": 11.044504995458674, "percentage": 92.12, "elapsed_time": "0:54:28", "remaining_time": "0:04:39"}
+{"current_steps": 3050, "total_steps": 3300, "loss": 0.6039, "learning_rate": 1.738099064114368e-07, "epoch": 11.080835603996366, "percentage": 92.42, "elapsed_time": "0:54:35", "remaining_time": "0:04:28"}
+{"current_steps": 3060, "total_steps": 3300, "loss": 0.6057, "learning_rate": 1.6025649301821877e-07, "epoch": 11.11716621253406, "percentage": 92.73, "elapsed_time": "0:54:41", "remaining_time": "0:04:17"}
+{"current_steps": 3070, "total_steps": 3300, "loss": 0.5966, "learning_rate": 1.4724458795681962e-07, "epoch": 11.153496821071753, "percentage": 93.03, "elapsed_time": "0:54:47", "remaining_time": "0:04:06"}
+{"current_steps": 3080, "total_steps": 3300, "loss": 0.5987, "learning_rate": 1.3477564710088097e-07, "epoch": 11.189827429609446, "percentage": 93.33, "elapsed_time": "0:54:53", "remaining_time": "0:03:55"}
+{"current_steps": 3090, "total_steps": 3300, "loss": 0.614, "learning_rate": 1.2285106557296479e-07, "epoch": 11.226158038147139, "percentage": 93.64, "elapsed_time": "0:54:59", "remaining_time": "0:03:44"}
+{"current_steps": 3100, "total_steps": 3300, "loss": 0.5854, "learning_rate": 1.1147217758845752e-07, "epoch": 11.262488646684831, "percentage": 93.94, "elapsed_time": "0:55:05", "remaining_time": "0:03:33"}
+{"current_steps": 3110, "total_steps": 3300, "loss": 0.5866, "learning_rate": 1.0064025630628583e-07, "epoch": 11.298819255222526, "percentage": 94.24, "elapsed_time": "0:55:11", "remaining_time": "0:03:22"}
+{"current_steps": 3120, "total_steps": 3300, "loss": 0.6412, "learning_rate": 9.035651368646647e-08, "epoch": 11.335149863760218, "percentage": 94.55, "elapsed_time": "0:55:17", "remaining_time": "0:03:11"}
+{"current_steps": 3130, "total_steps": 3300, "loss": 0.5935, "learning_rate": 8.06221003545038e-08, "epoch": 11.371480472297911, "percentage": 94.85, "elapsed_time": "0:55:23", "remaining_time": "0:03:00"}
+{"current_steps": 3140, "total_steps": 3300, "loss": 0.6097, "learning_rate": 7.143810547264762e-08, "epoch": 11.407811080835604, "percentage": 95.15, "elapsed_time": "0:55:28", "remaining_time": "0:02:49"}
+{"current_steps": 3150, "total_steps": 3300, "loss": 0.5737, "learning_rate": 6.280555661802857e-08, "epoch": 11.444141689373296, "percentage": 95.45, "elapsed_time": "0:55:34", "remaining_time": "0:02:38"}
+{"current_steps": 3160, "total_steps": 3300, "loss": 0.5908, "learning_rate": 5.472541966768552e-08, "epoch": 11.48047229791099, "percentage": 95.76, "elapsed_time": "0:55:40", "remaining_time": "0:02:27"}
+{"current_steps": 3170, "total_steps": 3300, "loss": 0.5884, "learning_rate": 4.719859869049659e-08, "epoch": 11.516802906448683, "percentage": 96.06, "elapsed_time": "0:55:45", "remaining_time": "0:02:17"}
+{"current_steps": 3180, "total_steps": 3300, "loss": 0.6072, "learning_rate": 4.02259358460233e-08, "epoch": 11.553133514986376, "percentage": 96.36, "elapsed_time": "0:55:51", "remaining_time": "0:02:06"}
+{"current_steps": 3190, "total_steps": 3300, "loss": 0.6049, "learning_rate": 3.3808211290284886e-08, "epoch": 11.589464123524069, "percentage": 96.67, "elapsed_time": "0:55:56", "remaining_time": "0:01:55"}
+{"current_steps": 3200, "total_steps": 3300, "loss": 0.6021, "learning_rate": 2.7946143088466437e-08, "epoch": 11.625794732061761, "percentage": 96.97, "elapsed_time": "0:56:03", "remaining_time": "0:01:45"}
+{"current_steps": 3210, "total_steps": 3300, "loss": 0.6059, "learning_rate": 2.264038713457706e-08, "epoch": 11.662125340599456, "percentage": 97.27, "elapsed_time": "0:56:18", "remaining_time": "0:01:34"}
+{"current_steps": 3220, "total_steps": 3300, "loss": 0.601, "learning_rate": 1.789153707806357e-08, "epoch": 11.698455949137148, "percentage": 97.58, "elapsed_time": "0:56:34", "remaining_time": "0:01:24"}
+{"current_steps": 3230, "total_steps": 3300, "loss": 0.5657, "learning_rate": 1.3700124257388092e-08, "epoch": 11.734786557674841, "percentage": 97.88, "elapsed_time": "0:56:49", "remaining_time": "0:01:13"}
+{"current_steps": 3240, "total_steps": 3300, "loss": 0.6255, "learning_rate": 1.006661764057837e-08, "epoch": 11.771117166212534, "percentage": 98.18, "elapsed_time": "0:57:04", "remaining_time": "0:01:03"}
+{"current_steps": 3250, "total_steps": 3300, "loss": 0.6209, "learning_rate": 6.991423772753636e-09, "epoch": 11.807447774750226, "percentage": 98.48, "elapsed_time": "0:57:20", "remaining_time": "0:00:52"}
+{"current_steps": 3260, "total_steps": 3300, "loss": 0.6111, "learning_rate": 4.474886730641004e-09, "epoch": 11.84377838328792, "percentage": 98.79, "elapsed_time": "0:57:35", "remaining_time": "0:00:42"}
+{"current_steps": 3270, "total_steps": 3300, "loss": 0.6328, "learning_rate": 2.5172880840745873e-09, "epoch": 11.880108991825614, "percentage": 99.09, "elapsed_time": "0:57:50", "remaining_time": "0:00:31"}
+{"current_steps": 3280, "total_steps": 3300, "loss": 0.5511, "learning_rate": 1.118846864490708e-09, "epoch": 11.916439600363306, "percentage": 99.39, "elapsed_time": "0:58:05", "remaining_time": "0:00:21"}
+{"current_steps": 3290, "total_steps": 3300, "loss": 0.5795, "learning_rate": 2.797195404247166e-10, "epoch": 11.952770208900999, "percentage": 99.7, "elapsed_time": "0:58:20", "remaining_time": "0:00:10"}
+{"current_steps": 3300, "total_steps": 3300, "loss": 0.5714, "learning_rate": 0.0, "epoch": 11.989100817438691, "percentage": 100.0, "elapsed_time": "0:58:35", "remaining_time": "0:00:00"}
+{"current_steps": 3300, "total_steps": 3300, "epoch": 11.989100817438691, "percentage": 100.0, "elapsed_time": "0:59:45", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,2376 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 11.989100817438691,
+  "eval_steps": 1000,
+  "global_step": 3300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03633060853769301,
+      "grad_norm": 5.34375,
+      "learning_rate": 3.0303030303030305e-07,
+      "loss": 2.0607,
+      "step": 10
+    },
+    {
+      "epoch": 0.07266121707538602,
+      "grad_norm": 5.90625,
+      "learning_rate": 6.060606060606061e-07,
+      "loss": 2.033,
+      "step": 20
+    },
+    {
+      "epoch": 0.10899182561307902,
+      "grad_norm": 5.46875,
+      "learning_rate": 9.090909090909091e-07,
+      "loss": 2.0622,
+      "step": 30
+    },
+    {
+      "epoch": 0.14532243415077203,
+      "grad_norm": 4.96875,
+      "learning_rate": 1.2121212121212122e-06,
+      "loss": 1.9896,
+      "step": 40
+    },
+    {
+      "epoch": 0.18165304268846502,
+      "grad_norm": 15.625,
+      "learning_rate": 1.5151515151515152e-06,
+      "loss": 1.9998,
+      "step": 50
+    },
+    {
+      "epoch": 0.21798365122615804,
+      "grad_norm": 18.0,
+      "learning_rate": 1.8181818181818183e-06,
+      "loss": 1.9608,
+      "step": 60
+    },
+    {
+      "epoch": 0.254314259763851,
+      "grad_norm": 15.625,
+      "learning_rate": 2.1212121212121216e-06,
+      "loss": 1.9272,
+      "step": 70
+    },
+    {
+      "epoch": 0.29064486830154407,
+      "grad_norm": 15.5625,
+      "learning_rate": 2.4242424242424244e-06,
+      "loss": 1.9031,
+      "step": 80
+    },
+    {
+      "epoch": 0.32697547683923706,
+      "grad_norm": 14.1875,
+      "learning_rate": 2.7272727272727272e-06,
+      "loss": 1.8012,
+      "step": 90
+    },
+    {
+      "epoch": 0.36330608537693004,
+      "grad_norm": 3.421875,
+      "learning_rate": 3.0303030303030305e-06,
+      "loss": 1.7756,
+      "step": 100
+    },
+    {
+      "epoch": 0.3996366939146231,
+      "grad_norm": 3.09375,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.6836,
+      "step": 110
+    },
+    {
+      "epoch": 0.4359673024523161,
+      "grad_norm": 2.46875,
+      "learning_rate": 3.6363636363636366e-06,
+      "loss": 1.7013,
+      "step": 120
+    },
+    {
+      "epoch": 0.47229791099000906,
+      "grad_norm": 2.859375,
+      "learning_rate": 3.93939393939394e-06,
+      "loss": 1.6328,
+      "step": 130
+    },
+    {
+      "epoch": 0.508628519527702,
+      "grad_norm": 2.6875,
+      "learning_rate": 4.242424242424243e-06,
+      "loss": 1.6888,
+      "step": 140
+    },
+    {
+      "epoch": 0.5449591280653951,
+      "grad_norm": 2.828125,
+      "learning_rate": 4.5454545454545455e-06,
+      "loss": 1.6583,
+      "step": 150
+    },
+    {
+      "epoch": 0.5812897366030881,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.848484848484849e-06,
+      "loss": 1.5485,
+      "step": 160
+    },
+    {
+      "epoch": 0.6176203451407811,
+      "grad_norm": 2.1875,
+      "learning_rate": 5.151515151515152e-06,
+      "loss": 1.5464,
+      "step": 170
+    },
+    {
+      "epoch": 0.6539509536784741,
+      "grad_norm": 2.25,
+      "learning_rate": 5.4545454545454545e-06,
+      "loss": 1.5506,
+      "step": 180
+    },
+    {
+      "epoch": 0.6902815622161671,
+      "grad_norm": 2.4375,
+      "learning_rate": 5.7575757575757586e-06,
+      "loss": 1.5301,
+      "step": 190
+    },
+    {
+      "epoch": 0.7266121707538601,
+      "grad_norm": 2.4375,
+      "learning_rate": 6.060606060606061e-06,
+      "loss": 1.5116,
+      "step": 200
+    },
+    {
+      "epoch": 0.7629427792915532,
+      "grad_norm": 2.609375,
+      "learning_rate": 6.363636363636364e-06,
+      "loss": 1.4874,
+      "step": 210
+    },
+    {
+      "epoch": 0.7992733878292462,
+      "grad_norm": 2.3125,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5056,
+      "step": 220
+    },
+    {
+      "epoch": 0.8356039963669392,
+      "grad_norm": 2.21875,
+      "learning_rate": 6.969696969696971e-06,
+      "loss": 1.5036,
+      "step": 230
+    },
+    {
+      "epoch": 0.8719346049046321,
+      "grad_norm": 2.359375,
+      "learning_rate": 7.272727272727273e-06,
+      "loss": 1.4625,
+      "step": 240
+    },
+    {
+      "epoch": 0.9082652134423251,
+      "grad_norm": 1.921875,
+      "learning_rate": 7.5757575757575764e-06,
+      "loss": 1.4439,
+      "step": 250
+    },
+    {
+      "epoch": 0.9445958219800181,
+      "grad_norm": 2.265625,
+      "learning_rate": 7.87878787878788e-06,
+      "loss": 1.4025,
+      "step": 260
+    },
+    {
+      "epoch": 0.9809264305177112,
+      "grad_norm": 2.609375,
+      "learning_rate": 8.181818181818183e-06,
+      "loss": 1.4267,
+      "step": 270
+    },
+    {
+      "epoch": 1.017257039055404,
+      "grad_norm": 1.84375,
+      "learning_rate": 8.484848484848486e-06,
+      "loss": 1.3484,
+      "step": 280
+    },
+    {
+      "epoch": 1.0535876475930972,
+      "grad_norm": 2.0,
+      "learning_rate": 8.787878787878788e-06,
+      "loss": 1.3809,
+      "step": 290
+    },
+    {
+      "epoch": 1.0899182561307903,
+      "grad_norm": 2.1875,
+      "learning_rate": 9.090909090909091e-06,
+      "loss": 1.3901,
+      "step": 300
+    },
+    {
+      "epoch": 1.1262488646684832,
+      "grad_norm": 1.8984375,
+      "learning_rate": 9.393939393939396e-06,
+      "loss": 1.3203,
+      "step": 310
+    },
+    {
+      "epoch": 1.1625794732061763,
+      "grad_norm": 1.9296875,
+      "learning_rate": 9.696969696969698e-06,
+      "loss": 1.3295,
+      "step": 320
+    },
+    {
+      "epoch": 1.1989100817438691,
+      "grad_norm": 1.9140625,
+      "learning_rate": 1e-05,
+      "loss": 1.3936,
+      "step": 330
+    },
+    {
+      "epoch": 1.2352406902815622,
+      "grad_norm": 2.5,
+      "learning_rate": 9.999720280459576e-06,
+      "loss": 1.3483,
+      "step": 340
+    },
+    {
+      "epoch": 1.2715712988192553,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.99888115313551e-06,
+      "loss": 1.3384,
+      "step": 350
+    },
+    {
+      "epoch": 1.3079019073569482,
+      "grad_norm": 1.921875,
+      "learning_rate": 9.997482711915926e-06,
+      "loss": 1.2888,
+      "step": 360
+    },
+    {
+      "epoch": 1.344232515894641,
+      "grad_norm": 1.9453125,
+      "learning_rate": 9.99552511326936e-06,
+      "loss": 1.3144,
+      "step": 370
+    },
+    {
+      "epoch": 1.3805631244323342,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.993008576227248e-06,
+      "loss": 1.2905,
+      "step": 380
+    },
+    {
+      "epoch": 1.4168937329700273,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.989933382359423e-06,
+      "loss": 1.2816,
+      "step": 390
+    },
+    {
+      "epoch": 1.4532243415077202,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.986299875742612e-06,
+      "loss": 1.3315,
+      "step": 400
+    },
+    {
+      "epoch": 1.4895549500454133,
+      "grad_norm": 1.7734375,
+      "learning_rate": 9.982108462921938e-06,
+      "loss": 1.2984,
+      "step": 410
+    },
+    {
+      "epoch": 1.5258855585831061,
+      "grad_norm": 2.765625,
+      "learning_rate": 9.977359612865424e-06,
+      "loss": 1.2677,
+      "step": 420
+    },
+    {
+      "epoch": 1.5622161671207992,
+      "grad_norm": 1.859375,
+      "learning_rate": 9.972053856911534e-06,
+      "loss": 1.3098,
+      "step": 430
+    },
+    {
+      "epoch": 1.5985467756584923,
+      "grad_norm": 1.84375,
+      "learning_rate": 9.966191788709716e-06,
+      "loss": 1.3503,
+      "step": 440
+    },
+    {
+      "epoch": 1.6348773841961854,
+      "grad_norm": 2.609375,
+      "learning_rate": 9.959774064153977e-06,
+      "loss": 1.3301,
+      "step": 450
+    },
+    {
+      "epoch": 1.6712079927338783,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.952801401309504e-06,
+      "loss": 1.2454,
+      "step": 460
+    },
+    {
+      "epoch": 1.7075386012715712,
+      "grad_norm": 1.8515625,
+      "learning_rate": 9.945274580332316e-06,
+      "loss": 1.239,
+      "step": 470
+    },
+    {
+      "epoch": 1.7438692098092643,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.937194443381972e-06,
+      "loss": 1.2823,
+      "step": 480
+    },
+    {
+      "epoch": 1.7801998183469574,
+      "grad_norm": 2.203125,
+      "learning_rate": 9.928561894527354e-06,
+      "loss": 1.2774,
+      "step": 490
+    },
+    {
+      "epoch": 1.8165304268846503,
+      "grad_norm": 2.15625,
+      "learning_rate": 9.919377899645497e-06,
+      "loss": 1.2215,
+      "step": 500
+    },
+    {
+      "epoch": 1.8528610354223434,
+      "grad_norm": 1.671875,
+      "learning_rate": 9.909643486313533e-06,
+      "loss": 1.2509,
+      "step": 510
+    },
+    {
+      "epoch": 1.8891916439600362,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.899359743693715e-06,
+      "loss": 1.2656,
+      "step": 520
+    },
+    {
+      "epoch": 1.9255222524977293,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.888527822411543e-06,
+      "loss": 1.186,
+      "step": 530
+    },
+    {
+      "epoch": 1.9618528610354224,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.877148934427037e-06,
+      "loss": 1.2468,
+      "step": 540
+    },
+    {
+      "epoch": 1.9981834695731153,
+      "grad_norm": 1.59375,
+      "learning_rate": 9.86522435289912e-06,
+      "loss": 1.2471,
+      "step": 550
+    },
+    {
+      "epoch": 2.034514078110808,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.85275541204318e-06,
+      "loss": 1.1688,
+      "step": 560
+    },
+    {
+      "epoch": 2.0708446866485013,
+      "grad_norm": 2.046875,
+      "learning_rate": 9.839743506981783e-06,
+      "loss": 1.1216,
+      "step": 570
+    },
+    {
+      "epoch": 2.1071752951861944,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.826190093588564e-06,
+      "loss": 1.1333,
+      "step": 580
+    },
+    {
+      "epoch": 2.1435059037238875,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.812096688325354e-06,
+      "loss": 1.1148,
+      "step": 590
+    },
+    {
+      "epoch": 2.1798365122615806,
+      "grad_norm": 1.796875,
+      "learning_rate": 9.797464868072489e-06,
+      "loss": 1.1331,
+      "step": 600
+    },
+    {
+      "epoch": 2.2161671207992732,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.78229626995238e-06,
+      "loss": 1.1931,
+      "step": 610
+    },
+    {
+      "epoch": 2.2524977293369663,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.766592591146353e-06,
+      "loss": 1.146,
+      "step": 620
+    },
+    {
+      "epoch": 2.2888283378746594,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.750355588704728e-06,
+      "loss": 1.1397,
+      "step": 630
+    },
+    {
+      "epoch": 2.3251589464123525,
+      "grad_norm": 1.8359375,
+      "learning_rate": 9.733587079350254e-06,
+      "loss": 1.0941,
+      "step": 640
+    },
+    {
+      "epoch": 2.3614895549500456,
+      "grad_norm": 1.7265625,
+      "learning_rate": 9.716288939274818e-06,
+      "loss": 1.101,
+      "step": 650
+    },
+    {
+      "epoch": 2.3978201634877383,
+      "grad_norm": 2.703125,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 1.0632,
+      "step": 660
+    },
+    {
+      "epoch": 2.4341507720254314,
+      "grad_norm": 2.5625,
+      "learning_rate": 9.680111567808212e-06,
+      "loss": 1.1315,
+      "step": 670
+    },
+    {
+      "epoch": 2.4704813805631245,
+      "grad_norm": 1.890625,
+      "learning_rate": 9.66123638422413e-06,
+      "loss": 1.0989,
+      "step": 680
+    },
+    {
+      "epoch": 2.5068119891008176,
+      "grad_norm": 1.8828125,
+      "learning_rate": 9.641839665080363e-06,
+      "loss": 1.0829,
+      "step": 690
+    },
+    {
+      "epoch": 2.5431425976385107,
+      "grad_norm": 1.9140625,
+      "learning_rate": 9.621923580633462e-06,
+      "loss": 1.1155,
+      "step": 700
+    },
+    {
+      "epoch": 2.5794732061762033,
+      "grad_norm": 1.5546875,
+      "learning_rate": 9.601490359250616e-06,
+      "loss": 1.1248,
+      "step": 710
+    },
+    {
+      "epoch": 2.6158038147138964,
+      "grad_norm": 1.7890625,
+      "learning_rate": 9.580542287160348e-06,
+      "loss": 1.1391,
+      "step": 720
+    },
+    {
+      "epoch": 2.6521344232515895,
+      "grad_norm": 1.734375,
+      "learning_rate": 9.559081708196696e-06,
+      "loss": 1.0538,
+      "step": 730
+    },
+    {
+      "epoch": 2.688465031789282,
+      "grad_norm": 1.953125,
+      "learning_rate": 9.537111023536973e-06,
+      "loss": 1.055,
+      "step": 740
+    },
+    {
+      "epoch": 2.7247956403269757,
+      "grad_norm": 1.6328125,
+      "learning_rate": 9.514632691433108e-06,
+      "loss": 1.1769,
+      "step": 750
+    },
+    {
+      "epoch": 2.7611262488646684,
+      "grad_norm": 2.609375,
+      "learning_rate": 9.491649226936586e-06,
+      "loss": 1.0949,
+      "step": 760
+    },
+    {
+      "epoch": 2.7974568574023615,
+      "grad_norm": 1.9609375,
+      "learning_rate": 9.468163201617063e-06,
+      "loss": 1.1308,
+      "step": 770
+    },
+    {
+      "epoch": 2.8337874659400546,
+      "grad_norm": 1.953125,
+      "learning_rate": 9.444177243274619e-06,
+      "loss": 1.1283,
+      "step": 780
+    },
+    {
+      "epoch": 2.8701180744777472,
+      "grad_norm": 1.703125,
+      "learning_rate": 9.419694035645753e-06,
+      "loss": 1.0907,
+      "step": 790
+    },
+    {
+      "epoch": 2.9064486830154403,
+      "grad_norm": 1.5,
+      "learning_rate": 9.394716318103098e-06,
+      "loss": 1.1043,
+      "step": 800
+    },
+    {
+      "epoch": 2.9427792915531334,
+      "grad_norm": 2.3125,
+      "learning_rate": 9.369246885348926e-06,
+      "loss": 1.0676,
+      "step": 810
+    },
+    {
+      "epoch": 2.9791099000908265,
+      "grad_norm": 1.65625,
+      "learning_rate": 9.343288587102444e-06,
+      "loss": 1.0642,
+      "step": 820
+    },
+    {
+      "epoch": 3.0154405086285196,
+      "grad_norm": 1.5234375,
+      "learning_rate": 9.316844327780955e-06,
+      "loss": 1.0437,
+      "step": 830
+    },
+    {
+      "epoch": 3.0517711171662127,
+      "grad_norm": 1.6953125,
+      "learning_rate": 9.289917066174887e-06,
+      "loss": 0.9874,
+      "step": 840
+    },
+    {
+      "epoch": 3.0881017257039054,
+      "grad_norm": 1.578125,
+      "learning_rate": 9.262509815116732e-06,
+      "loss": 0.9582,
+      "step": 850
+    },
+    {
+      "epoch": 3.1244323342415985,
+      "grad_norm": 1.8046875,
+      "learning_rate": 9.234625641143962e-06,
+      "loss": 0.9471,
+      "step": 860
+    },
+    {
+      "epoch": 3.1607629427792916,
+      "grad_norm": 2.015625,
+      "learning_rate": 9.206267664155906e-06,
+      "loss": 0.9424,
+      "step": 870
+    },
+    {
+      "epoch": 3.1970935513169847,
+      "grad_norm": 1.625,
+      "learning_rate": 9.177439057064684e-06,
+      "loss": 0.972,
+      "step": 880
+    },
+    {
+      "epoch": 3.2334241598546773,
+      "grad_norm": 1.4921875,
+      "learning_rate": 9.148143045440181e-06,
+      "loss": 0.9729,
+      "step": 890
+    },
+    {
+      "epoch": 3.2697547683923704,
+      "grad_norm": 1.8203125,
+      "learning_rate": 9.118382907149164e-06,
+      "loss": 0.9558,
+      "step": 900
+    },
+    {
+      "epoch": 3.3060853769300635,
+      "grad_norm": 1.453125,
+      "learning_rate": 9.088161971988517e-06,
+      "loss": 0.9518,
+      "step": 910
+    },
+    {
+      "epoch": 3.3424159854677566,
+      "grad_norm": 1.3671875,
+      "learning_rate": 9.057483621312671e-06,
+      "loss": 0.9694,
+      "step": 920
+    },
+    {
+      "epoch": 3.3787465940054497,
+      "grad_norm": 1.15625,
+      "learning_rate": 9.026351287655294e-06,
+      "loss": 0.9457,
+      "step": 930
+    },
+    {
+      "epoch": 3.4150772025431424,
+      "grad_norm": 1.3359375,
+      "learning_rate": 8.994768454345207e-06,
+      "loss": 0.9585,
+      "step": 940
+    },
+    {
+      "epoch": 3.4514078110808355,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.96273865511666e-06,
+      "loss": 0.9479,
+      "step": 950
+    },
+    {
+      "epoch": 3.4877384196185286,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.930265473713939e-06,
+      "loss": 0.9105,
+      "step": 960
+    },
+    {
+      "epoch": 3.5240690281562217,
+      "grad_norm": 1.3828125,
+      "learning_rate": 8.897352543490396e-06,
+      "loss": 0.9795,
+      "step": 970
+    },
+    {
+      "epoch": 3.560399636693915,
+      "grad_norm": 1.21875,
+      "learning_rate": 8.864003547001916e-06,
+      "loss": 0.9403,
+      "step": 980
+    },
+    {
+      "epoch": 3.5967302452316074,
+      "grad_norm": 1.3203125,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.925,
+      "step": 990
+    },
+    {
+      "epoch": 3.6330608537693005,
+      "grad_norm": 1.25,
+      "learning_rate": 8.796012328988716e-06,
+      "loss": 0.9225,
+      "step": 1000
+    },
+    {
+      "epoch": 3.6330608537693005,
+      "eval_loss": 1.1292678117752075,
+      "eval_runtime": 10.2075,
+      "eval_samples_per_second": 24.002,
+      "eval_steps_per_second": 24.002,
+      "step": 1000
+    },
+    {
+      "epoch": 3.6693914623069936,
+      "grad_norm": 1.171875,
+      "learning_rate": 8.7613777148529e-06,
+      "loss": 0.9778,
+      "step": 1010
+    },
+    {
+      "epoch": 3.7057220708446867,
+      "grad_norm": 1.234375,
+      "learning_rate": 8.726322248378775e-06,
+      "loss": 0.8997,
+      "step": 1020
+    },
+    {
+      "epoch": 3.74205267938238,
+      "grad_norm": 1.1328125,
+      "learning_rate": 8.690849851845933e-06,
+      "loss": 0.9874,
+      "step": 1030
+    },
+    {
+      "epoch": 3.7783832879200725,
+      "grad_norm": 1.453125,
+      "learning_rate": 8.65496449418336e-06,
+      "loss": 0.9101,
+      "step": 1040
+    },
+    {
+      "epoch": 3.8147138964577656,
+      "grad_norm": 1.3515625,
+      "learning_rate": 8.61867019052535e-06,
+      "loss": 0.9101,
+      "step": 1050
+    },
+    {
+      "epoch": 3.8510445049954587,
+      "grad_norm": 1.25,
+      "learning_rate": 8.581971001762287e-06,
+      "loss": 0.9549,
+      "step": 1060
+    },
+    {
+      "epoch": 3.887375113533152,
+      "grad_norm": 1.375,
+      "learning_rate": 8.54487103408625e-06,
+      "loss": 0.9486,
+      "step": 1070
+    },
+    {
+      "epoch": 3.923705722070845,
+      "grad_norm": 1.1953125,
+      "learning_rate": 8.507374438531606e-06,
+      "loss": 0.9476,
+      "step": 1080
+    },
+    {
+      "epoch": 3.9600363306085375,
+      "grad_norm": 1.2421875,
+      "learning_rate": 8.469485410510545e-06,
+      "loss": 0.9283,
+      "step": 1090
+    },
+    {
+      "epoch": 3.9963669391462306,
+      "grad_norm": 1.2109375,
+      "learning_rate": 8.43120818934367e-06,
+      "loss": 0.9616,
+      "step": 1100
+    },
+    {
+      "epoch": 4.032697547683924,
+      "grad_norm": 1.5,
+      "learning_rate": 8.392547057785662e-06,
+      "loss": 0.8816,
+      "step": 1110
+    },
+    {
+      "epoch": 4.069028156221616,
+      "grad_norm": 1.0546875,
+      "learning_rate": 8.353506341546106e-06,
+      "loss": 0.8704,
+      "step": 1120
+    },
+    {
+      "epoch": 4.10535876475931,
+      "grad_norm": 1.0859375,
+      "learning_rate": 8.314090408805481e-06,
+      "loss": 0.8515,
+      "step": 1130
+    },
+    {
+      "epoch": 4.141689373297003,
+      "grad_norm": 1.125,
+      "learning_rate": 8.274303669726427e-06,
+      "loss": 0.7986,
+      "step": 1140
+    },
+    {
+      "epoch": 4.178019981834696,
+      "grad_norm": 0.9765625,
+      "learning_rate": 8.234150575960288e-06,
+      "loss": 0.859,
+      "step": 1150
+    },
+    {
+      "epoch": 4.214350590372389,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.193635620149041e-06,
+      "loss": 0.8537,
+      "step": 1160
+    },
+    {
+      "epoch": 4.2506811989100814,
+      "grad_norm": 1.0625,
+      "learning_rate": 8.152763335422612e-06,
+      "loss": 0.8513,
+      "step": 1170
+    },
+    {
+      "epoch": 4.287011807447775,
+      "grad_norm": 1.0234375,
+      "learning_rate": 8.111538294891684e-06,
+      "loss": 0.8318,
+      "step": 1180
+    },
+    {
+      "epoch": 4.323342415985468,
+      "grad_norm": 1.03125,
+      "learning_rate": 8.06996511113601e-06,
+      "loss": 0.846,
+      "step": 1190
+    },
+    {
+      "epoch": 4.359673024523161,
+      "grad_norm": 1.0,
+      "learning_rate": 8.028048435688333e-06,
+      "loss": 0.8667,
+      "step": 1200
+    },
+    {
+      "epoch": 4.396003633060854,
+      "grad_norm": 0.9921875,
+      "learning_rate": 7.985792958513932e-06,
+      "loss": 0.8715,
+      "step": 1210
+    },
+    {
+      "epoch": 4.4323342415985465,
+      "grad_norm": 0.9296875,
+      "learning_rate": 7.943203407485864e-06,
+      "loss": 0.848,
+      "step": 1220
+    },
+    {
+      "epoch": 4.46866485013624,
+      "grad_norm": 0.94921875,
+      "learning_rate": 7.900284547855992e-06,
+      "loss": 0.8859,
+      "step": 1230
+    },
+    {
+      "epoch": 4.504995458673933,
+      "grad_norm": 0.98046875,
+      "learning_rate": 7.857041181721788e-06,
+      "loss": 0.8575,
+      "step": 1240
+    },
+    {
+      "epoch": 4.541326067211626,
+      "grad_norm": 0.94140625,
+      "learning_rate": 7.813478147489052e-06,
+      "loss": 0.8496,
+      "step": 1250
+    },
+    {
+      "epoch": 4.577656675749319,
+      "grad_norm": 0.92578125,
+      "learning_rate": 7.769600319330553e-06,
+      "loss": 0.8166,
+      "step": 1260
+    },
+    {
+      "epoch": 4.6139872842870115,
+      "grad_norm": 1.15625,
+      "learning_rate": 7.725412606640658e-06,
+      "loss": 0.8191,
+      "step": 1270
+    },
+    {
+      "epoch": 4.650317892824705,
+      "grad_norm": 1.046875,
+      "learning_rate": 7.680919953486047e-06,
+      "loss": 0.833,
+      "step": 1280
+    },
+    {
+      "epoch": 4.686648501362398,
+      "grad_norm": 1.0390625,
+      "learning_rate": 7.636127338052513e-06,
+      "loss": 0.839,
+      "step": 1290
+    },
+    {
+      "epoch": 4.722979109900091,
+      "grad_norm": 1.2421875,
+      "learning_rate": 7.5910397720879785e-06,
+      "loss": 0.807,
+      "step": 1300
+    },
+    {
+      "epoch": 4.759309718437784,
+      "grad_norm": 0.984375,
+      "learning_rate": 7.545662300341736e-06,
+      "loss": 0.8215,
+      "step": 1310
+    },
+    {
+      "epoch": 4.795640326975477,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8584,
+      "step": 1320
+    },
+    {
+      "epoch": 4.83197093551317,
+      "grad_norm": 1.0546875,
+      "learning_rate": 7.454057980117842e-06,
+      "loss": 0.7955,
+      "step": 1330
+    },
+    {
+      "epoch": 4.868301544050863,
+      "grad_norm": 1.140625,
+      "learning_rate": 7.407841381047533e-06,
+      "loss": 0.8482,
+      "step": 1340
+    },
+    {
+      "epoch": 4.904632152588556,
+      "grad_norm": 1.234375,
+      "learning_rate": 7.361355373863415e-06,
+      "loss": 0.8457,
+      "step": 1350
+    },
+    {
+      "epoch": 4.940962761126249,
+      "grad_norm": 0.91796875,
+      "learning_rate": 7.314605159783313e-06,
+      "loss": 0.8705,
+      "step": 1360
+    },
+    {
+      "epoch": 4.977293369663942,
+      "grad_norm": 1.0234375,
+      "learning_rate": 7.2675959695865896e-06,
+      "loss": 0.829,
+      "step": 1370
+    },
+    {
+      "epoch": 5.013623978201635,
+      "grad_norm": 0.9375,
+      "learning_rate": 7.2203330630288714e-06,
+      "loss": 0.8391,
+      "step": 1380
+    },
+    {
+      "epoch": 5.049954586739328,
+      "grad_norm": 0.9921875,
+      "learning_rate": 7.172821728253563e-06,
+      "loss": 0.7915,
+      "step": 1390
+    },
+    {
+      "epoch": 5.0862851952770205,
+      "grad_norm": 1.1171875,
+      "learning_rate": 7.1250672812001505e-06,
+      "loss": 0.8199,
+      "step": 1400
+    },
+    {
+      "epoch": 5.122615803814714,
+      "grad_norm": 1.0,
+      "learning_rate": 7.0770750650094335e-06,
+      "loss": 0.8065,
+      "step": 1410
+    },
+    {
+      "epoch": 5.158946412352407,
+      "grad_norm": 1.2578125,
+      "learning_rate": 7.02885044942567e-06,
+      "loss": 0.8098,
+      "step": 1420
+    },
+    {
+      "epoch": 5.1952770208901,
+      "grad_norm": 1.0625,
+      "learning_rate": 6.980398830195785e-06,
+      "loss": 0.7675,
+      "step": 1430
+    },
+    {
+      "epoch": 5.231607629427793,
+      "grad_norm": 1.125,
+      "learning_rate": 6.931725628465643e-06,
+      "loss": 0.7747,
+      "step": 1440
+    },
+    {
+      "epoch": 5.2679382379654855,
+      "grad_norm": 1.375,
+      "learning_rate": 6.882836290173493e-06,
+      "loss": 0.7623,
+      "step": 1450
+    },
+    {
+      "epoch": 5.304268846503179,
+      "grad_norm": 1.2109375,
+      "learning_rate": 6.833736285440632e-06,
+      "loss": 0.8113,
+      "step": 1460
+    },
+    {
+      "epoch": 5.340599455040872,
+      "grad_norm": 1.3359375,
+      "learning_rate": 6.78443110795936e-06,
+      "loss": 0.8411,
+      "step": 1470
+    },
+    {
+      "epoch": 5.376930063578565,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.734926274378313e-06,
+      "loss": 0.7592,
+      "step": 1480
+    },
+    {
+      "epoch": 5.413260672116258,
+      "grad_norm": 1.234375,
+      "learning_rate": 6.685227323685209e-06,
+      "loss": 0.7776,
+      "step": 1490
+    },
+    {
+      "epoch": 5.449591280653951,
+      "grad_norm": 1.46875,
+      "learning_rate": 6.635339816587109e-06,
+      "loss": 0.7727,
+      "step": 1500
+    },
+    {
+      "epoch": 5.485921889191644,
+      "grad_norm": 1.40625,
+      "learning_rate": 6.5852693348882345e-06,
+      "loss": 0.7539,
+      "step": 1510
+    },
+    {
+      "epoch": 5.522252497729337,
+      "grad_norm": 1.4609375,
+      "learning_rate": 6.535021480865439e-06,
+      "loss": 0.8292,
+      "step": 1520
+    },
+    {
+      "epoch": 5.55858310626703,
+      "grad_norm": 1.8359375,
+      "learning_rate": 6.484601876641375e-06,
+      "loss": 0.7463,
+      "step": 1530
+    },
+    {
+      "epoch": 5.594913714804723,
+      "grad_norm": 1.3515625,
+      "learning_rate": 6.434016163555452e-06,
+      "loss": 0.7744,
+      "step": 1540
+    },
+    {
+      "epoch": 5.631244323342416,
+      "grad_norm": 2.578125,
+      "learning_rate": 6.383270001532636e-06,
+      "loss": 0.7868,
+      "step": 1550
+    },
+    {
+      "epoch": 5.667574931880109,
+      "grad_norm": 2.65625,
+      "learning_rate": 6.332369068450175e-06,
+      "loss": 0.7485,
+      "step": 1560
+    },
+    {
+      "epoch": 5.703905540417802,
+      "grad_norm": 2.34375,
+      "learning_rate": 6.2813190595023135e-06,
+      "loss": 0.7783,
+      "step": 1570
+    },
+    {
+      "epoch": 5.740236148955495,
+      "grad_norm": 2.40625,
+      "learning_rate": 6.230125686563068e-06,
+      "loss": 0.7769,
+      "step": 1580
+    },
+    {
+      "epoch": 5.776566757493188,
+      "grad_norm": 2.390625,
+      "learning_rate": 6.178794677547138e-06,
+      "loss": 0.7977,
+      "step": 1590
+    },
+    {
+      "epoch": 5.812897366030881,
+      "grad_norm": 3.65625,
+      "learning_rate": 6.127331775769023e-06,
+      "loss": 0.8101,
+      "step": 1600
+    },
+    {
+      "epoch": 5.849227974568574,
+      "grad_norm": 5.4375,
+      "learning_rate": 6.07574273930042e-06,
+      "loss": 0.8397,
+      "step": 1610
+    },
+    {
+      "epoch": 5.885558583106267,
+      "grad_norm": 4.78125,
+      "learning_rate": 6.024033340325954e-06,
+      "loss": 0.8191,
+      "step": 1620
+    },
+    {
+      "epoch": 5.9218891916439595,
+      "grad_norm": 4.625,
+      "learning_rate": 5.972209364497355e-06,
+      "loss": 0.7843,
+      "step": 1630
+    },
+    {
+      "epoch": 5.958219800181653,
+      "grad_norm": 5.4375,
+      "learning_rate": 5.920276610286102e-06,
+      "loss": 0.8099,
+      "step": 1640
+    },
+    {
+      "epoch": 5.994550408719346,
+      "grad_norm": 10.875,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.8025,
+      "step": 1650
+    },
+    {
+      "epoch": 6.030881017257039,
+      "grad_norm": 10.25,
+      "learning_rate": 5.816108020806297e-06,
+      "loss": 0.7426,
+      "step": 1660
+    },
+    {
+      "epoch": 6.067211625794732,
+      "grad_norm": 9.8125,
+      "learning_rate": 5.763883840733736e-06,
+      "loss": 0.7439,
+      "step": 1670
+    },
+    {
+      "epoch": 6.1035422343324255,
+      "grad_norm": 8.4375,
+      "learning_rate": 5.711574191366427e-06,
+      "loss": 0.7617,
+      "step": 1680
+    },
+    {
+      "epoch": 6.139872842870118,
+      "grad_norm": 8.4375,
+      "learning_rate": 5.659184925516802e-06,
+      "loss": 0.7333,
+      "step": 1690
+    },
+    {
+      "epoch": 6.176203451407811,
+      "grad_norm": 2.453125,
+      "learning_rate": 5.60672190490541e-06,
+      "loss": 0.7747,
+      "step": 1700
+    },
+    {
+      "epoch": 6.212534059945504,
+      "grad_norm": 2.5625,
+      "learning_rate": 5.5541909995050554e-06,
+      "loss": 0.7469,
+      "step": 1710
+    },
+    {
+      "epoch": 6.248864668483197,
+      "grad_norm": 3.015625,
+      "learning_rate": 5.5015980868840254e-06,
+      "loss": 0.7507,
+      "step": 1720
+    },
+    {
+      "epoch": 6.28519527702089,
+      "grad_norm": 2.546875,
+      "learning_rate": 5.448949051548459e-06,
+      "loss": 0.7774,
+      "step": 1730
+    },
+    {
+      "epoch": 6.321525885558583,
+      "grad_norm": 2.921875,
+      "learning_rate": 5.396249784283943e-06,
+      "loss": 0.773,
+      "step": 1740
+    },
+    {
+      "epoch": 6.357856494096276,
+      "grad_norm": 2.21875,
+      "learning_rate": 5.343506181496405e-06,
+      "loss": 0.7333,
+      "step": 1750
+    },
+    {
+      "epoch": 6.394187102633969,
+      "grad_norm": 2.28125,
+      "learning_rate": 5.290724144552379e-06,
+      "loss": 0.7352,
+      "step": 1760
+    },
+    {
+      "epoch": 6.430517711171662,
+      "grad_norm": 2.3125,
+      "learning_rate": 5.237909579118713e-06,
+      "loss": 0.68,
+      "step": 1770
+    },
+    {
+      "epoch": 6.466848319709355,
+      "grad_norm": 2.296875,
+      "learning_rate": 5.185068394501791e-06,
+      "loss": 0.7279,
+      "step": 1780
+    },
+    {
+      "epoch": 6.503178928247048,
+      "grad_norm": 2.53125,
+      "learning_rate": 5.132206502986368e-06,
+      "loss": 0.7547,
+      "step": 1790
+    },
+    {
+      "epoch": 6.539509536784741,
+      "grad_norm": 2.421875,
+      "learning_rate": 5.07932981917404e-06,
+      "loss": 0.7015,
+      "step": 1800
+    },
+    {
+      "epoch": 6.575840145322434,
+      "grad_norm": 2.4375,
+      "learning_rate": 5.026444259321489e-06,
+      "loss": 0.7614,
+      "step": 1810
+    },
+    {
+      "epoch": 6.612170753860127,
+      "grad_norm": 2.171875,
+      "learning_rate": 4.973555740678512e-06,
+      "loss": 0.7953,
+      "step": 1820
+    },
+    {
+      "epoch": 6.64850136239782,
+      "grad_norm": 2.40625,
+      "learning_rate": 4.9206701808259605e-06,
+      "loss": 0.736,
+      "step": 1830
+    },
+    {
+      "epoch": 6.684831970935513,
+      "grad_norm": 2.28125,
+      "learning_rate": 4.867793497013634e-06,
+      "loss": 0.7502,
+      "step": 1840
+    },
+    {
+      "epoch": 6.721162579473206,
+      "grad_norm": 2.390625,
+      "learning_rate": 4.81493160549821e-06,
+      "loss": 0.7496,
+      "step": 1850
+    },
+    {
+      "epoch": 6.7574931880108995,
+      "grad_norm": 2.359375,
+      "learning_rate": 4.762090420881289e-06,
+      "loss": 0.7888,
+      "step": 1860
+    },
+    {
+      "epoch": 6.793823796548592,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.7092758554476215e-06,
+      "loss": 0.7238,
+      "step": 1870
+    },
+    {
+      "epoch": 6.830154405086285,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.6564938185035954e-06,
+      "loss": 0.7484,
+      "step": 1880
+    },
+    {
+      "epoch": 6.866485013623978,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.603750215716057e-06,
+      "loss": 0.7835,
+      "step": 1890
+    },
+    {
+      "epoch": 6.902815622161671,
+      "grad_norm": 2.53125,
+      "learning_rate": 4.551050948451542e-06,
+      "loss": 0.6878,
+      "step": 1900
+    },
+    {
+      "epoch": 6.9391462306993645,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.498401913115975e-06,
+      "loss": 0.7528,
+      "step": 1910
+    },
+    {
+      "epoch": 6.975476839237057,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.445809000494945e-06,
+      "loss": 0.7486,
+      "step": 1920
+    },
+    {
+      "epoch": 7.01180744777475,
+      "grad_norm": 2.15625,
+      "learning_rate": 4.393278095094591e-06,
+      "loss": 0.7948,
+      "step": 1930
+    },
+    {
+      "epoch": 7.048138056312443,
+      "grad_norm": 2.03125,
+      "learning_rate": 4.340815074483199e-06,
+      "loss": 0.6872,
+      "step": 1940
+    },
+    {
+      "epoch": 7.084468664850136,
+      "grad_norm": 1.953125,
+      "learning_rate": 4.2884258086335755e-06,
+      "loss": 0.7289,
+      "step": 1950
+    },
+    {
+      "epoch": 7.12079927338783,
+      "grad_norm": 2.15625,
+      "learning_rate": 4.2361161592662655e-06,
+      "loss": 0.612,
+      "step": 1960
+    },
+    {
+      "epoch": 7.157129881925522,
+      "grad_norm": 2.1875,
+      "learning_rate": 4.183891979193703e-06,
+      "loss": 0.7135,
+      "step": 1970
+    },
+    {
+      "epoch": 7.193460490463215,
+      "grad_norm": 2.28125,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.6932,
+      "step": 1980
+    },
+    {
+      "epoch": 7.229791099000908,
+      "grad_norm": 1.9453125,
+      "learning_rate": 4.079723389713899e-06,
+      "loss": 0.705,
+      "step": 1990
+    },
+    {
+      "epoch": 7.266121707538601,
+      "grad_norm": 2.09375,
+      "learning_rate": 4.027790635502646e-06,
+      "loss": 0.7145,
+      "step": 2000
+    },
+    {
+      "epoch": 7.266121707538601,
+      "eval_loss": 1.1055254936218262,
+      "eval_runtime": 10.2576,
+      "eval_samples_per_second": 23.885,
+      "eval_steps_per_second": 23.885,
+      "step": 2000
+    },
+    {
+      "epoch": 7.302452316076295,
+      "grad_norm": 1.921875,
+      "learning_rate": 3.975966659674048e-06,
+      "loss": 0.6724,
+      "step": 2010
+    },
+    {
+      "epoch": 7.338782924613987,
+      "grad_norm": 2.3125,
+      "learning_rate": 3.924257260699583e-06,
+      "loss": 0.6468,
+      "step": 2020
+    },
+    {
+      "epoch": 7.37511353315168,
+      "grad_norm": 2.140625,
+      "learning_rate": 3.872668224230979e-06,
+      "loss": 0.6792,
+      "step": 2030
+    },
+    {
+      "epoch": 7.4114441416893735,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.821205322452863e-06,
+      "loss": 0.723,
+      "step": 2040
+    },
+    {
+      "epoch": 7.447774750227066,
+      "grad_norm": 1.984375,
+      "learning_rate": 3.769874313436933e-06,
+      "loss": 0.6608,
+      "step": 2050
+    },
+    {
+      "epoch": 7.48410535876476,
+      "grad_norm": 2.21875,
+      "learning_rate": 3.7186809404976877e-06,
+      "loss": 0.6679,
+      "step": 2060
+    },
+    {
+      "epoch": 7.520435967302452,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.667630931549826e-06,
+      "loss": 0.6944,
+      "step": 2070
+    },
+    {
+      "epoch": 7.556766575840145,
+      "grad_norm": 2.15625,
+      "learning_rate": 3.6167299984673655e-06,
+      "loss": 0.7172,
+      "step": 2080
+    },
+    {
+      "epoch": 7.5930971843778385,
+      "grad_norm": 2.265625,
+      "learning_rate": 3.5659838364445505e-06,
+      "loss": 0.7029,
+      "step": 2090
+    },
+    {
+      "epoch": 7.629427792915531,
+      "grad_norm": 2.078125,
+      "learning_rate": 3.5153981233586277e-06,
+      "loss": 0.6549,
+      "step": 2100
+    },
+    {
+      "epoch": 7.665758401453225,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.4649785191345613e-06,
+      "loss": 0.7342,
+      "step": 2110
+    },
+    {
+      "epoch": 7.702089009990917,
+      "grad_norm": 2.09375,
+      "learning_rate": 3.4147306651117663e-06,
+      "loss": 0.6246,
+      "step": 2120
+    },
+    {
+      "epoch": 7.73841961852861,
+      "grad_norm": 1.90625,
+      "learning_rate": 3.3646601834128924e-06,
+      "loss": 0.6587,
+      "step": 2130
+    },
+    {
+      "epoch": 7.774750227066304,
+      "grad_norm": 1.953125,
+      "learning_rate": 3.3147726763147913e-06,
+      "loss": 0.6682,
+      "step": 2140
+    },
+    {
+      "epoch": 7.811080835603996,
+      "grad_norm": 2.421875,
+      "learning_rate": 3.2650737256216885e-06,
+      "loss": 0.6854,
+      "step": 2150
+    },
+    {
+      "epoch": 7.84741144414169,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.2155688920406415e-06,
+      "loss": 0.6908,
+      "step": 2160
+    },
+    {
+      "epoch": 7.883742052679382,
+      "grad_norm": 2.046875,
+      "learning_rate": 3.16626371455937e-06,
+      "loss": 0.6875,
+      "step": 2170
+    },
+    {
+      "epoch": 7.920072661217075,
+      "grad_norm": 2.28125,
+      "learning_rate": 3.1171637098265063e-06,
+      "loss": 0.6732,
+      "step": 2180
+    },
+    {
+      "epoch": 7.956403269754769,
+      "grad_norm": 1.9765625,
+      "learning_rate": 3.0682743715343565e-06,
+      "loss": 0.742,
+      "step": 2190
+    },
+    {
+      "epoch": 7.992733878292461,
+      "grad_norm": 2.796875,
+      "learning_rate": 3.019601169804216e-06,
+      "loss": 0.6791,
+      "step": 2200
+    },
+    {
+      "epoch": 8.029064486830155,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.9711495505743317e-06,
+      "loss": 0.654,
+      "step": 2210
+    },
+    {
+      "epoch": 8.065395095367847,
+      "grad_norm": 2.0,
+      "learning_rate": 2.9229249349905686e-06,
+      "loss": 0.705,
+      "step": 2220
+    },
+    {
+      "epoch": 8.10172570390554,
+      "grad_norm": 2.0,
+      "learning_rate": 2.8749327187998516e-06,
+      "loss": 0.6067,
+      "step": 2230
+    },
+    {
+      "epoch": 8.138056312443233,
+      "grad_norm": 2.03125,
+      "learning_rate": 2.8271782717464413e-06,
+      "loss": 0.6043,
+      "step": 2240
+    },
+    {
+      "epoch": 8.174386920980927,
+      "grad_norm": 1.6875,
+      "learning_rate": 2.7796669369711294e-06,
+      "loss": 0.6292,
+      "step": 2250
+    },
+    {
+      "epoch": 8.21071752951862,
+      "grad_norm": 2.0625,
+      "learning_rate": 2.7324040304134125e-06,
+      "loss": 0.6041,
+      "step": 2260
+    },
+    {
+      "epoch": 8.247048138056313,
+      "grad_norm": 2.296875,
+      "learning_rate": 2.685394840216688e-06,
+      "loss": 0.6222,
+      "step": 2270
+    },
+    {
+      "epoch": 8.283378746594005,
+      "grad_norm": 2.046875,
+      "learning_rate": 2.6386446261365874e-06,
+      "loss": 0.6586,
+      "step": 2280
+    },
+    {
+      "epoch": 8.319709355131698,
+      "grad_norm": 2.015625,
+      "learning_rate": 2.5921586189524694e-06,
+      "loss": 0.6612,
+      "step": 2290
+    },
+    {
+      "epoch": 8.356039963669392,
+      "grad_norm": 2.0,
+      "learning_rate": 2.5459420198821604e-06,
+      "loss": 0.6693,
+      "step": 2300
+    },
+    {
+      "epoch": 8.392370572207085,
+      "grad_norm": 2.125,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.6244,
+      "step": 2310
+    },
+    {
+      "epoch": 8.428701180744778,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.454337699658267e-06,
+      "loss": 0.6312,
+      "step": 2320
+    },
+    {
+      "epoch": 8.46503178928247,
+      "grad_norm": 2.09375,
+      "learning_rate": 2.4089602279120224e-06,
+      "loss": 0.6729,
+      "step": 2330
+    },
+    {
+      "epoch": 8.501362397820163,
+      "grad_norm": 1.8125,
+      "learning_rate": 2.363872661947488e-06,
+      "loss": 0.6276,
+      "step": 2340
+    },
+    {
+      "epoch": 8.537693006357856,
+      "grad_norm": 1.90625,
+      "learning_rate": 2.319080046513954e-06,
+      "loss": 0.6292,
+      "step": 2350
+    },
+    {
+      "epoch": 8.57402361489555,
+      "grad_norm": 2.125,
+      "learning_rate": 2.274587393359342e-06,
+      "loss": 0.6593,
+      "step": 2360
+    },
+    {
+      "epoch": 8.610354223433243,
+      "grad_norm": 1.875,
+      "learning_rate": 2.230399680669449e-06,
+      "loss": 0.6302,
+      "step": 2370
+    },
+    {
+      "epoch": 8.646684831970935,
+      "grad_norm": 1.796875,
+      "learning_rate": 2.1865218525109496e-06,
+      "loss": 0.6481,
+      "step": 2380
+    },
+    {
+      "epoch": 8.683015440508628,
+      "grad_norm": 2.15625,
+      "learning_rate": 2.1429588182782147e-06,
+      "loss": 0.6175,
+      "step": 2390
+    },
+    {
+      "epoch": 8.719346049046322,
+      "grad_norm": 1.953125,
+      "learning_rate": 2.09971545214401e-06,
+      "loss": 0.6144,
+      "step": 2400
+    },
+    {
+      "epoch": 8.755676657584015,
+      "grad_norm": 1.6875,
+      "learning_rate": 2.0567965925141366e-06,
+      "loss": 0.6572,
+      "step": 2410
+    },
+    {
+      "epoch": 8.792007266121708,
+      "grad_norm": 1.890625,
+      "learning_rate": 2.0142070414860704e-06,
+      "loss": 0.654,
+      "step": 2420
+    },
+    {
+      "epoch": 8.8283378746594,
+      "grad_norm": 1.8359375,
+      "learning_rate": 1.971951564311668e-06,
+      "loss": 0.621,
+      "step": 2430
+    },
+    {
+      "epoch": 8.864668483197093,
+      "grad_norm": 1.78125,
+      "learning_rate": 1.9300348888639915e-06,
+      "loss": 0.62,
+      "step": 2440
+    },
+    {
+      "epoch": 8.900999091734786,
+      "grad_norm": 1.6640625,
+      "learning_rate": 1.8884617051083183e-06,
+      "loss": 0.5858,
+      "step": 2450
+    },
+    {
+      "epoch": 8.93732970027248,
+      "grad_norm": 1.578125,
+      "learning_rate": 1.8472366645773892e-06,
+      "loss": 0.6467,
+      "step": 2460
+    },
+    {
+      "epoch": 8.973660308810173,
+      "grad_norm": 1.921875,
+      "learning_rate": 1.8063643798509594e-06,
+      "loss": 0.6138,
+      "step": 2470
+    },
+    {
+      "epoch": 9.009990917347865,
+      "grad_norm": 1.65625,
+      "learning_rate": 1.7658494240397127e-06,
+      "loss": 0.6388,
+      "step": 2480
+    },
+    {
+      "epoch": 9.046321525885558,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.7256963302735752e-06,
+      "loss": 0.5733,
+      "step": 2490
+    },
+    {
+      "epoch": 9.082652134423252,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.68590959119452e-06,
+      "loss": 0.6066,
+      "step": 2500
+    },
+    {
+      "epoch": 9.118982742960945,
+      "grad_norm": 1.2890625,
+      "learning_rate": 1.646493658453896e-06,
+      "loss": 0.5849,
+      "step": 2510
+    },
+    {
+      "epoch": 9.155313351498638,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.6074529422143398e-06,
+      "loss": 0.6136,
+      "step": 2520
+    },
+    {
+      "epoch": 9.19164396003633,
+      "grad_norm": 1.34375,
+      "learning_rate": 1.5687918106563326e-06,
+      "loss": 0.5891,
+      "step": 2530
+    },
+    {
+      "epoch": 9.227974568574023,
+      "grad_norm": 1.5234375,
+      "learning_rate": 1.5305145894894547e-06,
+      "loss": 0.6065,
+      "step": 2540
+    },
+    {
+      "epoch": 9.264305177111716,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.4926255614683931e-06,
+      "loss": 0.5854,
+      "step": 2550
+    },
+    {
+      "epoch": 9.30063578564941,
+      "grad_norm": 1.5703125,
+      "learning_rate": 1.4551289659137497e-06,
+      "loss": 0.6023,
+      "step": 2560
+    },
+    {
+      "epoch": 9.336966394187103,
+      "grad_norm": 1.4296875,
+      "learning_rate": 1.4180289982377138e-06,
+      "loss": 0.6052,
+      "step": 2570
+    },
+    {
+      "epoch": 9.373297002724795,
+      "grad_norm": 1.4453125,
+      "learning_rate": 1.3813298094746491e-06,
+      "loss": 0.5806,
+      "step": 2580
+    },
+    {
+      "epoch": 9.409627611262488,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.345035505816642e-06,
+      "loss": 0.6058,
+      "step": 2590
+    },
+    {
+      "epoch": 9.44595821980018,
+      "grad_norm": 1.3671875,
+      "learning_rate": 1.3091501481540676e-06,
+      "loss": 0.6339,
+      "step": 2600
+    },
+    {
+      "epoch": 9.482288828337875,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.2736777516212267e-06,
+      "loss": 0.6058,
+      "step": 2610
+    },
+    {
+      "epoch": 9.518619436875568,
+      "grad_norm": 1.546875,
+      "learning_rate": 1.238622285147103e-06,
+      "loss": 0.6186,
+      "step": 2620
+    },
+    {
+      "epoch": 9.55495004541326,
+      "grad_norm": 1.3203125,
+      "learning_rate": 1.2039876710112847e-06,
+      "loss": 0.5913,
+      "step": 2630
+    },
+    {
+      "epoch": 9.591280653950953,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.663,
+      "step": 2640
+    },
+    {
+      "epoch": 9.627611262488646,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.135996452998085e-06,
+      "loss": 0.6278,
+      "step": 2650
+    },
+    {
+      "epoch": 9.66394187102634,
+      "grad_norm": 1.390625,
+      "learning_rate": 1.1026474565096068e-06,
+      "loss": 0.6074,
+      "step": 2660
+    },
+    {
+      "epoch": 9.700272479564033,
+      "grad_norm": 1.4609375,
+      "learning_rate": 1.0697345262860638e-06,
+      "loss": 0.6545,
+      "step": 2670
+    },
+    {
+      "epoch": 9.736603088101726,
+      "grad_norm": 1.421875,
+      "learning_rate": 1.0372613448833429e-06,
+      "loss": 0.6141,
+      "step": 2680
+    },
+    {
+      "epoch": 9.772933696639418,
+      "grad_norm": 1.3125,
+      "learning_rate": 1.0052315456547934e-06,
+      "loss": 0.5699,
+      "step": 2690
+    },
+    {
+      "epoch": 9.809264305177111,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.73648712344707e-07,
+      "loss": 0.579,
+      "step": 2700
+    },
+    {
+      "epoch": 9.845594913714805,
+      "grad_norm": 1.2421875,
+      "learning_rate": 9.425163786873292e-07,
+      "loss": 0.61,
+      "step": 2710
+    },
+    {
+      "epoch": 9.881925522252498,
+      "grad_norm": 1.296875,
+      "learning_rate": 9.118380280114858e-07,
+      "loss": 0.6106,
+      "step": 2720
+    },
+    {
+      "epoch": 9.91825613079019,
+      "grad_norm": 1.296875,
+      "learning_rate": 8.816170928508367e-07,
+      "loss": 0.6066,
+      "step": 2730
+    },
+    {
+      "epoch": 9.954586739327883,
+      "grad_norm": 1.0703125,
+      "learning_rate": 8.518569545598198e-07,
+      "loss": 0.6094,
+      "step": 2740
+    },
+    {
+      "epoch": 9.990917347865576,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.225609429353187e-07,
+      "loss": 0.6383,
+      "step": 2750
+    },
+    {
+      "epoch": 10.02724795640327,
+      "grad_norm": 1.203125,
+      "learning_rate": 7.937323358440935e-07,
+      "loss": 0.6017,
+      "step": 2760
+    },
+    {
+      "epoch": 10.063578564940963,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.653743588560387e-07,
+      "loss": 0.6005,
+      "step": 2770
+    },
+    {
+      "epoch": 10.099909173478656,
+      "grad_norm": 1.03125,
+      "learning_rate": 7.374901848832683e-07,
+      "loss": 0.647,
+      "step": 2780
+    },
+    {
+      "epoch": 10.136239782016348,
+      "grad_norm": 1.0625,
+      "learning_rate": 7.100829338251147e-07,
+      "loss": 0.5894,
+      "step": 2790
+    },
+    {
+      "epoch": 10.172570390554041,
+      "grad_norm": 0.953125,
+      "learning_rate": 6.831556722190453e-07,
+      "loss": 0.6075,
+      "step": 2800
+    },
+    {
+      "epoch": 10.208900999091735,
+      "grad_norm": 0.97265625,
+      "learning_rate": 6.567114128975571e-07,
+      "loss": 0.5531,
+      "step": 2810
+    },
+    {
+      "epoch": 10.245231607629428,
+      "grad_norm": 1.1171875,
+      "learning_rate": 6.307531146510754e-07,
+      "loss": 0.6052,
+      "step": 2820
+    },
+    {
+      "epoch": 10.28156221616712,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.052836818969027e-07,
+      "loss": 0.5833,
+      "step": 2830
+    },
+    {
+      "epoch": 10.317892824704813,
+      "grad_norm": 1.1484375,
+      "learning_rate": 5.803059643542491e-07,
+      "loss": 0.5934,
+      "step": 2840
+    },
+    {
+      "epoch": 10.354223433242506,
+      "grad_norm": 0.9609375,
+      "learning_rate": 5.558227567253832e-07,
+      "loss": 0.5931,
+      "step": 2850
+    },
+    {
+      "epoch": 10.3905540417802,
+      "grad_norm": 1.15625,
+      "learning_rate": 5.318367983829393e-07,
+      "loss": 0.6253,
+      "step": 2860
+    },
+    {
+      "epoch": 10.426884650317893,
+      "grad_norm": 1.0390625,
+      "learning_rate": 5.083507730634152e-07,
+      "loss": 0.61,
+      "step": 2870
+    },
+    {
+      "epoch": 10.463215258855586,
+      "grad_norm": 1.0234375,
+      "learning_rate": 4.853673085668947e-07,
+      "loss": 0.6329,
+      "step": 2880
+    },
+    {
+      "epoch": 10.499545867393278,
+      "grad_norm": 0.96484375,
+      "learning_rate": 4.628889764630279e-07,
+      "loss": 0.5733,
+      "step": 2890
+    },
+    {
+      "epoch": 10.535876475930971,
+      "grad_norm": 1.0,
+      "learning_rate": 4.4091829180330503e-07,
+      "loss": 0.5922,
+      "step": 2900
+    },
+    {
+      "epoch": 10.572207084468666,
+      "grad_norm": 1.0078125,
+      "learning_rate": 4.194577128396521e-07,
+      "loss": 0.5843,
+      "step": 2910
+    },
+    {
+      "epoch": 10.608537693006358,
+      "grad_norm": 1.0546875,
+      "learning_rate": 3.985096407493838e-07,
+      "loss": 0.6028,
+      "step": 2920
+    },
+    {
+      "epoch": 10.64486830154405,
+      "grad_norm": 0.984375,
+      "learning_rate": 3.7807641936653984e-07,
+      "loss": 0.5767,
+      "step": 2930
+    },
+    {
+      "epoch": 10.681198910081743,
+      "grad_norm": 1.0625,
+      "learning_rate": 3.581603349196372e-07,
+      "loss": 0.6062,
+      "step": 2940
+    },
+    {
+      "epoch": 10.717529518619436,
+      "grad_norm": 1.0,
+      "learning_rate": 3.3876361577587115e-07,
+      "loss": 0.5978,
+      "step": 2950
+    },
+    {
+      "epoch": 10.75386012715713,
+      "grad_norm": 1.046875,
+      "learning_rate": 3.1988843219178776e-07,
+      "loss": 0.5984,
+      "step": 2960
+    },
+    {
+      "epoch": 10.790190735694823,
+      "grad_norm": 1.1953125,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.5761,
+      "step": 2970
+    },
+    {
+      "epoch": 10.826521344232516,
+      "grad_norm": 1.0078125,
+      "learning_rate": 2.8371106072518194e-07,
+      "loss": 0.5988,
+      "step": 2980
+    },
+    {
+      "epoch": 10.862851952770209,
+      "grad_norm": 1.015625,
+      "learning_rate": 2.664129206497479e-07,
+      "loss": 0.593,
+      "step": 2990
+    },
+    {
+      "epoch": 10.899182561307901,
+      "grad_norm": 1.125,
+      "learning_rate": 2.4964441129527337e-07,
+      "loss": 0.6401,
+      "step": 3000
+    },
+    {
+      "epoch": 10.899182561307901,
+      "eval_loss": 1.12338387966156,
+      "eval_runtime": 10.3307,
+      "eval_samples_per_second": 23.716,
+      "eval_steps_per_second": 23.716,
+      "step": 3000
+    },
+    {
+      "epoch": 10.935513169845596,
+      "grad_norm": 0.921875,
+      "learning_rate": 2.3340740885364922e-07,
+      "loss": 0.5798,
+      "step": 3010
+    },
+    {
+      "epoch": 10.971843778383288,
+      "grad_norm": 1.0546875,
+      "learning_rate": 2.1770373004762035e-07,
+      "loss": 0.5684,
+      "step": 3020
+    },
+    {
+      "epoch": 11.008174386920981,
+      "grad_norm": 1.171875,
+      "learning_rate": 2.0253513192751374e-07,
+      "loss": 0.619,
+      "step": 3030
+    },
+    {
+      "epoch": 11.044504995458674,
+      "grad_norm": 1.125,
+      "learning_rate": 1.8790331167464758e-07,
+      "loss": 0.5739,
+      "step": 3040
+    },
+    {
+      "epoch": 11.080835603996366,
+      "grad_norm": 1.140625,
+      "learning_rate": 1.738099064114368e-07,
+      "loss": 0.6039,
+      "step": 3050
+    },
+    {
+      "epoch": 11.11716621253406,
+      "grad_norm": 1.3359375,
+      "learning_rate": 1.6025649301821877e-07,
+      "loss": 0.6057,
+      "step": 3060
+    },
+    {
+      "epoch": 11.153496821071753,
+      "grad_norm": 1.2109375,
+      "learning_rate": 1.4724458795681962e-07,
+      "loss": 0.5966,
+      "step": 3070
+    },
+    {
+      "epoch": 11.189827429609446,
+      "grad_norm": 1.109375,
+      "learning_rate": 1.3477564710088097e-07,
+      "loss": 0.5987,
+      "step": 3080
+    },
+    {
+      "epoch": 11.226158038147139,
+      "grad_norm": 1.1796875,
+      "learning_rate": 1.2285106557296479e-07,
+      "loss": 0.614,
+      "step": 3090
+    },
+    {
+      "epoch": 11.262488646684831,
+      "grad_norm": 1.25,
+      "learning_rate": 1.1147217758845752e-07,
+      "loss": 0.5854,
+      "step": 3100
+    },
+    {
+      "epoch": 11.298819255222526,
+      "grad_norm": 1.2734375,
+      "learning_rate": 1.0064025630628583e-07,
+      "loss": 0.5866,
+      "step": 3110
+    },
+    {
+      "epoch": 11.335149863760218,
+      "grad_norm": 1.25,
+      "learning_rate": 9.035651368646647e-08,
+      "loss": 0.6412,
+      "step": 3120
+    },
+    {
+      "epoch": 11.371480472297911,
+      "grad_norm": 1.203125,
+      "learning_rate": 8.06221003545038e-08,
+      "loss": 0.5935,
+      "step": 3130
+    },
+    {
+      "epoch": 11.407811080835604,
+      "grad_norm": 1.3125,
+      "learning_rate": 7.143810547264762e-08,
+      "loss": 0.6097,
+      "step": 3140
+    },
+    {
+      "epoch": 11.444141689373296,
+      "grad_norm": 2.1875,
+      "learning_rate": 6.280555661802857e-08,
+      "loss": 0.5737,
+      "step": 3150
+    },
+    {
+      "epoch": 11.48047229791099,
+      "grad_norm": 2.09375,
+      "learning_rate": 5.472541966768552e-08,
+      "loss": 0.5908,
+      "step": 3160
+    },
+    {
+      "epoch": 11.516802906448683,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.719859869049659e-08,
+      "loss": 0.5884,
+      "step": 3170
+    },
+    {
+      "epoch": 11.553133514986376,
+      "grad_norm": 2.125,
+      "learning_rate": 4.02259358460233e-08,
+      "loss": 0.6072,
+      "step": 3180
+    },
+    {
+      "epoch": 11.589464123524069,
+      "grad_norm": 2.1875,
+      "learning_rate": 3.3808211290284886e-08,
+      "loss": 0.6049,
+      "step": 3190
+    },
+    {
+      "epoch": 11.625794732061761,
+      "grad_norm": 3.734375,
+      "learning_rate": 2.7946143088466437e-08,
+      "loss": 0.6021,
+      "step": 3200
+    },
+    {
+      "epoch": 11.662125340599456,
+      "grad_norm": 4.34375,
+      "learning_rate": 2.264038713457706e-08,
+      "loss": 0.6059,
+      "step": 3210
+    },
+    {
+      "epoch": 11.698455949137148,
+      "grad_norm": 3.9375,
+      "learning_rate": 1.789153707806357e-08,
+      "loss": 0.601,
+      "step": 3220
+    },
+    {
+      "epoch": 11.734786557674841,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.3700124257388092e-08,
+      "loss": 0.5657,
+      "step": 3230
+    },
+    {
+      "epoch": 11.771117166212534,
+      "grad_norm": 4.25,
+      "learning_rate": 1.006661764057837e-08,
+      "loss": 0.6255,
+      "step": 3240
+    },
+    {
+      "epoch": 11.807447774750226,
+      "grad_norm": 7.65625,
+      "learning_rate": 6.991423772753636e-09,
+      "loss": 0.6209,
+      "step": 3250
+    },
+    {
+      "epoch": 11.84377838328792,
+      "grad_norm": 7.90625,
+      "learning_rate": 4.474886730641004e-09,
+      "loss": 0.6111,
+      "step": 3260
+    },
+    {
+      "epoch": 11.880108991825614,
+      "grad_norm": 8.5625,
+      "learning_rate": 2.5172880840745873e-09,
+      "loss": 0.6328,
+      "step": 3270
+    },
+    {
+      "epoch": 11.916439600363306,
+      "grad_norm": 8.375,
+      "learning_rate": 1.118846864490708e-09,
+      "loss": 0.5511,
+      "step": 3280
+    },
+    {
+      "epoch": 11.952770208900999,
+      "grad_norm": 8.4375,
+      "learning_rate": 2.797195404247166e-10,
+      "loss": 0.5795,
+      "step": 3290
+    },
+    {
+      "epoch": 11.989100817438691,
+      "grad_norm": 2.59375,
+      "learning_rate": 0.0,
+      "loss": 0.5714,
+      "step": 3300
+    },
+    {
+      "epoch": 11.989100817438691,
+      "step": 3300,
+      "total_flos": 3.144153968877896e+17,
+      "train_loss": 0.880180758562955,
+      "train_runtime": 3585.8754,
+      "train_samples_per_second": 7.369,
+      "train_steps_per_second": 0.92
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 3300,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 12,
+  "save_steps": 0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.144153968877896e+17,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4bf2707d2b44041692fc48569fafa359449408ba1404e7dcad3487b612ff0546
+size 5304