Upload folder using huggingface_hub

.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 +1,58 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-1.5B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft_code
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# sft_code
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct) on the asynchow_python_fixed dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- gradient_accumulation_steps: 8
+- total_train_batch_size: 8
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 2.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.6
+- Pytorch 2.11.0+cu130
+- Datasets 4.0.0
+- Tokenizers 0.22.2

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 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.153078769590272e+16,
+    "train_loss": 0.266781858580057,
+    "train_runtime": 425.4095,
+    "train_samples_per_second": 6.455,
+    "train_steps_per_second": 0.809
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}
+    {%- endif %}
+    {{- "\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>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\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" }}
+{%- else %}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0]['content'] + '<|im_end|>\n' }}
+    {%- else %}
+        {{- '<|im_start|>system\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- for message in messages %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) or (message.role == "assistant" and not message.tool_calls) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {{- '<|im_start|>' + message.role }}
+        {%- if message.content %}
+            {{- '\n' + message.content }}
+        {%- endif %}
+        {%- for tool_call in message.tool_calls %}
+            {%- if tool_call.function is defined %}
+                {%- set tool_call = tool_call.function %}
+            {%- endif %}
+            {{- '\n<tool_call>\n{"name": "' }}
+            {{- tool_call.name }}
+            {{- '", "arguments": ' }}
+            {{- tool_call.arguments | tojson }}
+            {{- '}\n</tool_call>' }}
+        {%- endfor %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+{%- endif %}

config.json

@@ -0,0 +1,58 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "dtype": "float32",
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "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": "4.57.6"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f2737997899e5f257e64b3d743963b331a95f4b6e0d009cfe3f7dc04e442a9b
+size 4996670464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cfb9d8ecaf915f669c0ee40fdadd8bf24b4d29efa07f012adc75aac7097a7403
+size 1178224960

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_parameters": 1543714304,
+    "total_size": 6174857216
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.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,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.0,
+    "total_flos": 1.153078769590272e+16,
+    "train_loss": 0.266781858580057,
+    "train_runtime": 425.4095,
+    "train_samples_per_second": 6.455,
+    "train_steps_per_second": 0.809
+}

trainer_log.jsonl

@@ -0,0 +1,69 @@
+{"current_steps": 5, "total_steps": 344, "loss": 0.8279, "lr": 1.142857142857143e-06, "epoch": 0.029133284777858703, "percentage": 1.45, "elapsed_time": "0:00:06", "remaining_time": "0:07:38"}
+{"current_steps": 10, "total_steps": 344, "loss": 0.6482, "lr": 2.571428571428571e-06, "epoch": 0.05826656955571741, "percentage": 2.91, "elapsed_time": "0:00:12", "remaining_time": "0:07:08"}
+{"current_steps": 15, "total_steps": 344, "loss": 0.486, "lr": 4.000000000000001e-06, "epoch": 0.08739985433357611, "percentage": 4.36, "elapsed_time": "0:00:18", "remaining_time": "0:06:53"}
+{"current_steps": 20, "total_steps": 344, "loss": 0.3979, "lr": 5.428571428571429e-06, "epoch": 0.11653313911143481, "percentage": 5.81, "elapsed_time": "0:00:24", "remaining_time": "0:06:44"}
+{"current_steps": 25, "total_steps": 344, "loss": 0.3618, "lr": 6.857142857142858e-06, "epoch": 0.14566642388929352, "percentage": 7.27, "elapsed_time": "0:00:31", "remaining_time": "0:06:37"}
+{"current_steps": 30, "total_steps": 344, "loss": 0.4581, "lr": 8.285714285714287e-06, "epoch": 0.17479970866715222, "percentage": 8.72, "elapsed_time": "0:00:37", "remaining_time": "0:06:29"}
+{"current_steps": 35, "total_steps": 344, "loss": 0.3754, "lr": 9.714285714285715e-06, "epoch": 0.20393299344501092, "percentage": 10.17, "elapsed_time": "0:00:43", "remaining_time": "0:06:23"}
+{"current_steps": 40, "total_steps": 344, "loss": 0.3399, "lr": 9.995865881497621e-06, "epoch": 0.23306627822286963, "percentage": 11.63, "elapsed_time": "0:00:49", "remaining_time": "0:06:16"}
+{"current_steps": 45, "total_steps": 344, "loss": 0.3636, "lr": 9.979082741033047e-06, "epoch": 0.26219956300072833, "percentage": 13.08, "elapsed_time": "0:00:55", "remaining_time": "0:06:10"}
+{"current_steps": 50, "total_steps": 344, "loss": 0.2615, "lr": 9.949435524132245e-06, "epoch": 0.29133284777858703, "percentage": 14.53, "elapsed_time": "0:01:01", "remaining_time": "0:06:03"}
+{"current_steps": 55, "total_steps": 344, "loss": 0.3713, "lr": 9.907000828049001e-06, "epoch": 0.32046613255644574, "percentage": 15.99, "elapsed_time": "0:01:07", "remaining_time": "0:05:57"}
+{"current_steps": 60, "total_steps": 344, "loss": 0.3645, "lr": 9.851888288072053e-06, "epoch": 0.34959941733430444, "percentage": 17.44, "elapsed_time": "0:01:14", "remaining_time": "0:05:50"}
+{"current_steps": 65, "total_steps": 344, "loss": 0.3549, "lr": 9.784240294268756e-06, "epoch": 0.37873270211216314, "percentage": 18.9, "elapsed_time": "0:01:20", "remaining_time": "0:05:43"}
+{"current_steps": 70, "total_steps": 344, "loss": 0.3537, "lr": 9.704231623602721e-06, "epoch": 0.40786598689002185, "percentage": 20.35, "elapsed_time": "0:01:26", "remaining_time": "0:05:37"}
+{"current_steps": 75, "total_steps": 344, "loss": 0.3409, "lr": 9.612068988375898e-06, "epoch": 0.43699927166788055, "percentage": 21.8, "elapsed_time": "0:01:32", "remaining_time": "0:05:30"}
+{"current_steps": 80, "total_steps": 344, "loss": 0.3313, "lr": 9.507990502161769e-06, "epoch": 0.46613255644573925, "percentage": 23.26, "elapsed_time": "0:01:38", "remaining_time": "0:05:24"}
+{"current_steps": 85, "total_steps": 344, "loss": 0.3451, "lr": 9.392265064609455e-06, "epoch": 0.49526584122359796, "percentage": 24.71, "elapsed_time": "0:01:44", "remaining_time": "0:05:17"}
+{"current_steps": 90, "total_steps": 344, "loss": 0.2925, "lr": 9.26519166670821e-06, "epoch": 0.5243991260014567, "percentage": 26.16, "elapsed_time": "0:01:50", "remaining_time": "0:05:11"}
+{"current_steps": 95, "total_steps": 344, "loss": 0.255, "lr": 9.127098618307177e-06, "epoch": 0.5535324107793154, "percentage": 27.62, "elapsed_time": "0:01:56", "remaining_time": "0:05:05"}
+{"current_steps": 100, "total_steps": 344, "loss": 0.3099, "lr": 8.978342699886289e-06, "epoch": 0.5826656955571741, "percentage": 29.07, "elapsed_time": "0:02:02", "remaining_time": "0:04:58"}
+{"current_steps": 105, "total_steps": 344, "loss": 0.2269, "lr": 8.819308240769726e-06, "epoch": 0.6117989803350328, "percentage": 30.52, "elapsed_time": "0:02:08", "remaining_time": "0:04:52"}
+{"current_steps": 110, "total_steps": 344, "loss": 0.2653, "lr": 8.650406126163553e-06, "epoch": 0.6409322651128915, "percentage": 31.98, "elapsed_time": "0:02:14", "remaining_time": "0:04:46"}
+{"current_steps": 115, "total_steps": 344, "loss": 0.269, "lr": 8.472072735582942e-06, "epoch": 0.6700655498907502, "percentage": 33.43, "elapsed_time": "0:02:20", "remaining_time": "0:04:40"}
+{"current_steps": 120, "total_steps": 344, "loss": 0.4095, "lr": 8.284768815411693e-06, "epoch": 0.6991988346686089, "percentage": 34.88, "elapsed_time": "0:02:26", "remaining_time": "0:04:34"}
+{"current_steps": 125, "total_steps": 344, "loss": 0.2782, "lr": 8.088978288506923e-06, "epoch": 0.7283321194464676, "percentage": 36.34, "elapsed_time": "0:02:33", "remaining_time": "0:04:28"}
+{"current_steps": 130, "total_steps": 344, "loss": 0.3129, "lr": 7.885207003924498e-06, "epoch": 0.7574654042243263, "percentage": 37.79, "elapsed_time": "0:02:39", "remaining_time": "0:04:22"}
+{"current_steps": 135, "total_steps": 344, "loss": 0.3099, "lr": 7.673981429995372e-06, "epoch": 0.786598689002185, "percentage": 39.24, "elapsed_time": "0:02:45", "remaining_time": "0:04:16"}
+{"current_steps": 140, "total_steps": 344, "loss": 0.3116, "lr": 7.455847294129519e-06, "epoch": 0.8157319737800437, "percentage": 40.7, "elapsed_time": "0:02:51", "remaining_time": "0:04:09"}
+{"current_steps": 145, "total_steps": 344, "loss": 0.3163, "lr": 7.23136817286163e-06, "epoch": 0.8448652585579024, "percentage": 42.15, "elapsed_time": "0:02:57", "remaining_time": "0:04:03"}
+{"current_steps": 150, "total_steps": 344, "loss": 0.2765, "lr": 7.00112403578139e-06, "epoch": 0.8739985433357611, "percentage": 43.6, "elapsed_time": "0:03:03", "remaining_time": "0:03:57"}
+{"current_steps": 155, "total_steps": 344, "loss": 0.2822, "lr": 6.765709747110274e-06, "epoch": 0.9031318281136198, "percentage": 45.06, "elapsed_time": "0:03:09", "remaining_time": "0:03:51"}
+{"current_steps": 160, "total_steps": 344, "loss": 0.2809, "lr": 6.525733528796207e-06, "epoch": 0.9322651128914785, "percentage": 46.51, "elapsed_time": "0:03:16", "remaining_time": "0:03:45"}
+{"current_steps": 165, "total_steps": 344, "loss": 0.3121, "lr": 6.281815389096903e-06, "epoch": 0.9613983976693372, "percentage": 47.97, "elapsed_time": "0:03:22", "remaining_time": "0:03:39"}
+{"current_steps": 170, "total_steps": 344, "loss": 0.2421, "lr": 6.034585520711792e-06, "epoch": 0.9905316824471959, "percentage": 49.42, "elapsed_time": "0:03:28", "remaining_time": "0:03:33"}
+{"current_steps": 175, "total_steps": 344, "loss": 0.2224, "lr": 5.7846826726012076e-06, "epoch": 1.0174799708667153, "percentage": 50.87, "elapsed_time": "0:03:34", "remaining_time": "0:03:27"}
+{"current_steps": 180, "total_steps": 344, "loss": 0.1583, "lr": 5.532752499699381e-06, "epoch": 1.046613255644574, "percentage": 52.33, "elapsed_time": "0:03:40", "remaining_time": "0:03:21"}
+{"current_steps": 185, "total_steps": 344, "loss": 0.1885, "lr": 5.279445894785042e-06, "epoch": 1.0757465404224327, "percentage": 53.78, "elapsed_time": "0:03:46", "remaining_time": "0:03:15"}
+{"current_steps": 190, "total_steps": 344, "loss": 0.1929, "lr": 5.025417306819348e-06, "epoch": 1.1048798252002914, "percentage": 55.23, "elapsed_time": "0:03:53", "remaining_time": "0:03:08"}
+{"current_steps": 195, "total_steps": 344, "loss": 0.2046, "lr": 4.771323050096028e-06, "epoch": 1.13401310997815, "percentage": 56.69, "elapsed_time": "0:03:59", "remaining_time": "0:03:02"}
+{"current_steps": 200, "total_steps": 344, "loss": 0.2059, "lr": 4.5178196085721675e-06, "epoch": 1.1631463947560088, "percentage": 58.14, "elapsed_time": "0:04:04", "remaining_time": "0:02:56"}
+{"current_steps": 205, "total_steps": 344, "loss": 0.2045, "lr": 4.265561939760671e-06, "epoch": 1.1922796795338675, "percentage": 59.59, "elapsed_time": "0:04:10", "remaining_time": "0:02:49"}
+{"current_steps": 210, "total_steps": 344, "loss": 0.2349, "lr": 4.015201782566471e-06, "epoch": 1.2214129643117262, "percentage": 61.05, "elapsed_time": "0:04:15", "remaining_time": "0:02:43"}
+{"current_steps": 215, "total_steps": 344, "loss": 0.1986, "lr": 3.7673859734384153e-06, "epoch": 1.250546249089585, "percentage": 62.5, "elapsed_time": "0:04:21", "remaining_time": "0:02:36"}
+{"current_steps": 220, "total_steps": 344, "loss": 0.1424, "lr": 3.5227547751872548e-06, "epoch": 1.2796795338674436, "percentage": 63.95, "elapsed_time": "0:04:26", "remaining_time": "0:02:30"}
+{"current_steps": 225, "total_steps": 344, "loss": 0.1908, "lr": 3.2819402227874364e-06, "epoch": 1.3088128186453023, "percentage": 65.41, "elapsed_time": "0:04:32", "remaining_time": "0:02:24"}
+{"current_steps": 230, "total_steps": 344, "loss": 0.2572, "lr": 3.0455644904365234e-06, "epoch": 1.337946103423161, "percentage": 66.86, "elapsed_time": "0:04:37", "remaining_time": "0:02:17"}
+{"current_steps": 235, "total_steps": 344, "loss": 0.2184, "lr": 2.8142382840911747e-06, "epoch": 1.3670793882010197, "percentage": 68.31, "elapsed_time": "0:04:43", "remaining_time": "0:02:11"}
+{"current_steps": 240, "total_steps": 344, "loss": 0.2433, "lr": 2.588559263632719e-06, "epoch": 1.3962126729788784, "percentage": 69.77, "elapsed_time": "0:04:48", "remaining_time": "0:02:05"}
+{"current_steps": 245, "total_steps": 344, "loss": 0.177, "lr": 2.3691104987388923e-06, "epoch": 1.4253459577567371, "percentage": 71.22, "elapsed_time": "0:04:54", "remaining_time": "0:01:58"}
+{"current_steps": 250, "total_steps": 344, "loss": 0.2075, "lr": 2.156458962451164e-06, "epoch": 1.4544792425345958, "percentage": 72.67, "elapsed_time": "0:04:59", "remaining_time": "0:01:52"}
+{"current_steps": 255, "total_steps": 344, "loss": 0.1725, "lr": 1.9511540663297284e-06, "epoch": 1.4836125273124545, "percentage": 74.13, "elapsed_time": "0:05:16", "remaining_time": "0:01:50"}
+{"current_steps": 260, "total_steps": 344, "loss": 0.1353, "lr": 1.7537262409807476e-06, "epoch": 1.5127458120903132, "percentage": 75.58, "elapsed_time": "0:05:21", "remaining_time": "0:01:43"}
+{"current_steps": 265, "total_steps": 344, "loss": 0.182, "lr": 1.5646855656232296e-06, "epoch": 1.541879096868172, "percentage": 77.03, "elapsed_time": "0:05:27", "remaining_time": "0:01:37"}
+{"current_steps": 270, "total_steps": 344, "loss": 0.1732, "lr": 1.3845204502362442e-06, "epoch": 1.5710123816460306, "percentage": 78.49, "elapsed_time": "0:05:32", "remaining_time": "0:01:31"}
+{"current_steps": 275, "total_steps": 344, "loss": 0.1919, "lr": 1.2136963736913117e-06, "epoch": 1.6001456664238893, "percentage": 79.94, "elapsed_time": "0:05:38", "remaining_time": "0:01:24"}
+{"current_steps": 280, "total_steps": 344, "loss": 0.1666, "lr": 1.0526546811301203e-06, "epoch": 1.629278951201748, "percentage": 81.4, "elapsed_time": "0:05:43", "remaining_time": "0:01:18"}
+{"current_steps": 285, "total_steps": 344, "loss": 0.1412, "lr": 9.018114436947373e-07, "epoch": 1.6584122359796067, "percentage": 82.85, "elapsed_time": "0:05:49", "remaining_time": "0:01:12"}
+{"current_steps": 290, "total_steps": 344, "loss": 0.1833, "lr": 7.615563835563339e-07, "epoch": 1.6875455207574654, "percentage": 84.3, "elapsed_time": "0:05:54", "remaining_time": "0:01:06"}
+{"current_steps": 295, "total_steps": 344, "loss": 0.1167, "lr": 6.322518670197142e-07, "epoch": 1.7166788055353241, "percentage": 85.76, "elapsed_time": "0:05:59", "remaining_time": "0:00:59"}
+{"current_steps": 300, "total_steps": 344, "loss": 0.1117, "lr": 5.1423196830513e-07, "epoch": 1.7458120903131829, "percentage": 87.21, "elapsed_time": "0:06:05", "remaining_time": "0:00:53"}
+{"current_steps": 305, "total_steps": 344, "loss": 0.2101, "lr": 4.078016064261847e-07, "epoch": 1.7749453750910416, "percentage": 88.66, "elapsed_time": "0:06:10", "remaining_time": "0:00:47"}
+{"current_steps": 310, "total_steps": 344, "loss": 0.1407, "lr": 3.1323575739383716e-07, "epoch": 1.8040786598689003, "percentage": 90.12, "elapsed_time": "0:06:16", "remaining_time": "0:00:41"}
+{"current_steps": 315, "total_steps": 344, "loss": 0.1481, "lr": 2.307787437818365e-07, "epoch": 1.833211944646759, "percentage": 91.57, "elapsed_time": "0:06:21", "remaining_time": "0:00:35"}
+{"current_steps": 320, "total_steps": 344, "loss": 0.2063, "lr": 1.6064360348912567e-07, "epoch": 1.8623452294246177, "percentage": 93.02, "elapsed_time": "0:06:27", "remaining_time": "0:00:29"}
+{"current_steps": 325, "total_steps": 344, "loss": 0.2186, "lr": 1.0301153933006126e-07, "epoch": 1.8914785142024764, "percentage": 94.48, "elapsed_time": "0:06:32", "remaining_time": "0:00:22"}
+{"current_steps": 330, "total_steps": 344, "loss": 0.1676, "lr": 5.803145087451945e-08, "epoch": 1.920611798980335, "percentage": 95.93, "elapsed_time": "0:06:38", "remaining_time": "0:00:16"}
+{"current_steps": 335, "total_steps": 344, "loss": 0.1967, "lr": 2.581954974743117e-08, "epoch": 1.9497450837581938, "percentage": 97.38, "elapsed_time": "0:06:43", "remaining_time": "0:00:10"}
+{"current_steps": 340, "total_steps": 344, "loss": 0.1841, "lr": 6.4590593816676875e-09, "epoch": 1.9788783685360525, "percentage": 98.84, "elapsed_time": "0:06:49", "remaining_time": "0:00:04"}
+{"current_steps": 344, "total_steps": 344, "epoch": 2.0, "percentage": 100.0, "elapsed_time": "0:07:05", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,519 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 344,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.029133284777858703,
+      "grad_norm": 73.69664001464844,
+      "learning_rate": 1.142857142857143e-06,
+      "loss": 0.8279,
+      "step": 5
+    },
+    {
+      "epoch": 0.05826656955571741,
+      "grad_norm": 18.089183807373047,
+      "learning_rate": 2.571428571428571e-06,
+      "loss": 0.6482,
+      "step": 10
+    },
+    {
+      "epoch": 0.08739985433357611,
+      "grad_norm": 13.27970027923584,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.486,
+      "step": 15
+    },
+    {
+      "epoch": 0.11653313911143481,
+      "grad_norm": 15.923905372619629,
+      "learning_rate": 5.428571428571429e-06,
+      "loss": 0.3979,
+      "step": 20
+    },
+    {
+      "epoch": 0.14566642388929352,
+      "grad_norm": 8.179045677185059,
+      "learning_rate": 6.857142857142858e-06,
+      "loss": 0.3618,
+      "step": 25
+    },
+    {
+      "epoch": 0.17479970866715222,
+      "grad_norm": 14.475104331970215,
+      "learning_rate": 8.285714285714287e-06,
+      "loss": 0.4581,
+      "step": 30
+    },
+    {
+      "epoch": 0.20393299344501092,
+      "grad_norm": 7.016964435577393,
+      "learning_rate": 9.714285714285715e-06,
+      "loss": 0.3754,
+      "step": 35
+    },
+    {
+      "epoch": 0.23306627822286963,
+      "grad_norm": 11.657523155212402,
+      "learning_rate": 9.995865881497621e-06,
+      "loss": 0.3399,
+      "step": 40
+    },
+    {
+      "epoch": 0.26219956300072833,
+      "grad_norm": 7.404115200042725,
+      "learning_rate": 9.979082741033047e-06,
+      "loss": 0.3636,
+      "step": 45
+    },
+    {
+      "epoch": 0.29133284777858703,
+      "grad_norm": 6.842041015625,
+      "learning_rate": 9.949435524132245e-06,
+      "loss": 0.2615,
+      "step": 50
+    },
+    {
+      "epoch": 0.32046613255644574,
+      "grad_norm": 11.180706977844238,
+      "learning_rate": 9.907000828049001e-06,
+      "loss": 0.3713,
+      "step": 55
+    },
+    {
+      "epoch": 0.34959941733430444,
+      "grad_norm": 7.965044021606445,
+      "learning_rate": 9.851888288072053e-06,
+      "loss": 0.3645,
+      "step": 60
+    },
+    {
+      "epoch": 0.37873270211216314,
+      "grad_norm": 5.142039775848389,
+      "learning_rate": 9.784240294268756e-06,
+      "loss": 0.3549,
+      "step": 65
+    },
+    {
+      "epoch": 0.40786598689002185,
+      "grad_norm": 9.566123008728027,
+      "learning_rate": 9.704231623602721e-06,
+      "loss": 0.3537,
+      "step": 70
+    },
+    {
+      "epoch": 0.43699927166788055,
+      "grad_norm": 7.709802150726318,
+      "learning_rate": 9.612068988375898e-06,
+      "loss": 0.3409,
+      "step": 75
+    },
+    {
+      "epoch": 0.46613255644573925,
+      "grad_norm": 7.769692420959473,
+      "learning_rate": 9.507990502161769e-06,
+      "loss": 0.3313,
+      "step": 80
+    },
+    {
+      "epoch": 0.49526584122359796,
+      "grad_norm": 6.162425994873047,
+      "learning_rate": 9.392265064609455e-06,
+      "loss": 0.3451,
+      "step": 85
+    },
+    {
+      "epoch": 0.5243991260014567,
+      "grad_norm": 5.42238187789917,
+      "learning_rate": 9.26519166670821e-06,
+      "loss": 0.2925,
+      "step": 90
+    },
+    {
+      "epoch": 0.5535324107793154,
+      "grad_norm": 6.669449806213379,
+      "learning_rate": 9.127098618307177e-06,
+      "loss": 0.255,
+      "step": 95
+    },
+    {
+      "epoch": 0.5826656955571741,
+      "grad_norm": 8.019908905029297,
+      "learning_rate": 8.978342699886289e-06,
+      "loss": 0.3099,
+      "step": 100
+    },
+    {
+      "epoch": 0.6117989803350328,
+      "grad_norm": 3.589531660079956,
+      "learning_rate": 8.819308240769726e-06,
+      "loss": 0.2269,
+      "step": 105
+    },
+    {
+      "epoch": 0.6409322651128915,
+      "grad_norm": 4.610569000244141,
+      "learning_rate": 8.650406126163553e-06,
+      "loss": 0.2653,
+      "step": 110
+    },
+    {
+      "epoch": 0.6700655498907502,
+      "grad_norm": 6.664720058441162,
+      "learning_rate": 8.472072735582942e-06,
+      "loss": 0.269,
+      "step": 115
+    },
+    {
+      "epoch": 0.6991988346686089,
+      "grad_norm": 16.797792434692383,
+      "learning_rate": 8.284768815411693e-06,
+      "loss": 0.4095,
+      "step": 120
+    },
+    {
+      "epoch": 0.7283321194464676,
+      "grad_norm": 5.306704521179199,
+      "learning_rate": 8.088978288506923e-06,
+      "loss": 0.2782,
+      "step": 125
+    },
+    {
+      "epoch": 0.7574654042243263,
+      "grad_norm": 5.628018856048584,
+      "learning_rate": 7.885207003924498e-06,
+      "loss": 0.3129,
+      "step": 130
+    },
+    {
+      "epoch": 0.786598689002185,
+      "grad_norm": 5.6005449295043945,
+      "learning_rate": 7.673981429995372e-06,
+      "loss": 0.3099,
+      "step": 135
+    },
+    {
+      "epoch": 0.8157319737800437,
+      "grad_norm": 4.009358882904053,
+      "learning_rate": 7.455847294129519e-06,
+      "loss": 0.3116,
+      "step": 140
+    },
+    {
+      "epoch": 0.8448652585579024,
+      "grad_norm": 5.827634811401367,
+      "learning_rate": 7.23136817286163e-06,
+      "loss": 0.3163,
+      "step": 145
+    },
+    {
+      "epoch": 0.8739985433357611,
+      "grad_norm": 4.57042121887207,
+      "learning_rate": 7.00112403578139e-06,
+      "loss": 0.2765,
+      "step": 150
+    },
+    {
+      "epoch": 0.9031318281136198,
+      "grad_norm": 6.091691493988037,
+      "learning_rate": 6.765709747110274e-06,
+      "loss": 0.2822,
+      "step": 155
+    },
+    {
+      "epoch": 0.9322651128914785,
+      "grad_norm": 8.162725448608398,
+      "learning_rate": 6.525733528796207e-06,
+      "loss": 0.2809,
+      "step": 160
+    },
+    {
+      "epoch": 0.9613983976693372,
+      "grad_norm": 11.629427909851074,
+      "learning_rate": 6.281815389096903e-06,
+      "loss": 0.3121,
+      "step": 165
+    },
+    {
+      "epoch": 0.9905316824471959,
+      "grad_norm": 6.634247303009033,
+      "learning_rate": 6.034585520711792e-06,
+      "loss": 0.2421,
+      "step": 170
+    },
+    {
+      "epoch": 1.0174799708667153,
+      "grad_norm": 5.846076488494873,
+      "learning_rate": 5.7846826726012076e-06,
+      "loss": 0.2224,
+      "step": 175
+    },
+    {
+      "epoch": 1.046613255644574,
+      "grad_norm": 3.2555429935455322,
+      "learning_rate": 5.532752499699381e-06,
+      "loss": 0.1583,
+      "step": 180
+    },
+    {
+      "epoch": 1.0757465404224327,
+      "grad_norm": 6.249210834503174,
+      "learning_rate": 5.279445894785042e-06,
+      "loss": 0.1885,
+      "step": 185
+    },
+    {
+      "epoch": 1.1048798252002914,
+      "grad_norm": 4.369631290435791,
+      "learning_rate": 5.025417306819348e-06,
+      "loss": 0.1929,
+      "step": 190
+    },
+    {
+      "epoch": 1.13401310997815,
+      "grad_norm": 7.5276899337768555,
+      "learning_rate": 4.771323050096028e-06,
+      "loss": 0.2046,
+      "step": 195
+    },
+    {
+      "epoch": 1.1631463947560088,
+      "grad_norm": 4.717685699462891,
+      "learning_rate": 4.5178196085721675e-06,
+      "loss": 0.2059,
+      "step": 200
+    },
+    {
+      "epoch": 1.1922796795338675,
+      "grad_norm": 7.297747611999512,
+      "learning_rate": 4.265561939760671e-06,
+      "loss": 0.2045,
+      "step": 205
+    },
+    {
+      "epoch": 1.2214129643117262,
+      "grad_norm": 8.043347358703613,
+      "learning_rate": 4.015201782566471e-06,
+      "loss": 0.2349,
+      "step": 210
+    },
+    {
+      "epoch": 1.250546249089585,
+      "grad_norm": 4.949600696563721,
+      "learning_rate": 3.7673859734384153e-06,
+      "loss": 0.1986,
+      "step": 215
+    },
+    {
+      "epoch": 1.2796795338674436,
+      "grad_norm": 8.595296859741211,
+      "learning_rate": 3.5227547751872548e-06,
+      "loss": 0.1424,
+      "step": 220
+    },
+    {
+      "epoch": 1.3088128186453023,
+      "grad_norm": 4.086767673492432,
+      "learning_rate": 3.2819402227874364e-06,
+      "loss": 0.1908,
+      "step": 225
+    },
+    {
+      "epoch": 1.337946103423161,
+      "grad_norm": 8.891705513000488,
+      "learning_rate": 3.0455644904365234e-06,
+      "loss": 0.2572,
+      "step": 230
+    },
+    {
+      "epoch": 1.3670793882010197,
+      "grad_norm": 7.054013252258301,
+      "learning_rate": 2.8142382840911747e-06,
+      "loss": 0.2184,
+      "step": 235
+    },
+    {
+      "epoch": 1.3962126729788784,
+      "grad_norm": 5.363378524780273,
+      "learning_rate": 2.588559263632719e-06,
+      "loss": 0.2433,
+      "step": 240
+    },
+    {
+      "epoch": 1.4253459577567371,
+      "grad_norm": 5.505529880523682,
+      "learning_rate": 2.3691104987388923e-06,
+      "loss": 0.177,
+      "step": 245
+    },
+    {
+      "epoch": 1.4544792425345958,
+      "grad_norm": 4.260989665985107,
+      "learning_rate": 2.156458962451164e-06,
+      "loss": 0.2075,
+      "step": 250
+    },
+    {
+      "epoch": 1.4836125273124545,
+      "grad_norm": 4.446367263793945,
+      "learning_rate": 1.9511540663297284e-06,
+      "loss": 0.1725,
+      "step": 255
+    },
+    {
+      "epoch": 1.5127458120903132,
+      "grad_norm": 3.823702812194824,
+      "learning_rate": 1.7537262409807476e-06,
+      "loss": 0.1353,
+      "step": 260
+    },
+    {
+      "epoch": 1.541879096868172,
+      "grad_norm": 4.295354843139648,
+      "learning_rate": 1.5646855656232296e-06,
+      "loss": 0.182,
+      "step": 265
+    },
+    {
+      "epoch": 1.5710123816460306,
+      "grad_norm": 7.048524856567383,
+      "learning_rate": 1.3845204502362442e-06,
+      "loss": 0.1732,
+      "step": 270
+    },
+    {
+      "epoch": 1.6001456664238893,
+      "grad_norm": 7.241790771484375,
+      "learning_rate": 1.2136963736913117e-06,
+      "loss": 0.1919,
+      "step": 275
+    },
+    {
+      "epoch": 1.629278951201748,
+      "grad_norm": 5.843298435211182,
+      "learning_rate": 1.0526546811301203e-06,
+      "loss": 0.1666,
+      "step": 280
+    },
+    {
+      "epoch": 1.6584122359796067,
+      "grad_norm": 4.440147399902344,
+      "learning_rate": 9.018114436947373e-07,
+      "loss": 0.1412,
+      "step": 285
+    },
+    {
+      "epoch": 1.6875455207574654,
+      "grad_norm": 5.858366966247559,
+      "learning_rate": 7.615563835563339e-07,
+      "loss": 0.1833,
+      "step": 290
+    },
+    {
+      "epoch": 1.7166788055353241,
+      "grad_norm": 7.964084148406982,
+      "learning_rate": 6.322518670197142e-07,
+      "loss": 0.1167,
+      "step": 295
+    },
+    {
+      "epoch": 1.7458120903131829,
+      "grad_norm": 4.816522598266602,
+      "learning_rate": 5.1423196830513e-07,
+      "loss": 0.1117,
+      "step": 300
+    },
+    {
+      "epoch": 1.7749453750910416,
+      "grad_norm": 4.06934928894043,
+      "learning_rate": 4.078016064261847e-07,
+      "loss": 0.2101,
+      "step": 305
+    },
+    {
+      "epoch": 1.8040786598689003,
+      "grad_norm": 5.113325595855713,
+      "learning_rate": 3.1323575739383716e-07,
+      "loss": 0.1407,
+      "step": 310
+    },
+    {
+      "epoch": 1.833211944646759,
+      "grad_norm": 5.883960247039795,
+      "learning_rate": 2.307787437818365e-07,
+      "loss": 0.1481,
+      "step": 315
+    },
+    {
+      "epoch": 1.8623452294246177,
+      "grad_norm": 3.5390496253967285,
+      "learning_rate": 1.6064360348912567e-07,
+      "loss": 0.2063,
+      "step": 320
+    },
+    {
+      "epoch": 1.8914785142024764,
+      "grad_norm": 6.701529026031494,
+      "learning_rate": 1.0301153933006126e-07,
+      "loss": 0.2186,
+      "step": 325
+    },
+    {
+      "epoch": 1.920611798980335,
+      "grad_norm": 5.152849197387695,
+      "learning_rate": 5.803145087451945e-08,
+      "loss": 0.1676,
+      "step": 330
+    },
+    {
+      "epoch": 1.9497450837581938,
+      "grad_norm": 6.510392665863037,
+      "learning_rate": 2.581954974743117e-08,
+      "loss": 0.1967,
+      "step": 335
+    },
+    {
+      "epoch": 1.9788783685360525,
+      "grad_norm": 6.947445392608643,
+      "learning_rate": 6.4590593816676875e-09,
+      "loss": 0.1841,
+      "step": 340
+    },
+    {
+      "epoch": 2.0,
+      "step": 344,
+      "total_flos": 1.153078769590272e+16,
+      "train_loss": 0.266781858580057,
+      "train_runtime": 425.4095,
+      "train_samples_per_second": 6.455,
+      "train_steps_per_second": 0.809
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 344,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.153078769590272e+16,
+  "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 sha256:4a20063fdcbea0ac58ecaa09f17d78de464c8912e5866fd011628c966bfb5997
+size 6417