Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: mistralai/Mistral-7B-v0.3
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen
+  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. -->
+
+# qwen
+
+This model is a fine-tuned version of [mistralai/Mistral-7B-v0.3](https://huggingface.co/mistralai/Mistral-7B-v0.3) on the openhermes-2.5 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: 2e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.03
+- num_epochs: 1.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.1
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.20.0

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999882826231301,
+    "total_flos": 1.7902479199415828e+19,
+    "train_loss": 0.6576289132237434,
+    "train_runtime": 37752.4225,
+    "train_samples_per_second": 2.713,
+    "train_steps_per_second": 0.042
+}

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "mistralai/Mistral-7B-v0.3",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 32768,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.1",
+  "use_cache": false,
+  "vocab_size": 32768
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "transformers_version": "4.45.1"
+}

model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:729b805c33da1f3d2c9e754c16b5e72c980cd079132c35bb1442fc3e009b94fd
+size 4949453792

model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27efdc661e423688019c738d96875fec3e4c08101594f92b82bdd2f3373cd690
+size 4999819336

model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6b317efc6d50ca54648cb68fc2d26b562e66043cb07fa4cdff20513d3b855d
+size 4546807800

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 14496047104
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00003-of-00003.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37f00374dea48658ee8f5d0f21895b9bc55cb0103939607c8185bfd1c6ca1f89
+size 587404

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.999882826231301,
+    "total_flos": 1.7902479199415828e+19,
+    "train_loss": 0.6576289132237434,
+    "train_runtime": 37752.4225,
+    "train_samples_per_second": 2.713,
+    "train_steps_per_second": 0.042
+}

trainer_log.jsonl

@@ -0,0 +1,161 @@
+{"current_steps": 10, "total_steps": 1600, "loss": 0.7433, "learning_rate": 4.166666666666667e-06, "epoch": 0.006249267663945631, "percentage": 0.62, "elapsed_time": "0:04:29", "remaining_time": "11:53:27"}
+{"current_steps": 20, "total_steps": 1600, "loss": 0.6848, "learning_rate": 8.333333333333334e-06, "epoch": 0.012498535327891263, "percentage": 1.25, "elapsed_time": "0:08:52", "remaining_time": "11:41:43"}
+{"current_steps": 30, "total_steps": 1600, "loss": 0.6722, "learning_rate": 1.25e-05, "epoch": 0.018747802991836895, "percentage": 1.88, "elapsed_time": "0:13:15", "remaining_time": "11:33:47"}
+{"current_steps": 40, "total_steps": 1600, "loss": 0.6924, "learning_rate": 1.6666666666666667e-05, "epoch": 0.024997070655782525, "percentage": 2.5, "elapsed_time": "0:17:40", "remaining_time": "11:29:01"}
+{"current_steps": 50, "total_steps": 1600, "loss": 0.6759, "learning_rate": 1.999991805061211e-05, "epoch": 0.031246338319728156, "percentage": 3.12, "elapsed_time": "0:22:02", "remaining_time": "11:23:05"}
+{"current_steps": 60, "total_steps": 1600, "loss": 0.7484, "learning_rate": 1.999704996306308e-05, "epoch": 0.03749560598367379, "percentage": 3.75, "elapsed_time": "0:26:29", "remaining_time": "11:20:00"}
+{"current_steps": 70, "total_steps": 1600, "loss": 0.7298, "learning_rate": 1.999008574916082e-05, "epoch": 0.04374487364761942, "percentage": 4.38, "elapsed_time": "0:31:00", "remaining_time": "11:17:39"}
+{"current_steps": 80, "total_steps": 1600, "loss": 0.7381, "learning_rate": 1.997902826237712e-05, "epoch": 0.04999414131156505, "percentage": 5.0, "elapsed_time": "0:35:25", "remaining_time": "11:12:59"}
+{"current_steps": 90, "total_steps": 1600, "loss": 0.716, "learning_rate": 1.9963882033334827e-05, "epoch": 0.05624340897551068, "percentage": 5.62, "elapsed_time": "0:39:56", "remaining_time": "11:10:05"}
+{"current_steps": 100, "total_steps": 1600, "loss": 0.713, "learning_rate": 1.9944653267951507e-05, "epoch": 0.06249267663945631, "percentage": 6.25, "elapsed_time": "0:44:25", "remaining_time": "11:06:28"}
+{"current_steps": 110, "total_steps": 1600, "loss": 0.6886, "learning_rate": 1.9921349844896655e-05, "epoch": 0.06874194430340194, "percentage": 6.88, "elapsed_time": "0:49:00", "remaining_time": "11:03:50"}
+{"current_steps": 120, "total_steps": 1600, "loss": 0.7459, "learning_rate": 1.9893981312363563e-05, "epoch": 0.07499121196734758, "percentage": 7.5, "elapsed_time": "0:53:31", "remaining_time": "11:00:07"}
+{"current_steps": 130, "total_steps": 1600, "loss": 0.7131, "learning_rate": 1.9862558884157067e-05, "epoch": 0.0812404796312932, "percentage": 8.12, "elapsed_time": "0:58:02", "remaining_time": "10:56:23"}
+{"current_steps": 140, "total_steps": 1600, "loss": 0.7419, "learning_rate": 1.9827095435098926e-05, "epoch": 0.08748974729523884, "percentage": 8.75, "elapsed_time": "1:02:33", "remaining_time": "10:52:22"}
+{"current_steps": 150, "total_steps": 1600, "loss": 0.7093, "learning_rate": 1.9787605495752528e-05, "epoch": 0.09373901495918448, "percentage": 9.38, "elapsed_time": "1:07:05", "remaining_time": "10:48:37"}
+{"current_steps": 160, "total_steps": 1600, "loss": 0.7162, "learning_rate": 1.9744105246469264e-05, "epoch": 0.0999882826231301, "percentage": 10.0, "elapsed_time": "1:11:36", "remaining_time": "10:44:28"}
+{"current_steps": 170, "total_steps": 1600, "loss": 0.7501, "learning_rate": 1.9696612510758878e-05, "epoch": 0.10623755028707574, "percentage": 10.62, "elapsed_time": "1:16:07", "remaining_time": "10:40:23"}
+{"current_steps": 180, "total_steps": 1600, "loss": 0.7228, "learning_rate": 1.964514674798659e-05, "epoch": 0.11248681795102136, "percentage": 11.25, "elapsed_time": "1:20:36", "remaining_time": "10:35:56"}
+{"current_steps": 190, "total_steps": 1600, "loss": 0.7283, "learning_rate": 1.9589729045399935e-05, "epoch": 0.118736085614967, "percentage": 11.88, "elapsed_time": "1:25:09", "remaining_time": "10:31:56"}
+{"current_steps": 200, "total_steps": 1600, "loss": 0.7464, "learning_rate": 1.953038210948861e-05, "epoch": 0.12498535327891262, "percentage": 12.5, "elapsed_time": "1:29:39", "remaining_time": "10:27:37"}
+{"current_steps": 210, "total_steps": 1600, "loss": 0.721, "learning_rate": 1.9467130256680867e-05, "epoch": 0.13123462094285826, "percentage": 13.12, "elapsed_time": "1:34:10", "remaining_time": "10:23:19"}
+{"current_steps": 220, "total_steps": 1600, "loss": 0.711, "learning_rate": 1.9399999403380266e-05, "epoch": 0.13748388860680388, "percentage": 13.75, "elapsed_time": "1:38:41", "remaining_time": "10:19:01"}
+{"current_steps": 230, "total_steps": 1600, "loss": 0.7296, "learning_rate": 1.932901705534683e-05, "epoch": 0.14373315627074953, "percentage": 14.37, "elapsed_time": "1:43:11", "remaining_time": "10:14:37"}
+{"current_steps": 240, "total_steps": 1600, "loss": 0.7079, "learning_rate": 1.9254212296427043e-05, "epoch": 0.14998242393469516, "percentage": 15.0, "elapsed_time": "1:47:41", "remaining_time": "10:10:16"}
+{"current_steps": 250, "total_steps": 1600, "loss": 0.7231, "learning_rate": 1.9175615776637212e-05, "epoch": 0.15623169159864078, "percentage": 15.62, "elapsed_time": "1:52:14", "remaining_time": "10:06:08"}
+{"current_steps": 260, "total_steps": 1600, "loss": 0.7202, "learning_rate": 1.9093259699605125e-05, "epoch": 0.1624809592625864, "percentage": 16.25, "elapsed_time": "1:58:32", "remaining_time": "10:10:56"}
+{"current_steps": 270, "total_steps": 1600, "loss": 0.7129, "learning_rate": 1.900717780937514e-05, "epoch": 0.16873022692653206, "percentage": 16.88, "elapsed_time": "2:02:48", "remaining_time": "10:04:55"}
+{"current_steps": 280, "total_steps": 1600, "loss": 0.7142, "learning_rate": 1.8917405376582144e-05, "epoch": 0.17497949459047768, "percentage": 17.5, "elapsed_time": "2:07:05", "remaining_time": "9:59:07"}
+{"current_steps": 290, "total_steps": 1600, "loss": 0.7168, "learning_rate": 1.8823979183999965e-05, "epoch": 0.1812287622544233, "percentage": 18.12, "elapsed_time": "2:11:22", "remaining_time": "9:53:25"}
+{"current_steps": 300, "total_steps": 1600, "loss": 0.7209, "learning_rate": 1.8726937511470247e-05, "epoch": 0.18747802991836895, "percentage": 18.75, "elapsed_time": "2:15:39", "remaining_time": "9:47:49"}
+{"current_steps": 310, "total_steps": 1600, "loss": 0.7278, "learning_rate": 1.8626320120217922e-05, "epoch": 0.19372729758231458, "percentage": 19.38, "elapsed_time": "2:19:53", "remaining_time": "9:42:07"}
+{"current_steps": 320, "total_steps": 1600, "loss": 0.7229, "learning_rate": 1.8522168236559693e-05, "epoch": 0.1999765652462602, "percentage": 20.0, "elapsed_time": "2:24:04", "remaining_time": "9:36:16"}
+{"current_steps": 330, "total_steps": 1600, "loss": 0.7003, "learning_rate": 1.8414524535012244e-05, "epoch": 0.20622583291020583, "percentage": 20.62, "elapsed_time": "2:28:16", "remaining_time": "9:30:37"}
+{"current_steps": 340, "total_steps": 1600, "loss": 0.729, "learning_rate": 1.8303433120807043e-05, "epoch": 0.21247510057415148, "percentage": 21.25, "elapsed_time": "2:32:28", "remaining_time": "9:25:02"}
+{"current_steps": 350, "total_steps": 1600, "loss": 0.7437, "learning_rate": 1.8188939511818965e-05, "epoch": 0.2187243682380971, "percentage": 21.88, "elapsed_time": "2:36:43", "remaining_time": "9:19:42"}
+{"current_steps": 360, "total_steps": 1600, "loss": 0.7101, "learning_rate": 1.8071090619916095e-05, "epoch": 0.22497363590204272, "percentage": 22.5, "elapsed_time": "2:40:54", "remaining_time": "9:14:15"}
+{"current_steps": 370, "total_steps": 1600, "loss": 0.7297, "learning_rate": 1.7949934731738348e-05, "epoch": 0.23122290356598835, "percentage": 23.12, "elapsed_time": "2:45:09", "remaining_time": "9:09:01"}
+{"current_steps": 380, "total_steps": 1600, "loss": 0.7275, "learning_rate": 1.7825521488912833e-05, "epoch": 0.237472171229934, "percentage": 23.75, "elapsed_time": "2:49:20", "remaining_time": "9:03:41"}
+{"current_steps": 390, "total_steps": 1600, "loss": 0.7103, "learning_rate": 1.7697901867713997e-05, "epoch": 0.24372143889387962, "percentage": 24.38, "elapsed_time": "2:53:29", "remaining_time": "8:58:15"}
+{"current_steps": 400, "total_steps": 1600, "loss": 0.6981, "learning_rate": 1.7567128158176955e-05, "epoch": 0.24997070655782525, "percentage": 25.0, "elapsed_time": "2:57:41", "remaining_time": "8:53:04"}
+{"current_steps": 410, "total_steps": 1600, "loss": 0.7015, "learning_rate": 1.7433253942672497e-05, "epoch": 0.2562199742217709, "percentage": 25.62, "elapsed_time": "3:01:55", "remaining_time": "8:48:02"}
+{"current_steps": 420, "total_steps": 1600, "loss": 0.7242, "learning_rate": 1.7296334073952606e-05, "epoch": 0.2624692418857165, "percentage": 26.25, "elapsed_time": "3:06:08", "remaining_time": "8:42:57"}
+{"current_steps": 430, "total_steps": 1600, "loss": 0.7115, "learning_rate": 1.7156424652675433e-05, "epoch": 0.26871850954966214, "percentage": 26.88, "elapsed_time": "3:10:18", "remaining_time": "8:37:49"}
+{"current_steps": 440, "total_steps": 1600, "loss": 0.6912, "learning_rate": 1.7013583004418994e-05, "epoch": 0.27496777721360777, "percentage": 27.5, "elapsed_time": "3:14:29", "remaining_time": "8:32:45"}
+{"current_steps": 450, "total_steps": 1600, "loss": 0.7074, "learning_rate": 1.6867867656192946e-05, "epoch": 0.2812170448775534, "percentage": 28.12, "elapsed_time": "3:18:43", "remaining_time": "8:27:51"}
+{"current_steps": 460, "total_steps": 1600, "loss": 0.7048, "learning_rate": 1.6719338312458123e-05, "epoch": 0.28746631254149907, "percentage": 28.75, "elapsed_time": "3:23:01", "remaining_time": "8:23:09"}
+{"current_steps": 470, "total_steps": 1600, "loss": 0.7085, "learning_rate": 1.656805583066361e-05, "epoch": 0.2937155802054447, "percentage": 29.38, "elapsed_time": "3:27:20", "remaining_time": "8:18:31"}
+{"current_steps": 480, "total_steps": 1600, "loss": 0.6897, "learning_rate": 1.6414082196311402e-05, "epoch": 0.2999648478693903, "percentage": 30.0, "elapsed_time": "3:31:37", "remaining_time": "8:13:48"}
+{"current_steps": 490, "total_steps": 1600, "loss": 0.6941, "learning_rate": 1.6257480497558873e-05, "epoch": 0.30621411553333594, "percentage": 30.63, "elapsed_time": "3:35:51", "remaining_time": "8:08:58"}
+{"current_steps": 500, "total_steps": 1600, "loss": 0.7061, "learning_rate": 1.6098314899369446e-05, "epoch": 0.31246338319728156, "percentage": 31.25, "elapsed_time": "3:40:02", "remaining_time": "8:04:05"}
+{"current_steps": 510, "total_steps": 1600, "loss": 0.6958, "learning_rate": 1.5936650617222063e-05, "epoch": 0.3187126508612272, "percentage": 31.87, "elapsed_time": "3:44:15", "remaining_time": "7:59:18"}
+{"current_steps": 520, "total_steps": 1600, "loss": 0.7177, "learning_rate": 1.5772553890390196e-05, "epoch": 0.3249619185251728, "percentage": 32.5, "elapsed_time": "3:50:04", "remaining_time": "7:57:51"}
+{"current_steps": 530, "total_steps": 1600, "loss": 0.6803, "learning_rate": 1.560609195480142e-05, "epoch": 0.3312111861891185, "percentage": 33.12, "elapsed_time": "3:53:31", "remaining_time": "7:51:26"}
+{"current_steps": 540, "total_steps": 1600, "loss": 0.6694, "learning_rate": 1.5437333015488586e-05, "epoch": 0.3374604538530641, "percentage": 33.75, "elapsed_time": "3:57:00", "remaining_time": "7:45:13"}
+{"current_steps": 550, "total_steps": 1600, "loss": 0.6773, "learning_rate": 1.526634621864395e-05, "epoch": 0.34370972151700974, "percentage": 34.38, "elapsed_time": "4:00:31", "remaining_time": "7:39:10"}
+{"current_steps": 560, "total_steps": 1600, "loss": 0.7048, "learning_rate": 1.5093201623287631e-05, "epoch": 0.34995898918095536, "percentage": 35.0, "elapsed_time": "4:04:01", "remaining_time": "7:33:10"}
+{"current_steps": 570, "total_steps": 1600, "loss": 0.686, "learning_rate": 1.4917970172562122e-05, "epoch": 0.356208256844901, "percentage": 35.62, "elapsed_time": "4:07:32", "remaining_time": "7:27:18"}
+{"current_steps": 580, "total_steps": 1600, "loss": 0.6911, "learning_rate": 1.4740723664664483e-05, "epoch": 0.3624575245088466, "percentage": 36.25, "elapsed_time": "4:11:02", "remaining_time": "7:21:28"}
+{"current_steps": 590, "total_steps": 1600, "loss": 0.6828, "learning_rate": 1.4561534723428205e-05, "epoch": 0.36870679217279223, "percentage": 36.88, "elapsed_time": "4:14:30", "remaining_time": "7:15:41"}
+{"current_steps": 600, "total_steps": 1600, "loss": 0.6636, "learning_rate": 1.4380476768566825e-05, "epoch": 0.3749560598367379, "percentage": 37.5, "elapsed_time": "4:18:00", "remaining_time": "7:10:00"}
+{"current_steps": 610, "total_steps": 1600, "loss": 0.6902, "learning_rate": 1.4197623985591373e-05, "epoch": 0.38120532750068353, "percentage": 38.12, "elapsed_time": "4:21:30", "remaining_time": "7:04:25"}
+{"current_steps": 620, "total_steps": 1600, "loss": 0.6795, "learning_rate": 1.4013051295414108e-05, "epoch": 0.38745459516462916, "percentage": 38.75, "elapsed_time": "4:24:56", "remaining_time": "6:58:46"}
+{"current_steps": 630, "total_steps": 1600, "loss": 0.7005, "learning_rate": 1.3826834323650899e-05, "epoch": 0.3937038628285748, "percentage": 39.38, "elapsed_time": "4:28:23", "remaining_time": "6:53:13"}
+{"current_steps": 640, "total_steps": 1600, "loss": 0.6789, "learning_rate": 1.3639049369634878e-05, "epoch": 0.3999531304925204, "percentage": 40.0, "elapsed_time": "4:31:48", "remaining_time": "6:47:42"}
+{"current_steps": 650, "total_steps": 1600, "loss": 0.6808, "learning_rate": 1.344977337515404e-05, "epoch": 0.406202398156466, "percentage": 40.62, "elapsed_time": "4:35:12", "remaining_time": "6:42:13"}
+{"current_steps": 660, "total_steps": 1600, "loss": 0.6798, "learning_rate": 1.3259083892925633e-05, "epoch": 0.41245166582041165, "percentage": 41.25, "elapsed_time": "4:38:35", "remaining_time": "6:36:46"}
+{"current_steps": 670, "total_steps": 1600, "loss": 0.6587, "learning_rate": 1.3067059054820184e-05, "epoch": 0.41870093348435733, "percentage": 41.88, "elapsed_time": "4:42:00", "remaining_time": "6:31:26"}
+{"current_steps": 680, "total_steps": 1600, "loss": 0.6699, "learning_rate": 1.2873777539848284e-05, "epoch": 0.42495020114830295, "percentage": 42.5, "elapsed_time": "4:45:25", "remaining_time": "6:26:10"}
+{"current_steps": 690, "total_steps": 1600, "loss": 0.6644, "learning_rate": 1.2679318541923131e-05, "epoch": 0.4311994688122486, "percentage": 43.12, "elapsed_time": "4:48:52", "remaining_time": "6:20:59"}
+{"current_steps": 700, "total_steps": 1600, "loss": 0.68, "learning_rate": 1.248376173741215e-05, "epoch": 0.4374487364761942, "percentage": 43.75, "elapsed_time": "4:52:22", "remaining_time": "6:15:54"}
+{"current_steps": 710, "total_steps": 1600, "loss": 0.684, "learning_rate": 1.2287187252490914e-05, "epoch": 0.4436980041401398, "percentage": 44.38, "elapsed_time": "4:55:50", "remaining_time": "6:10:51"}
+{"current_steps": 720, "total_steps": 1600, "loss": 0.6515, "learning_rate": 1.2089675630312755e-05, "epoch": 0.44994727180408545, "percentage": 45.0, "elapsed_time": "4:59:19", "remaining_time": "6:05:50"}
+{"current_steps": 730, "total_steps": 1600, "loss": 0.6609, "learning_rate": 1.1891307798007536e-05, "epoch": 0.45619653946803107, "percentage": 45.62, "elapsed_time": "5:02:47", "remaining_time": "6:00:51"}
+{"current_steps": 740, "total_steps": 1600, "loss": 0.6801, "learning_rate": 1.1692165033523117e-05, "epoch": 0.4624458071319767, "percentage": 46.25, "elapsed_time": "5:06:15", "remaining_time": "5:55:55"}
+{"current_steps": 750, "total_steps": 1600, "loss": 0.6831, "learning_rate": 1.1492328932323022e-05, "epoch": 0.4686950747959224, "percentage": 46.88, "elapsed_time": "5:09:42", "remaining_time": "5:51:00"}
+{"current_steps": 760, "total_steps": 1600, "loss": 0.6725, "learning_rate": 1.1291881373954066e-05, "epoch": 0.474944342459868, "percentage": 47.5, "elapsed_time": "5:13:13", "remaining_time": "5:46:11"}
+{"current_steps": 770, "total_steps": 1600, "loss": 0.6394, "learning_rate": 1.109090448849755e-05, "epoch": 0.4811936101238136, "percentage": 48.12, "elapsed_time": "5:18:55", "remaining_time": "5:43:46"}
+{"current_steps": 780, "total_steps": 1600, "loss": 0.6682, "learning_rate": 1.088948062291783e-05, "epoch": 0.48744287778775924, "percentage": 48.75, "elapsed_time": "5:22:24", "remaining_time": "5:38:56"}
+{"current_steps": 790, "total_steps": 1600, "loss": 0.6353, "learning_rate": 1.0687692307321984e-05, "epoch": 0.49369214545170487, "percentage": 49.38, "elapsed_time": "5:25:50", "remaining_time": "5:34:04"}
+{"current_steps": 800, "total_steps": 1600, "loss": 0.6433, "learning_rate": 1.0485622221144485e-05, "epoch": 0.4999414131156505, "percentage": 50.0, "elapsed_time": "5:29:16", "remaining_time": "5:29:16"}
+{"current_steps": 810, "total_steps": 1600, "loss": 0.6719, "learning_rate": 1.0283353159270644e-05, "epoch": 0.5061906807795962, "percentage": 50.62, "elapsed_time": "5:32:42", "remaining_time": "5:24:29"}
+{"current_steps": 820, "total_steps": 1600, "loss": 0.6576, "learning_rate": 1.0080967998112787e-05, "epoch": 0.5124399484435418, "percentage": 51.25, "elapsed_time": "5:36:09", "remaining_time": "5:19:45"}
+{"current_steps": 830, "total_steps": 1600, "loss": 0.6547, "learning_rate": 9.878549661653013e-06, "epoch": 0.5186892161074874, "percentage": 51.88, "elapsed_time": "5:39:38", "remaining_time": "5:15:05"}
+{"current_steps": 840, "total_steps": 1600, "loss": 0.6361, "learning_rate": 9.676181087466444e-06, "epoch": 0.524938483771433, "percentage": 52.5, "elapsed_time": "5:43:07", "remaining_time": "5:10:26"}
+{"current_steps": 850, "total_steps": 1600, "loss": 0.6497, "learning_rate": 9.473945192738933e-06, "epoch": 0.5311877514353787, "percentage": 53.12, "elapsed_time": "5:46:34", "remaining_time": "5:05:48"}
+{"current_steps": 860, "total_steps": 1600, "loss": 0.6654, "learning_rate": 9.27192484029312e-06, "epoch": 0.5374370190993243, "percentage": 53.75, "elapsed_time": "5:50:01", "remaining_time": "5:01:10"}
+{"current_steps": 870, "total_steps": 1600, "loss": 0.6397, "learning_rate": 9.070202804636745e-06, "epoch": 0.5436862867632699, "percentage": 54.37, "elapsed_time": "5:53:27", "remaining_time": "4:56:34"}
+{"current_steps": 880, "total_steps": 1600, "loss": 0.6603, "learning_rate": 8.868861738047158e-06, "epoch": 0.5499355544272155, "percentage": 55.0, "elapsed_time": "5:56:52", "remaining_time": "4:51:59"}
+{"current_steps": 890, "total_steps": 1600, "loss": 0.6556, "learning_rate": 8.667984136705927e-06, "epoch": 0.5561848220911612, "percentage": 55.62, "elapsed_time": "6:00:20", "remaining_time": "4:47:28"}
+{"current_steps": 900, "total_steps": 1600, "loss": 0.6258, "learning_rate": 8.46765230689737e-06, "epoch": 0.5624340897551068, "percentage": 56.25, "elapsed_time": "6:03:48", "remaining_time": "4:42:58"}
+{"current_steps": 910, "total_steps": 1600, "loss": 0.6472, "learning_rate": 8.267948331284923e-06, "epoch": 0.5686833574190524, "percentage": 56.88, "elapsed_time": "6:07:20", "remaining_time": "4:38:31"}
+{"current_steps": 920, "total_steps": 1600, "loss": 0.6226, "learning_rate": 8.068954035279121e-06, "epoch": 0.5749326250829981, "percentage": 57.5, "elapsed_time": "6:10:51", "remaining_time": "4:34:06"}
+{"current_steps": 930, "total_steps": 1600, "loss": 0.617, "learning_rate": 7.870750953510983e-06, "epoch": 0.5811818927469438, "percentage": 58.13, "elapsed_time": "6:14:16", "remaining_time": "4:29:38"}
+{"current_steps": 940, "total_steps": 1600, "loss": 0.633, "learning_rate": 7.673420296424541e-06, "epoch": 0.5874311604108894, "percentage": 58.75, "elapsed_time": "6:17:44", "remaining_time": "4:25:13"}
+{"current_steps": 950, "total_steps": 1600, "loss": 0.6312, "learning_rate": 7.4770429170022e-06, "epoch": 0.593680428074835, "percentage": 59.38, "elapsed_time": "6:21:07", "remaining_time": "4:20:46"}
+{"current_steps": 960, "total_steps": 1600, "loss": 0.6252, "learning_rate": 7.2816992776365714e-06, "epoch": 0.5999296957387806, "percentage": 60.0, "elapsed_time": "6:24:30", "remaining_time": "4:16:20"}
+{"current_steps": 970, "total_steps": 1600, "loss": 0.634, "learning_rate": 7.08746941716232e-06, "epoch": 0.6061789634027263, "percentage": 60.62, "elapsed_time": "6:27:58", "remaining_time": "4:11:58"}
+{"current_steps": 980, "total_steps": 1600, "loss": 0.6216, "learning_rate": 6.894432918061579e-06, "epoch": 0.6124282310666719, "percentage": 61.25, "elapsed_time": "6:31:26", "remaining_time": "4:07:38"}
+{"current_steps": 990, "total_steps": 1600, "loss": 0.643, "learning_rate": 6.702668873856339e-06, "epoch": 0.6186774987306175, "percentage": 61.88, "elapsed_time": "6:34:53", "remaining_time": "4:03:18"}
+{"current_steps": 1000, "total_steps": 1600, "loss": 0.6409, "learning_rate": 6.5122558567011775e-06, "epoch": 0.6249267663945631, "percentage": 62.5, "elapsed_time": "6:38:22", "remaining_time": "3:59:01"}
+{"current_steps": 1010, "total_steps": 1600, "loss": 0.6418, "learning_rate": 6.323271885189636e-06, "epoch": 0.6311760340585088, "percentage": 63.12, "elapsed_time": "6:41:51", "remaining_time": "3:54:45"}
+{"current_steps": 1020, "total_steps": 1600, "loss": 0.635, "learning_rate": 6.135794392387353e-06, "epoch": 0.6374253017224544, "percentage": 63.75, "elapsed_time": "6:45:21", "remaining_time": "3:50:29"}
+{"current_steps": 1030, "total_steps": 1600, "loss": 0.6326, "learning_rate": 5.949900194105167e-06, "epoch": 0.6436745693864, "percentage": 64.38, "elapsed_time": "6:51:07", "remaining_time": "3:47:31"}
+{"current_steps": 1040, "total_steps": 1600, "loss": 0.6338, "learning_rate": 5.765665457425102e-06, "epoch": 0.6499238370503456, "percentage": 65.0, "elapsed_time": "6:54:36", "remaining_time": "3:43:15"}
+{"current_steps": 1050, "total_steps": 1600, "loss": 0.6262, "learning_rate": 5.5831656694921465e-06, "epoch": 0.6561731047142912, "percentage": 65.62, "elapsed_time": "6:58:04", "remaining_time": "3:38:59"}
+{"current_steps": 1060, "total_steps": 1600, "loss": 0.6421, "learning_rate": 5.40247560658467e-06, "epoch": 0.662422372378237, "percentage": 66.25, "elapsed_time": "7:01:29", "remaining_time": "3:34:43"}
+{"current_steps": 1070, "total_steps": 1600, "loss": 0.6166, "learning_rate": 5.223669303476041e-06, "epoch": 0.6686716400421826, "percentage": 66.88, "elapsed_time": "7:04:55", "remaining_time": "3:30:28"}
+{"current_steps": 1080, "total_steps": 1600, "loss": 0.6033, "learning_rate": 5.046820023100129e-06, "epoch": 0.6749209077061282, "percentage": 67.5, "elapsed_time": "7:08:22", "remaining_time": "3:26:15"}
+{"current_steps": 1090, "total_steps": 1600, "loss": 0.6292, "learning_rate": 4.872000226533001e-06, "epoch": 0.6811701753700738, "percentage": 68.12, "elapsed_time": "7:11:50", "remaining_time": "3:22:03"}
+{"current_steps": 1100, "total_steps": 1600, "loss": 0.6238, "learning_rate": 4.699281543303222e-06, "epoch": 0.6874194430340195, "percentage": 68.75, "elapsed_time": "7:15:15", "remaining_time": "3:17:50"}
+{"current_steps": 1110, "total_steps": 1600, "loss": 0.609, "learning_rate": 4.528734742042803e-06, "epoch": 0.6936687106979651, "percentage": 69.38, "elapsed_time": "7:18:40", "remaining_time": "3:13:39"}
+{"current_steps": 1120, "total_steps": 1600, "loss": 0.6116, "learning_rate": 4.360429701490935e-06, "epoch": 0.6999179783619107, "percentage": 70.0, "elapsed_time": "7:22:05", "remaining_time": "3:09:27"}
+{"current_steps": 1130, "total_steps": 1600, "loss": 0.6217, "learning_rate": 4.194435381862343e-06, "epoch": 0.7061672460258563, "percentage": 70.62, "elapsed_time": "7:25:30", "remaining_time": "3:05:18"}
+{"current_steps": 1140, "total_steps": 1600, "loss": 0.6247, "learning_rate": 4.03081979659195e-06, "epoch": 0.712416513689802, "percentage": 71.25, "elapsed_time": "7:29:00", "remaining_time": "3:01:10"}
+{"current_steps": 1150, "total_steps": 1600, "loss": 0.6092, "learning_rate": 3.869649984467504e-06, "epoch": 0.7186657813537476, "percentage": 71.88, "elapsed_time": "7:32:33", "remaining_time": "2:57:05"}
+{"current_steps": 1160, "total_steps": 1600, "loss": 0.6063, "learning_rate": 3.7109919821615546e-06, "epoch": 0.7249150490176932, "percentage": 72.5, "elapsed_time": "7:36:04", "remaining_time": "2:52:59"}
+{"current_steps": 1170, "total_steps": 1600, "loss": 0.6154, "learning_rate": 3.5549107971739905e-06, "epoch": 0.7311643166816388, "percentage": 73.12, "elapsed_time": "7:39:34", "remaining_time": "2:48:54"}
+{"current_steps": 1180, "total_steps": 1600, "loss": 0.6119, "learning_rate": 3.4014703811963024e-06, "epoch": 0.7374135843455845, "percentage": 73.75, "elapsed_time": "7:43:05", "remaining_time": "2:44:49"}
+{"current_steps": 1190, "total_steps": 1600, "loss": 0.6043, "learning_rate": 3.2507336039084315e-06, "epoch": 0.7436628520095301, "percentage": 74.38, "elapsed_time": "7:46:32", "remaining_time": "2:40:44"}
+{"current_steps": 1200, "total_steps": 1600, "loss": 0.6308, "learning_rate": 3.1027622272189572e-06, "epoch": 0.7499121196734758, "percentage": 75.0, "elapsed_time": "7:49:58", "remaining_time": "2:36:39"}
+{"current_steps": 1210, "total_steps": 1600, "loss": 0.5984, "learning_rate": 2.9576168799591663e-06, "epoch": 0.7561613873374214, "percentage": 75.62, "elapsed_time": "7:53:27", "remaining_time": "2:32:36"}
+{"current_steps": 1220, "total_steps": 1600, "loss": 0.6139, "learning_rate": 2.8153570330413925e-06, "epoch": 0.7624106550013671, "percentage": 76.25, "elapsed_time": "7:57:00", "remaining_time": "2:28:34"}
+{"current_steps": 1230, "total_steps": 1600, "loss": 0.5974, "learning_rate": 2.6760409750917925e-06, "epoch": 0.7686599226653127, "percentage": 76.88, "elapsed_time": "8:00:30", "remaining_time": "2:24:32"}
+{"current_steps": 1240, "total_steps": 1600, "loss": 0.6034, "learning_rate": 2.5397257885675396e-06, "epoch": 0.7749091903292583, "percentage": 77.5, "elapsed_time": "8:04:00", "remaining_time": "2:20:31"}
+{"current_steps": 1250, "total_steps": 1600, "loss": 0.6026, "learning_rate": 2.406467326368237e-06, "epoch": 0.7811584579932039, "percentage": 78.12, "elapsed_time": "8:07:31", "remaining_time": "2:16:30"}
+{"current_steps": 1260, "total_steps": 1600, "loss": 0.6216, "learning_rate": 2.2763201889510987e-06, "epoch": 0.7874077256571496, "percentage": 78.75, "elapsed_time": "8:11:03", "remaining_time": "2:12:30"}
+{"current_steps": 1270, "total_steps": 1600, "loss": 0.6198, "learning_rate": 2.149337701959325e-06, "epoch": 0.7936569933210952, "percentage": 79.38, "elapsed_time": "8:14:35", "remaining_time": "2:08:30"}
+{"current_steps": 1280, "total_steps": 1600, "loss": 0.5838, "learning_rate": 2.025571894372794e-06, "epoch": 0.7999062609850408, "percentage": 80.0, "elapsed_time": "8:18:06", "remaining_time": "2:04:31"}
+{"current_steps": 1290, "total_steps": 1600, "loss": 0.5999, "learning_rate": 1.9050734771900414e-06, "epoch": 0.8061555286489864, "percentage": 80.62, "elapsed_time": "8:24:22", "remaining_time": "2:01:12"}
+{"current_steps": 1300, "total_steps": 1600, "loss": 0.5956, "learning_rate": 1.7878918226502816e-06, "epoch": 0.812404796312932, "percentage": 81.25, "elapsed_time": "8:28:23", "remaining_time": "1:57:19"}
+{"current_steps": 1310, "total_steps": 1600, "loss": 0.6083, "learning_rate": 1.6740749440039262e-06, "epoch": 0.8186540639768777, "percentage": 81.88, "elapsed_time": "8:32:27", "remaining_time": "1:53:26"}
+{"current_steps": 1320, "total_steps": 1600, "loss": 0.5917, "learning_rate": 1.5636694758399563e-06, "epoch": 0.8249033316408233, "percentage": 82.5, "elapsed_time": "8:36:31", "remaining_time": "1:49:33"}
+{"current_steps": 1330, "total_steps": 1600, "loss": 0.5929, "learning_rate": 1.4567206549781699e-06, "epoch": 0.8311525993047689, "percentage": 83.12, "elapsed_time": "8:40:34", "remaining_time": "1:45:40"}
+{"current_steps": 1340, "total_steps": 1600, "loss": 0.5936, "learning_rate": 1.3532723019341376e-06, "epoch": 0.8374018669687147, "percentage": 83.75, "elapsed_time": "8:44:29", "remaining_time": "1:41:46"}
+{"current_steps": 1350, "total_steps": 1600, "loss": 0.5933, "learning_rate": 1.2533668029644751e-06, "epoch": 0.8436511346326603, "percentage": 84.38, "elapsed_time": "8:48:28", "remaining_time": "1:37:52"}
+{"current_steps": 1360, "total_steps": 1600, "loss": 0.5891, "learning_rate": 1.1570450926997657e-06, "epoch": 0.8499004022966059, "percentage": 85.0, "elapsed_time": "8:52:38", "remaining_time": "1:33:59"}
+{"current_steps": 1370, "total_steps": 1600, "loss": 0.5799, "learning_rate": 1.064346637372271e-06, "epoch": 0.8561496699605515, "percentage": 85.62, "elapsed_time": "8:56:35", "remaining_time": "1:30:05"}
+{"current_steps": 1380, "total_steps": 1600, "loss": 0.5994, "learning_rate": 9.753094186453028e-07, "epoch": 0.8623989376244972, "percentage": 86.25, "elapsed_time": "9:00:29", "remaining_time": "1:26:09"}
+{"current_steps": 1390, "total_steps": 1600, "loss": 0.6119, "learning_rate": 8.89969918050847e-07, "epoch": 0.8686482052884428, "percentage": 86.88, "elapsed_time": "9:04:21", "remaining_time": "1:22:14"}
+{"current_steps": 1400, "total_steps": 1600, "loss": 0.5958, "learning_rate": 8.083631020418792e-07, "epoch": 0.8748974729523884, "percentage": 87.5, "elapsed_time": "9:08:16", "remaining_time": "1:18:19"}
+{"current_steps": 1410, "total_steps": 1600, "loss": 0.6025, "learning_rate": 7.305224076654127e-07, "epoch": 0.881146740616334, "percentage": 88.12, "elapsed_time": "9:12:10", "remaining_time": "1:14:24"}
+{"current_steps": 1420, "total_steps": 1600, "loss": 0.5985, "learning_rate": 6.564797288622371e-07, "epoch": 0.8873960082802796, "percentage": 88.75, "elapsed_time": "9:16:06", "remaining_time": "1:10:29"}
+{"current_steps": 1430, "total_steps": 1600, "loss": 0.5992, "learning_rate": 5.86265403398899e-07, "epoch": 0.8936452759442253, "percentage": 89.38, "elapsed_time": "9:20:06", "remaining_time": "1:06:35"}
+{"current_steps": 1440, "total_steps": 1600, "loss": 0.5714, "learning_rate": 5.199082004372958e-07, "epoch": 0.8998945436081709, "percentage": 90.0, "elapsed_time": "9:24:08", "remaining_time": "1:02:40"}
+{"current_steps": 1450, "total_steps": 1600, "loss": 0.5967, "learning_rate": 4.5743530874699293e-07, "epoch": 0.9061438112721165, "percentage": 90.62, "elapsed_time": "9:28:07", "remaining_time": "0:58:46"}
+{"current_steps": 1460, "total_steps": 1600, "loss": 0.5883, "learning_rate": 3.988723255650728e-07, "epoch": 0.9123930789360621, "percentage": 91.25, "elapsed_time": "9:32:07", "remaining_time": "0:54:51"}
+{"current_steps": 1470, "total_steps": 1600, "loss": 0.6041, "learning_rate": 3.442432461080858e-07, "epoch": 0.9186423466000078, "percentage": 91.88, "elapsed_time": "9:36:08", "remaining_time": "0:50:57"}
+{"current_steps": 1480, "total_steps": 1600, "loss": 0.6076, "learning_rate": 2.935704537404083e-07, "epoch": 0.9248916142639534, "percentage": 92.5, "elapsed_time": "9:40:06", "remaining_time": "0:47:02"}
+{"current_steps": 1490, "total_steps": 1600, "loss": 0.593, "learning_rate": 2.468747108030289e-07, "epoch": 0.9311408819278991, "percentage": 93.12, "elapsed_time": "9:44:05", "remaining_time": "0:43:07"}
+{"current_steps": 1500, "total_steps": 1600, "loss": 0.5928, "learning_rate": 2.0417515010652032e-07, "epoch": 0.9373901495918447, "percentage": 93.75, "elapsed_time": "9:48:08", "remaining_time": "0:39:12"}
+{"current_steps": 1510, "total_steps": 1600, "loss": 0.6025, "learning_rate": 1.6548926709168634e-07, "epoch": 0.9436394172557904, "percentage": 94.38, "elapsed_time": "9:52:12", "remaining_time": "0:35:17"}
+{"current_steps": 1520, "total_steps": 1600, "loss": 0.5937, "learning_rate": 1.30832912661093e-07, "epoch": 0.949888684919736, "percentage": 95.0, "elapsed_time": "9:56:10", "remaining_time": "0:31:22"}
+{"current_steps": 1530, "total_steps": 1600, "loss": 0.5874, "learning_rate": 1.0022028668442374e-07, "epoch": 0.9561379525836816, "percentage": 95.62, "elapsed_time": "10:00:04", "remaining_time": "0:27:27"}
+{"current_steps": 1540, "total_steps": 1600, "loss": 0.6099, "learning_rate": 7.366393218031564e-08, "epoch": 0.9623872202476272, "percentage": 96.25, "elapsed_time": "10:06:06", "remaining_time": "0:23:36"}
+{"current_steps": 1550, "total_steps": 1600, "loss": 0.5902, "learning_rate": 5.1174730177064866e-08, "epoch": 0.9686364879115729, "percentage": 96.88, "elapsed_time": "10:09:35", "remaining_time": "0:19:39"}
+{"current_steps": 1560, "total_steps": 1600, "loss": 0.5852, "learning_rate": 3.2761895254306285e-08, "epoch": 0.9748857555755185, "percentage": 97.5, "elapsed_time": "10:13:04", "remaining_time": "0:15:43"}
+{"current_steps": 1570, "total_steps": 1600, "loss": 0.5962, "learning_rate": 1.8432971767488038e-08, "epoch": 0.9811350232394641, "percentage": 98.12, "elapsed_time": "10:16:34", "remaining_time": "0:11:46"}
+{"current_steps": 1580, "total_steps": 1600, "loss": 0.6002, "learning_rate": 8.193830756699773e-09, "epoch": 0.9873842909034097, "percentage": 98.75, "elapsed_time": "10:20:01", "remaining_time": "0:07:50"}
+{"current_steps": 1590, "total_steps": 1600, "loss": 0.5943, "learning_rate": 2.0486675411102165e-09, "epoch": 0.9936335585673554, "percentage": 99.38, "elapsed_time": "10:23:30", "remaining_time": "0:03:55"}
+{"current_steps": 1600, "total_steps": 1600, "loss": 0.5911, "learning_rate": 0.0, "epoch": 0.999882826231301, "percentage": 100.0, "elapsed_time": "10:26:59", "remaining_time": "0:00:00"}
+{"current_steps": 1600, "total_steps": 1600, "epoch": 0.999882826231301, "percentage": 100.0, "elapsed_time": "10:29:11", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1162 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.999882826231301,
+  "eval_steps": 500,
+  "global_step": 1600,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006249267663945631,
+      "grad_norm": 6.042294502258301,
+      "learning_rate": 4.166666666666667e-06,
+      "loss": 0.7433,
+      "step": 10
+    },
+    {
+      "epoch": 0.012498535327891263,
+      "grad_norm": 3.4981777667999268,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 0.6848,
+      "step": 20
+    },
+    {
+      "epoch": 0.018747802991836895,
+      "grad_norm": 7.156867980957031,
+      "learning_rate": 1.25e-05,
+      "loss": 0.6722,
+      "step": 30
+    },
+    {
+      "epoch": 0.024997070655782525,
+      "grad_norm": 3.301668167114258,
+      "learning_rate": 1.6666666666666667e-05,
+      "loss": 0.6924,
+      "step": 40
+    },
+    {
+      "epoch": 0.031246338319728156,
+      "grad_norm": 2.7308597564697266,
+      "learning_rate": 1.999991805061211e-05,
+      "loss": 0.6759,
+      "step": 50
+    },
+    {
+      "epoch": 0.03749560598367379,
+      "grad_norm": 5.730428695678711,
+      "learning_rate": 1.999704996306308e-05,
+      "loss": 0.7484,
+      "step": 60
+    },
+    {
+      "epoch": 0.04374487364761942,
+      "grad_norm": 2.7434427738189697,
+      "learning_rate": 1.999008574916082e-05,
+      "loss": 0.7298,
+      "step": 70
+    },
+    {
+      "epoch": 0.04999414131156505,
+      "grad_norm": 2.67563533782959,
+      "learning_rate": 1.997902826237712e-05,
+      "loss": 0.7381,
+      "step": 80
+    },
+    {
+      "epoch": 0.05624340897551068,
+      "grad_norm": 4.653203010559082,
+      "learning_rate": 1.9963882033334827e-05,
+      "loss": 0.716,
+      "step": 90
+    },
+    {
+      "epoch": 0.06249267663945631,
+      "grad_norm": 3.6553049087524414,
+      "learning_rate": 1.9944653267951507e-05,
+      "loss": 0.713,
+      "step": 100
+    },
+    {
+      "epoch": 0.06874194430340194,
+      "grad_norm": 3.856987953186035,
+      "learning_rate": 1.9921349844896655e-05,
+      "loss": 0.6886,
+      "step": 110
+    },
+    {
+      "epoch": 0.07499121196734758,
+      "grad_norm": 2.80169677734375,
+      "learning_rate": 1.9893981312363563e-05,
+      "loss": 0.7459,
+      "step": 120
+    },
+    {
+      "epoch": 0.0812404796312932,
+      "grad_norm": 9.439187049865723,
+      "learning_rate": 1.9862558884157067e-05,
+      "loss": 0.7131,
+      "step": 130
+    },
+    {
+      "epoch": 0.08748974729523884,
+      "grad_norm": 3.0188660621643066,
+      "learning_rate": 1.9827095435098926e-05,
+      "loss": 0.7419,
+      "step": 140
+    },
+    {
+      "epoch": 0.09373901495918448,
+      "grad_norm": 6.821515083312988,
+      "learning_rate": 1.9787605495752528e-05,
+      "loss": 0.7093,
+      "step": 150
+    },
+    {
+      "epoch": 0.0999882826231301,
+      "grad_norm": 3.1190407276153564,
+      "learning_rate": 1.9744105246469264e-05,
+      "loss": 0.7162,
+      "step": 160
+    },
+    {
+      "epoch": 0.10623755028707574,
+      "grad_norm": 3.4266233444213867,
+      "learning_rate": 1.9696612510758878e-05,
+      "loss": 0.7501,
+      "step": 170
+    },
+    {
+      "epoch": 0.11248681795102136,
+      "grad_norm": 6.012339115142822,
+      "learning_rate": 1.964514674798659e-05,
+      "loss": 0.7228,
+      "step": 180
+    },
+    {
+      "epoch": 0.118736085614967,
+      "grad_norm": 2.518491268157959,
+      "learning_rate": 1.9589729045399935e-05,
+      "loss": 0.7283,
+      "step": 190
+    },
+    {
+      "epoch": 0.12498535327891262,
+      "grad_norm": 2.739582061767578,
+      "learning_rate": 1.953038210948861e-05,
+      "loss": 0.7464,
+      "step": 200
+    },
+    {
+      "epoch": 0.13123462094285826,
+      "grad_norm": 2.70062518119812,
+      "learning_rate": 1.9467130256680867e-05,
+      "loss": 0.721,
+      "step": 210
+    },
+    {
+      "epoch": 0.13748388860680388,
+      "grad_norm": 2.4166440963745117,
+      "learning_rate": 1.9399999403380266e-05,
+      "loss": 0.711,
+      "step": 220
+    },
+    {
+      "epoch": 0.14373315627074953,
+      "grad_norm": 3.875697374343872,
+      "learning_rate": 1.932901705534683e-05,
+      "loss": 0.7296,
+      "step": 230
+    },
+    {
+      "epoch": 0.14998242393469516,
+      "grad_norm": 3.1276426315307617,
+      "learning_rate": 1.9254212296427043e-05,
+      "loss": 0.7079,
+      "step": 240
+    },
+    {
+      "epoch": 0.15623169159864078,
+      "grad_norm": 3.067948341369629,
+      "learning_rate": 1.9175615776637212e-05,
+      "loss": 0.7231,
+      "step": 250
+    },
+    {
+      "epoch": 0.1624809592625864,
+      "grad_norm": 2.604984760284424,
+      "learning_rate": 1.9093259699605125e-05,
+      "loss": 0.7202,
+      "step": 260
+    },
+    {
+      "epoch": 0.16873022692653206,
+      "grad_norm": 2.3994998931884766,
+      "learning_rate": 1.900717780937514e-05,
+      "loss": 0.7129,
+      "step": 270
+    },
+    {
+      "epoch": 0.17497949459047768,
+      "grad_norm": 2.617325782775879,
+      "learning_rate": 1.8917405376582144e-05,
+      "loss": 0.7142,
+      "step": 280
+    },
+    {
+      "epoch": 0.1812287622544233,
+      "grad_norm": 2.6472878456115723,
+      "learning_rate": 1.8823979183999965e-05,
+      "loss": 0.7168,
+      "step": 290
+    },
+    {
+      "epoch": 0.18747802991836895,
+      "grad_norm": 2.1472179889678955,
+      "learning_rate": 1.8726937511470247e-05,
+      "loss": 0.7209,
+      "step": 300
+    },
+    {
+      "epoch": 0.19372729758231458,
+      "grad_norm": 2.5548176765441895,
+      "learning_rate": 1.8626320120217922e-05,
+      "loss": 0.7278,
+      "step": 310
+    },
+    {
+      "epoch": 0.1999765652462602,
+      "grad_norm": 2.2397587299346924,
+      "learning_rate": 1.8522168236559693e-05,
+      "loss": 0.7229,
+      "step": 320
+    },
+    {
+      "epoch": 0.20622583291020583,
+      "grad_norm": 2.72623872756958,
+      "learning_rate": 1.8414524535012244e-05,
+      "loss": 0.7003,
+      "step": 330
+    },
+    {
+      "epoch": 0.21247510057415148,
+      "grad_norm": 2.6225929260253906,
+      "learning_rate": 1.8303433120807043e-05,
+      "loss": 0.729,
+      "step": 340
+    },
+    {
+      "epoch": 0.2187243682380971,
+      "grad_norm": 4.628861427307129,
+      "learning_rate": 1.8188939511818965e-05,
+      "loss": 0.7437,
+      "step": 350
+    },
+    {
+      "epoch": 0.22497363590204272,
+      "grad_norm": 2.2117223739624023,
+      "learning_rate": 1.8071090619916095e-05,
+      "loss": 0.7101,
+      "step": 360
+    },
+    {
+      "epoch": 0.23122290356598835,
+      "grad_norm": 2.2710976600646973,
+      "learning_rate": 1.7949934731738348e-05,
+      "loss": 0.7297,
+      "step": 370
+    },
+    {
+      "epoch": 0.237472171229934,
+      "grad_norm": 2.2278854846954346,
+      "learning_rate": 1.7825521488912833e-05,
+      "loss": 0.7275,
+      "step": 380
+    },
+    {
+      "epoch": 0.24372143889387962,
+      "grad_norm": 2.332300901412964,
+      "learning_rate": 1.7697901867713997e-05,
+      "loss": 0.7103,
+      "step": 390
+    },
+    {
+      "epoch": 0.24997070655782525,
+      "grad_norm": 1.9451990127563477,
+      "learning_rate": 1.7567128158176955e-05,
+      "loss": 0.6981,
+      "step": 400
+    },
+    {
+      "epoch": 0.2562199742217709,
+      "grad_norm": 2.7532973289489746,
+      "learning_rate": 1.7433253942672497e-05,
+      "loss": 0.7015,
+      "step": 410
+    },
+    {
+      "epoch": 0.2624692418857165,
+      "grad_norm": 2.6847236156463623,
+      "learning_rate": 1.7296334073952606e-05,
+      "loss": 0.7242,
+      "step": 420
+    },
+    {
+      "epoch": 0.26871850954966214,
+      "grad_norm": 2.6689813137054443,
+      "learning_rate": 1.7156424652675433e-05,
+      "loss": 0.7115,
+      "step": 430
+    },
+    {
+      "epoch": 0.27496777721360777,
+      "grad_norm": 2.2913591861724854,
+      "learning_rate": 1.7013583004418994e-05,
+      "loss": 0.6912,
+      "step": 440
+    },
+    {
+      "epoch": 0.2812170448775534,
+      "grad_norm": 2.5969536304473877,
+      "learning_rate": 1.6867867656192946e-05,
+      "loss": 0.7074,
+      "step": 450
+    },
+    {
+      "epoch": 0.28746631254149907,
+      "grad_norm": 2.246922731399536,
+      "learning_rate": 1.6719338312458123e-05,
+      "loss": 0.7048,
+      "step": 460
+    },
+    {
+      "epoch": 0.2937155802054447,
+      "grad_norm": 2.251768112182617,
+      "learning_rate": 1.656805583066361e-05,
+      "loss": 0.7085,
+      "step": 470
+    },
+    {
+      "epoch": 0.2999648478693903,
+      "grad_norm": 2.249643325805664,
+      "learning_rate": 1.6414082196311402e-05,
+      "loss": 0.6897,
+      "step": 480
+    },
+    {
+      "epoch": 0.30621411553333594,
+      "grad_norm": 1.974482536315918,
+      "learning_rate": 1.6257480497558873e-05,
+      "loss": 0.6941,
+      "step": 490
+    },
+    {
+      "epoch": 0.31246338319728156,
+      "grad_norm": 2.1665918827056885,
+      "learning_rate": 1.6098314899369446e-05,
+      "loss": 0.7061,
+      "step": 500
+    },
+    {
+      "epoch": 0.3187126508612272,
+      "grad_norm": 2.391334295272827,
+      "learning_rate": 1.5936650617222063e-05,
+      "loss": 0.6958,
+      "step": 510
+    },
+    {
+      "epoch": 0.3249619185251728,
+      "grad_norm": 2.047011375427246,
+      "learning_rate": 1.5772553890390196e-05,
+      "loss": 0.7177,
+      "step": 520
+    },
+    {
+      "epoch": 0.3312111861891185,
+      "grad_norm": 1.8378033638000488,
+      "learning_rate": 1.560609195480142e-05,
+      "loss": 0.6803,
+      "step": 530
+    },
+    {
+      "epoch": 0.3374604538530641,
+      "grad_norm": 2.126997232437134,
+      "learning_rate": 1.5437333015488586e-05,
+      "loss": 0.6694,
+      "step": 540
+    },
+    {
+      "epoch": 0.34370972151700974,
+      "grad_norm": 2.4227328300476074,
+      "learning_rate": 1.526634621864395e-05,
+      "loss": 0.6773,
+      "step": 550
+    },
+    {
+      "epoch": 0.34995898918095536,
+      "grad_norm": 2.368255615234375,
+      "learning_rate": 1.5093201623287631e-05,
+      "loss": 0.7048,
+      "step": 560
+    },
+    {
+      "epoch": 0.356208256844901,
+      "grad_norm": 1.9544981718063354,
+      "learning_rate": 1.4917970172562122e-05,
+      "loss": 0.686,
+      "step": 570
+    },
+    {
+      "epoch": 0.3624575245088466,
+      "grad_norm": 2.019627809524536,
+      "learning_rate": 1.4740723664664483e-05,
+      "loss": 0.6911,
+      "step": 580
+    },
+    {
+      "epoch": 0.36870679217279223,
+      "grad_norm": 1.8915493488311768,
+      "learning_rate": 1.4561534723428205e-05,
+      "loss": 0.6828,
+      "step": 590
+    },
+    {
+      "epoch": 0.3749560598367379,
+      "grad_norm": 2.211825370788574,
+      "learning_rate": 1.4380476768566825e-05,
+      "loss": 0.6636,
+      "step": 600
+    },
+    {
+      "epoch": 0.38120532750068353,
+      "grad_norm": 1.9755256175994873,
+      "learning_rate": 1.4197623985591373e-05,
+      "loss": 0.6902,
+      "step": 610
+    },
+    {
+      "epoch": 0.38745459516462916,
+      "grad_norm": 1.9239295721054077,
+      "learning_rate": 1.4013051295414108e-05,
+      "loss": 0.6795,
+      "step": 620
+    },
+    {
+      "epoch": 0.3937038628285748,
+      "grad_norm": 2.1901464462280273,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.7005,
+      "step": 630
+    },
+    {
+      "epoch": 0.3999531304925204,
+      "grad_norm": 1.9579427242279053,
+      "learning_rate": 1.3639049369634878e-05,
+      "loss": 0.6789,
+      "step": 640
+    },
+    {
+      "epoch": 0.406202398156466,
+      "grad_norm": 1.819069266319275,
+      "learning_rate": 1.344977337515404e-05,
+      "loss": 0.6808,
+      "step": 650
+    },
+    {
+      "epoch": 0.41245166582041165,
+      "grad_norm": 2.11354923248291,
+      "learning_rate": 1.3259083892925633e-05,
+      "loss": 0.6798,
+      "step": 660
+    },
+    {
+      "epoch": 0.41870093348435733,
+      "grad_norm": 2.0537407398223877,
+      "learning_rate": 1.3067059054820184e-05,
+      "loss": 0.6587,
+      "step": 670
+    },
+    {
+      "epoch": 0.42495020114830295,
+      "grad_norm": 2.4250621795654297,
+      "learning_rate": 1.2873777539848284e-05,
+      "loss": 0.6699,
+      "step": 680
+    },
+    {
+      "epoch": 0.4311994688122486,
+      "grad_norm": 2.0022125244140625,
+      "learning_rate": 1.2679318541923131e-05,
+      "loss": 0.6644,
+      "step": 690
+    },
+    {
+      "epoch": 0.4374487364761942,
+      "grad_norm": 1.9328835010528564,
+      "learning_rate": 1.248376173741215e-05,
+      "loss": 0.68,
+      "step": 700
+    },
+    {
+      "epoch": 0.4436980041401398,
+      "grad_norm": 2.0376391410827637,
+      "learning_rate": 1.2287187252490914e-05,
+      "loss": 0.684,
+      "step": 710
+    },
+    {
+      "epoch": 0.44994727180408545,
+      "grad_norm": 1.9673105478286743,
+      "learning_rate": 1.2089675630312755e-05,
+      "loss": 0.6515,
+      "step": 720
+    },
+    {
+      "epoch": 0.45619653946803107,
+      "grad_norm": 1.7611652612686157,
+      "learning_rate": 1.1891307798007536e-05,
+      "loss": 0.6609,
+      "step": 730
+    },
+    {
+      "epoch": 0.4624458071319767,
+      "grad_norm": 1.9665021896362305,
+      "learning_rate": 1.1692165033523117e-05,
+      "loss": 0.6801,
+      "step": 740
+    },
+    {
+      "epoch": 0.4686950747959224,
+      "grad_norm": 2.349421977996826,
+      "learning_rate": 1.1492328932323022e-05,
+      "loss": 0.6831,
+      "step": 750
+    },
+    {
+      "epoch": 0.474944342459868,
+      "grad_norm": 2.5945515632629395,
+      "learning_rate": 1.1291881373954066e-05,
+      "loss": 0.6725,
+      "step": 760
+    },
+    {
+      "epoch": 0.4811936101238136,
+      "grad_norm": 1.7327567338943481,
+      "learning_rate": 1.109090448849755e-05,
+      "loss": 0.6394,
+      "step": 770
+    },
+    {
+      "epoch": 0.48744287778775924,
+      "grad_norm": 1.980264663696289,
+      "learning_rate": 1.088948062291783e-05,
+      "loss": 0.6682,
+      "step": 780
+    },
+    {
+      "epoch": 0.49369214545170487,
+      "grad_norm": 2.313495635986328,
+      "learning_rate": 1.0687692307321984e-05,
+      "loss": 0.6353,
+      "step": 790
+    },
+    {
+      "epoch": 0.4999414131156505,
+      "grad_norm": 2.176020860671997,
+      "learning_rate": 1.0485622221144485e-05,
+      "loss": 0.6433,
+      "step": 800
+    },
+    {
+      "epoch": 0.5061906807795962,
+      "grad_norm": 2.5199544429779053,
+      "learning_rate": 1.0283353159270644e-05,
+      "loss": 0.6719,
+      "step": 810
+    },
+    {
+      "epoch": 0.5124399484435418,
+      "grad_norm": 2.6333529949188232,
+      "learning_rate": 1.0080967998112787e-05,
+      "loss": 0.6576,
+      "step": 820
+    },
+    {
+      "epoch": 0.5186892161074874,
+      "grad_norm": 2.367847204208374,
+      "learning_rate": 9.878549661653013e-06,
+      "loss": 0.6547,
+      "step": 830
+    },
+    {
+      "epoch": 0.524938483771433,
+      "grad_norm": 1.736178994178772,
+      "learning_rate": 9.676181087466444e-06,
+      "loss": 0.6361,
+      "step": 840
+    },
+    {
+      "epoch": 0.5311877514353787,
+      "grad_norm": 1.8639039993286133,
+      "learning_rate": 9.473945192738933e-06,
+      "loss": 0.6497,
+      "step": 850
+    },
+    {
+      "epoch": 0.5374370190993243,
+      "grad_norm": 1.7635918855667114,
+      "learning_rate": 9.27192484029312e-06,
+      "loss": 0.6654,
+      "step": 860
+    },
+    {
+      "epoch": 0.5436862867632699,
+      "grad_norm": 2.0125083923339844,
+      "learning_rate": 9.070202804636745e-06,
+      "loss": 0.6397,
+      "step": 870
+    },
+    {
+      "epoch": 0.5499355544272155,
+      "grad_norm": 2.078883171081543,
+      "learning_rate": 8.868861738047158e-06,
+      "loss": 0.6603,
+      "step": 880
+    },
+    {
+      "epoch": 0.5561848220911612,
+      "grad_norm": 1.781632423400879,
+      "learning_rate": 8.667984136705927e-06,
+      "loss": 0.6556,
+      "step": 890
+    },
+    {
+      "epoch": 0.5624340897551068,
+      "grad_norm": 2.0591318607330322,
+      "learning_rate": 8.46765230689737e-06,
+      "loss": 0.6258,
+      "step": 900
+    },
+    {
+      "epoch": 0.5686833574190524,
+      "grad_norm": 1.6111246347427368,
+      "learning_rate": 8.267948331284923e-06,
+      "loss": 0.6472,
+      "step": 910
+    },
+    {
+      "epoch": 0.5749326250829981,
+      "grad_norm": 2.417381763458252,
+      "learning_rate": 8.068954035279121e-06,
+      "loss": 0.6226,
+      "step": 920
+    },
+    {
+      "epoch": 0.5811818927469438,
+      "grad_norm": 2.185147762298584,
+      "learning_rate": 7.870750953510983e-06,
+      "loss": 0.617,
+      "step": 930
+    },
+    {
+      "epoch": 0.5874311604108894,
+      "grad_norm": 2.3496596813201904,
+      "learning_rate": 7.673420296424541e-06,
+      "loss": 0.633,
+      "step": 940
+    },
+    {
+      "epoch": 0.593680428074835,
+      "grad_norm": 2.4552910327911377,
+      "learning_rate": 7.4770429170022e-06,
+      "loss": 0.6312,
+      "step": 950
+    },
+    {
+      "epoch": 0.5999296957387806,
+      "grad_norm": 2.7454309463500977,
+      "learning_rate": 7.2816992776365714e-06,
+      "loss": 0.6252,
+      "step": 960
+    },
+    {
+      "epoch": 0.6061789634027263,
+      "grad_norm": 2.967708110809326,
+      "learning_rate": 7.08746941716232e-06,
+      "loss": 0.634,
+      "step": 970
+    },
+    {
+      "epoch": 0.6124282310666719,
+      "grad_norm": 2.755345582962036,
+      "learning_rate": 6.894432918061579e-06,
+      "loss": 0.6216,
+      "step": 980
+    },
+    {
+      "epoch": 0.6186774987306175,
+      "grad_norm": 1.987317681312561,
+      "learning_rate": 6.702668873856339e-06,
+      "loss": 0.643,
+      "step": 990
+    },
+    {
+      "epoch": 0.6249267663945631,
+      "grad_norm": 2.4610655307769775,
+      "learning_rate": 6.5122558567011775e-06,
+      "loss": 0.6409,
+      "step": 1000
+    },
+    {
+      "epoch": 0.6311760340585088,
+      "grad_norm": 1.9931960105895996,
+      "learning_rate": 6.323271885189636e-06,
+      "loss": 0.6418,
+      "step": 1010
+    },
+    {
+      "epoch": 0.6374253017224544,
+      "grad_norm": 3.0215256214141846,
+      "learning_rate": 6.135794392387353e-06,
+      "loss": 0.635,
+      "step": 1020
+    },
+    {
+      "epoch": 0.6436745693864,
+      "grad_norm": 1.752156376838684,
+      "learning_rate": 5.949900194105167e-06,
+      "loss": 0.6326,
+      "step": 1030
+    },
+    {
+      "epoch": 0.6499238370503456,
+      "grad_norm": 1.8890056610107422,
+      "learning_rate": 5.765665457425102e-06,
+      "loss": 0.6338,
+      "step": 1040
+    },
+    {
+      "epoch": 0.6561731047142912,
+      "grad_norm": 2.2345621585845947,
+      "learning_rate": 5.5831656694921465e-06,
+      "loss": 0.6262,
+      "step": 1050
+    },
+    {
+      "epoch": 0.662422372378237,
+      "grad_norm": 1.983519196510315,
+      "learning_rate": 5.40247560658467e-06,
+      "loss": 0.6421,
+      "step": 1060
+    },
+    {
+      "epoch": 0.6686716400421826,
+      "grad_norm": 2.091252326965332,
+      "learning_rate": 5.223669303476041e-06,
+      "loss": 0.6166,
+      "step": 1070
+    },
+    {
+      "epoch": 0.6749209077061282,
+      "grad_norm": 1.9888851642608643,
+      "learning_rate": 5.046820023100129e-06,
+      "loss": 0.6033,
+      "step": 1080
+    },
+    {
+      "epoch": 0.6811701753700738,
+      "grad_norm": 3.788809061050415,
+      "learning_rate": 4.872000226533001e-06,
+      "loss": 0.6292,
+      "step": 1090
+    },
+    {
+      "epoch": 0.6874194430340195,
+      "grad_norm": 2.0238468647003174,
+      "learning_rate": 4.699281543303222e-06,
+      "loss": 0.6238,
+      "step": 1100
+    },
+    {
+      "epoch": 0.6936687106979651,
+      "grad_norm": 1.7076054811477661,
+      "learning_rate": 4.528734742042803e-06,
+      "loss": 0.609,
+      "step": 1110
+    },
+    {
+      "epoch": 0.6999179783619107,
+      "grad_norm": 2.1124353408813477,
+      "learning_rate": 4.360429701490935e-06,
+      "loss": 0.6116,
+      "step": 1120
+    },
+    {
+      "epoch": 0.7061672460258563,
+      "grad_norm": 1.8266746997833252,
+      "learning_rate": 4.194435381862343e-06,
+      "loss": 0.6217,
+      "step": 1130
+    },
+    {
+      "epoch": 0.712416513689802,
+      "grad_norm": 1.7669917345046997,
+      "learning_rate": 4.03081979659195e-06,
+      "loss": 0.6247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.7186657813537476,
+      "grad_norm": 2.847994565963745,
+      "learning_rate": 3.869649984467504e-06,
+      "loss": 0.6092,
+      "step": 1150
+    },
+    {
+      "epoch": 0.7249150490176932,
+      "grad_norm": 5.524293899536133,
+      "learning_rate": 3.7109919821615546e-06,
+      "loss": 0.6063,
+      "step": 1160
+    },
+    {
+      "epoch": 0.7311643166816388,
+      "grad_norm": 2.3931970596313477,
+      "learning_rate": 3.5549107971739905e-06,
+      "loss": 0.6154,
+      "step": 1170
+    },
+    {
+      "epoch": 0.7374135843455845,
+      "grad_norm": 1.9852912425994873,
+      "learning_rate": 3.4014703811963024e-06,
+      "loss": 0.6119,
+      "step": 1180
+    },
+    {
+      "epoch": 0.7436628520095301,
+      "grad_norm": 1.8052198886871338,
+      "learning_rate": 3.2507336039084315e-06,
+      "loss": 0.6043,
+      "step": 1190
+    },
+    {
+      "epoch": 0.7499121196734758,
+      "grad_norm": 1.8438955545425415,
+      "learning_rate": 3.1027622272189572e-06,
+      "loss": 0.6308,
+      "step": 1200
+    },
+    {
+      "epoch": 0.7561613873374214,
+      "grad_norm": 2.11885929107666,
+      "learning_rate": 2.9576168799591663e-06,
+      "loss": 0.5984,
+      "step": 1210
+    },
+    {
+      "epoch": 0.7624106550013671,
+      "grad_norm": 2.6443002223968506,
+      "learning_rate": 2.8153570330413925e-06,
+      "loss": 0.6139,
+      "step": 1220
+    },
+    {
+      "epoch": 0.7686599226653127,
+      "grad_norm": 2.413456678390503,
+      "learning_rate": 2.6760409750917925e-06,
+      "loss": 0.5974,
+      "step": 1230
+    },
+    {
+      "epoch": 0.7749091903292583,
+      "grad_norm": 2.166473627090454,
+      "learning_rate": 2.5397257885675396e-06,
+      "loss": 0.6034,
+      "step": 1240
+    },
+    {
+      "epoch": 0.7811584579932039,
+      "grad_norm": 1.9241559505462646,
+      "learning_rate": 2.406467326368237e-06,
+      "loss": 0.6026,
+      "step": 1250
+    },
+    {
+      "epoch": 0.7874077256571496,
+      "grad_norm": 2.043766736984253,
+      "learning_rate": 2.2763201889510987e-06,
+      "loss": 0.6216,
+      "step": 1260
+    },
+    {
+      "epoch": 0.7936569933210952,
+      "grad_norm": 1.6110656261444092,
+      "learning_rate": 2.149337701959325e-06,
+      "loss": 0.6198,
+      "step": 1270
+    },
+    {
+      "epoch": 0.7999062609850408,
+      "grad_norm": 1.7661818265914917,
+      "learning_rate": 2.025571894372794e-06,
+      "loss": 0.5838,
+      "step": 1280
+    },
+    {
+      "epoch": 0.8061555286489864,
+      "grad_norm": 1.8362523317337036,
+      "learning_rate": 1.9050734771900414e-06,
+      "loss": 0.5999,
+      "step": 1290
+    },
+    {
+      "epoch": 0.812404796312932,
+      "grad_norm": 1.9224945306777954,
+      "learning_rate": 1.7878918226502816e-06,
+      "loss": 0.5956,
+      "step": 1300
+    },
+    {
+      "epoch": 0.8186540639768777,
+      "grad_norm": 2.024622678756714,
+      "learning_rate": 1.6740749440039262e-06,
+      "loss": 0.6083,
+      "step": 1310
+    },
+    {
+      "epoch": 0.8249033316408233,
+      "grad_norm": 2.0744571685791016,
+      "learning_rate": 1.5636694758399563e-06,
+      "loss": 0.5917,
+      "step": 1320
+    },
+    {
+      "epoch": 0.8311525993047689,
+      "grad_norm": 2.3073995113372803,
+      "learning_rate": 1.4567206549781699e-06,
+      "loss": 0.5929,
+      "step": 1330
+    },
+    {
+      "epoch": 0.8374018669687147,
+      "grad_norm": 1.8136156797409058,
+      "learning_rate": 1.3532723019341376e-06,
+      "loss": 0.5936,
+      "step": 1340
+    },
+    {
+      "epoch": 0.8436511346326603,
+      "grad_norm": 1.8207391500473022,
+      "learning_rate": 1.2533668029644751e-06,
+      "loss": 0.5933,
+      "step": 1350
+    },
+    {
+      "epoch": 0.8499004022966059,
+      "grad_norm": 2.001443386077881,
+      "learning_rate": 1.1570450926997657e-06,
+      "loss": 0.5891,
+      "step": 1360
+    },
+    {
+      "epoch": 0.8561496699605515,
+      "grad_norm": 1.8668729066848755,
+      "learning_rate": 1.064346637372271e-06,
+      "loss": 0.5799,
+      "step": 1370
+    },
+    {
+      "epoch": 0.8623989376244972,
+      "grad_norm": 2.3950822353363037,
+      "learning_rate": 9.753094186453028e-07,
+      "loss": 0.5994,
+      "step": 1380
+    },
+    {
+      "epoch": 0.8686482052884428,
+      "grad_norm": 1.9551249742507935,
+      "learning_rate": 8.89969918050847e-07,
+      "loss": 0.6119,
+      "step": 1390
+    },
+    {
+      "epoch": 0.8748974729523884,
+      "grad_norm": 1.774511456489563,
+      "learning_rate": 8.083631020418792e-07,
+      "loss": 0.5958,
+      "step": 1400
+    },
+    {
+      "epoch": 0.881146740616334,
+      "grad_norm": 1.6152182817459106,
+      "learning_rate": 7.305224076654127e-07,
+      "loss": 0.6025,
+      "step": 1410
+    },
+    {
+      "epoch": 0.8873960082802796,
+      "grad_norm": 3.579341173171997,
+      "learning_rate": 6.564797288622371e-07,
+      "loss": 0.5985,
+      "step": 1420
+    },
+    {
+      "epoch": 0.8936452759442253,
+      "grad_norm": 1.9974656105041504,
+      "learning_rate": 5.86265403398899e-07,
+      "loss": 0.5992,
+      "step": 1430
+    },
+    {
+      "epoch": 0.8998945436081709,
+      "grad_norm": 1.8749598264694214,
+      "learning_rate": 5.199082004372958e-07,
+      "loss": 0.5714,
+      "step": 1440
+    },
+    {
+      "epoch": 0.9061438112721165,
+      "grad_norm": 2.20654296875,
+      "learning_rate": 4.5743530874699293e-07,
+      "loss": 0.5967,
+      "step": 1450
+    },
+    {
+      "epoch": 0.9123930789360621,
+      "grad_norm": 1.7783575057983398,
+      "learning_rate": 3.988723255650728e-07,
+      "loss": 0.5883,
+      "step": 1460
+    },
+    {
+      "epoch": 0.9186423466000078,
+      "grad_norm": 1.8559459447860718,
+      "learning_rate": 3.442432461080858e-07,
+      "loss": 0.6041,
+      "step": 1470
+    },
+    {
+      "epoch": 0.9248916142639534,
+      "grad_norm": 1.6267383098602295,
+      "learning_rate": 2.935704537404083e-07,
+      "loss": 0.6076,
+      "step": 1480
+    },
+    {
+      "epoch": 0.9311408819278991,
+      "grad_norm": 1.5899640321731567,
+      "learning_rate": 2.468747108030289e-07,
+      "loss": 0.593,
+      "step": 1490
+    },
+    {
+      "epoch": 0.9373901495918447,
+      "grad_norm": 1.630462884902954,
+      "learning_rate": 2.0417515010652032e-07,
+      "loss": 0.5928,
+      "step": 1500
+    },
+    {
+      "epoch": 0.9436394172557904,
+      "grad_norm": 1.6635667085647583,
+      "learning_rate": 1.6548926709168634e-07,
+      "loss": 0.6025,
+      "step": 1510
+    },
+    {
+      "epoch": 0.949888684919736,
+      "grad_norm": 1.7267752885818481,
+      "learning_rate": 1.30832912661093e-07,
+      "loss": 0.5937,
+      "step": 1520
+    },
+    {
+      "epoch": 0.9561379525836816,
+      "grad_norm": 1.8789523839950562,
+      "learning_rate": 1.0022028668442374e-07,
+      "loss": 0.5874,
+      "step": 1530
+    },
+    {
+      "epoch": 0.9623872202476272,
+      "grad_norm": 1.6144094467163086,
+      "learning_rate": 7.366393218031564e-08,
+      "loss": 0.6099,
+      "step": 1540
+    },
+    {
+      "epoch": 0.9686364879115729,
+      "grad_norm": 1.5856353044509888,
+      "learning_rate": 5.1174730177064866e-08,
+      "loss": 0.5902,
+      "step": 1550
+    },
+    {
+      "epoch": 0.9748857555755185,
+      "grad_norm": 1.5565356016159058,
+      "learning_rate": 3.2761895254306285e-08,
+      "loss": 0.5852,
+      "step": 1560
+    },
+    {
+      "epoch": 0.9811350232394641,
+      "grad_norm": 1.7339156866073608,
+      "learning_rate": 1.8432971767488038e-08,
+      "loss": 0.5962,
+      "step": 1570
+    },
+    {
+      "epoch": 0.9873842909034097,
+      "grad_norm": 1.5991542339324951,
+      "learning_rate": 8.193830756699773e-09,
+      "loss": 0.6002,
+      "step": 1580
+    },
+    {
+      "epoch": 0.9936335585673554,
+      "grad_norm": 1.7472448348999023,
+      "learning_rate": 2.0486675411102165e-09,
+      "loss": 0.5943,
+      "step": 1590
+    },
+    {
+      "epoch": 0.999882826231301,
+      "grad_norm": 1.9169718027114868,
+      "learning_rate": 0.0,
+      "loss": 0.5911,
+      "step": 1600
+    },
+    {
+      "epoch": 0.999882826231301,
+      "step": 1600,
+      "total_flos": 1.7902479199415828e+19,
+      "train_loss": 0.6576289132237434,
+      "train_runtime": 37752.4225,
+      "train_samples_per_second": 2.713,
+      "train_steps_per_second": 0.042
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 256,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.7902479199415828e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db132c23ed25a4d38913d642e9191ae87bca53f2574a459187c6eda4b58f5e8c
+size 6648