Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,64 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-7B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: t1_5k_v1_tag5_hermes
+  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. -->
+
+# t1_5k_v1_tag5_hermes
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-7B-Instruct) on the t1_5k_v1_tag5_hermes dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.3219
+
+## 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-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.3312        | 0.6897 | 100  | 0.3295          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.3218812644481659,
+    "eval_runtime": 0.9342,
+    "eval_samples_per_second": 2.141,
+    "eval_steps_per_second": 1.07,
+    "total_flos": 27838218240000.0,
+    "train_loss": 0.41041072442613796,
+    "train_runtime": 554.2459,
+    "train_samples_per_second": 2.089,
+    "train_steps_per_second": 0.262
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.3218812644481659,
+    "eval_runtime": 0.9342,
+    "eval_samples_per_second": 2.141,
+    "eval_steps_per_second": 1.07
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c041c0a99a6cb47fe9a3e8f5f22f1ed4744ad29c71de0b765b05d2bb3b4e5c8
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57fe5053e6246db19fee69bc6de3f9e31c15980042774db1a496b99d78b95a2c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c7930d7f56dbe82e53b1a55f4dda8ff173a26f69ee13f189918a1ffe224c29b
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28bee0f873326692f3707770277a59e9da02424102ef718cb151546e86d94701
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 27838218240000.0,
+    "train_loss": 0.41041072442613796,
+    "train_runtime": 554.2459,
+    "train_samples_per_second": 2.089,
+    "train_steps_per_second": 0.262
+}

trainer_log.jsonl

@@ -0,0 +1,147 @@
+{"current_steps": 1, "total_steps": 145, "loss": 1.1472, "lr": 4.99941324504621e-06, "epoch": 0.006896551724137931, "percentage": 0.69, "elapsed_time": "0:00:05", "remaining_time": "0:12:08"}
+{"current_steps": 2, "total_steps": 145, "loss": 1.1414, "lr": 4.9976532556099425e-06, "epoch": 0.013793103448275862, "percentage": 1.38, "elapsed_time": "0:00:08", "remaining_time": "0:10:23"}
+{"current_steps": 3, "total_steps": 145, "loss": 1.0506, "lr": 4.994720857837211e-06, "epoch": 0.020689655172413793, "percentage": 2.07, "elapsed_time": "0:00:12", "remaining_time": "0:09:37"}
+{"current_steps": 4, "total_steps": 145, "loss": 0.9044, "lr": 4.990617428207153e-06, "epoch": 0.027586206896551724, "percentage": 2.76, "elapsed_time": "0:00:15", "remaining_time": "0:09:13"}
+{"current_steps": 5, "total_steps": 145, "loss": 0.8582, "lr": 4.985344892885899e-06, "epoch": 0.034482758620689655, "percentage": 3.45, "elapsed_time": "0:00:19", "remaining_time": "0:08:59"}
+{"current_steps": 6, "total_steps": 145, "loss": 0.7791, "lr": 4.978905726822424e-06, "epoch": 0.041379310344827586, "percentage": 4.14, "elapsed_time": "0:00:22", "remaining_time": "0:08:49"}
+{"current_steps": 7, "total_steps": 145, "loss": 0.7543, "lr": 4.971302952586796e-06, "epoch": 0.04827586206896552, "percentage": 4.83, "elapsed_time": "0:00:26", "remaining_time": "0:08:39"}
+{"current_steps": 8, "total_steps": 145, "loss": 0.7355, "lr": 4.962540138951371e-06, "epoch": 0.05517241379310345, "percentage": 5.52, "elapsed_time": "0:00:29", "remaining_time": "0:08:31"}
+{"current_steps": 9, "total_steps": 145, "loss": 0.6316, "lr": 4.952621399215598e-06, "epoch": 0.06206896551724138, "percentage": 6.21, "elapsed_time": "0:00:33", "remaining_time": "0:08:24"}
+{"current_steps": 10, "total_steps": 145, "loss": 0.6295, "lr": 4.941551389275217e-06, "epoch": 0.06896551724137931, "percentage": 6.9, "elapsed_time": "0:00:36", "remaining_time": "0:08:18"}
+{"current_steps": 11, "total_steps": 145, "loss": 0.5673, "lr": 4.929335305436764e-06, "epoch": 0.07586206896551724, "percentage": 7.59, "elapsed_time": "0:00:40", "remaining_time": "0:08:12"}
+{"current_steps": 12, "total_steps": 145, "loss": 0.5537, "lr": 4.915978881978407e-06, "epoch": 0.08275862068965517, "percentage": 8.28, "elapsed_time": "0:00:44", "remaining_time": "0:08:08"}
+{"current_steps": 13, "total_steps": 145, "loss": 0.5724, "lr": 4.901488388458247e-06, "epoch": 0.0896551724137931, "percentage": 8.97, "elapsed_time": "0:00:47", "remaining_time": "0:08:03"}
+{"current_steps": 14, "total_steps": 145, "loss": 0.5543, "lr": 4.885870626771371e-06, "epoch": 0.09655172413793103, "percentage": 9.66, "elapsed_time": "0:00:51", "remaining_time": "0:07:57"}
+{"current_steps": 15, "total_steps": 145, "loss": 0.5479, "lr": 4.869132927957007e-06, "epoch": 0.10344827586206896, "percentage": 10.34, "elapsed_time": "0:00:54", "remaining_time": "0:07:53"}
+{"current_steps": 16, "total_steps": 145, "loss": 0.5247, "lr": 4.85128314875731e-06, "epoch": 0.1103448275862069, "percentage": 11.03, "elapsed_time": "0:00:58", "remaining_time": "0:07:48"}
+{"current_steps": 17, "total_steps": 145, "loss": 0.5608, "lr": 4.832329667929378e-06, "epoch": 0.11724137931034483, "percentage": 11.72, "elapsed_time": "0:01:01", "remaining_time": "0:07:45"}
+{"current_steps": 18, "total_steps": 145, "loss": 0.5105, "lr": 4.812281382312222e-06, "epoch": 0.12413793103448276, "percentage": 12.41, "elapsed_time": "0:01:05", "remaining_time": "0:07:41"}
+{"current_steps": 19, "total_steps": 145, "loss": 0.5061, "lr": 4.7911477026505656e-06, "epoch": 0.1310344827586207, "percentage": 13.1, "elapsed_time": "0:01:08", "remaining_time": "0:07:36"}
+{"current_steps": 20, "total_steps": 145, "loss": 0.5024, "lr": 4.7689385491773934e-06, "epoch": 0.13793103448275862, "percentage": 13.79, "elapsed_time": "0:01:12", "remaining_time": "0:07:33"}
+{"current_steps": 21, "total_steps": 145, "loss": 0.5257, "lr": 4.745664346957362e-06, "epoch": 0.14482758620689656, "percentage": 14.48, "elapsed_time": "0:01:16", "remaining_time": "0:07:29"}
+{"current_steps": 22, "total_steps": 145, "loss": 0.4905, "lr": 4.721336020993228e-06, "epoch": 0.15172413793103448, "percentage": 15.17, "elapsed_time": "0:01:19", "remaining_time": "0:07:25"}
+{"current_steps": 23, "total_steps": 145, "loss": 0.5305, "lr": 4.6959649910976165e-06, "epoch": 0.15862068965517243, "percentage": 15.86, "elapsed_time": "0:01:23", "remaining_time": "0:07:21"}
+{"current_steps": 24, "total_steps": 145, "loss": 0.4625, "lr": 4.669563166532504e-06, "epoch": 0.16551724137931034, "percentage": 16.55, "elapsed_time": "0:01:26", "remaining_time": "0:07:18"}
+{"current_steps": 25, "total_steps": 145, "loss": 0.4763, "lr": 4.642142940418973e-06, "epoch": 0.1724137931034483, "percentage": 17.24, "elapsed_time": "0:01:30", "remaining_time": "0:07:14"}
+{"current_steps": 26, "total_steps": 145, "loss": 0.4844, "lr": 4.61371718391983e-06, "epoch": 0.1793103448275862, "percentage": 17.93, "elapsed_time": "0:01:34", "remaining_time": "0:07:10"}
+{"current_steps": 27, "total_steps": 145, "loss": 0.4626, "lr": 4.584299240197826e-06, "epoch": 0.18620689655172415, "percentage": 18.62, "elapsed_time": "0:01:37", "remaining_time": "0:07:06"}
+{"current_steps": 28, "total_steps": 145, "loss": 0.4605, "lr": 4.553902918152329e-06, "epoch": 0.19310344827586207, "percentage": 19.31, "elapsed_time": "0:01:41", "remaining_time": "0:07:02"}
+{"current_steps": 29, "total_steps": 145, "loss": 0.4849, "lr": 4.522542485937369e-06, "epoch": 0.2, "percentage": 20.0, "elapsed_time": "0:01:44", "remaining_time": "0:06:59"}
+{"current_steps": 30, "total_steps": 145, "loss": 0.4299, "lr": 4.49023266426411e-06, "epoch": 0.20689655172413793, "percentage": 20.69, "elapsed_time": "0:01:48", "remaining_time": "0:06:55"}
+{"current_steps": 31, "total_steps": 145, "loss": 0.4457, "lr": 4.45698861949089e-06, "epoch": 0.21379310344827587, "percentage": 21.38, "elapsed_time": "0:01:51", "remaining_time": "0:06:51"}
+{"current_steps": 32, "total_steps": 145, "loss": 0.4038, "lr": 4.422825956504073e-06, "epoch": 0.2206896551724138, "percentage": 22.07, "elapsed_time": "0:01:55", "remaining_time": "0:06:47"}
+{"current_steps": 33, "total_steps": 145, "loss": 0.465, "lr": 4.387760711393052e-06, "epoch": 0.22758620689655173, "percentage": 22.76, "elapsed_time": "0:01:58", "remaining_time": "0:06:43"}
+{"current_steps": 34, "total_steps": 145, "loss": 0.4502, "lr": 4.3518093439228484e-06, "epoch": 0.23448275862068965, "percentage": 23.45, "elapsed_time": "0:02:02", "remaining_time": "0:06:39"}
+{"current_steps": 35, "total_steps": 145, "loss": 0.4425, "lr": 4.3149887298078275e-06, "epoch": 0.2413793103448276, "percentage": 24.14, "elapsed_time": "0:02:05", "remaining_time": "0:06:35"}
+{"current_steps": 36, "total_steps": 145, "loss": 0.4199, "lr": 4.277316152790177e-06, "epoch": 0.2482758620689655, "percentage": 24.83, "elapsed_time": "0:02:09", "remaining_time": "0:06:32"}
+{"current_steps": 37, "total_steps": 145, "loss": 0.4259, "lr": 4.238809296526847e-06, "epoch": 0.25517241379310346, "percentage": 25.52, "elapsed_time": "0:02:13", "remaining_time": "0:06:28"}
+{"current_steps": 38, "total_steps": 145, "loss": 0.4093, "lr": 4.19948623628877e-06, "epoch": 0.2620689655172414, "percentage": 26.21, "elapsed_time": "0:02:16", "remaining_time": "0:06:24"}
+{"current_steps": 39, "total_steps": 145, "loss": 0.4047, "lr": 4.159365430476262e-06, "epoch": 0.2689655172413793, "percentage": 26.9, "elapsed_time": "0:02:20", "remaining_time": "0:06:20"}
+{"current_steps": 40, "total_steps": 145, "loss": 0.4066, "lr": 4.11846571195457e-06, "epoch": 0.27586206896551724, "percentage": 27.59, "elapsed_time": "0:02:23", "remaining_time": "0:06:17"}
+{"current_steps": 41, "total_steps": 145, "loss": 0.3912, "lr": 4.076806279213656e-06, "epoch": 0.2827586206896552, "percentage": 28.28, "elapsed_time": "0:02:27", "remaining_time": "0:06:13"}
+{"current_steps": 42, "total_steps": 145, "loss": 0.3883, "lr": 4.034406687356344e-06, "epoch": 0.2896551724137931, "percentage": 28.97, "elapsed_time": "0:02:30", "remaining_time": "0:06:09"}
+{"current_steps": 43, "total_steps": 145, "loss": 0.3615, "lr": 3.991286838919086e-06, "epoch": 0.296551724137931, "percentage": 29.66, "elapsed_time": "0:02:34", "remaining_time": "0:06:06"}
+{"current_steps": 44, "total_steps": 145, "loss": 0.3768, "lr": 3.947466974529622e-06, "epoch": 0.30344827586206896, "percentage": 30.34, "elapsed_time": "0:02:37", "remaining_time": "0:06:02"}
+{"current_steps": 45, "total_steps": 145, "loss": 0.3623, "lr": 3.9029676634059565e-06, "epoch": 0.3103448275862069, "percentage": 31.03, "elapsed_time": "0:02:41", "remaining_time": "0:05:58"}
+{"current_steps": 46, "total_steps": 145, "loss": 0.494, "lr": 3.857809793701082e-06, "epoch": 0.31724137931034485, "percentage": 31.72, "elapsed_time": "0:02:45", "remaining_time": "0:05:55"}
+{"current_steps": 47, "total_steps": 145, "loss": 0.481, "lr": 3.812014562698002e-06, "epoch": 0.32413793103448274, "percentage": 32.41, "elapsed_time": "0:02:48", "remaining_time": "0:05:51"}
+{"current_steps": 48, "total_steps": 145, "loss": 0.4082, "lr": 3.765603466859635e-06, "epoch": 0.3310344827586207, "percentage": 33.1, "elapsed_time": "0:02:52", "remaining_time": "0:05:47"}
+{"current_steps": 49, "total_steps": 145, "loss": 0.4291, "lr": 3.7185982917382986e-06, "epoch": 0.33793103448275863, "percentage": 33.79, "elapsed_time": "0:02:55", "remaining_time": "0:05:44"}
+{"current_steps": 50, "total_steps": 145, "loss": 0.4031, "lr": 3.671021101749476e-06, "epoch": 0.3448275862068966, "percentage": 34.48, "elapsed_time": "0:02:59", "remaining_time": "0:05:40"}
+{"current_steps": 51, "total_steps": 145, "loss": 0.4132, "lr": 3.6228942298146985e-06, "epoch": 0.35172413793103446, "percentage": 35.17, "elapsed_time": "0:03:02", "remaining_time": "0:05:36"}
+{"current_steps": 52, "total_steps": 145, "loss": 0.3793, "lr": 3.5742402668783797e-06, "epoch": 0.3586206896551724, "percentage": 35.86, "elapsed_time": "0:03:06", "remaining_time": "0:05:33"}
+{"current_steps": 53, "total_steps": 145, "loss": 0.395, "lr": 3.5250820513035403e-06, "epoch": 0.36551724137931035, "percentage": 36.55, "elapsed_time": "0:03:09", "remaining_time": "0:05:29"}
+{"current_steps": 54, "total_steps": 145, "loss": 0.3705, "lr": 3.4754426581513866e-06, "epoch": 0.3724137931034483, "percentage": 37.24, "elapsed_time": "0:03:13", "remaining_time": "0:05:26"}
+{"current_steps": 55, "total_steps": 145, "loss": 0.3679, "lr": 3.425345388349787e-06, "epoch": 0.3793103448275862, "percentage": 37.93, "elapsed_time": "0:03:17", "remaining_time": "0:05:22"}
+{"current_steps": 56, "total_steps": 145, "loss": 0.352, "lr": 3.3748137577557216e-06, "epoch": 0.38620689655172413, "percentage": 38.62, "elapsed_time": "0:03:20", "remaining_time": "0:05:18"}
+{"current_steps": 57, "total_steps": 145, "loss": 0.3726, "lr": 3.3238714861168513e-06, "epoch": 0.3931034482758621, "percentage": 39.31, "elapsed_time": "0:03:24", "remaining_time": "0:05:15"}
+{"current_steps": 58, "total_steps": 145, "loss": 0.3538, "lr": 3.272542485937369e-06, "epoch": 0.4, "percentage": 40.0, "elapsed_time": "0:03:27", "remaining_time": "0:05:11"}
+{"current_steps": 59, "total_steps": 145, "loss": 0.4338, "lr": 3.2208508512533777e-06, "epoch": 0.4068965517241379, "percentage": 40.69, "elapsed_time": "0:03:31", "remaining_time": "0:05:07"}
+{"current_steps": 60, "total_steps": 145, "loss": 0.3988, "lr": 3.168820846323053e-06, "epoch": 0.41379310344827586, "percentage": 41.38, "elapsed_time": "0:03:34", "remaining_time": "0:05:04"}
+{"current_steps": 61, "total_steps": 145, "loss": 0.3348, "lr": 3.1164768942369058e-06, "epoch": 0.4206896551724138, "percentage": 42.07, "elapsed_time": "0:03:38", "remaining_time": "0:05:00"}
+{"current_steps": 62, "total_steps": 145, "loss": 0.3536, "lr": 3.063843565453486e-06, "epoch": 0.42758620689655175, "percentage": 42.76, "elapsed_time": "0:03:41", "remaining_time": "0:04:56"}
+{"current_steps": 63, "total_steps": 145, "loss": 0.4152, "lr": 3.0109455662659126e-06, "epoch": 0.43448275862068964, "percentage": 43.45, "elapsed_time": "0:03:45", "remaining_time": "0:04:53"}
+{"current_steps": 64, "total_steps": 145, "loss": 0.4114, "lr": 2.9578077272046407e-06, "epoch": 0.4413793103448276, "percentage": 44.14, "elapsed_time": "0:03:48", "remaining_time": "0:04:49"}
+{"current_steps": 65, "total_steps": 145, "loss": 0.3937, "lr": 2.9044549913819125e-06, "epoch": 0.4482758620689655, "percentage": 44.83, "elapsed_time": "0:03:52", "remaining_time": "0:04:46"}
+{"current_steps": 66, "total_steps": 145, "loss": 0.3639, "lr": 2.850912402783361e-06, "epoch": 0.45517241379310347, "percentage": 45.52, "elapsed_time": "0:03:56", "remaining_time": "0:04:42"}
+{"current_steps": 67, "total_steps": 145, "loss": 0.3699, "lr": 2.7972050945122666e-06, "epoch": 0.46206896551724136, "percentage": 46.21, "elapsed_time": "0:03:59", "remaining_time": "0:04:38"}
+{"current_steps": 68, "total_steps": 145, "loss": 0.3416, "lr": 2.7433582769919752e-06, "epoch": 0.4689655172413793, "percentage": 46.9, "elapsed_time": "0:04:03", "remaining_time": "0:04:35"}
+{"current_steps": 69, "total_steps": 145, "loss": 0.3491, "lr": 2.6893972261320265e-06, "epoch": 0.47586206896551725, "percentage": 47.59, "elapsed_time": "0:04:06", "remaining_time": "0:04:31"}
+{"current_steps": 70, "total_steps": 145, "loss": 0.3551, "lr": 2.6353472714635443e-06, "epoch": 0.4827586206896552, "percentage": 48.28, "elapsed_time": "0:04:10", "remaining_time": "0:04:28"}
+{"current_steps": 71, "total_steps": 145, "loss": 0.3606, "lr": 2.5812337842494517e-06, "epoch": 0.4896551724137931, "percentage": 48.97, "elapsed_time": "0:04:13", "remaining_time": "0:04:24"}
+{"current_steps": 72, "total_steps": 145, "loss": 0.3403, "lr": 2.5270821655750997e-06, "epoch": 0.496551724137931, "percentage": 49.66, "elapsed_time": "0:04:17", "remaining_time": "0:04:21"}
+{"current_steps": 73, "total_steps": 145, "loss": 0.3467, "lr": 2.4729178344249007e-06, "epoch": 0.503448275862069, "percentage": 50.34, "elapsed_time": "0:04:21", "remaining_time": "0:04:17"}
+{"current_steps": 74, "total_steps": 145, "loss": 0.376, "lr": 2.418766215750549e-06, "epoch": 0.5103448275862069, "percentage": 51.03, "elapsed_time": "0:04:24", "remaining_time": "0:04:13"}
+{"current_steps": 75, "total_steps": 145, "loss": 0.4078, "lr": 2.3646527285364565e-06, "epoch": 0.5172413793103449, "percentage": 51.72, "elapsed_time": "0:04:28", "remaining_time": "0:04:10"}
+{"current_steps": 76, "total_steps": 145, "loss": 0.3445, "lr": 2.3106027738679743e-06, "epoch": 0.5241379310344828, "percentage": 52.41, "elapsed_time": "0:04:31", "remaining_time": "0:04:06"}
+{"current_steps": 77, "total_steps": 145, "loss": 0.3271, "lr": 2.256641723008026e-06, "epoch": 0.5310344827586206, "percentage": 53.1, "elapsed_time": "0:04:35", "remaining_time": "0:04:03"}
+{"current_steps": 78, "total_steps": 145, "loss": 0.3654, "lr": 2.2027949054877342e-06, "epoch": 0.5379310344827586, "percentage": 53.79, "elapsed_time": "0:04:38", "remaining_time": "0:03:59"}
+{"current_steps": 79, "total_steps": 145, "loss": 0.349, "lr": 2.1490875972166394e-06, "epoch": 0.5448275862068965, "percentage": 54.48, "elapsed_time": "0:04:42", "remaining_time": "0:03:56"}
+{"current_steps": 80, "total_steps": 145, "loss": 0.3312, "lr": 2.0955450086180883e-06, "epoch": 0.5517241379310345, "percentage": 55.17, "elapsed_time": "0:04:46", "remaining_time": "0:03:52"}
+{"current_steps": 81, "total_steps": 145, "loss": 0.353, "lr": 2.0421922727953597e-06, "epoch": 0.5586206896551724, "percentage": 55.86, "elapsed_time": "0:04:49", "remaining_time": "0:03:48"}
+{"current_steps": 82, "total_steps": 145, "loss": 0.3487, "lr": 1.9890544337340882e-06, "epoch": 0.5655172413793104, "percentage": 56.55, "elapsed_time": "0:04:53", "remaining_time": "0:03:45"}
+{"current_steps": 83, "total_steps": 145, "loss": 0.3388, "lr": 1.936156434546515e-06, "epoch": 0.5724137931034483, "percentage": 57.24, "elapsed_time": "0:04:56", "remaining_time": "0:03:41"}
+{"current_steps": 84, "total_steps": 145, "loss": 0.3475, "lr": 1.8835231057630955e-06, "epoch": 0.5793103448275863, "percentage": 57.93, "elapsed_time": "0:05:00", "remaining_time": "0:03:38"}
+{"current_steps": 85, "total_steps": 145, "loss": 0.3439, "lr": 1.8311791536769485e-06, "epoch": 0.5862068965517241, "percentage": 58.62, "elapsed_time": "0:05:04", "remaining_time": "0:03:34"}
+{"current_steps": 86, "total_steps": 145, "loss": 0.3238, "lr": 1.7791491487466234e-06, "epoch": 0.593103448275862, "percentage": 59.31, "elapsed_time": "0:05:07", "remaining_time": "0:03:31"}
+{"current_steps": 87, "total_steps": 145, "loss": 0.3493, "lr": 1.7274575140626318e-06, "epoch": 0.6, "percentage": 60.0, "elapsed_time": "0:05:11", "remaining_time": "0:03:27"}
+{"current_steps": 88, "total_steps": 145, "loss": 0.354, "lr": 1.6761285138831493e-06, "epoch": 0.6068965517241379, "percentage": 60.69, "elapsed_time": "0:05:14", "remaining_time": "0:03:23"}
+{"current_steps": 89, "total_steps": 145, "loss": 0.3388, "lr": 1.625186242244279e-06, "epoch": 0.6137931034482759, "percentage": 61.38, "elapsed_time": "0:05:18", "remaining_time": "0:03:20"}
+{"current_steps": 90, "total_steps": 145, "loss": 0.3355, "lr": 1.574654611650214e-06, "epoch": 0.6206896551724138, "percentage": 62.07, "elapsed_time": "0:05:21", "remaining_time": "0:03:16"}
+{"current_steps": 91, "total_steps": 145, "loss": 0.3429, "lr": 1.5245573418486136e-06, "epoch": 0.6275862068965518, "percentage": 62.76, "elapsed_time": "0:05:25", "remaining_time": "0:03:13"}
+{"current_steps": 92, "total_steps": 145, "loss": 0.3411, "lr": 1.4749179486964599e-06, "epoch": 0.6344827586206897, "percentage": 63.45, "elapsed_time": "0:05:28", "remaining_time": "0:03:09"}
+{"current_steps": 93, "total_steps": 145, "loss": 0.3335, "lr": 1.4257597331216211e-06, "epoch": 0.6413793103448275, "percentage": 64.14, "elapsed_time": "0:05:32", "remaining_time": "0:03:05"}
+{"current_steps": 94, "total_steps": 145, "loss": 0.3444, "lr": 1.3771057701853034e-06, "epoch": 0.6482758620689655, "percentage": 64.83, "elapsed_time": "0:05:35", "remaining_time": "0:03:02"}
+{"current_steps": 95, "total_steps": 145, "loss": 0.3192, "lr": 1.328978898250525e-06, "epoch": 0.6551724137931034, "percentage": 65.52, "elapsed_time": "0:05:39", "remaining_time": "0:02:58"}
+{"current_steps": 96, "total_steps": 145, "loss": 0.3383, "lr": 1.2814017082617025e-06, "epoch": 0.6620689655172414, "percentage": 66.21, "elapsed_time": "0:05:43", "remaining_time": "0:02:55"}
+{"current_steps": 97, "total_steps": 145, "loss": 0.3386, "lr": 1.234396533140365e-06, "epoch": 0.6689655172413793, "percentage": 66.9, "elapsed_time": "0:05:46", "remaining_time": "0:02:51"}
+{"current_steps": 98, "total_steps": 145, "loss": 0.3277, "lr": 1.187985437301999e-06, "epoch": 0.6758620689655173, "percentage": 67.59, "elapsed_time": "0:05:50", "remaining_time": "0:02:48"}
+{"current_steps": 99, "total_steps": 145, "loss": 0.3325, "lr": 1.1421902062989178e-06, "epoch": 0.6827586206896552, "percentage": 68.28, "elapsed_time": "0:05:53", "remaining_time": "0:02:44"}
+{"current_steps": 100, "total_steps": 145, "loss": 0.3312, "lr": 1.0970323365940443e-06, "epoch": 0.6896551724137931, "percentage": 68.97, "elapsed_time": "0:05:57", "remaining_time": "0:02:40"}
+{"current_steps": 100, "total_steps": 145, "eval_loss": 0.32950592041015625, "epoch": 0.6896551724137931, "percentage": 68.97, "elapsed_time": "0:05:58", "remaining_time": "0:02:41"}
+{"current_steps": 101, "total_steps": 145, "loss": 0.3801, "lr": 1.052533025470379e-06, "epoch": 0.696551724137931, "percentage": 69.66, "elapsed_time": "0:06:02", "remaining_time": "0:02:37"}
+{"current_steps": 102, "total_steps": 145, "loss": 0.338, "lr": 1.0087131610809153e-06, "epoch": 0.7034482758620689, "percentage": 70.34, "elapsed_time": "0:06:05", "remaining_time": "0:02:34"}
+{"current_steps": 103, "total_steps": 145, "loss": 0.3344, "lr": 9.655933126436565e-07, "epoch": 0.7103448275862069, "percentage": 71.03, "elapsed_time": "0:06:09", "remaining_time": "0:02:30"}
+{"current_steps": 104, "total_steps": 145, "loss": 0.3299, "lr": 9.231937207863459e-07, "epoch": 0.7172413793103448, "percentage": 71.72, "elapsed_time": "0:06:12", "remaining_time": "0:02:26"}
+{"current_steps": 105, "total_steps": 145, "loss": 0.3304, "lr": 8.815342880454312e-07, "epoch": 0.7241379310344828, "percentage": 72.41, "elapsed_time": "0:06:16", "remaining_time": "0:02:23"}
+{"current_steps": 106, "total_steps": 145, "loss": 0.3617, "lr": 8.406345695237394e-07, "epoch": 0.7310344827586207, "percentage": 73.1, "elapsed_time": "0:06:19", "remaining_time": "0:02:19"}
+{"current_steps": 107, "total_steps": 145, "loss": 0.3087, "lr": 8.005137637112303e-07, "epoch": 0.7379310344827587, "percentage": 73.79, "elapsed_time": "0:06:23", "remaining_time": "0:02:16"}
+{"current_steps": 108, "total_steps": 145, "loss": 0.3331, "lr": 7.611907034731538e-07, "epoch": 0.7448275862068966, "percentage": 74.48, "elapsed_time": "0:06:27", "remaining_time": "0:02:12"}
+{"current_steps": 109, "total_steps": 145, "loss": 0.3075, "lr": 7.226838472098239e-07, "epoch": 0.7517241379310344, "percentage": 75.17, "elapsed_time": "0:06:30", "remaining_time": "0:02:09"}
+{"current_steps": 110, "total_steps": 145, "loss": 0.2988, "lr": 6.850112701921735e-07, "epoch": 0.7586206896551724, "percentage": 75.86, "elapsed_time": "0:06:34", "remaining_time": "0:02:05"}
+{"current_steps": 111, "total_steps": 145, "loss": 0.3385, "lr": 6.481906560771525e-07, "epoch": 0.7655172413793103, "percentage": 76.55, "elapsed_time": "0:06:38", "remaining_time": "0:02:01"}
+{"current_steps": 112, "total_steps": 145, "loss": 0.329, "lr": 6.122392886069486e-07, "epoch": 0.7724137931034483, "percentage": 77.24, "elapsed_time": "0:06:41", "remaining_time": "0:01:58"}
+{"current_steps": 113, "total_steps": 145, "loss": 0.3151, "lr": 5.771740434959278e-07, "epoch": 0.7793103448275862, "percentage": 77.93, "elapsed_time": "0:06:45", "remaining_time": "0:01:54"}
+{"current_steps": 114, "total_steps": 145, "loss": 0.3264, "lr": 5.430113805091111e-07, "epoch": 0.7862068965517242, "percentage": 78.62, "elapsed_time": "0:06:48", "remaining_time": "0:01:51"}
+{"current_steps": 115, "total_steps": 145, "loss": 0.347, "lr": 5.097673357358906e-07, "epoch": 0.7931034482758621, "percentage": 79.31, "elapsed_time": "0:06:52", "remaining_time": "0:01:47"}
+{"current_steps": 116, "total_steps": 145, "loss": 0.3017, "lr": 4.774575140626317e-07, "epoch": 0.8, "percentage": 80.0, "elapsed_time": "0:06:55", "remaining_time": "0:01:43"}
+{"current_steps": 117, "total_steps": 145, "loss": 0.3021, "lr": 4.4609708184767177e-07, "epoch": 0.8068965517241379, "percentage": 80.69, "elapsed_time": "0:06:59", "remaining_time": "0:01:40"}
+{"current_steps": 118, "total_steps": 145, "loss": 0.3223, "lr": 4.1570075980217503e-07, "epoch": 0.8137931034482758, "percentage": 81.38, "elapsed_time": "0:07:03", "remaining_time": "0:01:36"}
+{"current_steps": 119, "total_steps": 145, "loss": 0.2995, "lr": 3.862828160801707e-07, "epoch": 0.8206896551724138, "percentage": 82.07, "elapsed_time": "0:07:06", "remaining_time": "0:01:33"}
+{"current_steps": 120, "total_steps": 145, "loss": 0.3264, "lr": 3.578570595810274e-07, "epoch": 0.8275862068965517, "percentage": 82.76, "elapsed_time": "0:07:10", "remaining_time": "0:01:29"}
+{"current_steps": 121, "total_steps": 145, "loss": 0.3056, "lr": 3.304368334674965e-07, "epoch": 0.8344827586206897, "percentage": 83.45, "elapsed_time": "0:07:13", "remaining_time": "0:01:26"}
+{"current_steps": 122, "total_steps": 145, "loss": 0.3177, "lr": 3.040350089023844e-07, "epoch": 0.8413793103448276, "percentage": 84.14, "elapsed_time": "0:07:17", "remaining_time": "0:01:22"}
+{"current_steps": 123, "total_steps": 145, "loss": 0.2999, "lr": 2.786639790067719e-07, "epoch": 0.8482758620689655, "percentage": 84.83, "elapsed_time": "0:07:21", "remaining_time": "0:01:18"}
+{"current_steps": 124, "total_steps": 145, "loss": 0.3006, "lr": 2.543356530426394e-07, "epoch": 0.8551724137931035, "percentage": 85.52, "elapsed_time": "0:07:24", "remaining_time": "0:01:15"}
+{"current_steps": 125, "total_steps": 145, "loss": 0.2969, "lr": 2.3106145082260777e-07, "epoch": 0.8620689655172413, "percentage": 86.21, "elapsed_time": "0:07:28", "remaining_time": "0:01:11"}
+{"current_steps": 126, "total_steps": 145, "loss": 0.3116, "lr": 2.0885229734943501e-07, "epoch": 0.8689655172413793, "percentage": 86.9, "elapsed_time": "0:07:31", "remaining_time": "0:01:08"}
+{"current_steps": 127, "total_steps": 145, "loss": 0.3232, "lr": 1.8771861768777794e-07, "epoch": 0.8758620689655172, "percentage": 87.59, "elapsed_time": "0:07:35", "remaining_time": "0:01:04"}
+{"current_steps": 128, "total_steps": 145, "loss": 0.3326, "lr": 1.67670332070623e-07, "epoch": 0.8827586206896552, "percentage": 88.28, "elapsed_time": "0:07:38", "remaining_time": "0:01:00"}
+{"current_steps": 129, "total_steps": 145, "loss": 0.3294, "lr": 1.487168512426901e-07, "epoch": 0.8896551724137931, "percentage": 88.97, "elapsed_time": "0:07:42", "remaining_time": "0:00:57"}
+{"current_steps": 130, "total_steps": 145, "loss": 0.3354, "lr": 1.3086707204299415e-07, "epoch": 0.896551724137931, "percentage": 89.66, "elapsed_time": "0:07:46", "remaining_time": "0:00:53"}
+{"current_steps": 131, "total_steps": 145, "loss": 0.3252, "lr": 1.1412937322862971e-07, "epoch": 0.903448275862069, "percentage": 90.34, "elapsed_time": "0:07:49", "remaining_time": "0:00:50"}
+{"current_steps": 132, "total_steps": 145, "loss": 0.306, "lr": 9.851161154175337e-08, "epoch": 0.9103448275862069, "percentage": 91.03, "elapsed_time": "0:07:53", "remaining_time": "0:00:46"}
+{"current_steps": 133, "total_steps": 145, "loss": 0.3189, "lr": 8.402111802159413e-08, "epoch": 0.9172413793103448, "percentage": 91.72, "elapsed_time": "0:07:56", "remaining_time": "0:00:43"}
+{"current_steps": 134, "total_steps": 145, "loss": 0.3147, "lr": 7.06646945632361e-08, "epoch": 0.9241379310344827, "percentage": 92.41, "elapsed_time": "0:08:00", "remaining_time": "0:00:39"}
+{"current_steps": 135, "total_steps": 145, "loss": 0.3334, "lr": 5.844861072478336e-08, "epoch": 0.9310344827586207, "percentage": 93.1, "elapsed_time": "0:08:03", "remaining_time": "0:00:35"}
+{"current_steps": 136, "total_steps": 145, "loss": 0.3315, "lr": 4.7378600784402095e-08, "epoch": 0.9379310344827586, "percentage": 93.79, "elapsed_time": "0:08:07", "remaining_time": "0:00:32"}
+{"current_steps": 137, "total_steps": 145, "loss": 0.3082, "lr": 3.745986104862903e-08, "epoch": 0.9448275862068966, "percentage": 94.48, "elapsed_time": "0:08:10", "remaining_time": "0:00:28"}
+{"current_steps": 138, "total_steps": 145, "loss": 0.3134, "lr": 2.869704741320478e-08, "epoch": 0.9517241379310345, "percentage": 95.17, "elapsed_time": "0:08:14", "remaining_time": "0:00:25"}
+{"current_steps": 139, "total_steps": 145, "loss": 0.3398, "lr": 2.1094273177576508e-08, "epoch": 0.9586206896551724, "percentage": 95.86, "elapsed_time": "0:08:18", "remaining_time": "0:00:21"}
+{"current_steps": 140, "total_steps": 145, "loss": 0.3254, "lr": 1.4655107114101008e-08, "epoch": 0.9655172413793104, "percentage": 96.55, "elapsed_time": "0:08:21", "remaining_time": "0:00:17"}
+{"current_steps": 141, "total_steps": 145, "loss": 0.3033, "lr": 9.382571792846962e-09, "epoch": 0.9724137931034482, "percentage": 97.24, "elapsed_time": "0:08:25", "remaining_time": "0:00:14"}
+{"current_steps": 142, "total_steps": 145, "loss": 0.3386, "lr": 5.279142162789019e-09, "epoch": 0.9793103448275862, "percentage": 97.93, "elapsed_time": "0:08:28", "remaining_time": "0:00:10"}
+{"current_steps": 143, "total_steps": 145, "loss": 0.3121, "lr": 2.34674439005822e-09, "epoch": 0.9862068965517241, "percentage": 98.62, "elapsed_time": "0:08:32", "remaining_time": "0:00:07"}
+{"current_steps": 144, "total_steps": 145, "loss": 0.3061, "lr": 5.86754953789681e-10, "epoch": 0.993103448275862, "percentage": 99.31, "elapsed_time": "0:08:35", "remaining_time": "0:00:03"}
+{"current_steps": 145, "total_steps": 145, "loss": 0.2844, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:08:39", "remaining_time": "0:00:00"}
+{"current_steps": 145, "total_steps": 145, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:09:14", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1065 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 145,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.006896551724137931,
+      "grad_norm": 31.03218072798058,
+      "learning_rate": 4.99941324504621e-06,
+      "loss": 1.1472,
+      "step": 1
+    },
+    {
+      "epoch": 0.013793103448275862,
+      "grad_norm": 40.571468688350755,
+      "learning_rate": 4.9976532556099425e-06,
+      "loss": 1.1414,
+      "step": 2
+    },
+    {
+      "epoch": 0.020689655172413793,
+      "grad_norm": 21.456766088217545,
+      "learning_rate": 4.994720857837211e-06,
+      "loss": 1.0506,
+      "step": 3
+    },
+    {
+      "epoch": 0.027586206896551724,
+      "grad_norm": 29.951853669934376,
+      "learning_rate": 4.990617428207153e-06,
+      "loss": 0.9044,
+      "step": 4
+    },
+    {
+      "epoch": 0.034482758620689655,
+      "grad_norm": 9.14916531515459,
+      "learning_rate": 4.985344892885899e-06,
+      "loss": 0.8582,
+      "step": 5
+    },
+    {
+      "epoch": 0.041379310344827586,
+      "grad_norm": 7.608658971894189,
+      "learning_rate": 4.978905726822424e-06,
+      "loss": 0.7791,
+      "step": 6
+    },
+    {
+      "epoch": 0.04827586206896552,
+      "grad_norm": 7.305096625333466,
+      "learning_rate": 4.971302952586796e-06,
+      "loss": 0.7543,
+      "step": 7
+    },
+    {
+      "epoch": 0.05517241379310345,
+      "grad_norm": 3.527448201835038,
+      "learning_rate": 4.962540138951371e-06,
+      "loss": 0.7355,
+      "step": 8
+    },
+    {
+      "epoch": 0.06206896551724138,
+      "grad_norm": 3.1225203984788066,
+      "learning_rate": 4.952621399215598e-06,
+      "loss": 0.6316,
+      "step": 9
+    },
+    {
+      "epoch": 0.06896551724137931,
+      "grad_norm": 2.8026256813779167,
+      "learning_rate": 4.941551389275217e-06,
+      "loss": 0.6295,
+      "step": 10
+    },
+    {
+      "epoch": 0.07586206896551724,
+      "grad_norm": 2.0514195141398814,
+      "learning_rate": 4.929335305436764e-06,
+      "loss": 0.5673,
+      "step": 11
+    },
+    {
+      "epoch": 0.08275862068965517,
+      "grad_norm": 1.5899379118058201,
+      "learning_rate": 4.915978881978407e-06,
+      "loss": 0.5537,
+      "step": 12
+    },
+    {
+      "epoch": 0.0896551724137931,
+      "grad_norm": 1.41483410053127,
+      "learning_rate": 4.901488388458247e-06,
+      "loss": 0.5724,
+      "step": 13
+    },
+    {
+      "epoch": 0.09655172413793103,
+      "grad_norm": 1.708329942565822,
+      "learning_rate": 4.885870626771371e-06,
+      "loss": 0.5543,
+      "step": 14
+    },
+    {
+      "epoch": 0.10344827586206896,
+      "grad_norm": 1.951276037369855,
+      "learning_rate": 4.869132927957007e-06,
+      "loss": 0.5479,
+      "step": 15
+    },
+    {
+      "epoch": 0.1103448275862069,
+      "grad_norm": 1.5107535293484684,
+      "learning_rate": 4.85128314875731e-06,
+      "loss": 0.5247,
+      "step": 16
+    },
+    {
+      "epoch": 0.11724137931034483,
+      "grad_norm": 1.3814563917343559,
+      "learning_rate": 4.832329667929378e-06,
+      "loss": 0.5608,
+      "step": 17
+    },
+    {
+      "epoch": 0.12413793103448276,
+      "grad_norm": 1.1990088178536704,
+      "learning_rate": 4.812281382312222e-06,
+      "loss": 0.5105,
+      "step": 18
+    },
+    {
+      "epoch": 0.1310344827586207,
+      "grad_norm": 1.2640990090997495,
+      "learning_rate": 4.7911477026505656e-06,
+      "loss": 0.5061,
+      "step": 19
+    },
+    {
+      "epoch": 0.13793103448275862,
+      "grad_norm": 1.248681134153344,
+      "learning_rate": 4.7689385491773934e-06,
+      "loss": 0.5024,
+      "step": 20
+    },
+    {
+      "epoch": 0.14482758620689656,
+      "grad_norm": 1.3037907941530413,
+      "learning_rate": 4.745664346957362e-06,
+      "loss": 0.5257,
+      "step": 21
+    },
+    {
+      "epoch": 0.15172413793103448,
+      "grad_norm": 1.42693290628275,
+      "learning_rate": 4.721336020993228e-06,
+      "loss": 0.4905,
+      "step": 22
+    },
+    {
+      "epoch": 0.15862068965517243,
+      "grad_norm": 1.2363521488486766,
+      "learning_rate": 4.6959649910976165e-06,
+      "loss": 0.5305,
+      "step": 23
+    },
+    {
+      "epoch": 0.16551724137931034,
+      "grad_norm": 1.312777528169162,
+      "learning_rate": 4.669563166532504e-06,
+      "loss": 0.4625,
+      "step": 24
+    },
+    {
+      "epoch": 0.1724137931034483,
+      "grad_norm": 1.389027989009955,
+      "learning_rate": 4.642142940418973e-06,
+      "loss": 0.4763,
+      "step": 25
+    },
+    {
+      "epoch": 0.1793103448275862,
+      "grad_norm": 1.4093557446739753,
+      "learning_rate": 4.61371718391983e-06,
+      "loss": 0.4844,
+      "step": 26
+    },
+    {
+      "epoch": 0.18620689655172415,
+      "grad_norm": 1.6606693381483022,
+      "learning_rate": 4.584299240197826e-06,
+      "loss": 0.4626,
+      "step": 27
+    },
+    {
+      "epoch": 0.19310344827586207,
+      "grad_norm": 1.749655731871402,
+      "learning_rate": 4.553902918152329e-06,
+      "loss": 0.4605,
+      "step": 28
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 1.677563257235422,
+      "learning_rate": 4.522542485937369e-06,
+      "loss": 0.4849,
+      "step": 29
+    },
+    {
+      "epoch": 0.20689655172413793,
+      "grad_norm": 1.7343815664184612,
+      "learning_rate": 4.49023266426411e-06,
+      "loss": 0.4299,
+      "step": 30
+    },
+    {
+      "epoch": 0.21379310344827587,
+      "grad_norm": 1.697910060549286,
+      "learning_rate": 4.45698861949089e-06,
+      "loss": 0.4457,
+      "step": 31
+    },
+    {
+      "epoch": 0.2206896551724138,
+      "grad_norm": 1.6727401425074877,
+      "learning_rate": 4.422825956504073e-06,
+      "loss": 0.4038,
+      "step": 32
+    },
+    {
+      "epoch": 0.22758620689655173,
+      "grad_norm": 1.734171173055874,
+      "learning_rate": 4.387760711393052e-06,
+      "loss": 0.465,
+      "step": 33
+    },
+    {
+      "epoch": 0.23448275862068965,
+      "grad_norm": 1.9134807613873142,
+      "learning_rate": 4.3518093439228484e-06,
+      "loss": 0.4502,
+      "step": 34
+    },
+    {
+      "epoch": 0.2413793103448276,
+      "grad_norm": 1.7603021646706738,
+      "learning_rate": 4.3149887298078275e-06,
+      "loss": 0.4425,
+      "step": 35
+    },
+    {
+      "epoch": 0.2482758620689655,
+      "grad_norm": 1.8751179947725263,
+      "learning_rate": 4.277316152790177e-06,
+      "loss": 0.4199,
+      "step": 36
+    },
+    {
+      "epoch": 0.25517241379310346,
+      "grad_norm": 1.8322843272863023,
+      "learning_rate": 4.238809296526847e-06,
+      "loss": 0.4259,
+      "step": 37
+    },
+    {
+      "epoch": 0.2620689655172414,
+      "grad_norm": 1.8939695398250387,
+      "learning_rate": 4.19948623628877e-06,
+      "loss": 0.4093,
+      "step": 38
+    },
+    {
+      "epoch": 0.2689655172413793,
+      "grad_norm": 1.6848860066426272,
+      "learning_rate": 4.159365430476262e-06,
+      "loss": 0.4047,
+      "step": 39
+    },
+    {
+      "epoch": 0.27586206896551724,
+      "grad_norm": 1.8363785138180755,
+      "learning_rate": 4.11846571195457e-06,
+      "loss": 0.4066,
+      "step": 40
+    },
+    {
+      "epoch": 0.2827586206896552,
+      "grad_norm": 1.7728131417502844,
+      "learning_rate": 4.076806279213656e-06,
+      "loss": 0.3912,
+      "step": 41
+    },
+    {
+      "epoch": 0.2896551724137931,
+      "grad_norm": 1.936143087402197,
+      "learning_rate": 4.034406687356344e-06,
+      "loss": 0.3883,
+      "step": 42
+    },
+    {
+      "epoch": 0.296551724137931,
+      "grad_norm": 1.8356277945670665,
+      "learning_rate": 3.991286838919086e-06,
+      "loss": 0.3615,
+      "step": 43
+    },
+    {
+      "epoch": 0.30344827586206896,
+      "grad_norm": 1.8854492388098718,
+      "learning_rate": 3.947466974529622e-06,
+      "loss": 0.3768,
+      "step": 44
+    },
+    {
+      "epoch": 0.3103448275862069,
+      "grad_norm": 1.8201374587143715,
+      "learning_rate": 3.9029676634059565e-06,
+      "loss": 0.3623,
+      "step": 45
+    },
+    {
+      "epoch": 0.31724137931034485,
+      "grad_norm": 1.7503723332439074,
+      "learning_rate": 3.857809793701082e-06,
+      "loss": 0.494,
+      "step": 46
+    },
+    {
+      "epoch": 0.32413793103448274,
+      "grad_norm": 2.1756275341354874,
+      "learning_rate": 3.812014562698002e-06,
+      "loss": 0.481,
+      "step": 47
+    },
+    {
+      "epoch": 0.3310344827586207,
+      "grad_norm": 1.8722692193970432,
+      "learning_rate": 3.765603466859635e-06,
+      "loss": 0.4082,
+      "step": 48
+    },
+    {
+      "epoch": 0.33793103448275863,
+      "grad_norm": 1.9691346941839627,
+      "learning_rate": 3.7185982917382986e-06,
+      "loss": 0.4291,
+      "step": 49
+    },
+    {
+      "epoch": 0.3448275862068966,
+      "grad_norm": 1.8936722422482075,
+      "learning_rate": 3.671021101749476e-06,
+      "loss": 0.4031,
+      "step": 50
+    },
+    {
+      "epoch": 0.35172413793103446,
+      "grad_norm": 1.8025792062134904,
+      "learning_rate": 3.6228942298146985e-06,
+      "loss": 0.4132,
+      "step": 51
+    },
+    {
+      "epoch": 0.3586206896551724,
+      "grad_norm": 1.6870378106507296,
+      "learning_rate": 3.5742402668783797e-06,
+      "loss": 0.3793,
+      "step": 52
+    },
+    {
+      "epoch": 0.36551724137931035,
+      "grad_norm": 1.9105755340012387,
+      "learning_rate": 3.5250820513035403e-06,
+      "loss": 0.395,
+      "step": 53
+    },
+    {
+      "epoch": 0.3724137931034483,
+      "grad_norm": 1.8805371993317115,
+      "learning_rate": 3.4754426581513866e-06,
+      "loss": 0.3705,
+      "step": 54
+    },
+    {
+      "epoch": 0.3793103448275862,
+      "grad_norm": 1.8811267846682296,
+      "learning_rate": 3.425345388349787e-06,
+      "loss": 0.3679,
+      "step": 55
+    },
+    {
+      "epoch": 0.38620689655172413,
+      "grad_norm": 1.7732434001607817,
+      "learning_rate": 3.3748137577557216e-06,
+      "loss": 0.352,
+      "step": 56
+    },
+    {
+      "epoch": 0.3931034482758621,
+      "grad_norm": 1.9254843771751957,
+      "learning_rate": 3.3238714861168513e-06,
+      "loss": 0.3726,
+      "step": 57
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 1.7426839053037437,
+      "learning_rate": 3.272542485937369e-06,
+      "loss": 0.3538,
+      "step": 58
+    },
+    {
+      "epoch": 0.4068965517241379,
+      "grad_norm": 1.889875840529081,
+      "learning_rate": 3.2208508512533777e-06,
+      "loss": 0.4338,
+      "step": 59
+    },
+    {
+      "epoch": 0.41379310344827586,
+      "grad_norm": 2.119735352005384,
+      "learning_rate": 3.168820846323053e-06,
+      "loss": 0.3988,
+      "step": 60
+    },
+    {
+      "epoch": 0.4206896551724138,
+      "grad_norm": 1.6951342324925656,
+      "learning_rate": 3.1164768942369058e-06,
+      "loss": 0.3348,
+      "step": 61
+    },
+    {
+      "epoch": 0.42758620689655175,
+      "grad_norm": 1.6936054133611658,
+      "learning_rate": 3.063843565453486e-06,
+      "loss": 0.3536,
+      "step": 62
+    },
+    {
+      "epoch": 0.43448275862068964,
+      "grad_norm": 1.7779442342291463,
+      "learning_rate": 3.0109455662659126e-06,
+      "loss": 0.4152,
+      "step": 63
+    },
+    {
+      "epoch": 0.4413793103448276,
+      "grad_norm": 1.7416015843522563,
+      "learning_rate": 2.9578077272046407e-06,
+      "loss": 0.4114,
+      "step": 64
+    },
+    {
+      "epoch": 0.4482758620689655,
+      "grad_norm": 1.8748850420288656,
+      "learning_rate": 2.9044549913819125e-06,
+      "loss": 0.3937,
+      "step": 65
+    },
+    {
+      "epoch": 0.45517241379310347,
+      "grad_norm": 1.9464207272398613,
+      "learning_rate": 2.850912402783361e-06,
+      "loss": 0.3639,
+      "step": 66
+    },
+    {
+      "epoch": 0.46206896551724136,
+      "grad_norm": 1.8277666119654024,
+      "learning_rate": 2.7972050945122666e-06,
+      "loss": 0.3699,
+      "step": 67
+    },
+    {
+      "epoch": 0.4689655172413793,
+      "grad_norm": 1.7869403081749455,
+      "learning_rate": 2.7433582769919752e-06,
+      "loss": 0.3416,
+      "step": 68
+    },
+    {
+      "epoch": 0.47586206896551725,
+      "grad_norm": 1.7776612158208631,
+      "learning_rate": 2.6893972261320265e-06,
+      "loss": 0.3491,
+      "step": 69
+    },
+    {
+      "epoch": 0.4827586206896552,
+      "grad_norm": 1.8358328629735843,
+      "learning_rate": 2.6353472714635443e-06,
+      "loss": 0.3551,
+      "step": 70
+    },
+    {
+      "epoch": 0.4896551724137931,
+      "grad_norm": 1.7434649654505425,
+      "learning_rate": 2.5812337842494517e-06,
+      "loss": 0.3606,
+      "step": 71
+    },
+    {
+      "epoch": 0.496551724137931,
+      "grad_norm": 1.7698889051181665,
+      "learning_rate": 2.5270821655750997e-06,
+      "loss": 0.3403,
+      "step": 72
+    },
+    {
+      "epoch": 0.503448275862069,
+      "grad_norm": 1.826216728994691,
+      "learning_rate": 2.4729178344249007e-06,
+      "loss": 0.3467,
+      "step": 73
+    },
+    {
+      "epoch": 0.5103448275862069,
+      "grad_norm": 1.7299445572771408,
+      "learning_rate": 2.418766215750549e-06,
+      "loss": 0.376,
+      "step": 74
+    },
+    {
+      "epoch": 0.5172413793103449,
+      "grad_norm": 1.7936259659594962,
+      "learning_rate": 2.3646527285364565e-06,
+      "loss": 0.4078,
+      "step": 75
+    },
+    {
+      "epoch": 0.5241379310344828,
+      "grad_norm": 1.8499509434768147,
+      "learning_rate": 2.3106027738679743e-06,
+      "loss": 0.3445,
+      "step": 76
+    },
+    {
+      "epoch": 0.5310344827586206,
+      "grad_norm": 1.8447996857451392,
+      "learning_rate": 2.256641723008026e-06,
+      "loss": 0.3271,
+      "step": 77
+    },
+    {
+      "epoch": 0.5379310344827586,
+      "grad_norm": 1.7594056172456962,
+      "learning_rate": 2.2027949054877342e-06,
+      "loss": 0.3654,
+      "step": 78
+    },
+    {
+      "epoch": 0.5448275862068965,
+      "grad_norm": 1.6028484461062982,
+      "learning_rate": 2.1490875972166394e-06,
+      "loss": 0.349,
+      "step": 79
+    },
+    {
+      "epoch": 0.5517241379310345,
+      "grad_norm": 1.8066616100345232,
+      "learning_rate": 2.0955450086180883e-06,
+      "loss": 0.3312,
+      "step": 80
+    },
+    {
+      "epoch": 0.5586206896551724,
+      "grad_norm": 1.6155019648712206,
+      "learning_rate": 2.0421922727953597e-06,
+      "loss": 0.353,
+      "step": 81
+    },
+    {
+      "epoch": 0.5655172413793104,
+      "grad_norm": 1.6885497227508972,
+      "learning_rate": 1.9890544337340882e-06,
+      "loss": 0.3487,
+      "step": 82
+    },
+    {
+      "epoch": 0.5724137931034483,
+      "grad_norm": 1.925745717035657,
+      "learning_rate": 1.936156434546515e-06,
+      "loss": 0.3388,
+      "step": 83
+    },
+    {
+      "epoch": 0.5793103448275863,
+      "grad_norm": 1.77461714799377,
+      "learning_rate": 1.8835231057630955e-06,
+      "loss": 0.3475,
+      "step": 84
+    },
+    {
+      "epoch": 0.5862068965517241,
+      "grad_norm": 1.6219762033918024,
+      "learning_rate": 1.8311791536769485e-06,
+      "loss": 0.3439,
+      "step": 85
+    },
+    {
+      "epoch": 0.593103448275862,
+      "grad_norm": 1.5607838994419105,
+      "learning_rate": 1.7791491487466234e-06,
+      "loss": 0.3238,
+      "step": 86
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 1.7014989682224375,
+      "learning_rate": 1.7274575140626318e-06,
+      "loss": 0.3493,
+      "step": 87
+    },
+    {
+      "epoch": 0.6068965517241379,
+      "grad_norm": 1.9290482180806454,
+      "learning_rate": 1.6761285138831493e-06,
+      "loss": 0.354,
+      "step": 88
+    },
+    {
+      "epoch": 0.6137931034482759,
+      "grad_norm": 1.7863234874905578,
+      "learning_rate": 1.625186242244279e-06,
+      "loss": 0.3388,
+      "step": 89
+    },
+    {
+      "epoch": 0.6206896551724138,
+      "grad_norm": 1.8038578805955316,
+      "learning_rate": 1.574654611650214e-06,
+      "loss": 0.3355,
+      "step": 90
+    },
+    {
+      "epoch": 0.6275862068965518,
+      "grad_norm": 1.6899830497679904,
+      "learning_rate": 1.5245573418486136e-06,
+      "loss": 0.3429,
+      "step": 91
+    },
+    {
+      "epoch": 0.6344827586206897,
+      "grad_norm": 1.7428197335464033,
+      "learning_rate": 1.4749179486964599e-06,
+      "loss": 0.3411,
+      "step": 92
+    },
+    {
+      "epoch": 0.6413793103448275,
+      "grad_norm": 1.664821668703834,
+      "learning_rate": 1.4257597331216211e-06,
+      "loss": 0.3335,
+      "step": 93
+    },
+    {
+      "epoch": 0.6482758620689655,
+      "grad_norm": 1.5588042268225262,
+      "learning_rate": 1.3771057701853034e-06,
+      "loss": 0.3444,
+      "step": 94
+    },
+    {
+      "epoch": 0.6551724137931034,
+      "grad_norm": 1.5929427164530576,
+      "learning_rate": 1.328978898250525e-06,
+      "loss": 0.3192,
+      "step": 95
+    },
+    {
+      "epoch": 0.6620689655172414,
+      "grad_norm": 1.550899495054241,
+      "learning_rate": 1.2814017082617025e-06,
+      "loss": 0.3383,
+      "step": 96
+    },
+    {
+      "epoch": 0.6689655172413793,
+      "grad_norm": 1.7049899538632087,
+      "learning_rate": 1.234396533140365e-06,
+      "loss": 0.3386,
+      "step": 97
+    },
+    {
+      "epoch": 0.6758620689655173,
+      "grad_norm": 1.6893577790955345,
+      "learning_rate": 1.187985437301999e-06,
+      "loss": 0.3277,
+      "step": 98
+    },
+    {
+      "epoch": 0.6827586206896552,
+      "grad_norm": 1.7137316188256908,
+      "learning_rate": 1.1421902062989178e-06,
+      "loss": 0.3325,
+      "step": 99
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "grad_norm": 1.517826756813662,
+      "learning_rate": 1.0970323365940443e-06,
+      "loss": 0.3312,
+      "step": 100
+    },
+    {
+      "epoch": 0.6896551724137931,
+      "eval_loss": 0.32950592041015625,
+      "eval_runtime": 0.9022,
+      "eval_samples_per_second": 2.217,
+      "eval_steps_per_second": 1.108,
+      "step": 100
+    },
+    {
+      "epoch": 0.696551724137931,
+      "grad_norm": 1.6901854989499794,
+      "learning_rate": 1.052533025470379e-06,
+      "loss": 0.3801,
+      "step": 101
+    },
+    {
+      "epoch": 0.7034482758620689,
+      "grad_norm": 1.5426130174399313,
+      "learning_rate": 1.0087131610809153e-06,
+      "loss": 0.338,
+      "step": 102
+    },
+    {
+      "epoch": 0.7103448275862069,
+      "grad_norm": 1.5732849334470578,
+      "learning_rate": 9.655933126436565e-07,
+      "loss": 0.3344,
+      "step": 103
+    },
+    {
+      "epoch": 0.7172413793103448,
+      "grad_norm": 1.4759695731759543,
+      "learning_rate": 9.231937207863459e-07,
+      "loss": 0.3299,
+      "step": 104
+    },
+    {
+      "epoch": 0.7241379310344828,
+      "grad_norm": 1.6672161821790785,
+      "learning_rate": 8.815342880454312e-07,
+      "loss": 0.3304,
+      "step": 105
+    },
+    {
+      "epoch": 0.7310344827586207,
+      "grad_norm": 1.4353459489905598,
+      "learning_rate": 8.406345695237394e-07,
+      "loss": 0.3617,
+      "step": 106
+    },
+    {
+      "epoch": 0.7379310344827587,
+      "grad_norm": 1.561435365406429,
+      "learning_rate": 8.005137637112303e-07,
+      "loss": 0.3087,
+      "step": 107
+    },
+    {
+      "epoch": 0.7448275862068966,
+      "grad_norm": 1.5581007718923978,
+      "learning_rate": 7.611907034731538e-07,
+      "loss": 0.3331,
+      "step": 108
+    },
+    {
+      "epoch": 0.7517241379310344,
+      "grad_norm": 1.6436378125831586,
+      "learning_rate": 7.226838472098239e-07,
+      "loss": 0.3075,
+      "step": 109
+    },
+    {
+      "epoch": 0.7586206896551724,
+      "grad_norm": 1.528759356164454,
+      "learning_rate": 6.850112701921735e-07,
+      "loss": 0.2988,
+      "step": 110
+    },
+    {
+      "epoch": 0.7655172413793103,
+      "grad_norm": 1.632160606943736,
+      "learning_rate": 6.481906560771525e-07,
+      "loss": 0.3385,
+      "step": 111
+    },
+    {
+      "epoch": 0.7724137931034483,
+      "grad_norm": 1.6601968785202443,
+      "learning_rate": 6.122392886069486e-07,
+      "loss": 0.329,
+      "step": 112
+    },
+    {
+      "epoch": 0.7793103448275862,
+      "grad_norm": 1.5710086244464967,
+      "learning_rate": 5.771740434959278e-07,
+      "loss": 0.3151,
+      "step": 113
+    },
+    {
+      "epoch": 0.7862068965517242,
+      "grad_norm": 1.539260970720398,
+      "learning_rate": 5.430113805091111e-07,
+      "loss": 0.3264,
+      "step": 114
+    },
+    {
+      "epoch": 0.7931034482758621,
+      "grad_norm": 1.397348441720902,
+      "learning_rate": 5.097673357358906e-07,
+      "loss": 0.347,
+      "step": 115
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 1.5082249093498752,
+      "learning_rate": 4.774575140626317e-07,
+      "loss": 0.3017,
+      "step": 116
+    },
+    {
+      "epoch": 0.8068965517241379,
+      "grad_norm": 1.5384938622913757,
+      "learning_rate": 4.4609708184767177e-07,
+      "loss": 0.3021,
+      "step": 117
+    },
+    {
+      "epoch": 0.8137931034482758,
+      "grad_norm": 1.527752357649668,
+      "learning_rate": 4.1570075980217503e-07,
+      "loss": 0.3223,
+      "step": 118
+    },
+    {
+      "epoch": 0.8206896551724138,
+      "grad_norm": 1.5677542978180121,
+      "learning_rate": 3.862828160801707e-07,
+      "loss": 0.2995,
+      "step": 119
+    },
+    {
+      "epoch": 0.8275862068965517,
+      "grad_norm": 1.5074886497463051,
+      "learning_rate": 3.578570595810274e-07,
+      "loss": 0.3264,
+      "step": 120
+    },
+    {
+      "epoch": 0.8344827586206897,
+      "grad_norm": 1.4518905236690687,
+      "learning_rate": 3.304368334674965e-07,
+      "loss": 0.3056,
+      "step": 121
+    },
+    {
+      "epoch": 0.8413793103448276,
+      "grad_norm": 1.4669883513825657,
+      "learning_rate": 3.040350089023844e-07,
+      "loss": 0.3177,
+      "step": 122
+    },
+    {
+      "epoch": 0.8482758620689655,
+      "grad_norm": 1.464969848523391,
+      "learning_rate": 2.786639790067719e-07,
+      "loss": 0.2999,
+      "step": 123
+    },
+    {
+      "epoch": 0.8551724137931035,
+      "grad_norm": 1.4530128650793055,
+      "learning_rate": 2.543356530426394e-07,
+      "loss": 0.3006,
+      "step": 124
+    },
+    {
+      "epoch": 0.8620689655172413,
+      "grad_norm": 1.4469356462257426,
+      "learning_rate": 2.3106145082260777e-07,
+      "loss": 0.2969,
+      "step": 125
+    },
+    {
+      "epoch": 0.8689655172413793,
+      "grad_norm": 1.484634295583908,
+      "learning_rate": 2.0885229734943501e-07,
+      "loss": 0.3116,
+      "step": 126
+    },
+    {
+      "epoch": 0.8758620689655172,
+      "grad_norm": 1.453131879007429,
+      "learning_rate": 1.8771861768777794e-07,
+      "loss": 0.3232,
+      "step": 127
+    },
+    {
+      "epoch": 0.8827586206896552,
+      "grad_norm": 1.4161021963404912,
+      "learning_rate": 1.67670332070623e-07,
+      "loss": 0.3326,
+      "step": 128
+    },
+    {
+      "epoch": 0.8896551724137931,
+      "grad_norm": 1.4058622653592632,
+      "learning_rate": 1.487168512426901e-07,
+      "loss": 0.3294,
+      "step": 129
+    },
+    {
+      "epoch": 0.896551724137931,
+      "grad_norm": 1.4690807219077968,
+      "learning_rate": 1.3086707204299415e-07,
+      "loss": 0.3354,
+      "step": 130
+    },
+    {
+      "epoch": 0.903448275862069,
+      "grad_norm": 1.616265393129677,
+      "learning_rate": 1.1412937322862971e-07,
+      "loss": 0.3252,
+      "step": 131
+    },
+    {
+      "epoch": 0.9103448275862069,
+      "grad_norm": 1.5728258584532129,
+      "learning_rate": 9.851161154175337e-08,
+      "loss": 0.306,
+      "step": 132
+    },
+    {
+      "epoch": 0.9172413793103448,
+      "grad_norm": 1.5204457230720907,
+      "learning_rate": 8.402111802159413e-08,
+      "loss": 0.3189,
+      "step": 133
+    },
+    {
+      "epoch": 0.9241379310344827,
+      "grad_norm": 1.4200900255728217,
+      "learning_rate": 7.06646945632361e-08,
+      "loss": 0.3147,
+      "step": 134
+    },
+    {
+      "epoch": 0.9310344827586207,
+      "grad_norm": 1.5420106297173888,
+      "learning_rate": 5.844861072478336e-08,
+      "loss": 0.3334,
+      "step": 135
+    },
+    {
+      "epoch": 0.9379310344827586,
+      "grad_norm": 1.469631099877013,
+      "learning_rate": 4.7378600784402095e-08,
+      "loss": 0.3315,
+      "step": 136
+    },
+    {
+      "epoch": 0.9448275862068966,
+      "grad_norm": 1.4029575813070734,
+      "learning_rate": 3.745986104862903e-08,
+      "loss": 0.3082,
+      "step": 137
+    },
+    {
+      "epoch": 0.9517241379310345,
+      "grad_norm": 1.4157363425093275,
+      "learning_rate": 2.869704741320478e-08,
+      "loss": 0.3134,
+      "step": 138
+    },
+    {
+      "epoch": 0.9586206896551724,
+      "grad_norm": 1.5622557979711562,
+      "learning_rate": 2.1094273177576508e-08,
+      "loss": 0.3398,
+      "step": 139
+    },
+    {
+      "epoch": 0.9655172413793104,
+      "grad_norm": 1.52108359896788,
+      "learning_rate": 1.4655107114101008e-08,
+      "loss": 0.3254,
+      "step": 140
+    },
+    {
+      "epoch": 0.9724137931034482,
+      "grad_norm": 1.5214323989901455,
+      "learning_rate": 9.382571792846962e-09,
+      "loss": 0.3033,
+      "step": 141
+    },
+    {
+      "epoch": 0.9793103448275862,
+      "grad_norm": 1.516641370375961,
+      "learning_rate": 5.279142162789019e-09,
+      "loss": 0.3386,
+      "step": 142
+    },
+    {
+      "epoch": 0.9862068965517241,
+      "grad_norm": 1.5535203911563618,
+      "learning_rate": 2.34674439005822e-09,
+      "loss": 0.3121,
+      "step": 143
+    },
+    {
+      "epoch": 0.993103448275862,
+      "grad_norm": 1.4979034235499458,
+      "learning_rate": 5.86754953789681e-10,
+      "loss": 0.3061,
+      "step": 144
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.524689672236255,
+      "learning_rate": 0.0,
+      "loss": 0.2844,
+      "step": 145
+    },
+    {
+      "epoch": 1.0,
+      "step": 145,
+      "total_flos": 27838218240000.0,
+      "train_loss": 0.41041072442613796,
+      "train_runtime": 554.2459,
+      "train_samples_per_second": 2.089,
+      "train_steps_per_second": 0.262
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 145,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 27838218240000.0,
+  "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 sha256:197c0ec05206cd860c4cfc62e5e5a0352df2c4f0a714c5dc4be83ead9f7944f0
+size 7160