Upload 16 files

README.md

@@ -1,3 +1,58 @@
 ---
-license: mit
+license: other
+base_model: calm2-7b
+tags:
+- llama-factory
+- freeze
+- generated_from_trainer
+model-index:
+- name: noberai-main-8
+  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. -->
+
+# noberai-main-8
+
+This model is a fine-tuned version of [calm2-7b](https://huggingface.co/calm2-7b) on the super-jeneri-beta dataset.
+
+## 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: 5e-05
+- train_batch_size: 8
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 50
+- num_epochs: 4.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.38.2
+- Pytorch 2.2.0+cu121
+- Datasets 2.18.0
+- Tokenizers 0.15.2

all_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.7700594385850776,
+    "train_runtime": 36129.1454,
+    "train_samples_per_second": 4.385,
+    "train_steps_per_second": 0.034
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "calm2-7b",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 32,
+  "pad_token_id": 1,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.38.2",
+  "unsloth_version": "2024.3",
+  "use_cache": false,
+  "vocab_size": 65024
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 0,
+  "eos_token_id": 0,
+  "pad_token_id": 1,
+  "transformers_version": "4.38.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe81fbff13d612d990fa08b756b2195535ce8da5e60221793faf4d02d66edfab
+size 4985122016

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad65cd5700cec88718144f534da33b59dd190caccbc91556c5bb95e8e3f1af1f
+size 4991431320

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cdb930b6bb0317e06139e957bcb4a081ae3893bb7bc0130a3ee90f007abadcd0
+size 4723000112

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:34af159500a527b2b1f7617d46478c9a29d33cde1ba94f1c49c00470cf21afd2
+size 532676736

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 15232196608
+  },
+  "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-00001-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-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-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-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-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-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-00003-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-00001-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|padding|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,31 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<|padding|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|endoftext|>",
+  "chat_template": "{% if messages[0]['role'] == 'system' %}{% set system_message = messages[0]['content'] %}{% endif %}{% if system_message is defined %}{{ system_message + '\\n' }}{% endif %}{% for message in messages %}{% set content = message['content'] %}{% if message['role'] == 'user' %}{{ 'Human: ' + content + '\\nAssistant: ' }}{% elif message['role'] == 'assistant' %}{{ content + '<|endoftext|>' + '\\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|endoftext|>",
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<|padding|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "GPTNeoXTokenizer",
+  "unk_token": "<|endoftext|>"
+}

train_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 4.0,
+    "train_loss": 0.7700594385850776,
+    "train_runtime": 36129.1454,
+    "train_samples_per_second": 4.385,
+    "train_steps_per_second": 0.034
+}

trainer_log.jsonl

@@ -0,0 +1,269 @@
+{"current_steps": 5, "total_steps": 927, "loss": 3.2917, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-06, "epoch": 0.02, "percentage": 0.54, "elapsed_time": "0:08:42", "remaining_time": "1 day, 2:47:19"}
+{"current_steps": 10, "total_steps": 927, "loss": 3.3179, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1e-05, "epoch": 0.03, "percentage": 1.08, "elapsed_time": "0:17:37", "remaining_time": "1 day, 2:55:59"}
+{"current_steps": 15, "total_steps": 927, "loss": 3.3109, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5e-05, "epoch": 0.05, "percentage": 1.62, "elapsed_time": "0:26:31", "remaining_time": "1 day, 2:52:55"}
+{"current_steps": 20, "total_steps": 927, "loss": 3.251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2e-05, "epoch": 0.06, "percentage": 2.16, "elapsed_time": "0:35:25", "remaining_time": "1 day, 2:46:51"}
+{"current_steps": 25, "total_steps": 927, "loss": 3.2489, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5e-05, "epoch": 0.08, "percentage": 2.7, "elapsed_time": "0:44:20", "remaining_time": "1 day, 2:39:45"}
+{"current_steps": 30, "total_steps": 927, "loss": 3.2527, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3e-05, "epoch": 0.1, "percentage": 3.24, "elapsed_time": "0:53:15", "remaining_time": "1 day, 2:32:27"}
+{"current_steps": 35, "total_steps": 927, "loss": 3.225, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5e-05, "epoch": 0.11, "percentage": 3.78, "elapsed_time": "1:02:10", "remaining_time": "1 day, 2:24:38"}
+{"current_steps": 40, "total_steps": 927, "loss": 3.2243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4e-05, "epoch": 0.13, "percentage": 4.31, "elapsed_time": "1:11:04", "remaining_time": "1 day, 2:16:07"}
+{"current_steps": 45, "total_steps": 927, "loss": 3.2182, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5e-05, "epoch": 0.15, "percentage": 4.85, "elapsed_time": "1:19:56", "remaining_time": "1 day, 2:06:59"}
+{"current_steps": 50, "total_steps": 927, "loss": 3.2524, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5e-05, "epoch": 0.16, "percentage": 5.39, "elapsed_time": "1:28:52", "remaining_time": "1 day, 1:58:44"}
+{"current_steps": 55, "total_steps": 927, "loss": 3.2055, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.999599004988406e-05, "epoch": 0.18, "percentage": 5.93, "elapsed_time": "1:37:45", "remaining_time": "1 day, 1:50:00"}
+{"current_steps": 60, "total_steps": 927, "loss": 3.2122, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9983961485912235e-05, "epoch": 0.19, "percentage": 6.47, "elapsed_time": "1:46:39", "remaining_time": "1 day, 1:41:16"}
+{"current_steps": 65, "total_steps": 927, "loss": 3.2483, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9963918166799836e-05, "epoch": 0.21, "percentage": 7.01, "elapsed_time": "1:55:35", "remaining_time": "1 day, 1:32:53"}
+{"current_steps": 70, "total_steps": 927, "loss": 3.2212, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9935866522363665e-05, "epoch": 0.23, "percentage": 7.55, "elapsed_time": "2:04:30", "remaining_time": "1 day, 1:24:18"}
+{"current_steps": 75, "total_steps": 927, "loss": 3.2017, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.989981555145928e-05, "epoch": 0.24, "percentage": 8.09, "elapsed_time": "2:13:24", "remaining_time": "1 day, 1:15:31"}
+{"current_steps": 80, "total_steps": 927, "loss": 3.1735, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.985577681909431e-05, "epoch": 0.26, "percentage": 8.63, "elapsed_time": "2:22:19", "remaining_time": "1 day, 1:06:48"}
+{"current_steps": 85, "total_steps": 927, "loss": 3.2362, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9803764452718335e-05, "epoch": 0.27, "percentage": 9.17, "elapsed_time": "2:31:13", "remaining_time": "1 day, 0:58:01"}
+{"current_steps": 90, "total_steps": 927, "loss": 3.1873, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.974379513769093e-05, "epoch": 0.29, "percentage": 9.71, "elapsed_time": "2:40:07", "remaining_time": "1 day, 0:49:10"}
+{"current_steps": 95, "total_steps": 927, "loss": 3.2065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.967588811192902e-05, "epoch": 0.31, "percentage": 10.25, "elapsed_time": "2:49:03", "remaining_time": "1 day, 0:40:32"}
+{"current_steps": 100, "total_steps": 927, "loss": 3.2155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.960006515973548e-05, "epoch": 0.32, "percentage": 10.79, "elapsed_time": "2:57:57", "remaining_time": "1 day, 0:31:45"}
+{"current_steps": 105, "total_steps": 927, "loss": 3.2032, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9516350604810793e-05, "epoch": 0.34, "percentage": 11.33, "elapsed_time": "3:08:37", "remaining_time": "1 day, 0:36:37"}
+{"current_steps": 110, "total_steps": 927, "loss": 3.1732, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9424771302450084e-05, "epoch": 0.36, "percentage": 11.87, "elapsed_time": "3:17:31", "remaining_time": "1 day, 0:27:08"}
+{"current_steps": 115, "total_steps": 927, "loss": 3.1764, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.932535663092809e-05, "epoch": 0.37, "percentage": 12.41, "elapsed_time": "3:26:27", "remaining_time": "1 day, 0:17:47"}
+{"current_steps": 120, "total_steps": 927, "loss": 3.1902, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.921813848207469e-05, "epoch": 0.39, "percentage": 12.94, "elapsed_time": "3:35:20", "remaining_time": "1 day, 0:08:09"}
+{"current_steps": 125, "total_steps": 927, "loss": 3.1871, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.9103151251044174e-05, "epoch": 0.4, "percentage": 13.48, "elapsed_time": "3:44:14", "remaining_time": "23:58:42"}
+{"current_steps": 130, "total_steps": 927, "loss": 3.1487, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.898043182528136e-05, "epoch": 0.42, "percentage": 14.02, "elapsed_time": "3:53:06", "remaining_time": "23:49:10"}
+{"current_steps": 135, "total_steps": 927, "loss": 3.1696, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.88500195726883e-05, "epoch": 0.44, "percentage": 14.56, "elapsed_time": "4:02:00", "remaining_time": "23:39:49"}
+{"current_steps": 140, "total_steps": 927, "loss": 3.1775, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.871195632899518e-05, "epoch": 0.45, "percentage": 15.1, "elapsed_time": "4:10:52", "remaining_time": "23:30:18"}
+{"current_steps": 145, "total_steps": 927, "loss": 3.1691, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.856628638433962e-05, "epoch": 0.47, "percentage": 15.64, "elapsed_time": "4:19:46", "remaining_time": "23:20:59"}
+{"current_steps": 150, "total_steps": 927, "loss": 3.1456, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.841305646905851e-05, "epoch": 0.48, "percentage": 16.18, "elapsed_time": "4:28:40", "remaining_time": "23:11:44"}
+{"current_steps": 155, "total_steps": 927, "loss": 3.1269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.825231573869721e-05, "epoch": 0.5, "percentage": 16.72, "elapsed_time": "4:37:32", "remaining_time": "23:02:22"}
+{"current_steps": 160, "total_steps": 927, "loss": 3.181, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.808411575824051e-05, "epoch": 0.52, "percentage": 17.26, "elapsed_time": "4:46:26", "remaining_time": "22:53:09"}
+{"current_steps": 165, "total_steps": 927, "loss": 3.145, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7908510485570925e-05, "epoch": 0.53, "percentage": 17.8, "elapsed_time": "4:55:21", "remaining_time": "22:44:01"}
+{"current_steps": 170, "total_steps": 927, "loss": 3.1727, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.772555625415912e-05, "epoch": 0.55, "percentage": 18.34, "elapsed_time": "5:04:16", "remaining_time": "22:34:56"}
+{"current_steps": 175, "total_steps": 927, "loss": 3.147, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.753531175499243e-05, "epoch": 0.57, "percentage": 18.88, "elapsed_time": "5:13:09", "remaining_time": "22:25:42"}
+{"current_steps": 180, "total_steps": 927, "loss": 3.1401, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.733783801774696e-05, "epoch": 0.58, "percentage": 19.42, "elapsed_time": "5:22:03", "remaining_time": "22:16:32"}
+{"current_steps": 185, "total_steps": 927, "loss": 3.1175, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.7133198391209566e-05, "epoch": 0.6, "percentage": 19.96, "elapsed_time": "5:30:58", "remaining_time": "22:07:27"}
+{"current_steps": 190, "total_steps": 927, "loss": 3.1431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.692145852295576e-05, "epoch": 0.61, "percentage": 20.5, "elapsed_time": "5:39:49", "remaining_time": "21:58:10"}
+{"current_steps": 195, "total_steps": 927, "loss": 3.1332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.670268633829031e-05, "epoch": 0.63, "percentage": 21.04, "elapsed_time": "5:48:42", "remaining_time": "21:49:01"}
+{"current_steps": 200, "total_steps": 927, "loss": 3.0935, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6476952018456974e-05, "epoch": 0.65, "percentage": 21.57, "elapsed_time": "5:57:34", "remaining_time": "21:39:47"}
+{"current_steps": 205, "total_steps": 927, "loss": 3.1763, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.6244327978124734e-05, "epoch": 0.66, "percentage": 22.11, "elapsed_time": "6:07:36", "remaining_time": "21:34:41"}
+{"current_steps": 210, "total_steps": 927, "loss": 3.1111, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.600488884215737e-05, "epoch": 0.68, "percentage": 22.65, "elapsed_time": "6:16:29", "remaining_time": "21:25:28"}
+{"current_steps": 215, "total_steps": 927, "loss": 3.1324, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5758711421674166e-05, "epoch": 0.69, "percentage": 23.19, "elapsed_time": "6:25:24", "remaining_time": "21:16:20"}
+{"current_steps": 220, "total_steps": 927, "loss": 3.1194, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.55058746894092e-05, "epoch": 0.71, "percentage": 23.73, "elapsed_time": "6:34:18", "remaining_time": "21:07:09"}
+{"current_steps": 225, "total_steps": 927, "loss": 3.1486, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.524645975437717e-05, "epoch": 0.73, "percentage": 24.27, "elapsed_time": "6:43:13", "remaining_time": "20:58:03"}
+{"current_steps": 230, "total_steps": 927, "loss": 3.1491, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.498054983585398e-05, "epoch": 0.74, "percentage": 24.81, "elapsed_time": "6:52:07", "remaining_time": "20:48:54"}
+{"current_steps": 235, "total_steps": 927, "loss": 3.1492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.470823023668032e-05, "epoch": 0.76, "percentage": 25.35, "elapsed_time": "7:01:01", "remaining_time": "20:39:46"}
+{"current_steps": 240, "total_steps": 927, "loss": 3.1251, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.442958831589686e-05, "epoch": 0.78, "percentage": 25.89, "elapsed_time": "7:09:55", "remaining_time": "20:30:38"}
+{"current_steps": 245, "total_steps": 927, "loss": 3.1005, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.41447134607198e-05, "epoch": 0.79, "percentage": 26.43, "elapsed_time": "7:18:49", "remaining_time": "20:21:31"}
+{"current_steps": 250, "total_steps": 927, "loss": 3.1378, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3853697057865816e-05, "epoch": 0.81, "percentage": 26.97, "elapsed_time": "7:27:43", "remaining_time": "20:12:26"}
+{"current_steps": 255, "total_steps": 927, "loss": 3.139, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3556632464235594e-05, "epoch": 0.82, "percentage": 27.51, "elapsed_time": "7:36:36", "remaining_time": "20:03:18"}
+{"current_steps": 260, "total_steps": 927, "loss": 3.1213, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3253614976965254e-05, "epoch": 0.84, "percentage": 28.05, "elapsed_time": "7:45:28", "remaining_time": "19:54:07"}
+{"current_steps": 265, "total_steps": 927, "loss": 3.1044, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.294474180285545e-05, "epoch": 0.86, "percentage": 28.59, "elapsed_time": "7:54:21", "remaining_time": "19:44:58"}
+{"current_steps": 270, "total_steps": 927, "loss": 3.1343, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.2630112027187816e-05, "epoch": 0.87, "percentage": 29.13, "elapsed_time": "8:03:14", "remaining_time": "19:35:53"}
+{"current_steps": 275, "total_steps": 927, "loss": 3.1137, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.230982658193879e-05, "epoch": 0.89, "percentage": 29.67, "elapsed_time": "8:12:05", "remaining_time": "19:26:42"}
+{"current_steps": 280, "total_steps": 927, "loss": 3.1064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.1983988213401024e-05, "epoch": 0.9, "percentage": 30.2, "elapsed_time": "8:20:59", "remaining_time": "19:17:39"}
+{"current_steps": 285, "total_steps": 927, "loss": 3.0868, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.165270144922283e-05, "epoch": 0.92, "percentage": 30.74, "elapsed_time": "8:29:54", "remaining_time": "19:08:37"}
+{"current_steps": 290, "total_steps": 927, "loss": 3.124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.131607256487606e-05, "epoch": 0.94, "percentage": 31.28, "elapsed_time": "8:38:47", "remaining_time": "18:59:33"}
+{"current_steps": 295, "total_steps": 927, "loss": 3.0944, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.097420954956345e-05, "epoch": 0.95, "percentage": 31.82, "elapsed_time": "8:47:40", "remaining_time": "18:50:29"}
+{"current_steps": 300, "total_steps": 927, "loss": 3.1295, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.0627222071576e-05, "epoch": 0.97, "percentage": 32.36, "elapsed_time": "8:56:34", "remaining_time": "18:41:27"}
+{"current_steps": 305, "total_steps": 927, "loss": 3.1082, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.027522144311193e-05, "epoch": 0.99, "percentage": 32.9, "elapsed_time": "9:06:31", "remaining_time": "18:34:32"}
+{"current_steps": 310, "total_steps": 927, "loss": 3.0918, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.991832058456812e-05, "epoch": 1.0, "percentage": 33.44, "elapsed_time": "9:15:19", "remaining_time": "18:25:16"}
+{"current_steps": 315, "total_steps": 927, "loss": 3.0422, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.955663398831569e-05, "epoch": 1.02, "percentage": 33.98, "elapsed_time": "9:24:14", "remaining_time": "18:16:14"}
+{"current_steps": 320, "total_steps": 927, "loss": 3.0276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.919027768197132e-05, "epoch": 1.03, "percentage": 34.52, "elapsed_time": "9:33:07", "remaining_time": "18:07:08"}
+{"current_steps": 325, "total_steps": 927, "loss": 3.0004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.881936919117607e-05, "epoch": 1.05, "percentage": 35.06, "elapsed_time": "9:42:00", "remaining_time": "17:58:03"}
+{"current_steps": 330, "total_steps": 927, "loss": 3.019, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.84440275018936e-05, "epoch": 1.07, "percentage": 35.6, "elapsed_time": "9:50:52", "remaining_time": "17:48:57"}
+{"current_steps": 335, "total_steps": 927, "loss": 3.0234, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.806437302223992e-05, "epoch": 1.08, "percentage": 36.14, "elapsed_time": "9:59:47", "remaining_time": "17:39:56"}
+{"current_steps": 340, "total_steps": 927, "loss": 3.0334, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.768052754385703e-05, "epoch": 1.1, "percentage": 36.68, "elapsed_time": "10:08:40", "remaining_time": "17:30:51"}
+{"current_steps": 345, "total_steps": 927, "loss": 3.0101, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.7292614202842566e-05, "epoch": 1.11, "percentage": 37.22, "elapsed_time": "10:17:32", "remaining_time": "17:21:46"}
+{"current_steps": 350, "total_steps": 927, "loss": 3.0098, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.690075744024826e-05, "epoch": 1.13, "percentage": 37.76, "elapsed_time": "10:26:27", "remaining_time": "17:12:45"}
+{"current_steps": 355, "total_steps": 927, "loss": 3.0064, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.650508296215978e-05, "epoch": 1.15, "percentage": 38.3, "elapsed_time": "10:35:21", "remaining_time": "17:03:43"}
+{"current_steps": 360, "total_steps": 927, "loss": 2.9863, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.610571769937066e-05, "epoch": 1.16, "percentage": 38.83, "elapsed_time": "10:44:14", "remaining_time": "16:54:41"}
+{"current_steps": 365, "total_steps": 927, "loss": 3.0066, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5702789766663435e-05, "epoch": 1.18, "percentage": 39.37, "elapsed_time": "10:53:06", "remaining_time": "16:45:36"}
+{"current_steps": 370, "total_steps": 927, "loss": 3.0356, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.529642842171096e-05, "epoch": 1.2, "percentage": 39.91, "elapsed_time": "11:02:00", "remaining_time": "16:36:36"}
+{"current_steps": 375, "total_steps": 927, "loss": 2.9687, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.488676402361101e-05, "epoch": 1.21, "percentage": 40.45, "elapsed_time": "11:10:54", "remaining_time": "16:27:34"}
+{"current_steps": 380, "total_steps": 927, "loss": 3.0223, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4473927991067636e-05, "epoch": 1.23, "percentage": 40.99, "elapsed_time": "11:19:48", "remaining_time": "16:18:33"}
+{"current_steps": 385, "total_steps": 927, "loss": 3.0031, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.405805276023256e-05, "epoch": 1.24, "percentage": 41.53, "elapsed_time": "11:28:40", "remaining_time": "16:09:30"}
+{"current_steps": 390, "total_steps": 927, "loss": 3.0106, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.363927174222021e-05, "epoch": 1.26, "percentage": 42.07, "elapsed_time": "11:37:35", "remaining_time": "16:00:31"}
+{"current_steps": 395, "total_steps": 927, "loss": 2.9939, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3217719280309905e-05, "epoch": 1.28, "percentage": 42.61, "elapsed_time": "11:46:27", "remaining_time": "15:51:28"}
+{"current_steps": 400, "total_steps": 927, "loss": 2.9843, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.279353060684914e-05, "epoch": 1.29, "percentage": 43.15, "elapsed_time": "11:55:20", "remaining_time": "15:42:28"}
+{"current_steps": 405, "total_steps": 927, "loss": 2.967, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.236684179987152e-05, "epoch": 1.31, "percentage": 43.69, "elapsed_time": "12:05:38", "remaining_time": "15:35:16"}
+{"current_steps": 410, "total_steps": 927, "loss": 2.9838, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.193778973944354e-05, "epoch": 1.32, "percentage": 44.23, "elapsed_time": "12:14:34", "remaining_time": "15:26:16"}
+{"current_steps": 415, "total_steps": 927, "loss": 3.0091, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.150651206375397e-05, "epoch": 1.34, "percentage": 44.77, "elapsed_time": "12:23:28", "remaining_time": "15:17:15"}
+{"current_steps": 420, "total_steps": 927, "loss": 2.9995, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.1073147124960034e-05, "epoch": 1.36, "percentage": 45.31, "elapsed_time": "12:32:20", "remaining_time": "15:08:10"}
+{"current_steps": 425, "total_steps": 927, "loss": 3.0065, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.063783394480467e-05, "epoch": 1.37, "percentage": 45.85, "elapsed_time": "12:41:12", "remaining_time": "14:59:07"}
+{"current_steps": 430, "total_steps": 927, "loss": 2.976, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.0200712170018852e-05, "epoch": 1.39, "percentage": 46.39, "elapsed_time": "12:50:06", "remaining_time": "14:50:06"}
+{"current_steps": 435, "total_steps": 927, "loss": 2.9819, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9761922027523513e-05, "epoch": 1.41, "percentage": 46.93, "elapsed_time": "12:59:00", "remaining_time": "14:41:05"}
+{"current_steps": 440, "total_steps": 927, "loss": 3.0025, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9321604279445258e-05, "epoch": 1.42, "percentage": 47.46, "elapsed_time": "13:07:54", "remaining_time": "14:32:04"}
+{"current_steps": 445, "total_steps": 927, "loss": 2.9868, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8879900177960488e-05, "epoch": 1.44, "percentage": 48.0, "elapsed_time": "13:16:47", "remaining_time": "14:23:02"}
+{"current_steps": 450, "total_steps": 927, "loss": 2.9699, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.843695141998225e-05, "epoch": 1.45, "percentage": 48.54, "elapsed_time": "13:25:41", "remaining_time": "14:14:02"}
+{"current_steps": 455, "total_steps": 927, "loss": 3.0146, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7992900101704406e-05, "epoch": 1.47, "percentage": 49.08, "elapsed_time": "13:34:36", "remaining_time": "14:05:02"}
+{"current_steps": 460, "total_steps": 927, "loss": 2.9556, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7547888673017775e-05, "epoch": 1.49, "percentage": 49.62, "elapsed_time": "13:43:31", "remaining_time": "13:56:03"}
+{"current_steps": 465, "total_steps": 927, "loss": 2.9929, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7102059891812757e-05, "epoch": 1.5, "percentage": 50.16, "elapsed_time": "13:52:25", "remaining_time": "13:47:03"}
+{"current_steps": 470, "total_steps": 927, "loss": 2.969, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6655556778183198e-05, "epoch": 1.52, "percentage": 50.7, "elapsed_time": "14:01:19", "remaining_time": "13:38:03"}
+{"current_steps": 475, "total_steps": 927, "loss": 2.9893, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6208522568546063e-05, "epoch": 1.54, "percentage": 51.24, "elapsed_time": "14:10:13", "remaining_time": "13:29:02"}
+{"current_steps": 480, "total_steps": 927, "loss": 2.9813, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5761100669691817e-05, "epoch": 1.55, "percentage": 51.78, "elapsed_time": "14:19:07", "remaining_time": "13:20:03"}
+{"current_steps": 485, "total_steps": 927, "loss": 2.9651, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.5313434612780084e-05, "epoch": 1.57, "percentage": 52.32, "elapsed_time": "14:28:01", "remaining_time": "13:11:04"}
+{"current_steps": 490, "total_steps": 927, "loss": 2.9521, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4865668007295394e-05, "epoch": 1.58, "percentage": 52.86, "elapsed_time": "14:36:56", "remaining_time": "13:02:05"}
+{"current_steps": 495, "total_steps": 927, "loss": 2.9846, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.4417944494977888e-05, "epoch": 1.6, "percentage": 53.4, "elapsed_time": "14:45:50", "remaining_time": "12:53:06"}
+{"current_steps": 500, "total_steps": 927, "loss": 2.9799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3970407703743568e-05, "epoch": 1.62, "percentage": 53.94, "elapsed_time": "14:54:45", "remaining_time": "12:44:07"}
+{"current_steps": 505, "total_steps": 927, "loss": 2.9651, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.352320120160907e-05, "epoch": 1.63, "percentage": 54.48, "elapsed_time": "15:04:27", "remaining_time": "12:35:48"}
+{"current_steps": 510, "total_steps": 927, "loss": 3.0041, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3076468450635593e-05, "epoch": 1.65, "percentage": 55.02, "elapsed_time": "15:13:21", "remaining_time": "12:26:47"}
+{"current_steps": 515, "total_steps": 927, "loss": 2.9815, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.263035276090687e-05, "epoch": 1.66, "percentage": 55.56, "elapsed_time": "15:22:15", "remaining_time": "12:17:48"}
+{"current_steps": 520, "total_steps": 927, "loss": 3.0102, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.218499724455584e-05, "epoch": 1.68, "percentage": 56.09, "elapsed_time": "15:31:10", "remaining_time": "12:08:49"}
+{"current_steps": 525, "total_steps": 927, "loss": 2.9728, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1740544769854852e-05, "epoch": 1.7, "percentage": 56.63, "elapsed_time": "15:40:05", "remaining_time": "11:59:50"}
+{"current_steps": 530, "total_steps": 927, "loss": 2.9326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.129713791538411e-05, "epoch": 1.71, "percentage": 57.17, "elapsed_time": "15:49:00", "remaining_time": "11:50:51"}
+{"current_steps": 535, "total_steps": 927, "loss": 2.9677, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.0854918924293006e-05, "epoch": 1.73, "percentage": 57.71, "elapsed_time": "15:57:52", "remaining_time": "11:41:51"}
+{"current_steps": 540, "total_steps": 927, "loss": 2.9511, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.041402965866911e-05, "epoch": 1.75, "percentage": 58.25, "elapsed_time": "16:06:45", "remaining_time": "11:32:50"}
+{"current_steps": 545, "total_steps": 927, "loss": 2.9258, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9974611554029374e-05, "epoch": 1.76, "percentage": 58.79, "elapsed_time": "16:15:38", "remaining_time": "11:23:50"}
+{"current_steps": 550, "total_steps": 927, "loss": 2.9502, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.953680557394816e-05, "epoch": 1.78, "percentage": 59.33, "elapsed_time": "16:24:30", "remaining_time": "11:14:50"}
+{"current_steps": 555, "total_steps": 927, "loss": 2.9492, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.910075216483672e-05, "epoch": 1.79, "percentage": 59.87, "elapsed_time": "16:33:23", "remaining_time": "11:05:50"}
+{"current_steps": 560, "total_steps": 927, "loss": 2.9583, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8666591210888524e-05, "epoch": 1.81, "percentage": 60.41, "elapsed_time": "16:42:15", "remaining_time": "10:56:50"}
+{"current_steps": 565, "total_steps": 927, "loss": 2.9586, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8234461989204984e-05, "epoch": 1.83, "percentage": 60.95, "elapsed_time": "16:51:07", "remaining_time": "10:47:50"}
+{"current_steps": 570, "total_steps": 927, "loss": 2.9489, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7804503125115908e-05, "epoch": 1.84, "percentage": 61.49, "elapsed_time": "16:59:59", "remaining_time": "10:38:50"}
+{"current_steps": 575, "total_steps": 927, "loss": 2.9444, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.7376852547709042e-05, "epoch": 1.86, "percentage": 62.03, "elapsed_time": "17:08:51", "remaining_time": "10:29:50"}
+{"current_steps": 580, "total_steps": 927, "loss": 2.9398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6951647445582997e-05, "epoch": 1.87, "percentage": 62.57, "elapsed_time": "17:17:46", "remaining_time": "10:20:52"}
+{"current_steps": 585, "total_steps": 927, "loss": 2.9243, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.652902422283764e-05, "epoch": 1.89, "percentage": 63.11, "elapsed_time": "17:26:41", "remaining_time": "10:11:55"}
+{"current_steps": 590, "total_steps": 927, "loss": 2.9431, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6109118455316273e-05, "epoch": 1.91, "percentage": 63.65, "elapsed_time": "17:35:36", "remaining_time": "10:02:56"}
+{"current_steps": 595, "total_steps": 927, "loss": 2.9359, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5692064847113375e-05, "epoch": 1.92, "percentage": 64.19, "elapsed_time": "17:44:29", "remaining_time": "9:53:58"}
+{"current_steps": 600, "total_steps": 927, "loss": 2.9224, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.5277997187362113e-05, "epoch": 1.94, "percentage": 64.72, "elapsed_time": "17:53:21", "remaining_time": "9:44:58"}
+{"current_steps": 605, "total_steps": 927, "loss": 2.9303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4867048307315318e-05, "epoch": 1.96, "percentage": 65.26, "elapsed_time": "18:02:51", "remaining_time": "9:36:19"}
+{"current_steps": 610, "total_steps": 927, "loss": 2.965, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.445935003773371e-05, "epoch": 1.97, "percentage": 65.8, "elapsed_time": "18:11:44", "remaining_time": "9:27:21"}
+{"current_steps": 615, "total_steps": 927, "loss": 2.9572, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4055033166595159e-05, "epoch": 1.99, "percentage": 66.34, "elapsed_time": "18:20:37", "remaining_time": "9:18:21"}
+{"current_steps": 620, "total_steps": 927, "loss": 2.9187, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3654227397138419e-05, "epoch": 2.0, "percentage": 66.88, "elapsed_time": "18:29:27", "remaining_time": "9:09:21"}
+{"current_steps": 625, "total_steps": 927, "loss": 2.9113, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3257061306254825e-05, "epoch": 2.02, "percentage": 67.42, "elapsed_time": "18:38:21", "remaining_time": "9:00:23"}
+{"current_steps": 630, "total_steps": 927, "loss": 2.8691, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2863662303241342e-05, "epoch": 2.04, "percentage": 67.96, "elapsed_time": "18:47:15", "remaining_time": "8:51:25"}
+{"current_steps": 635, "total_steps": 927, "loss": 2.8508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2474156588928201e-05, "epoch": 2.05, "percentage": 68.5, "elapsed_time": "18:56:09", "remaining_time": "8:42:27"}
+{"current_steps": 640, "total_steps": 927, "loss": 2.8914, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.208866911519414e-05, "epoch": 2.07, "percentage": 69.04, "elapsed_time": "19:05:03", "remaining_time": "8:33:29"}
+{"current_steps": 645, "total_steps": 927, "loss": 2.8692, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1707323544882348e-05, "epoch": 2.08, "percentage": 69.58, "elapsed_time": "19:13:56", "remaining_time": "8:24:30"}
+{"current_steps": 650, "total_steps": 927, "loss": 2.8271, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1330242212129946e-05, "epoch": 2.1, "percentage": 70.12, "elapsed_time": "19:22:51", "remaining_time": "8:15:33"}
+{"current_steps": 655, "total_steps": 927, "loss": 2.8766, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.095754608312366e-05, "epoch": 2.12, "percentage": 70.66, "elapsed_time": "19:31:45", "remaining_time": "8:06:35"}
+{"current_steps": 660, "total_steps": 927, "loss": 2.8624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0589354717294339e-05, "epoch": 2.13, "percentage": 71.2, "elapsed_time": "19:40:40", "remaining_time": "7:57:38"}
+{"current_steps": 665, "total_steps": 927, "loss": 2.8448, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0225786228962794e-05, "epoch": 2.15, "percentage": 71.74, "elapsed_time": "19:49:36", "remaining_time": "7:48:41"}
+{"current_steps": 670, "total_steps": 927, "loss": 2.8518, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.866957249449168e-06, "epoch": 2.17, "percentage": 72.28, "elapsed_time": "19:58:31", "remaining_time": "7:39:43"}
+{"current_steps": 675, "total_steps": 927, "loss": 2.8477, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.512982889658118e-06, "epoch": 2.18, "percentage": 72.82, "elapsed_time": "20:07:24", "remaining_time": "7:30:45"}
+{"current_steps": 680, "total_steps": 927, "loss": 2.856, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.163976703151645e-06, "epoch": 2.2, "percentage": 73.35, "elapsed_time": "20:16:20", "remaining_time": "7:21:48"}
+{"current_steps": 685, "total_steps": 927, "loss": 2.8622, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.820050649721581e-06, "epoch": 2.21, "percentage": 73.89, "elapsed_time": "20:25:16", "remaining_time": "7:12:52"}
+{"current_steps": 690, "total_steps": 927, "loss": 2.8614, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.481315059473372e-06, "epoch": 2.23, "percentage": 74.43, "elapsed_time": "20:34:11", "remaining_time": "7:03:55"}
+{"current_steps": 695, "total_steps": 927, "loss": 2.8515, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.14787859743256e-06, "epoch": 2.25, "percentage": 74.97, "elapsed_time": "20:43:06", "remaining_time": "6:54:57"}
+{"current_steps": 700, "total_steps": 927, "loss": 2.8315, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.819848228685511e-06, "epoch": 2.26, "percentage": 75.51, "elapsed_time": "20:52:02", "remaining_time": "6:46:01"}
+{"current_steps": 705, "total_steps": 927, "loss": 2.8405, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.497329184065438e-06, "epoch": 2.28, "percentage": 76.05, "elapsed_time": "21:01:49", "remaining_time": "6:37:20"}
+{"current_steps": 710, "total_steps": 927, "loss": 2.8578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.1804249263947825e-06, "epoch": 2.29, "percentage": 76.59, "elapsed_time": "21:10:43", "remaining_time": "6:28:22"}
+{"current_steps": 715, "total_steps": 927, "loss": 2.8221, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.869237117294722e-06, "epoch": 2.31, "percentage": 77.13, "elapsed_time": "21:19:39", "remaining_time": "6:19:25"}
+{"current_steps": 720, "total_steps": 927, "loss": 2.8116, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.56386558457254e-06, "epoch": 2.33, "percentage": 77.67, "elapsed_time": "21:28:32", "remaining_time": "6:10:27"}
+{"current_steps": 725, "total_steps": 927, "loss": 2.8525, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.264408290197296e-06, "epoch": 2.34, "percentage": 78.21, "elapsed_time": "21:37:28", "remaining_time": "6:01:30"}
+{"current_steps": 730, "total_steps": 927, "loss": 2.8241, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.9709612988739695e-06, "epoch": 2.36, "percentage": 78.75, "elapsed_time": "21:46:22", "remaining_time": "5:52:32"}
+{"current_steps": 735, "total_steps": 927, "loss": 2.8624, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.683618747226302e-06, "epoch": 2.38, "percentage": 79.29, "elapsed_time": "21:55:15", "remaining_time": "5:43:34"}
+{"current_steps": 740, "total_steps": 927, "loss": 2.8759, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.4024728135981695e-06, "epoch": 2.39, "percentage": 79.83, "elapsed_time": "22:04:10", "remaining_time": "5:34:37"}
+{"current_steps": 745, "total_steps": 927, "loss": 2.8545, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.127613688483099e-06, "epoch": 2.41, "percentage": 80.37, "elapsed_time": "22:13:03", "remaining_time": "5:25:39"}
+{"current_steps": 750, "total_steps": 927, "loss": 2.8478, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.8591295455915396e-06, "epoch": 2.42, "percentage": 80.91, "elapsed_time": "22:21:57", "remaining_time": "5:16:42"}
+{"current_steps": 755, "total_steps": 927, "loss": 2.8373, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5971065135650775e-06, "epoch": 2.44, "percentage": 81.45, "elapsed_time": "22:30:52", "remaining_time": "5:07:44"}
+{"current_steps": 760, "total_steps": 927, "loss": 2.8495, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.341628648346738e-06, "epoch": 2.46, "percentage": 81.98, "elapsed_time": "22:39:46", "remaining_time": "4:58:47"}
+{"current_steps": 765, "total_steps": 927, "loss": 2.8437, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.092777906216136e-06, "epoch": 2.47, "percentage": 82.52, "elapsed_time": "22:48:39", "remaining_time": "4:49:49"}
+{"current_steps": 770, "total_steps": 927, "loss": 2.822, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.850634117498248e-06, "epoch": 2.49, "percentage": 83.06, "elapsed_time": "22:57:33", "remaining_time": "4:40:52"}
+{"current_steps": 775, "total_steps": 927, "loss": 2.8418, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.615274960954171e-06, "epoch": 2.5, "percentage": 83.6, "elapsed_time": "23:06:27", "remaining_time": "4:31:55"}
+{"current_steps": 780, "total_steps": 927, "loss": 2.8767, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.3867759388620717e-06, "epoch": 2.52, "percentage": 84.14, "elapsed_time": "23:15:20", "remaining_time": "4:22:58"}
+{"current_steps": 785, "total_steps": 927, "loss": 2.8508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.165210352796355e-06, "epoch": 2.54, "percentage": 84.68, "elapsed_time": "23:24:13", "remaining_time": "4:14:00"}
+{"current_steps": 790, "total_steps": 927, "loss": 2.864, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9506492801128216e-06, "epoch": 2.55, "percentage": 85.22, "elapsed_time": "23:33:09", "remaining_time": "4:05:03"}
+{"current_steps": 795, "total_steps": 927, "loss": 2.8496, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.743161551147344e-06, "epoch": 2.57, "percentage": 85.76, "elapsed_time": "23:42:04", "remaining_time": "3:56:07"}
+{"current_steps": 800, "total_steps": 927, "loss": 2.8862, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.542813727135343e-06, "epoch": 2.59, "percentage": 86.3, "elapsed_time": "23:51:00", "remaining_time": "3:47:10"}
+{"current_steps": 805, "total_steps": 927, "loss": 2.8716, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.349670078859226e-06, "epoch": 2.6, "percentage": 86.84, "elapsed_time": "1 day, 0:02:48", "remaining_time": "3:38:39"}
+{"current_steps": 810, "total_steps": 927, "loss": 2.8465, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1637925660305756e-06, "epoch": 2.62, "percentage": 87.38, "elapsed_time": "1 day, 0:11:42", "remaining_time": "3:29:41"}
+{"current_steps": 815, "total_steps": 927, "loss": 2.8681, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9852408174137305e-06, "epoch": 2.63, "percentage": 87.92, "elapsed_time": "1 day, 0:20:36", "remaining_time": "3:20:43"}
+{"current_steps": 820, "total_steps": 927, "loss": 2.8529, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8140721116970904e-06, "epoch": 2.65, "percentage": 88.46, "elapsed_time": "1 day, 0:29:31", "remaining_time": "3:11:45"}
+{"current_steps": 825, "total_steps": 927, "loss": 2.8326, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6503413591183598e-06, "epoch": 2.67, "percentage": 89.0, "elapsed_time": "1 day, 0:38:26", "remaining_time": "3:02:47"}
+{"current_steps": 830, "total_steps": 927, "loss": 2.8605, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.494101083849564e-06, "epoch": 2.68, "percentage": 89.54, "elapsed_time": "1 day, 0:47:22", "remaining_time": "2:53:49"}
+{"current_steps": 835, "total_steps": 927, "loss": 2.861, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3454014071475008e-06, "epoch": 2.7, "percentage": 90.08, "elapsed_time": "1 day, 0:56:18", "remaining_time": "2:44:51"}
+{"current_steps": 840, "total_steps": 927, "loss": 2.8452, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2042900312750265e-06, "epoch": 2.71, "percentage": 90.61, "elapsed_time": "1 day, 1:05:13", "remaining_time": "2:35:53"}
+{"current_steps": 845, "total_steps": 927, "loss": 2.8216, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0708122241983949e-06, "epoch": 2.73, "percentage": 91.15, "elapsed_time": "1 day, 1:14:07", "remaining_time": "2:26:55"}
+{"current_steps": 850, "total_steps": 927, "loss": 2.8401, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.45010805065441e-07, "epoch": 2.75, "percentage": 91.69, "elapsed_time": "1 day, 1:23:03", "remaining_time": "2:17:58"}
+{"current_steps": 855, "total_steps": 927, "loss": 2.84, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.269261304693798e-07, "epoch": 2.76, "percentage": 92.23, "elapsed_time": "1 day, 1:31:59", "remaining_time": "2:09:00"}
+{"current_steps": 860, "total_steps": 927, "loss": 2.8205, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.165960815025769e-07, "epoch": 2.78, "percentage": 92.77, "elapsed_time": "1 day, 1:40:52", "remaining_time": "2:00:02"}
+{"current_steps": 865, "total_steps": 927, "loss": 2.8615, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.14056051604453e-07, "epoch": 2.8, "percentage": 93.31, "elapsed_time": "1 day, 1:49:46", "remaining_time": "1:51:04"}
+{"current_steps": 870, "total_steps": 927, "loss": 2.8303, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.193389352073836e-07, "epoch": 2.81, "percentage": 93.85, "elapsed_time": "1 day, 1:58:40", "remaining_time": "1:42:07"}
+{"current_steps": 874, "total_steps": 927, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 2.82, "percentage": 94.28, "elapsed_time": "1 day, 2:05:46", "remaining_time": "1:34:57"}
+{"current_steps": 805, "total_steps": 927, "loss": 2.8799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.349670078859226e-06, "epoch": 2.6, "percentage": 86.84, "elapsed_time": "0:08:42", "remaining_time": "0:01:19"}
+{"current_steps": 810, "total_steps": 927, "loss": 2.8744, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1637925660305756e-06, "epoch": 2.62, "percentage": 87.38, "elapsed_time": "0:17:36", "remaining_time": "0:02:32"}
+{"current_steps": 815, "total_steps": 927, "loss": 2.8959, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.9852408174137305e-06, "epoch": 2.64, "percentage": 87.92, "elapsed_time": "0:26:29", "remaining_time": "0:03:38"}
+{"current_steps": 820, "total_steps": 927, "loss": 2.8413, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8140721116970904e-06, "epoch": 2.65, "percentage": 88.46, "elapsed_time": "0:35:23", "remaining_time": "0:04:37"}
+{"current_steps": 825, "total_steps": 927, "loss": 2.8479, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6503413591183598e-06, "epoch": 2.67, "percentage": 89.0, "elapsed_time": "0:44:18", "remaining_time": "0:05:28"}
+{"current_steps": 830, "total_steps": 927, "loss": 2.8886, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.494101083849564e-06, "epoch": 2.69, "percentage": 89.54, "elapsed_time": "0:53:14", "remaining_time": "0:06:13"}
+{"current_steps": 835, "total_steps": 927, "loss": 2.8745, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3454014071475008e-06, "epoch": 2.7, "percentage": 90.08, "elapsed_time": "1:02:09", "remaining_time": "0:06:50"}
+{"current_steps": 840, "total_steps": 927, "loss": 2.8619, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2042900312750265e-06, "epoch": 2.72, "percentage": 90.61, "elapsed_time": "1:11:03", "remaining_time": "0:07:21"}
+{"current_steps": 845, "total_steps": 927, "loss": 2.8327, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0708122241983949e-06, "epoch": 2.73, "percentage": 91.15, "elapsed_time": "1:19:56", "remaining_time": "0:07:45"}
+{"current_steps": 850, "total_steps": 927, "loss": 2.8462, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.45010805065441e-07, "epoch": 2.75, "percentage": 91.69, "elapsed_time": "1:28:50", "remaining_time": "0:08:02"}
+{"current_steps": 855, "total_steps": 927, "loss": 2.858, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.269261304693798e-07, "epoch": 2.77, "percentage": 92.23, "elapsed_time": "1:37:45", "remaining_time": "0:08:13"}
+{"current_steps": 860, "total_steps": 927, "loss": 2.8449, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.165960815025769e-07, "epoch": 2.78, "percentage": 92.77, "elapsed_time": "1:46:38", "remaining_time": "0:08:18"}
+{"current_steps": 865, "total_steps": 927, "loss": 2.8543, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.14056051604453e-07, "epoch": 2.8, "percentage": 93.31, "elapsed_time": "1:55:33", "remaining_time": "0:08:16"}
+{"current_steps": 870, "total_steps": 927, "loss": 2.8563, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.193389352073836e-07, "epoch": 2.81, "percentage": 93.85, "elapsed_time": "2:04:27", "remaining_time": "0:08:09"}
+{"current_steps": 875, "total_steps": 927, "loss": 2.8676, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3247511718431663e-07, "epoch": 2.83, "percentage": 94.39, "elapsed_time": "2:13:19", "remaining_time": "0:07:55"}
+{"current_steps": 880, "total_steps": 927, "loss": 2.849, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.5349246310142914e-07, "epoch": 2.85, "percentage": 94.93, "elapsed_time": "2:22:12", "remaining_time": "0:07:35"}
+{"current_steps": 885, "total_steps": 927, "loss": 2.8742, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8241631027895454e-07, "epoch": 2.86, "percentage": 95.47, "elapsed_time": "2:31:06", "remaining_time": "0:07:10"}
+{"current_steps": 890, "total_steps": 927, "loss": 2.8629, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1926945966306568e-07, "epoch": 2.88, "percentage": 96.01, "elapsed_time": "2:40:01", "remaining_time": "0:06:39"}
+{"current_steps": 895, "total_steps": 927, "loss": 2.8601, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6407216851144491e-07, "epoch": 2.9, "percentage": 96.55, "elapsed_time": "2:48:54", "remaining_time": "0:06:02"}
+{"current_steps": 900, "total_steps": 927, "loss": 2.8737, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1684214389481307e-07, "epoch": 2.91, "percentage": 97.09, "elapsed_time": "2:57:48", "remaining_time": "0:05:20"}
+{"current_steps": 905, "total_steps": 927, "loss": 2.8721, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.759453701658704e-08, "epoch": 2.93, "percentage": 97.63, "elapsed_time": "3:09:21", "remaining_time": "0:04:36"}
+{"current_steps": 910, "total_steps": 927, "loss": 2.8909, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.634193835242606e-08, "epoch": 2.94, "percentage": 98.17, "elapsed_time": "3:18:16", "remaining_time": "0:03:42"}
+{"current_steps": 915, "total_steps": 927, "loss": 2.8415, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3094373611262654e-08, "epoch": 2.96, "percentage": 98.71, "elapsed_time": "3:27:11", "remaining_time": "0:02:43"}
+{"current_steps": 920, "total_steps": 927, "loss": 2.8594, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.85930051908912e-09, "epoch": 2.98, "percentage": 99.24, "elapsed_time": "3:36:04", "remaining_time": "0:01:38"}
+{"current_steps": 925, "total_steps": 927, "loss": 2.8407, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.416064265546417e-10, "epoch": 2.99, "percentage": 99.78, "elapsed_time": "3:45:00", "remaining_time": "0:00:29"}
+{"current_steps": 927, "total_steps": 927, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "3:48:34", "remaining_time": "0:00:00"}
+{"current_steps": 905, "total_steps": 1236, "loss": 2.8718, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.009358251619367e-06, "epoch": 2.93, "percentage": 73.22, "elapsed_time": "0:08:39", "remaining_time": "0:03:10"}
+{"current_steps": 910, "total_steps": 1236, "loss": 2.89, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.756246682582565e-06, "epoch": 2.94, "percentage": 73.62, "elapsed_time": "0:17:33", "remaining_time": "0:06:17"}
+{"current_steps": 915, "total_steps": 1236, "loss": 2.8403, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.505984493817182e-06, "epoch": 2.96, "percentage": 74.03, "elapsed_time": "0:26:27", "remaining_time": "0:09:16"}
+{"current_steps": 920, "total_steps": 1236, "loss": 2.8578, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.258615584792079e-06, "epoch": 2.98, "percentage": 74.43, "elapsed_time": "0:35:18", "remaining_time": "0:12:07"}
+{"current_steps": 925, "total_steps": 1236, "loss": 2.8394, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.014183347454662e-06, "epoch": 2.99, "percentage": 74.84, "elapsed_time": "0:44:12", "remaining_time": "0:14:51"}
+{"current_steps": 930, "total_steps": 1236, "loss": 2.8518, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.77273065861924e-06, "epoch": 3.01, "percentage": 75.24, "elapsed_time": "0:53:02", "remaining_time": "0:17:27"}
+{"current_steps": 935, "total_steps": 1236, "loss": 2.8264, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.534299872445855e-06, "epoch": 3.02, "percentage": 75.65, "elapsed_time": "1:01:55", "remaining_time": "0:19:56"}
+{"current_steps": 940, "total_steps": 1236, "loss": 2.8247, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.298932813010834e-06, "epoch": 3.04, "percentage": 76.05, "elapsed_time": "1:10:47", "remaining_time": "0:22:17"}
+{"current_steps": 945, "total_steps": 1236, "loss": 2.8686, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.066670766970201e-06, "epoch": 3.06, "percentage": 76.46, "elapsed_time": "1:19:42", "remaining_time": "0:24:32"}
+{"current_steps": 950, "total_steps": 1236, "loss": 2.8339, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.837554476317412e-06, "epoch": 3.07, "percentage": 76.86, "elapsed_time": "1:28:36", "remaining_time": "0:26:40"}
+{"current_steps": 955, "total_steps": 1236, "loss": 2.8544, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.611624131236724e-06, "epoch": 3.09, "percentage": 77.27, "elapsed_time": "1:37:31", "remaining_time": "0:28:41"}
+{"current_steps": 960, "total_steps": 1236, "loss": 2.8552, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.388919363053197e-06, "epoch": 3.11, "percentage": 77.67, "elapsed_time": "1:46:25", "remaining_time": "0:30:35"}
+{"current_steps": 965, "total_steps": 1236, "loss": 2.8238, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.169479237280823e-06, "epoch": 3.12, "percentage": 78.07, "elapsed_time": "1:55:17", "remaining_time": "0:32:22"}
+{"current_steps": 970, "total_steps": 1236, "loss": 2.8314, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.95334224676995e-06, "epoch": 3.14, "percentage": 78.48, "elapsed_time": "2:04:10", "remaining_time": "0:34:03"}
+{"current_steps": 975, "total_steps": 1236, "loss": 2.8377, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.740546304955024e-06, "epoch": 3.15, "percentage": 78.88, "elapsed_time": "2:13:06", "remaining_time": "0:35:37"}
+{"current_steps": 980, "total_steps": 1236, "loss": 2.8314, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.531128739204072e-06, "epoch": 3.17, "percentage": 79.29, "elapsed_time": "2:22:00", "remaining_time": "0:37:05"}
+{"current_steps": 985, "total_steps": 1236, "loss": 2.8072, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.325126284270998e-06, "epoch": 3.19, "percentage": 79.69, "elapsed_time": "2:30:55", "remaining_time": "0:38:27"}
+{"current_steps": 990, "total_steps": 1236, "loss": 2.8477, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.1225750758517545e-06, "epoch": 3.2, "percentage": 80.1, "elapsed_time": "2:39:49", "remaining_time": "0:39:42"}
+{"current_steps": 995, "total_steps": 1236, "loss": 2.8143, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.923510644245632e-06, "epoch": 3.22, "percentage": 80.5, "elapsed_time": "2:48:45", "remaining_time": "0:40:52"}
+{"current_steps": 1000, "total_steps": 1236, "loss": 2.8508, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.727967908122788e-06, "epoch": 3.23, "percentage": 80.91, "elapsed_time": "2:57:39", "remaining_time": "0:41:55"}
+{"current_steps": 1005, "total_steps": 1236, "loss": 2.8267, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.5359811683990175e-06, "epoch": 3.25, "percentage": 81.31, "elapsed_time": "3:07:38", "remaining_time": "0:43:07"}
+{"current_steps": 1010, "total_steps": 1236, "loss": 2.8183, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.3475841022188604e-06, "epoch": 3.27, "percentage": 81.72, "elapsed_time": "3:16:30", "remaining_time": "0:43:58"}
+{"current_steps": 1015, "total_steps": 1236, "loss": 2.799, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.162809757048197e-06, "epoch": 3.28, "percentage": 82.12, "elapsed_time": "3:25:23", "remaining_time": "0:44:43"}
+{"current_steps": 1020, "total_steps": 1236, "loss": 2.867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.981690544877273e-06, "epoch": 3.3, "percentage": 82.52, "elapsed_time": "3:34:17", "remaining_time": "0:45:22"}
+{"current_steps": 1025, "total_steps": 1236, "loss": 2.8302, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.80425823653513e-06, "epoch": 3.32, "percentage": 82.93, "elapsed_time": "3:43:11", "remaining_time": "0:45:56"}
+{"current_steps": 1030, "total_steps": 1236, "loss": 2.8301, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.630543956116614e-06, "epoch": 3.33, "percentage": 83.33, "elapsed_time": "3:52:03", "remaining_time": "0:46:24"}
+{"current_steps": 1035, "total_steps": 1236, "loss": 2.8322, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.4605781755227774e-06, "epoch": 3.35, "percentage": 83.74, "elapsed_time": "4:00:56", "remaining_time": "0:46:47"}
+{"current_steps": 1040, "total_steps": 1236, "loss": 2.8633, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.294390709115622e-06, "epoch": 3.36, "percentage": 84.14, "elapsed_time": "4:09:49", "remaining_time": "0:47:05"}
+{"current_steps": 1045, "total_steps": 1236, "loss": 2.8269, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.132010708488317e-06, "epoch": 3.38, "percentage": 84.55, "elapsed_time": "4:18:43", "remaining_time": "0:47:17"}
+{"current_steps": 1050, "total_steps": 1236, "loss": 2.8466, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.9734666573515784e-06, "epoch": 3.4, "percentage": 84.95, "elapsed_time": "4:27:36", "remaining_time": "0:47:24"}
+{"current_steps": 1055, "total_steps": 1236, "loss": 2.8398, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.8187863665372017e-06, "epoch": 3.41, "percentage": 85.36, "elapsed_time": "4:36:28", "remaining_time": "0:47:25"}
+{"current_steps": 1060, "total_steps": 1236, "loss": 2.801, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.6679969691196904e-06, "epoch": 3.43, "percentage": 85.76, "elapsed_time": "4:45:19", "remaining_time": "0:47:22"}
+{"current_steps": 1065, "total_steps": 1236, "loss": 2.8276, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.52112491565675e-06, "epoch": 3.44, "percentage": 86.17, "elapsed_time": "4:54:10", "remaining_time": "0:47:13"}
+{"current_steps": 1070, "total_steps": 1236, "loss": 2.8394, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.3781959695494267e-06, "epoch": 3.46, "percentage": 86.57, "elapsed_time": "5:03:01", "remaining_time": "0:47:00"}
+{"current_steps": 1075, "total_steps": 1236, "loss": 2.831, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2392352025229184e-06, "epoch": 3.48, "percentage": 86.97, "elapsed_time": "5:11:54", "remaining_time": "0:46:42"}
+{"current_steps": 1080, "total_steps": 1236, "loss": 2.8119, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.1042669902286204e-06, "epoch": 3.49, "percentage": 87.38, "elapsed_time": "5:20:47", "remaining_time": "0:46:20"}
+{"current_steps": 1085, "total_steps": 1236, "loss": 2.8602, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.973315007968274e-06, "epoch": 3.51, "percentage": 87.78, "elapsed_time": "5:29:40", "remaining_time": "0:45:52"}
+{"current_steps": 1090, "total_steps": 1236, "loss": 2.8384, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.846402226541019e-06, "epoch": 3.53, "percentage": 88.19, "elapsed_time": "5:38:34", "remaining_time": "0:45:21"}
+{"current_steps": 1095, "total_steps": 1236, "loss": 2.8427, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.723550908214e-06, "epoch": 3.54, "percentage": 88.59, "elapsed_time": "5:47:27", "remaining_time": "0:44:44"}
+{"current_steps": 1100, "total_steps": 1236, "loss": 2.8229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.6047826028172202e-06, "epoch": 3.56, "percentage": 89.0, "elapsed_time": "5:56:20", "remaining_time": "0:44:03"}
+{"current_steps": 1105, "total_steps": 1236, "loss": 2.8229, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4901181439634288e-06, "epoch": 3.57, "percentage": 89.4, "elapsed_time": "6:06:25", "remaining_time": "0:43:26"}
+{"current_steps": 1110, "total_steps": 1236, "loss": 2.8075, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.3795776453936287e-06, "epoch": 3.59, "percentage": 89.81, "elapsed_time": "6:15:19", "remaining_time": "0:42:36"}
+{"current_steps": 1115, "total_steps": 1236, "loss": 2.8388, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.2731804974487977e-06, "epoch": 3.61, "percentage": 90.21, "elapsed_time": "6:24:14", "remaining_time": "0:41:41"}
+{"current_steps": 1120, "total_steps": 1236, "loss": 2.8469, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1709453636685964e-06, "epoch": 3.62, "percentage": 90.61, "elapsed_time": "6:33:10", "remaining_time": "0:40:43"}
+{"current_steps": 1125, "total_steps": 1236, "loss": 2.8171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0728901775175272e-06, "epoch": 3.64, "percentage": 91.02, "elapsed_time": "6:42:04", "remaining_time": "0:39:40"}
+{"current_steps": 1130, "total_steps": 1236, "loss": 2.8332, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 9.790321392391027e-07, "epoch": 3.65, "percentage": 91.42, "elapsed_time": "6:50:57", "remaining_time": "0:38:33"}
+{"current_steps": 1135, "total_steps": 1236, "loss": 2.836, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.893877128387462e-07, "epoch": 3.67, "percentage": 91.83, "elapsed_time": "6:59:52", "remaining_time": "0:37:21"}
+{"current_steps": 1140, "total_steps": 1236, "loss": 2.804, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.039726231957479e-07, "epoch": 3.69, "percentage": 92.23, "elapsed_time": "7:08:46", "remaining_time": "0:36:06"}
+{"current_steps": 1145, "total_steps": 1236, "loss": 2.8004, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 7.228018533048886e-07, "epoch": 3.7, "percentage": 92.64, "elapsed_time": "7:17:40", "remaining_time": "0:34:47"}
+{"current_steps": 1150, "total_steps": 1236, "loss": 2.8458, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 6.45889641648234e-07, "epoch": 3.72, "percentage": 93.04, "elapsed_time": "7:26:34", "remaining_time": "0:33:23"}
+{"current_steps": 1155, "total_steps": 1236, "loss": 2.853, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.732494796975157e-07, "epoch": 3.74, "percentage": 93.45, "elapsed_time": "7:35:27", "remaining_time": "0:31:56"}
+{"current_steps": 1160, "total_steps": 1236, "loss": 2.8043, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.048941095475074e-07, "epoch": 3.75, "percentage": 93.85, "elapsed_time": "7:44:23", "remaining_time": "0:30:25"}
+{"current_steps": 1165, "total_steps": 1236, "loss": 2.867, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 4.408355216809129e-07, "epoch": 3.77, "percentage": 94.26, "elapsed_time": "7:53:16", "remaining_time": "0:28:50"}
+{"current_steps": 1170, "total_steps": 1236, "loss": 2.8478, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.810849528650545e-07, "epoch": 3.78, "percentage": 94.66, "elapsed_time": "8:02:11", "remaining_time": "0:27:12"}
+{"current_steps": 1175, "total_steps": 1236, "loss": 2.8324, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.2565288418079096e-07, "epoch": 3.8, "percentage": 95.06, "elapsed_time": "8:11:05", "remaining_time": "0:25:29"}
+{"current_steps": 1180, "total_steps": 1236, "loss": 2.8174, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.7454903918399386e-07, "epoch": 3.82, "percentage": 95.47, "elapsed_time": "8:20:00", "remaining_time": "0:23:43"}
+{"current_steps": 1185, "total_steps": 1236, "loss": 2.8396, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2778238219989533e-07, "epoch": 3.83, "percentage": 95.87, "elapsed_time": "8:28:55", "remaining_time": "0:21:54"}
+{"current_steps": 1190, "total_steps": 1236, "loss": 2.822, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.8536111675062084e-07, "epoch": 3.85, "percentage": 96.28, "elapsed_time": "8:37:48", "remaining_time": "0:20:00"}
+{"current_steps": 1195, "total_steps": 1236, "loss": 2.8396, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.4729268411618202e-07, "epoch": 3.86, "percentage": 96.68, "elapsed_time": "8:46:44", "remaining_time": "0:18:04"}
+{"current_steps": 1200, "total_steps": 1236, "loss": 2.8289, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.1358376202916798e-07, "epoch": 3.88, "percentage": 97.09, "elapsed_time": "8:55:39", "remaining_time": "0:16:04"}
+{"current_steps": 1205, "total_steps": 1236, "loss": 2.8171, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.42402635033851e-08, "epoch": 3.9, "percentage": 97.49, "elapsed_time": "9:06:45", "remaining_time": "0:14:03"}
+{"current_steps": 1210, "total_steps": 1236, "loss": 2.7882, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 5.926733579661725e-08, "epoch": 3.91, "percentage": 97.9, "elapsed_time": "9:15:41", "remaining_time": "0:11:56"}
+{"current_steps": 1215, "total_steps": 1236, "loss": 2.8312, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.866935950774253e-08, "epoch": 3.93, "percentage": 98.3, "elapsed_time": "9:24:39", "remaining_time": "0:09:45"}
+{"current_steps": 1220, "total_steps": 1236, "loss": 2.8118, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 2.2449947808309002e-08, "epoch": 3.95, "percentage": 98.71, "elapsed_time": "9:33:36", "remaining_time": "0:07:31"}
+{"current_steps": 1225, "total_steps": 1236, "loss": 2.8038, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 1.0611945808725043e-08, "epoch": 3.96, "percentage": 99.11, "elapsed_time": "9:42:31", "remaining_time": "0:05:13"}
+{"current_steps": 1230, "total_steps": 1236, "loss": 2.8124, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 3.157430059200217e-09, "epoch": 3.98, "percentage": 99.51, "elapsed_time": "9:51:26", "remaining_time": "0:02:53"}
+{"current_steps": 1235, "total_steps": 1236, "loss": 2.8155, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": 8.770818548942128e-11, "epoch": 3.99, "percentage": 99.92, "elapsed_time": "10:00:22", "remaining_time": "0:00:29"}
+{"current_steps": 1236, "total_steps": 1236, "loss": null, "eval_loss": null, "predict_loss": null, "reward": null, "learning_rate": null, "epoch": 4.0, "percentage": 100.0, "elapsed_time": "10:02:09", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1759 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.9971722884265803,
+  "eval_steps": 500,
+  "global_step": 1236,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 0.31760987639427185,
+      "learning_rate": 5e-06,
+      "loss": 3.2917,
+      "step": 5
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 0.24959272146224976,
+      "learning_rate": 1e-05,
+      "loss": 3.3179,
+      "step": 10
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 0.2924320101737976,
+      "learning_rate": 1.5e-05,
+      "loss": 3.3109,
+      "step": 15
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 0.22757597267627716,
+      "learning_rate": 2e-05,
+      "loss": 3.251,
+      "step": 20
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 0.1803845316171646,
+      "learning_rate": 2.5e-05,
+      "loss": 3.2489,
+      "step": 25
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 0.19006718695163727,
+      "learning_rate": 3e-05,
+      "loss": 3.2527,
+      "step": 30
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 0.17421793937683105,
+      "learning_rate": 3.5e-05,
+      "loss": 3.225,
+      "step": 35
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 0.16238895058631897,
+      "learning_rate": 4e-05,
+      "loss": 3.2243,
+      "step": 40
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 0.16933956742286682,
+      "learning_rate": 4.5e-05,
+      "loss": 3.2182,
+      "step": 45
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 0.16001147031784058,
+      "learning_rate": 5e-05,
+      "loss": 3.2524,
+      "step": 50
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 0.16399356722831726,
+      "learning_rate": 4.999599004988406e-05,
+      "loss": 3.2055,
+      "step": 55
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 0.17454692721366882,
+      "learning_rate": 4.9983961485912235e-05,
+      "loss": 3.2122,
+      "step": 60
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 0.17302922904491425,
+      "learning_rate": 4.9963918166799836e-05,
+      "loss": 3.2483,
+      "step": 65
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 0.16110074520111084,
+      "learning_rate": 4.9935866522363665e-05,
+      "loss": 3.2212,
+      "step": 70
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 0.16342906653881073,
+      "learning_rate": 4.989981555145928e-05,
+      "loss": 3.2017,
+      "step": 75
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 0.16569341719150543,
+      "learning_rate": 4.985577681909431e-05,
+      "loss": 3.1735,
+      "step": 80
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 0.16199316084384918,
+      "learning_rate": 4.9803764452718335e-05,
+      "loss": 3.2362,
+      "step": 85
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 0.163334921002388,
+      "learning_rate": 4.974379513769093e-05,
+      "loss": 3.1873,
+      "step": 90
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 0.17866787314414978,
+      "learning_rate": 4.967588811192902e-05,
+      "loss": 3.2065,
+      "step": 95
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.16487747430801392,
+      "learning_rate": 4.960006515973548e-05,
+      "loss": 3.2155,
+      "step": 100
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 0.1537981629371643,
+      "learning_rate": 4.9516350604810793e-05,
+      "loss": 3.2032,
+      "step": 105
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 0.16236944496631622,
+      "learning_rate": 4.9424771302450084e-05,
+      "loss": 3.1732,
+      "step": 110
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 0.18180155754089355,
+      "learning_rate": 4.932535663092809e-05,
+      "loss": 3.1764,
+      "step": 115
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 0.21276631951332092,
+      "learning_rate": 4.921813848207469e-05,
+      "loss": 3.1902,
+      "step": 120
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 0.18672068417072296,
+      "learning_rate": 4.9103151251044174e-05,
+      "loss": 3.1871,
+      "step": 125
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 0.1597897857427597,
+      "learning_rate": 4.898043182528136e-05,
+      "loss": 3.1487,
+      "step": 130
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 0.1650695651769638,
+      "learning_rate": 4.88500195726883e-05,
+      "loss": 3.1696,
+      "step": 135
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 0.19672705233097076,
+      "learning_rate": 4.871195632899518e-05,
+      "loss": 3.1775,
+      "step": 140
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 0.21495744585990906,
+      "learning_rate": 4.856628638433962e-05,
+      "loss": 3.1691,
+      "step": 145
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 0.2001628875732422,
+      "learning_rate": 4.841305646905851e-05,
+      "loss": 3.1456,
+      "step": 150
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.18947800993919373,
+      "learning_rate": 4.825231573869721e-05,
+      "loss": 3.1269,
+      "step": 155
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 0.17868556082248688,
+      "learning_rate": 4.808411575824051e-05,
+      "loss": 3.181,
+      "step": 160
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 0.16371792554855347,
+      "learning_rate": 4.7908510485570925e-05,
+      "loss": 3.145,
+      "step": 165
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 0.16323748230934143,
+      "learning_rate": 4.772555625415912e-05,
+      "loss": 3.1727,
+      "step": 170
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 0.1625365912914276,
+      "learning_rate": 4.753531175499243e-05,
+      "loss": 3.147,
+      "step": 175
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 0.1947379857301712,
+      "learning_rate": 4.733783801774696e-05,
+      "loss": 3.1401,
+      "step": 180
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.19056910276412964,
+      "learning_rate": 4.7133198391209566e-05,
+      "loss": 3.1175,
+      "step": 185
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 0.184840589761734,
+      "learning_rate": 4.692145852295576e-05,
+      "loss": 3.1431,
+      "step": 190
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 0.16869348287582397,
+      "learning_rate": 4.670268633829031e-05,
+      "loss": 3.1332,
+      "step": 195
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 0.18127334117889404,
+      "learning_rate": 4.6476952018456974e-05,
+      "loss": 3.0935,
+      "step": 200
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 0.19219477474689484,
+      "learning_rate": 4.6244327978124734e-05,
+      "loss": 3.1763,
+      "step": 205
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.17717011272907257,
+      "learning_rate": 4.600488884215737e-05,
+      "loss": 3.1111,
+      "step": 210
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 0.17769476771354675,
+      "learning_rate": 4.5758711421674166e-05,
+      "loss": 3.1324,
+      "step": 215
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 0.1706475168466568,
+      "learning_rate": 4.55058746894092e-05,
+      "loss": 3.1194,
+      "step": 220
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 0.17008131742477417,
+      "learning_rate": 4.524645975437717e-05,
+      "loss": 3.1486,
+      "step": 225
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 0.19806550443172455,
+      "learning_rate": 4.498054983585398e-05,
+      "loss": 3.1491,
+      "step": 230
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.17164206504821777,
+      "learning_rate": 4.470823023668032e-05,
+      "loss": 3.1492,
+      "step": 235
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.16124162077903748,
+      "learning_rate": 4.442958831589686e-05,
+      "loss": 3.1251,
+      "step": 240
+    },
+    {
+      "epoch": 0.79,
+      "grad_norm": 0.17326141893863678,
+      "learning_rate": 4.41447134607198e-05,
+      "loss": 3.1005,
+      "step": 245
+    },
+    {
+      "epoch": 0.81,
+      "grad_norm": 0.18267503380775452,
+      "learning_rate": 4.3853697057865816e-05,
+      "loss": 3.1378,
+      "step": 250
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 0.17902736365795135,
+      "learning_rate": 4.3556632464235594e-05,
+      "loss": 3.139,
+      "step": 255
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.18006114661693573,
+      "learning_rate": 4.3253614976965254e-05,
+      "loss": 3.1213,
+      "step": 260
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 0.18118861317634583,
+      "learning_rate": 4.294474180285545e-05,
+      "loss": 3.1044,
+      "step": 265
+    },
+    {
+      "epoch": 0.87,
+      "grad_norm": 0.17744861543178558,
+      "learning_rate": 4.2630112027187816e-05,
+      "loss": 3.1343,
+      "step": 270
+    },
+    {
+      "epoch": 0.89,
+      "grad_norm": 0.16853739321231842,
+      "learning_rate": 4.230982658193879e-05,
+      "loss": 3.1137,
+      "step": 275
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.19506467878818512,
+      "learning_rate": 4.1983988213401024e-05,
+      "loss": 3.1064,
+      "step": 280
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 0.17228995263576508,
+      "learning_rate": 4.165270144922283e-05,
+      "loss": 3.0868,
+      "step": 285
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.17022188007831573,
+      "learning_rate": 4.131607256487606e-05,
+      "loss": 3.124,
+      "step": 290
+    },
+    {
+      "epoch": 0.95,
+      "grad_norm": 0.17359808087348938,
+      "learning_rate": 4.097420954956345e-05,
+      "loss": 3.0944,
+      "step": 295
+    },
+    {
+      "epoch": 0.97,
+      "grad_norm": 0.16375815868377686,
+      "learning_rate": 4.0627222071576e-05,
+      "loss": 3.1295,
+      "step": 300
+    },
+    {
+      "epoch": 0.99,
+      "grad_norm": 0.18526001274585724,
+      "learning_rate": 4.027522144311193e-05,
+      "loss": 3.1082,
+      "step": 305
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.19401881098747253,
+      "learning_rate": 3.991832058456812e-05,
+      "loss": 3.0918,
+      "step": 310
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 0.19234879314899445,
+      "learning_rate": 3.955663398831569e-05,
+      "loss": 3.0422,
+      "step": 315
+    },
+    {
+      "epoch": 1.03,
+      "grad_norm": 0.18378770351409912,
+      "learning_rate": 3.919027768197132e-05,
+      "loss": 3.0276,
+      "step": 320
+    },
+    {
+      "epoch": 1.05,
+      "grad_norm": 0.189378023147583,
+      "learning_rate": 3.881936919117607e-05,
+      "loss": 3.0004,
+      "step": 325
+    },
+    {
+      "epoch": 1.07,
+      "grad_norm": 0.2043304294347763,
+      "learning_rate": 3.84440275018936e-05,
+      "loss": 3.019,
+      "step": 330
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 0.1825193613767624,
+      "learning_rate": 3.806437302223992e-05,
+      "loss": 3.0234,
+      "step": 335
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 0.20000045001506805,
+      "learning_rate": 3.768052754385703e-05,
+      "loss": 3.0334,
+      "step": 340
+    },
+    {
+      "epoch": 1.11,
+      "grad_norm": 0.2001664638519287,
+      "learning_rate": 3.7292614202842566e-05,
+      "loss": 3.0101,
+      "step": 345
+    },
+    {
+      "epoch": 1.13,
+      "grad_norm": 0.18154805898666382,
+      "learning_rate": 3.690075744024826e-05,
+      "loss": 3.0098,
+      "step": 350
+    },
+    {
+      "epoch": 1.15,
+      "grad_norm": 0.19567397236824036,
+      "learning_rate": 3.650508296215978e-05,
+      "loss": 3.0064,
+      "step": 355
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 0.19580692052841187,
+      "learning_rate": 3.610571769937066e-05,
+      "loss": 2.9863,
+      "step": 360
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 0.1916712522506714,
+      "learning_rate": 3.5702789766663435e-05,
+      "loss": 3.0066,
+      "step": 365
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.19139952957630157,
+      "learning_rate": 3.529642842171096e-05,
+      "loss": 3.0356,
+      "step": 370
+    },
+    {
+      "epoch": 1.21,
+      "grad_norm": 0.18503962457180023,
+      "learning_rate": 3.488676402361101e-05,
+      "loss": 2.9687,
+      "step": 375
+    },
+    {
+      "epoch": 1.23,
+      "grad_norm": 0.18717491626739502,
+      "learning_rate": 3.4473927991067636e-05,
+      "loss": 3.0223,
+      "step": 380
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.19255763292312622,
+      "learning_rate": 3.405805276023256e-05,
+      "loss": 3.0031,
+      "step": 385
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 0.1963498741388321,
+      "learning_rate": 3.363927174222021e-05,
+      "loss": 3.0106,
+      "step": 390
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.19114218652248383,
+      "learning_rate": 3.3217719280309905e-05,
+      "loss": 2.9939,
+      "step": 395
+    },
+    {
+      "epoch": 1.29,
+      "grad_norm": 0.18220435082912445,
+      "learning_rate": 3.279353060684914e-05,
+      "loss": 2.9843,
+      "step": 400
+    },
+    {
+      "epoch": 1.31,
+      "grad_norm": 0.19181542098522186,
+      "learning_rate": 3.236684179987152e-05,
+      "loss": 2.967,
+      "step": 405
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 0.188537135720253,
+      "learning_rate": 3.193778973944354e-05,
+      "loss": 2.9838,
+      "step": 410
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 0.18813706934452057,
+      "learning_rate": 3.150651206375397e-05,
+      "loss": 3.0091,
+      "step": 415
+    },
+    {
+      "epoch": 1.36,
+      "grad_norm": 0.212008997797966,
+      "learning_rate": 3.1073147124960034e-05,
+      "loss": 2.9995,
+      "step": 420
+    },
+    {
+      "epoch": 1.37,
+      "grad_norm": 0.22185884416103363,
+      "learning_rate": 3.063783394480467e-05,
+      "loss": 3.0065,
+      "step": 425
+    },
+    {
+      "epoch": 1.39,
+      "grad_norm": 0.19503167271614075,
+      "learning_rate": 3.0200712170018852e-05,
+      "loss": 2.976,
+      "step": 430
+    },
+    {
+      "epoch": 1.41,
+      "grad_norm": 0.2213529348373413,
+      "learning_rate": 2.9761922027523513e-05,
+      "loss": 2.9819,
+      "step": 435
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.1939724087715149,
+      "learning_rate": 2.9321604279445258e-05,
+      "loss": 3.0025,
+      "step": 440
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 0.19026894867420197,
+      "learning_rate": 2.8879900177960488e-05,
+      "loss": 2.9868,
+      "step": 445
+    },
+    {
+      "epoch": 1.45,
+      "grad_norm": 0.2038724273443222,
+      "learning_rate": 2.843695141998225e-05,
+      "loss": 2.9699,
+      "step": 450
+    },
+    {
+      "epoch": 1.47,
+      "grad_norm": 0.19388242065906525,
+      "learning_rate": 2.7992900101704406e-05,
+      "loss": 3.0146,
+      "step": 455
+    },
+    {
+      "epoch": 1.49,
+      "grad_norm": 0.21257171034812927,
+      "learning_rate": 2.7547888673017775e-05,
+      "loss": 2.9556,
+      "step": 460
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.204994797706604,
+      "learning_rate": 2.7102059891812757e-05,
+      "loss": 2.9929,
+      "step": 465
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 0.21233408153057098,
+      "learning_rate": 2.6655556778183198e-05,
+      "loss": 2.969,
+      "step": 470
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 0.20436938107013702,
+      "learning_rate": 2.6208522568546063e-05,
+      "loss": 2.9893,
+      "step": 475
+    },
+    {
+      "epoch": 1.55,
+      "grad_norm": 0.196218803524971,
+      "learning_rate": 2.5761100669691817e-05,
+      "loss": 2.9813,
+      "step": 480
+    },
+    {
+      "epoch": 1.57,
+      "grad_norm": 0.20421084761619568,
+      "learning_rate": 2.5313434612780084e-05,
+      "loss": 2.9651,
+      "step": 485
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 0.18784867227077484,
+      "learning_rate": 2.4865668007295394e-05,
+      "loss": 2.9521,
+      "step": 490
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 0.22264321148395538,
+      "learning_rate": 2.4417944494977888e-05,
+      "loss": 2.9846,
+      "step": 495
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 0.20101739466190338,
+      "learning_rate": 2.3970407703743568e-05,
+      "loss": 2.9799,
+      "step": 500
+    },
+    {
+      "epoch": 1.63,
+      "grad_norm": 0.20549960434436798,
+      "learning_rate": 2.352320120160907e-05,
+      "loss": 2.9651,
+      "step": 505
+    },
+    {
+      "epoch": 1.65,
+      "grad_norm": 0.20113161206245422,
+      "learning_rate": 2.3076468450635593e-05,
+      "loss": 3.0041,
+      "step": 510
+    },
+    {
+      "epoch": 1.66,
+      "grad_norm": 0.19988353550434113,
+      "learning_rate": 2.263035276090687e-05,
+      "loss": 2.9815,
+      "step": 515
+    },
+    {
+      "epoch": 1.68,
+      "grad_norm": 0.20471665263175964,
+      "learning_rate": 2.218499724455584e-05,
+      "loss": 3.0102,
+      "step": 520
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.1928517073392868,
+      "learning_rate": 2.1740544769854852e-05,
+      "loss": 2.9728,
+      "step": 525
+    },
+    {
+      "epoch": 1.71,
+      "grad_norm": 0.19472594559192657,
+      "learning_rate": 2.129713791538411e-05,
+      "loss": 2.9326,
+      "step": 530
+    },
+    {
+      "epoch": 1.73,
+      "grad_norm": 0.19601967930793762,
+      "learning_rate": 2.0854918924293006e-05,
+      "loss": 2.9677,
+      "step": 535
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.21098604798316956,
+      "learning_rate": 2.041402965866911e-05,
+      "loss": 2.9511,
+      "step": 540
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.2089085876941681,
+      "learning_rate": 1.9974611554029374e-05,
+      "loss": 2.9258,
+      "step": 545
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 0.19997884333133698,
+      "learning_rate": 1.953680557394816e-05,
+      "loss": 2.9502,
+      "step": 550
+    },
+    {
+      "epoch": 1.79,
+      "grad_norm": 0.19092586636543274,
+      "learning_rate": 1.910075216483672e-05,
+      "loss": 2.9492,
+      "step": 555
+    },
+    {
+      "epoch": 1.81,
+      "grad_norm": 0.2013268768787384,
+      "learning_rate": 1.8666591210888524e-05,
+      "loss": 2.9583,
+      "step": 560
+    },
+    {
+      "epoch": 1.83,
+      "grad_norm": 0.19930323958396912,
+      "learning_rate": 1.8234461989204984e-05,
+      "loss": 2.9586,
+      "step": 565
+    },
+    {
+      "epoch": 1.84,
+      "grad_norm": 0.20546257495880127,
+      "learning_rate": 1.7804503125115908e-05,
+      "loss": 2.9489,
+      "step": 570
+    },
+    {
+      "epoch": 1.86,
+      "grad_norm": 0.2034834921360016,
+      "learning_rate": 1.7376852547709042e-05,
+      "loss": 2.9444,
+      "step": 575
+    },
+    {
+      "epoch": 1.87,
+      "grad_norm": 0.2054486870765686,
+      "learning_rate": 1.6951647445582997e-05,
+      "loss": 2.9398,
+      "step": 580
+    },
+    {
+      "epoch": 1.89,
+      "grad_norm": 0.2075914889574051,
+      "learning_rate": 1.652902422283764e-05,
+      "loss": 2.9243,
+      "step": 585
+    },
+    {
+      "epoch": 1.91,
+      "grad_norm": 0.20934872329235077,
+      "learning_rate": 1.6109118455316273e-05,
+      "loss": 2.9431,
+      "step": 590
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.21601444482803345,
+      "learning_rate": 1.5692064847113375e-05,
+      "loss": 2.9359,
+      "step": 595
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 0.19840656220912933,
+      "learning_rate": 1.5277997187362113e-05,
+      "loss": 2.9224,
+      "step": 600
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 0.19977068901062012,
+      "learning_rate": 1.4867048307315318e-05,
+      "loss": 2.9303,
+      "step": 605
+    },
+    {
+      "epoch": 1.97,
+      "grad_norm": 0.20031294226646423,
+      "learning_rate": 1.445935003773371e-05,
+      "loss": 2.965,
+      "step": 610
+    },
+    {
+      "epoch": 1.99,
+      "grad_norm": 0.20860356092453003,
+      "learning_rate": 1.4055033166595159e-05,
+      "loss": 2.9572,
+      "step": 615
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.2589782774448395,
+      "learning_rate": 1.3654227397138419e-05,
+      "loss": 2.9187,
+      "step": 620
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.22443072497844696,
+      "learning_rate": 1.3257061306254825e-05,
+      "loss": 2.9113,
+      "step": 625
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 0.22083857655525208,
+      "learning_rate": 1.2863662303241342e-05,
+      "loss": 2.8691,
+      "step": 630
+    },
+    {
+      "epoch": 2.05,
+      "grad_norm": 0.22610703110694885,
+      "learning_rate": 1.2474156588928201e-05,
+      "loss": 2.8508,
+      "step": 635
+    },
+    {
+      "epoch": 2.07,
+      "grad_norm": 0.2190137356519699,
+      "learning_rate": 1.208866911519414e-05,
+      "loss": 2.8914,
+      "step": 640
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 0.22293512523174286,
+      "learning_rate": 1.1707323544882348e-05,
+      "loss": 2.8692,
+      "step": 645
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.21358615159988403,
+      "learning_rate": 1.1330242212129946e-05,
+      "loss": 2.8271,
+      "step": 650
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.21398493647575378,
+      "learning_rate": 1.095754608312366e-05,
+      "loss": 2.8766,
+      "step": 655
+    },
+    {
+      "epoch": 2.13,
+      "grad_norm": 0.22630859911441803,
+      "learning_rate": 1.0589354717294339e-05,
+      "loss": 2.8624,
+      "step": 660
+    },
+    {
+      "epoch": 2.15,
+      "grad_norm": 0.20600877702236176,
+      "learning_rate": 1.0225786228962794e-05,
+      "loss": 2.8448,
+      "step": 665
+    },
+    {
+      "epoch": 2.17,
+      "grad_norm": 0.2191879153251648,
+      "learning_rate": 9.866957249449168e-06,
+      "loss": 2.8518,
+      "step": 670
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.22143206000328064,
+      "learning_rate": 9.512982889658118e-06,
+      "loss": 2.8477,
+      "step": 675
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 0.2108563482761383,
+      "learning_rate": 9.163976703151645e-06,
+      "loss": 2.856,
+      "step": 680
+    },
+    {
+      "epoch": 2.21,
+      "grad_norm": 0.21850666403770447,
+      "learning_rate": 8.820050649721581e-06,
+      "loss": 2.8622,
+      "step": 685
+    },
+    {
+      "epoch": 2.23,
+      "grad_norm": 0.2310490608215332,
+      "learning_rate": 8.481315059473372e-06,
+      "loss": 2.8614,
+      "step": 690
+    },
+    {
+      "epoch": 2.25,
+      "grad_norm": 0.22149670124053955,
+      "learning_rate": 8.14787859743256e-06,
+      "loss": 2.8515,
+      "step": 695
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 0.2082003504037857,
+      "learning_rate": 7.819848228685511e-06,
+      "loss": 2.8315,
+      "step": 700
+    },
+    {
+      "epoch": 2.28,
+      "grad_norm": 0.23224076628684998,
+      "learning_rate": 7.497329184065438e-06,
+      "loss": 2.8405,
+      "step": 705
+    },
+    {
+      "epoch": 2.29,
+      "grad_norm": 0.2128145843744278,
+      "learning_rate": 7.1804249263947825e-06,
+      "loss": 2.8578,
+      "step": 710
+    },
+    {
+      "epoch": 2.31,
+      "grad_norm": 0.21818694472312927,
+      "learning_rate": 6.869237117294722e-06,
+      "loss": 2.8221,
+      "step": 715
+    },
+    {
+      "epoch": 2.33,
+      "grad_norm": 0.21370700001716614,
+      "learning_rate": 6.56386558457254e-06,
+      "loss": 2.8116,
+      "step": 720
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 0.2164902687072754,
+      "learning_rate": 6.264408290197296e-06,
+      "loss": 2.8525,
+      "step": 725
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 0.22312401235103607,
+      "learning_rate": 5.9709612988739695e-06,
+      "loss": 2.8241,
+      "step": 730
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 0.22373555600643158,
+      "learning_rate": 5.683618747226302e-06,
+      "loss": 2.8624,
+      "step": 735
+    },
+    {
+      "epoch": 2.39,
+      "grad_norm": 0.22297130525112152,
+      "learning_rate": 5.4024728135981695e-06,
+      "loss": 2.8759,
+      "step": 740
+    },
+    {
+      "epoch": 2.41,
+      "grad_norm": 0.20991022884845734,
+      "learning_rate": 5.127613688483099e-06,
+      "loss": 2.8545,
+      "step": 745
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 0.23325349390506744,
+      "learning_rate": 4.8591295455915396e-06,
+      "loss": 2.8478,
+      "step": 750
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 0.20747652649879456,
+      "learning_rate": 4.5971065135650775e-06,
+      "loss": 2.8373,
+      "step": 755
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 0.2196613997220993,
+      "learning_rate": 4.341628648346738e-06,
+      "loss": 2.8495,
+      "step": 760
+    },
+    {
+      "epoch": 2.47,
+      "grad_norm": 0.21464018523693085,
+      "learning_rate": 4.092777906216136e-06,
+      "loss": 2.8437,
+      "step": 765
+    },
+    {
+      "epoch": 2.49,
+      "grad_norm": 0.21386373043060303,
+      "learning_rate": 3.850634117498248e-06,
+      "loss": 2.822,
+      "step": 770
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.22314497828483582,
+      "learning_rate": 3.615274960954171e-06,
+      "loss": 2.8418,
+      "step": 775
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 0.21419712901115417,
+      "learning_rate": 3.3867759388620717e-06,
+      "loss": 2.8767,
+      "step": 780
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 0.2160976380109787,
+      "learning_rate": 3.165210352796355e-06,
+      "loss": 2.8508,
+      "step": 785
+    },
+    {
+      "epoch": 2.55,
+      "grad_norm": 0.22127215564250946,
+      "learning_rate": 2.9506492801128216e-06,
+      "loss": 2.864,
+      "step": 790
+    },
+    {
+      "epoch": 2.57,
+      "grad_norm": 0.22035780549049377,
+      "learning_rate": 2.743161551147344e-06,
+      "loss": 2.8496,
+      "step": 795
+    },
+    {
+      "epoch": 2.59,
+      "grad_norm": 0.21932028234004974,
+      "learning_rate": 2.542813727135343e-06,
+      "loss": 2.8862,
+      "step": 800
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 0.22386135160923004,
+      "learning_rate": 2.349670078859226e-06,
+      "loss": 2.8799,
+      "step": 805
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 0.2204558104276657,
+      "learning_rate": 2.1637925660305756e-06,
+      "loss": 2.8744,
+      "step": 810
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 0.2307337075471878,
+      "learning_rate": 1.9852408174137305e-06,
+      "loss": 2.8959,
+      "step": 815
+    },
+    {
+      "epoch": 2.65,
+      "grad_norm": 0.21677350997924805,
+      "learning_rate": 1.8140721116970904e-06,
+      "loss": 2.8413,
+      "step": 820
+    },
+    {
+      "epoch": 2.67,
+      "grad_norm": 0.20689088106155396,
+      "learning_rate": 1.6503413591183598e-06,
+      "loss": 2.8479,
+      "step": 825
+    },
+    {
+      "epoch": 2.69,
+      "grad_norm": 0.21706977486610413,
+      "learning_rate": 1.494101083849564e-06,
+      "loss": 2.8886,
+      "step": 830
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.20675326883792877,
+      "learning_rate": 1.3454014071475008e-06,
+      "loss": 2.8745,
+      "step": 835
+    },
+    {
+      "epoch": 2.72,
+      "grad_norm": 0.232208713889122,
+      "learning_rate": 1.2042900312750265e-06,
+      "loss": 2.8619,
+      "step": 840
+    },
+    {
+      "epoch": 2.73,
+      "grad_norm": 0.22064746916294098,
+      "learning_rate": 1.0708122241983949e-06,
+      "loss": 2.8327,
+      "step": 845
+    },
+    {
+      "epoch": 2.75,
+      "grad_norm": 0.22476071119308472,
+      "learning_rate": 9.45010805065441e-07,
+      "loss": 2.8462,
+      "step": 850
+    },
+    {
+      "epoch": 2.77,
+      "grad_norm": 0.21655958890914917,
+      "learning_rate": 8.269261304693798e-07,
+      "loss": 2.858,
+      "step": 855
+    },
+    {
+      "epoch": 2.78,
+      "grad_norm": 0.2096630185842514,
+      "learning_rate": 7.165960815025769e-07,
+      "loss": 2.8449,
+      "step": 860
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 0.20629090070724487,
+      "learning_rate": 6.14056051604453e-07,
+      "loss": 2.8543,
+      "step": 865
+    },
+    {
+      "epoch": 2.81,
+      "grad_norm": 0.2086755633354187,
+      "learning_rate": 5.193389352073836e-07,
+      "loss": 2.8563,
+      "step": 870
+    },
+    {
+      "epoch": 2.83,
+      "grad_norm": 0.2304910272359848,
+      "learning_rate": 4.3247511718431663e-07,
+      "loss": 2.8676,
+      "step": 875
+    },
+    {
+      "epoch": 2.85,
+      "grad_norm": 0.21316254138946533,
+      "learning_rate": 3.5349246310142914e-07,
+      "loss": 2.849,
+      "step": 880
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.22124738991260529,
+      "learning_rate": 2.8241631027895454e-07,
+      "loss": 2.8742,
+      "step": 885
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.21196460723876953,
+      "learning_rate": 2.1926945966306568e-07,
+      "loss": 2.8629,
+      "step": 890
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 0.21042677760124207,
+      "learning_rate": 1.6407216851144491e-07,
+      "loss": 2.8601,
+      "step": 895
+    },
+    {
+      "epoch": 2.91,
+      "grad_norm": 0.2190413475036621,
+      "learning_rate": 1.1684214389481307e-07,
+      "loss": 2.8737,
+      "step": 900
+    },
+    {
+      "epoch": 2.93,
+      "grad_norm": 0.2288431078195572,
+      "learning_rate": 9.009358251619367e-06,
+      "loss": 2.8718,
+      "step": 905
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 0.2152530401945114,
+      "learning_rate": 8.756246682582565e-06,
+      "loss": 2.89,
+      "step": 910
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 0.21837005019187927,
+      "learning_rate": 8.505984493817182e-06,
+      "loss": 2.8403,
+      "step": 915
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 0.21821348369121552,
+      "learning_rate": 8.258615584792079e-06,
+      "loss": 2.8578,
+      "step": 920
+    },
+    {
+      "epoch": 2.99,
+      "grad_norm": 0.22208793461322784,
+      "learning_rate": 8.014183347454662e-06,
+      "loss": 2.8394,
+      "step": 925
+    },
+    {
+      "epoch": 3.01,
+      "grad_norm": 0.21861128509044647,
+      "learning_rate": 7.77273065861924e-06,
+      "loss": 2.8518,
+      "step": 930
+    },
+    {
+      "epoch": 3.02,
+      "grad_norm": 0.21865125000476837,
+      "learning_rate": 7.534299872445855e-06,
+      "loss": 2.8264,
+      "step": 935
+    },
+    {
+      "epoch": 3.04,
+      "grad_norm": 0.22050639986991882,
+      "learning_rate": 7.298932813010834e-06,
+      "loss": 2.8247,
+      "step": 940
+    },
+    {
+      "epoch": 3.06,
+      "grad_norm": 0.21507680416107178,
+      "learning_rate": 7.066670766970201e-06,
+      "loss": 2.8686,
+      "step": 945
+    },
+    {
+      "epoch": 3.07,
+      "grad_norm": 0.22617888450622559,
+      "learning_rate": 6.837554476317412e-06,
+      "loss": 2.8339,
+      "step": 950
+    },
+    {
+      "epoch": 3.09,
+      "grad_norm": 0.22186200320720673,
+      "learning_rate": 6.611624131236724e-06,
+      "loss": 2.8544,
+      "step": 955
+    },
+    {
+      "epoch": 3.11,
+      "grad_norm": 0.22832706570625305,
+      "learning_rate": 6.388919363053197e-06,
+      "loss": 2.8552,
+      "step": 960
+    },
+    {
+      "epoch": 3.12,
+      "grad_norm": 0.22354218363761902,
+      "learning_rate": 6.169479237280823e-06,
+      "loss": 2.8238,
+      "step": 965
+    },
+    {
+      "epoch": 3.14,
+      "grad_norm": 0.2282090187072754,
+      "learning_rate": 5.95334224676995e-06,
+      "loss": 2.8314,
+      "step": 970
+    },
+    {
+      "epoch": 3.15,
+      "grad_norm": 0.24048872292041779,
+      "learning_rate": 5.740546304955024e-06,
+      "loss": 2.8377,
+      "step": 975
+    },
+    {
+      "epoch": 3.17,
+      "grad_norm": 0.22570078074932098,
+      "learning_rate": 5.531128739204072e-06,
+      "loss": 2.8314,
+      "step": 980
+    },
+    {
+      "epoch": 3.19,
+      "grad_norm": 0.22778679430484772,
+      "learning_rate": 5.325126284270998e-06,
+      "loss": 2.8072,
+      "step": 985
+    },
+    {
+      "epoch": 3.2,
+      "grad_norm": 0.2253977507352829,
+      "learning_rate": 5.1225750758517545e-06,
+      "loss": 2.8477,
+      "step": 990
+    },
+    {
+      "epoch": 3.22,
+      "grad_norm": 0.21220557391643524,
+      "learning_rate": 4.923510644245632e-06,
+      "loss": 2.8143,
+      "step": 995
+    },
+    {
+      "epoch": 3.23,
+      "grad_norm": 0.2333599179983139,
+      "learning_rate": 4.727967908122788e-06,
+      "loss": 2.8508,
+      "step": 1000
+    },
+    {
+      "epoch": 3.25,
+      "grad_norm": 0.2198331207036972,
+      "learning_rate": 4.5359811683990175e-06,
+      "loss": 2.8267,
+      "step": 1005
+    },
+    {
+      "epoch": 3.27,
+      "grad_norm": 0.22090409696102142,
+      "learning_rate": 4.3475841022188604e-06,
+      "loss": 2.8183,
+      "step": 1010
+    },
+    {
+      "epoch": 3.28,
+      "grad_norm": 0.21586580574512482,
+      "learning_rate": 4.162809757048197e-06,
+      "loss": 2.799,
+      "step": 1015
+    },
+    {
+      "epoch": 3.3,
+      "grad_norm": 0.22138214111328125,
+      "learning_rate": 3.981690544877273e-06,
+      "loss": 2.867,
+      "step": 1020
+    },
+    {
+      "epoch": 3.32,
+      "grad_norm": 0.23438501358032227,
+      "learning_rate": 3.80425823653513e-06,
+      "loss": 2.8302,
+      "step": 1025
+    },
+    {
+      "epoch": 3.33,
+      "grad_norm": 0.2235979288816452,
+      "learning_rate": 3.630543956116614e-06,
+      "loss": 2.8301,
+      "step": 1030
+    },
+    {
+      "epoch": 3.35,
+      "grad_norm": 0.2205328643321991,
+      "learning_rate": 3.4605781755227774e-06,
+      "loss": 2.8322,
+      "step": 1035
+    },
+    {
+      "epoch": 3.36,
+      "grad_norm": 0.226404070854187,
+      "learning_rate": 3.294390709115622e-06,
+      "loss": 2.8633,
+      "step": 1040
+    },
+    {
+      "epoch": 3.38,
+      "grad_norm": 0.22632290422916412,
+      "learning_rate": 3.132010708488317e-06,
+      "loss": 2.8269,
+      "step": 1045
+    },
+    {
+      "epoch": 3.4,
+      "grad_norm": 0.22171452641487122,
+      "learning_rate": 2.9734666573515784e-06,
+      "loss": 2.8466,
+      "step": 1050
+    },
+    {
+      "epoch": 3.41,
+      "grad_norm": 0.2134045958518982,
+      "learning_rate": 2.8187863665372017e-06,
+      "loss": 2.8398,
+      "step": 1055
+    },
+    {
+      "epoch": 3.43,
+      "grad_norm": 0.22553056478500366,
+      "learning_rate": 2.6679969691196904e-06,
+      "loss": 2.801,
+      "step": 1060
+    },
+    {
+      "epoch": 3.44,
+      "grad_norm": 0.23389177024364471,
+      "learning_rate": 2.52112491565675e-06,
+      "loss": 2.8276,
+      "step": 1065
+    },
+    {
+      "epoch": 3.46,
+      "grad_norm": 0.22804100811481476,
+      "learning_rate": 2.3781959695494267e-06,
+      "loss": 2.8394,
+      "step": 1070
+    },
+    {
+      "epoch": 3.48,
+      "grad_norm": 0.2190062403678894,
+      "learning_rate": 2.2392352025229184e-06,
+      "loss": 2.831,
+      "step": 1075
+    },
+    {
+      "epoch": 3.49,
+      "grad_norm": 0.21799859404563904,
+      "learning_rate": 2.1042669902286204e-06,
+      "loss": 2.8119,
+      "step": 1080
+    },
+    {
+      "epoch": 3.51,
+      "grad_norm": 0.22122910618782043,
+      "learning_rate": 1.973315007968274e-06,
+      "loss": 2.8602,
+      "step": 1085
+    },
+    {
+      "epoch": 3.53,
+      "grad_norm": 0.2231130748987198,
+      "learning_rate": 1.846402226541019e-06,
+      "loss": 2.8384,
+      "step": 1090
+    },
+    {
+      "epoch": 3.54,
+      "grad_norm": 0.23154446482658386,
+      "learning_rate": 1.723550908214e-06,
+      "loss": 2.8427,
+      "step": 1095
+    },
+    {
+      "epoch": 3.56,
+      "grad_norm": 0.21399781107902527,
+      "learning_rate": 1.6047826028172202e-06,
+      "loss": 2.8229,
+      "step": 1100
+    },
+    {
+      "epoch": 3.57,
+      "grad_norm": 0.2319013625383377,
+      "learning_rate": 1.4901181439634288e-06,
+      "loss": 2.8229,
+      "step": 1105
+    },
+    {
+      "epoch": 3.59,
+      "grad_norm": 0.22346845269203186,
+      "learning_rate": 1.3795776453936287e-06,
+      "loss": 2.8075,
+      "step": 1110
+    },
+    {
+      "epoch": 3.61,
+      "grad_norm": 0.22235344350337982,
+      "learning_rate": 1.2731804974487977e-06,
+      "loss": 2.8388,
+      "step": 1115
+    },
+    {
+      "epoch": 3.62,
+      "grad_norm": 0.22748830914497375,
+      "learning_rate": 1.1709453636685964e-06,
+      "loss": 2.8469,
+      "step": 1120
+    },
+    {
+      "epoch": 3.64,
+      "grad_norm": 0.2320627123117447,
+      "learning_rate": 1.0728901775175272e-06,
+      "loss": 2.8171,
+      "step": 1125
+    },
+    {
+      "epoch": 3.65,
+      "grad_norm": 0.2156900018453598,
+      "learning_rate": 9.790321392391027e-07,
+      "loss": 2.8332,
+      "step": 1130
+    },
+    {
+      "epoch": 3.67,
+      "grad_norm": 0.21801438927650452,
+      "learning_rate": 8.893877128387462e-07,
+      "loss": 2.836,
+      "step": 1135
+    },
+    {
+      "epoch": 3.69,
+      "grad_norm": 0.23140712082386017,
+      "learning_rate": 8.039726231957479e-07,
+      "loss": 2.804,
+      "step": 1140
+    },
+    {
+      "epoch": 3.7,
+      "grad_norm": 0.22428776323795319,
+      "learning_rate": 7.228018533048886e-07,
+      "loss": 2.8004,
+      "step": 1145
+    },
+    {
+      "epoch": 3.72,
+      "grad_norm": 0.22678926587104797,
+      "learning_rate": 6.45889641648234e-07,
+      "loss": 2.8458,
+      "step": 1150
+    },
+    {
+      "epoch": 3.74,
+      "grad_norm": 0.23222048580646515,
+      "learning_rate": 5.732494796975157e-07,
+      "loss": 2.853,
+      "step": 1155
+    },
+    {
+      "epoch": 3.75,
+      "grad_norm": 0.20704413950443268,
+      "learning_rate": 5.048941095475074e-07,
+      "loss": 2.8043,
+      "step": 1160
+    },
+    {
+      "epoch": 3.77,
+      "grad_norm": 0.2371576577425003,
+      "learning_rate": 4.408355216809129e-07,
+      "loss": 2.867,
+      "step": 1165
+    },
+    {
+      "epoch": 3.78,
+      "grad_norm": 0.21293425559997559,
+      "learning_rate": 3.810849528650545e-07,
+      "loss": 2.8478,
+      "step": 1170
+    },
+    {
+      "epoch": 3.8,
+      "grad_norm": 0.25140973925590515,
+      "learning_rate": 3.2565288418079096e-07,
+      "loss": 2.8324,
+      "step": 1175
+    },
+    {
+      "epoch": 3.82,
+      "grad_norm": 0.21989835798740387,
+      "learning_rate": 2.7454903918399386e-07,
+      "loss": 2.8174,
+      "step": 1180
+    },
+    {
+      "epoch": 3.83,
+      "grad_norm": 0.22354339063167572,
+      "learning_rate": 2.2778238219989533e-07,
+      "loss": 2.8396,
+      "step": 1185
+    },
+    {
+      "epoch": 3.85,
+      "grad_norm": 0.23933887481689453,
+      "learning_rate": 1.8536111675062084e-07,
+      "loss": 2.822,
+      "step": 1190
+    },
+    {
+      "epoch": 3.86,
+      "grad_norm": 0.21597786247730255,
+      "learning_rate": 1.4729268411618202e-07,
+      "loss": 2.8396,
+      "step": 1195
+    },
+    {
+      "epoch": 3.88,
+      "grad_norm": 0.2182658612728119,
+      "learning_rate": 1.1358376202916798e-07,
+      "loss": 2.8289,
+      "step": 1200
+    },
+    {
+      "epoch": 3.9,
+      "grad_norm": 0.23224902153015137,
+      "learning_rate": 8.42402635033851e-08,
+      "loss": 2.8171,
+      "step": 1205
+    },
+    {
+      "epoch": 3.91,
+      "grad_norm": 0.2257353514432907,
+      "learning_rate": 5.926733579661725e-08,
+      "loss": 2.7882,
+      "step": 1210
+    },
+    {
+      "epoch": 3.93,
+      "grad_norm": 0.2192804217338562,
+      "learning_rate": 3.866935950774253e-08,
+      "loss": 2.8312,
+      "step": 1215
+    },
+    {
+      "epoch": 3.95,
+      "grad_norm": 0.2221554070711136,
+      "learning_rate": 2.2449947808309002e-08,
+      "loss": 2.8118,
+      "step": 1220
+    },
+    {
+      "epoch": 3.96,
+      "grad_norm": 0.2162608802318573,
+      "learning_rate": 1.0611945808725043e-08,
+      "loss": 2.8038,
+      "step": 1225
+    },
+    {
+      "epoch": 3.98,
+      "grad_norm": 0.2273118495941162,
+      "learning_rate": 3.157430059200217e-09,
+      "loss": 2.8124,
+      "step": 1230
+    },
+    {
+      "epoch": 3.99,
+      "grad_norm": 0.22424130141735077,
+      "learning_rate": 8.770818548942128e-11,
+      "loss": 2.8155,
+      "step": 1235
+    },
+    {
+      "epoch": 4.0,
+      "step": 1236,
+      "total_flos": 1.3106595430434079e+19,
+      "train_loss": 0.7700594385850776,
+      "train_runtime": 36129.1454,
+      "train_samples_per_second": 4.385,
+      "train_steps_per_second": 0.034
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1236,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 100,
+  "total_flos": 1.3106595430434079e+19,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69facfb02acb7c28ed594ad5e9b7c625b089a00b09097672f97e39d5fb1a5c07
+size 5112