初始化项目，由ModelHub XC社区提供模型

Model: sathiiiii/polyalign-qwen2.5-1.5b-en-sft
Source: Original Platform

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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/Qwen2.5-1.5B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: polyalign
+  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. -->
+
+# polyalign
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B](https://huggingface.co/Qwen/Qwen2.5-1.5B) on the polyalign_train dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.4072
+
+## 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: 2
+- eval_batch_size: 2
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 16
+- 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: 1.0
+- mixed_precision_training: Native AMP
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.57.1
+- Pytorch 2.11.0+rocm7.2
+- 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 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.4072046279907227,
+    "eval_runtime": 249.6497,
+    "eval_samples_per_second": 222.612,
+    "eval_steps_per_second": 13.915,
+    "total_flos": 1.591591112898773e+18,
+    "train_loss": 1.633884816748293,
+    "train_runtime": 12935.5693,
+    "train_samples_per_second": 45.179,
+    "train_steps_per_second": 0.706
+}

chat_template.jinja

@@ -0,0 +1,54 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0]['role'] == 'system' %}
+        {{- messages[0]['content'] }}
+    {%- else %}
+        {{- '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 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 +1,59 @@
+{
+  "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": 131072,
+  "max_window_layers": 28,
+  "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": "4.57.1",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 1.4072046279907227,
+    "eval_runtime": 249.6497,
+    "eval_samples_per_second": 222.612,
+    "eval_steps_per_second": 13.915
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_new_tokens": 2048,
+  "pad_token_id": 151643,
+  "transformers_version": "4.57.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ed15994002197c2fbfe1bfeb4c4743509b6a015bddff0dc07a0aa5d8dfbbda53
+size 4996670464

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e6b0739fad87a9e1f9885e19033b3d187d5e5ec9a6e2c6fe72f18318c8fcdc6
+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": 1.0,
+    "total_flos": 1.591591112898773e+18,
+    "train_loss": 1.633884816748293,
+    "train_runtime": 12935.5693,
+    "train_samples_per_second": 45.179,
+    "train_steps_per_second": 0.706
+}

trainer_log.jsonl

@@ -0,0 +1,92 @@
+{"current_steps": 100, "total_steps": 9132, "loss": 2.5966, "lr": 1.0831509846827136e-06, "epoch": 0.010950803515207929, "percentage": 1.1, "elapsed_time": "0:02:28", "remaining_time": "3:43:05"}
+{"current_steps": 200, "total_steps": 9132, "loss": 2.3125, "lr": 2.177242888402626e-06, "epoch": 0.021901607030415857, "percentage": 2.19, "elapsed_time": "0:04:48", "remaining_time": "3:34:49"}
+{"current_steps": 300, "total_steps": 9132, "loss": 2.1574, "lr": 3.2713347921225385e-06, "epoch": 0.03285241054562379, "percentage": 3.29, "elapsed_time": "0:07:09", "remaining_time": "3:30:57"}
+{"current_steps": 400, "total_steps": 9132, "loss": 1.9882, "lr": 4.365426695842451e-06, "epoch": 0.043803214060831715, "percentage": 4.38, "elapsed_time": "0:09:31", "remaining_time": "3:28:02"}
+{"current_steps": 500, "total_steps": 9132, "loss": 1.9221, "lr": 5.459518599562363e-06, "epoch": 0.05475401757603964, "percentage": 5.48, "elapsed_time": "0:11:52", "remaining_time": "3:25:04"}
+{"current_steps": 600, "total_steps": 9132, "loss": 1.9077, "lr": 6.553610503282276e-06, "epoch": 0.06570482109124758, "percentage": 6.57, "elapsed_time": "0:14:14", "remaining_time": "3:22:37"}
+{"current_steps": 700, "total_steps": 9132, "loss": 1.8748, "lr": 7.64770240700219e-06, "epoch": 0.0766556246064555, "percentage": 7.67, "elapsed_time": "0:16:34", "remaining_time": "3:19:36"}
+{"current_steps": 800, "total_steps": 9132, "loss": 1.88, "lr": 8.741794310722102e-06, "epoch": 0.08760642812166343, "percentage": 8.76, "elapsed_time": "0:18:55", "remaining_time": "3:17:10"}
+{"current_steps": 900, "total_steps": 9132, "loss": 1.8617, "lr": 9.835886214442013e-06, "epoch": 0.09855723163687136, "percentage": 9.86, "elapsed_time": "0:21:17", "remaining_time": "3:14:41"}
+{"current_steps": 1000, "total_steps": 9132, "loss": 1.8323, "lr": 9.997360588415263e-06, "epoch": 0.10950803515207928, "percentage": 10.95, "elapsed_time": "0:23:38", "remaining_time": "3:12:17"}
+{"current_steps": 1100, "total_steps": 9132, "loss": 1.8238, "lr": 9.987501154068591e-06, "epoch": 0.12045883866728721, "percentage": 12.05, "elapsed_time": "0:25:59", "remaining_time": "3:09:47"}
+{"current_steps": 1200, "total_steps": 9132, "loss": 1.8213, "lr": 9.970353900512644e-06, "epoch": 0.13140964218249515, "percentage": 13.14, "elapsed_time": "0:28:19", "remaining_time": "3:07:11"}
+{"current_steps": 1300, "total_steps": 9132, "loss": 1.8147, "lr": 9.945943883598031e-06, "epoch": 0.14236044569770306, "percentage": 14.24, "elapsed_time": "0:30:41", "remaining_time": "3:04:54"}
+{"current_steps": 1400, "total_steps": 9132, "loss": 1.7824, "lr": 9.914306771645357e-06, "epoch": 0.153311249212911, "percentage": 15.33, "elapsed_time": "0:33:04", "remaining_time": "3:02:41"}
+{"current_steps": 1500, "total_steps": 9132, "loss": 1.7896, "lr": 9.875488793326074e-06, "epoch": 0.16426205272811892, "percentage": 16.43, "elapsed_time": "0:35:25", "remaining_time": "3:00:13"}
+{"current_steps": 1600, "total_steps": 9132, "loss": 1.7788, "lr": 9.82954667011238e-06, "epoch": 0.17521285624332686, "percentage": 17.52, "elapsed_time": "0:37:47", "remaining_time": "2:57:53"}
+{"current_steps": 1700, "total_steps": 9132, "loss": 1.7894, "lr": 9.776547533394874e-06, "epoch": 0.18616365975853477, "percentage": 18.62, "elapsed_time": "0:40:09", "remaining_time": "2:55:31"}
+{"current_steps": 1800, "total_steps": 9132, "loss": 1.752, "lr": 9.716568826389045e-06, "epoch": 0.1971144632737427, "percentage": 19.71, "elapsed_time": "0:42:32", "remaining_time": "2:53:16"}
+{"current_steps": 1900, "total_steps": 9132, "loss": 1.7587, "lr": 9.649698190973977e-06, "epoch": 0.20806526678895063, "percentage": 20.81, "elapsed_time": "0:44:54", "remaining_time": "2:50:55"}
+{"current_steps": 2000, "total_steps": 9132, "loss": 1.7648, "lr": 9.576033339628578e-06, "epoch": 0.21901607030415857, "percentage": 21.9, "elapsed_time": "0:47:14", "remaining_time": "2:48:28"}
+{"current_steps": 2100, "total_steps": 9132, "loss": 1.7507, "lr": 9.495681912652486e-06, "epoch": 0.2299668738193665, "percentage": 23.0, "elapsed_time": "0:49:34", "remaining_time": "2:46:01"}
+{"current_steps": 2200, "total_steps": 9132, "loss": 1.7628, "lr": 9.408761320880292e-06, "epoch": 0.24091767733457442, "percentage": 24.09, "elapsed_time": "0:51:56", "remaining_time": "2:43:41"}
+{"current_steps": 2300, "total_steps": 9132, "loss": 1.7299, "lr": 9.315398574118876e-06, "epoch": 0.25186848084978236, "percentage": 25.19, "elapsed_time": "0:54:18", "remaining_time": "2:41:19"}
+{"current_steps": 2400, "total_steps": 9132, "loss": 1.7188, "lr": 9.215730095558582e-06, "epoch": 0.2628192843649903, "percentage": 26.28, "elapsed_time": "0:56:38", "remaining_time": "2:38:51"}
+{"current_steps": 2500, "total_steps": 9132, "loss": 1.7139, "lr": 9.10990152242939e-06, "epoch": 0.2737700878801982, "percentage": 27.38, "elapsed_time": "0:59:02", "remaining_time": "2:36:36"}
+{"current_steps": 2600, "total_steps": 9132, "loss": 1.711, "lr": 8.998067493193395e-06, "epoch": 0.28472089139540613, "percentage": 28.47, "elapsed_time": "1:01:23", "remaining_time": "2:34:13"}
+{"current_steps": 2700, "total_steps": 9132, "loss": 1.7143, "lr": 8.880391421584511e-06, "epoch": 0.29567169491061407, "percentage": 29.57, "elapsed_time": "1:03:43", "remaining_time": "2:31:49"}
+{"current_steps": 2800, "total_steps": 9132, "loss": 1.693, "lr": 8.757045257825642e-06, "epoch": 0.306622498425822, "percentage": 30.66, "elapsed_time": "1:06:06", "remaining_time": "2:29:30"}
+{"current_steps": 2900, "total_steps": 9132, "loss": 1.6915, "lr": 8.628209237372148e-06, "epoch": 0.31757330194102995, "percentage": 31.76, "elapsed_time": "1:08:29", "remaining_time": "2:27:11"}
+{"current_steps": 3000, "total_steps": 9132, "loss": 1.6932, "lr": 8.494071617548831e-06, "epoch": 0.32852410545623784, "percentage": 32.85, "elapsed_time": "1:10:50", "remaining_time": "2:24:48"}
+{"current_steps": 3100, "total_steps": 9132, "loss": 1.6522, "lr": 8.354828402465215e-06, "epoch": 0.3394749089714458, "percentage": 33.95, "elapsed_time": "1:13:10", "remaining_time": "2:22:22"}
+{"current_steps": 3200, "total_steps": 9132, "loss": 1.6759, "lr": 8.210683056611086e-06, "epoch": 0.3504257124866537, "percentage": 35.04, "elapsed_time": "1:15:31", "remaining_time": "2:20:00"}
+{"current_steps": 3300, "total_steps": 9132, "loss": 1.6584, "lr": 8.06184620755083e-06, "epoch": 0.36137651600186166, "percentage": 36.14, "elapsed_time": "1:17:52", "remaining_time": "2:17:37"}
+{"current_steps": 3400, "total_steps": 9132, "loss": 1.6598, "lr": 7.90853533815094e-06, "epoch": 0.37232731951706954, "percentage": 37.23, "elapsed_time": "1:20:14", "remaining_time": "2:15:16"}
+{"current_steps": 3500, "total_steps": 9132, "loss": 1.6602, "lr": 7.750974468790462e-06, "epoch": 0.3832781230322775, "percentage": 38.33, "elapsed_time": "1:22:34", "remaining_time": "2:12:53"}
+{"current_steps": 3600, "total_steps": 9132, "loss": 1.6466, "lr": 7.589393830018696e-06, "epoch": 0.3942289265474854, "percentage": 39.42, "elapsed_time": "1:24:56", "remaining_time": "2:10:31"}
+{"current_steps": 3700, "total_steps": 9132, "loss": 1.6247, "lr": 7.4240295261385205e-06, "epoch": 0.40517973006269337, "percentage": 40.52, "elapsed_time": "1:27:16", "remaining_time": "2:08:08"}
+{"current_steps": 3800, "total_steps": 9132, "loss": 1.6204, "lr": 7.2551231902068775e-06, "epoch": 0.41613053357790125, "percentage": 41.61, "elapsed_time": "1:29:38", "remaining_time": "2:05:46"}
+{"current_steps": 3900, "total_steps": 9132, "loss": 1.618, "lr": 7.082921630956545e-06, "epoch": 0.4270813370931092, "percentage": 42.71, "elapsed_time": "1:31:57", "remaining_time": "2:03:22"}
+{"current_steps": 4000, "total_steps": 9132, "loss": 1.6237, "lr": 6.9076764721551385e-06, "epoch": 0.43803214060831713, "percentage": 43.8, "elapsed_time": "1:34:18", "remaining_time": "2:00:59"}
+{"current_steps": 4100, "total_steps": 9132, "loss": 1.6185, "lr": 6.729643784928295e-06, "epoch": 0.4489829441235251, "percentage": 44.9, "elapsed_time": "1:36:40", "remaining_time": "1:58:38"}
+{"current_steps": 4200, "total_steps": 9132, "loss": 1.6114, "lr": 6.549083713584314e-06, "epoch": 0.459933747638733, "percentage": 45.99, "elapsed_time": "1:38:59", "remaining_time": "1:56:14"}
+{"current_steps": 4300, "total_steps": 9132, "loss": 1.6123, "lr": 6.366260095486977e-06, "epoch": 0.4708845511539409, "percentage": 47.09, "elapsed_time": "1:41:18", "remaining_time": "1:53:50"}
+{"current_steps": 4400, "total_steps": 9132, "loss": 1.5628, "lr": 6.181440075532042e-06, "epoch": 0.48183535466914884, "percentage": 48.18, "elapsed_time": "1:43:40", "remaining_time": "1:51:30"}
+{"current_steps": 4500, "total_steps": 9132, "loss": 1.5712, "lr": 5.99489371579069e-06, "epoch": 0.4927861581843568, "percentage": 49.28, "elapsed_time": "1:46:02", "remaining_time": "1:49:09"}
+{"current_steps": 4600, "total_steps": 9132, "loss": 1.5599, "lr": 5.806893600890361e-06, "epoch": 0.5037369616995647, "percentage": 50.37, "elapsed_time": "1:48:22", "remaining_time": "1:46:46"}
+{"current_steps": 4700, "total_steps": 9132, "loss": 1.5595, "lr": 5.617714439709588e-06, "epoch": 0.5146877652147727, "percentage": 51.47, "elapsed_time": "1:50:43", "remaining_time": "1:44:25"}
+{"current_steps": 4800, "total_steps": 9132, "loss": 1.5747, "lr": 5.42763266396884e-06, "epoch": 0.5256385687299806, "percentage": 52.56, "elapsed_time": "1:53:05", "remaining_time": "1:42:04"}
+{"current_steps": 4900, "total_steps": 9132, "loss": 1.5547, "lr": 5.236926024303909e-06, "epoch": 0.5365893722451885, "percentage": 53.66, "elapsed_time": "1:55:25", "remaining_time": "1:39:41"}
+{"current_steps": 5000, "total_steps": 9132, "loss": 1.5846, "lr": 5.045873184412099e-06, "epoch": 0.5475401757603964, "percentage": 54.75, "elapsed_time": "1:57:44", "remaining_time": "1:37:18"}
+{"current_steps": 5100, "total_steps": 9132, "loss": 1.5473, "lr": 4.854753313864212e-06, "epoch": 0.5584909792756043, "percentage": 55.85, "elapsed_time": "2:00:03", "remaining_time": "1:34:55"}
+{"current_steps": 5200, "total_steps": 9132, "loss": 1.5513, "lr": 4.663845680177349e-06, "epoch": 0.5694417827908123, "percentage": 56.94, "elapsed_time": "2:02:26", "remaining_time": "1:32:34"}
+{"current_steps": 5300, "total_steps": 9132, "loss": 1.5596, "lr": 4.473429240744606e-06, "epoch": 0.5803925863060202, "percentage": 58.04, "elapsed_time": "2:04:48", "remaining_time": "1:30:14"}
+{"current_steps": 5400, "total_steps": 9132, "loss": 1.5334, "lr": 4.283782235217901e-06, "epoch": 0.5913433898212281, "percentage": 59.13, "elapsed_time": "2:07:10", "remaining_time": "1:27:53"}
+{"current_steps": 5500, "total_steps": 9132, "loss": 1.5183, "lr": 4.095181778939598e-06, "epoch": 0.6022941933364361, "percentage": 60.23, "elapsed_time": "2:09:30", "remaining_time": "1:25:31"}
+{"current_steps": 5600, "total_steps": 9132, "loss": 1.5402, "lr": 3.90790345801699e-06, "epoch": 0.613244996851644, "percentage": 61.32, "elapsed_time": "2:11:51", "remaining_time": "1:23:09"}
+{"current_steps": 5700, "total_steps": 9132, "loss": 1.5132, "lr": 3.7222209266313026e-06, "epoch": 0.624195800366852, "percentage": 62.42, "elapsed_time": "2:14:14", "remaining_time": "1:20:49"}
+{"current_steps": 5800, "total_steps": 9132, "loss": 1.5098, "lr": 3.538405507169692e-06, "epoch": 0.6351466038820599, "percentage": 63.51, "elapsed_time": "2:16:35", "remaining_time": "1:18:27"}
+{"current_steps": 5900, "total_steps": 9132, "loss": 1.5147, "lr": 3.356725793764477e-06, "epoch": 0.6460974073972677, "percentage": 64.61, "elapsed_time": "2:18:55", "remaining_time": "1:16:06"}
+{"current_steps": 6000, "total_steps": 9132, "loss": 1.5384, "lr": 3.1774472598189503e-06, "epoch": 0.6570482109124757, "percentage": 65.7, "elapsed_time": "2:21:17", "remaining_time": "1:13:45"}
+{"current_steps": 6100, "total_steps": 9132, "loss": 1.5411, "lr": 3.0008318700932426e-06, "epoch": 0.6679990144276836, "percentage": 66.8, "elapsed_time": "2:23:38", "remaining_time": "1:11:23"}
+{"current_steps": 6200, "total_steps": 9132, "loss": 1.5003, "lr": 2.827137697917096e-06, "epoch": 0.6789498179428916, "percentage": 67.89, "elapsed_time": "2:26:00", "remaining_time": "1:09:02"}
+{"current_steps": 6300, "total_steps": 9132, "loss": 1.5175, "lr": 2.6566185480888276e-06, "epoch": 0.6899006214580995, "percentage": 68.99, "elapsed_time": "2:28:20", "remaining_time": "1:06:40"}
+{"current_steps": 6400, "total_steps": 9132, "loss": 1.4974, "lr": 2.4895235860115652e-06, "epoch": 0.7008514249733074, "percentage": 70.08, "elapsed_time": "2:30:41", "remaining_time": "1:04:19"}
+{"current_steps": 6500, "total_steps": 9132, "loss": 1.497, "lr": 2.326096973608648e-06, "epoch": 0.7118022284885154, "percentage": 71.18, "elapsed_time": "2:33:01", "remaining_time": "1:01:57"}
+{"current_steps": 6600, "total_steps": 9132, "loss": 1.502, "lr": 2.166577512550162e-06, "epoch": 0.7227530320037233, "percentage": 72.27, "elapsed_time": "2:35:21", "remaining_time": "0:59:35"}
+{"current_steps": 6700, "total_steps": 9132, "loss": 1.5173, "lr": 2.0111982953120073e-06, "epoch": 0.7337038355189311, "percentage": 73.37, "elapsed_time": "2:37:42", "remaining_time": "0:57:14"}
+{"current_steps": 6800, "total_steps": 9132, "loss": 1.4877, "lr": 1.8601863645773128e-06, "epoch": 0.7446546390341391, "percentage": 74.46, "elapsed_time": "2:40:03", "remaining_time": "0:54:53"}
+{"current_steps": 6900, "total_steps": 9132, "loss": 1.4705, "lr": 1.7137623814779036e-06, "epoch": 0.755605442549347, "percentage": 75.56, "elapsed_time": "2:42:24", "remaining_time": "0:52:31"}
+{"current_steps": 7000, "total_steps": 9132, "loss": 1.4747, "lr": 1.5721403031606048e-06, "epoch": 0.766556246064555, "percentage": 76.65, "elapsed_time": "2:44:47", "remaining_time": "0:50:11"}
+{"current_steps": 7100, "total_steps": 9132, "loss": 1.5005, "lr": 1.43552707014953e-06, "epoch": 0.7775070495797629, "percentage": 77.75, "elapsed_time": "2:47:10", "remaining_time": "0:47:50"}
+{"current_steps": 7200, "total_steps": 9132, "loss": 1.5038, "lr": 1.3041223039611489e-06, "epoch": 0.7884578530949709, "percentage": 78.84, "elapsed_time": "2:49:33", "remaining_time": "0:45:29"}
+{"current_steps": 7300, "total_steps": 9132, "loss": 1.5086, "lr": 1.1781180154140331e-06, "epoch": 0.7994086566101788, "percentage": 79.94, "elapsed_time": "2:51:54", "remaining_time": "0:43:08"}
+{"current_steps": 7400, "total_steps": 9132, "loss": 1.4665, "lr": 1.057698324059469e-06, "epoch": 0.8103594601253867, "percentage": 81.03, "elapsed_time": "2:54:14", "remaining_time": "0:40:46"}
+{"current_steps": 7500, "total_steps": 9132, "loss": 1.4686, "lr": 9.43039189142922e-07, "epoch": 0.8213102636405947, "percentage": 82.13, "elapsed_time": "2:56:32", "remaining_time": "0:38:25"}
+{"current_steps": 7600, "total_steps": 9132, "loss": 1.4933, "lr": 8.343081524894763e-07, "epoch": 0.8322610671558025, "percentage": 83.22, "elapsed_time": "2:58:54", "remaining_time": "0:36:03"}
+{"current_steps": 7700, "total_steps": 9132, "loss": 1.4976, "lr": 7.316640936889491e-07, "epoch": 0.8432118706710104, "percentage": 84.32, "elapsed_time": "3:01:15", "remaining_time": "0:33:42"}
+{"current_steps": 7800, "total_steps": 9132, "loss": 1.4663, "lr": 6.352569979384027e-07, "epoch": 0.8541626741862184, "percentage": 85.41, "elapsed_time": "3:03:34", "remaining_time": "0:31:21"}
+{"current_steps": 7900, "total_steps": 9132, "loss": 1.4635, "lr": 5.452277368812936e-07, "epoch": 0.8651134777014263, "percentage": 86.51, "elapsed_time": "3:05:55", "remaining_time": "0:28:59"}
+{"current_steps": 8000, "total_steps": 9132, "loss": 1.4739, "lr": 4.617078627635019e-07, "epoch": 0.8760642812166343, "percentage": 87.6, "elapsed_time": "3:08:15", "remaining_time": "0:26:38"}
+{"current_steps": 8100, "total_steps": 9132, "loss": 1.4525, "lr": 3.8481941620700127e-07, "epoch": 0.8870150847318422, "percentage": 88.7, "elapsed_time": "3:10:34", "remaining_time": "0:24:16"}
+{"current_steps": 8200, "total_steps": 9132, "loss": 1.4467, "lr": 3.146747478820938e-07, "epoch": 0.8979658882470501, "percentage": 89.79, "elapsed_time": "3:12:54", "remaining_time": "0:21:55"}
+{"current_steps": 8300, "total_steps": 9132, "loss": 1.4893, "lr": 2.513763543387465e-07, "epoch": 0.9089166917622581, "percentage": 90.89, "elapsed_time": "3:15:16", "remaining_time": "0:19:34"}
+{"current_steps": 8400, "total_steps": 9132, "loss": 1.4246, "lr": 1.9501672823693584e-07, "epoch": 0.919867495277466, "percentage": 91.98, "elapsed_time": "3:17:35", "remaining_time": "0:17:13"}
+{"current_steps": 8500, "total_steps": 9132, "loss": 1.456, "lr": 1.4567822319484614e-07, "epoch": 0.9308182987926739, "percentage": 93.08, "elapsed_time": "3:19:56", "remaining_time": "0:14:52"}
+{"current_steps": 8600, "total_steps": 9132, "loss": 1.4473, "lr": 1.0343293345239702e-07, "epoch": 0.9417691023078818, "percentage": 94.17, "elapsed_time": "3:22:16", "remaining_time": "0:12:30"}
+{"current_steps": 8700, "total_steps": 9132, "loss": 1.4813, "lr": 6.834258852594866e-08, "epoch": 0.9527199058230897, "percentage": 95.27, "elapsed_time": "3:24:36", "remaining_time": "0:10:09"}
+{"current_steps": 8800, "total_steps": 9132, "loss": 1.4259, "lr": 4.045846300811229e-08, "epoch": 0.9636707093382977, "percentage": 96.36, "elapsed_time": "3:27:01", "remaining_time": "0:07:48"}
+{"current_steps": 8900, "total_steps": 9132, "loss": 1.4595, "lr": 1.9821301644462056e-08, "epoch": 0.9746215128535056, "percentage": 97.46, "elapsed_time": "3:29:23", "remaining_time": "0:05:27"}
+{"current_steps": 9000, "total_steps": 9132, "loss": 1.4601, "lr": 6.461259796644026e-09, "epoch": 0.9855723163687136, "percentage": 98.55, "elapsed_time": "3:31:43", "remaining_time": "0:03:06"}
+{"current_steps": 9100, "total_steps": 9132, "loss": 1.4738, "lr": 3.978593788622753e-10, "epoch": 0.9965231198839215, "percentage": 99.65, "elapsed_time": "3:34:03", "remaining_time": "0:00:45"}
+{"current_steps": 9132, "total_steps": 9132, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:35:30", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,680 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 10000,
+  "global_step": 9132,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010950803515207929,
+      "grad_norm": 5.517458438873291,
+      "learning_rate": 1.0831509846827136e-06,
+      "loss": 2.5966,
+      "step": 100
+    },
+    {
+      "epoch": 0.021901607030415857,
+      "grad_norm": 5.273920059204102,
+      "learning_rate": 2.177242888402626e-06,
+      "loss": 2.3125,
+      "step": 200
+    },
+    {
+      "epoch": 0.03285241054562379,
+      "grad_norm": 5.7524261474609375,
+      "learning_rate": 3.2713347921225385e-06,
+      "loss": 2.1574,
+      "step": 300
+    },
+    {
+      "epoch": 0.043803214060831715,
+      "grad_norm": 4.415042400360107,
+      "learning_rate": 4.365426695842451e-06,
+      "loss": 1.9882,
+      "step": 400
+    },
+    {
+      "epoch": 0.05475401757603964,
+      "grad_norm": 3.4843761920928955,
+      "learning_rate": 5.459518599562363e-06,
+      "loss": 1.9221,
+      "step": 500
+    },
+    {
+      "epoch": 0.06570482109124758,
+      "grad_norm": 3.8609654903411865,
+      "learning_rate": 6.553610503282276e-06,
+      "loss": 1.9077,
+      "step": 600
+    },
+    {
+      "epoch": 0.0766556246064555,
+      "grad_norm": 3.310288429260254,
+      "learning_rate": 7.64770240700219e-06,
+      "loss": 1.8748,
+      "step": 700
+    },
+    {
+      "epoch": 0.08760642812166343,
+      "grad_norm": 3.843994140625,
+      "learning_rate": 8.741794310722102e-06,
+      "loss": 1.88,
+      "step": 800
+    },
+    {
+      "epoch": 0.09855723163687136,
+      "grad_norm": 3.1463918685913086,
+      "learning_rate": 9.835886214442013e-06,
+      "loss": 1.8617,
+      "step": 900
+    },
+    {
+      "epoch": 0.10950803515207928,
+      "grad_norm": 3.763201951980591,
+      "learning_rate": 9.997360588415263e-06,
+      "loss": 1.8323,
+      "step": 1000
+    },
+    {
+      "epoch": 0.12045883866728721,
+      "grad_norm": 2.8540737628936768,
+      "learning_rate": 9.987501154068591e-06,
+      "loss": 1.8238,
+      "step": 1100
+    },
+    {
+      "epoch": 0.13140964218249515,
+      "grad_norm": 3.5842385292053223,
+      "learning_rate": 9.970353900512644e-06,
+      "loss": 1.8213,
+      "step": 1200
+    },
+    {
+      "epoch": 0.14236044569770306,
+      "grad_norm": 4.1146135330200195,
+      "learning_rate": 9.945943883598031e-06,
+      "loss": 1.8147,
+      "step": 1300
+    },
+    {
+      "epoch": 0.153311249212911,
+      "grad_norm": 3.3109846115112305,
+      "learning_rate": 9.914306771645357e-06,
+      "loss": 1.7824,
+      "step": 1400
+    },
+    {
+      "epoch": 0.16426205272811892,
+      "grad_norm": 3.7267284393310547,
+      "learning_rate": 9.875488793326074e-06,
+      "loss": 1.7896,
+      "step": 1500
+    },
+    {
+      "epoch": 0.17521285624332686,
+      "grad_norm": 4.14414644241333,
+      "learning_rate": 9.82954667011238e-06,
+      "loss": 1.7788,
+      "step": 1600
+    },
+    {
+      "epoch": 0.18616365975853477,
+      "grad_norm": 3.413673162460327,
+      "learning_rate": 9.776547533394874e-06,
+      "loss": 1.7894,
+      "step": 1700
+    },
+    {
+      "epoch": 0.1971144632737427,
+      "grad_norm": 3.6218016147613525,
+      "learning_rate": 9.716568826389045e-06,
+      "loss": 1.752,
+      "step": 1800
+    },
+    {
+      "epoch": 0.20806526678895063,
+      "grad_norm": 3.2655038833618164,
+      "learning_rate": 9.649698190973977e-06,
+      "loss": 1.7587,
+      "step": 1900
+    },
+    {
+      "epoch": 0.21901607030415857,
+      "grad_norm": 3.188708543777466,
+      "learning_rate": 9.576033339628578e-06,
+      "loss": 1.7648,
+      "step": 2000
+    },
+    {
+      "epoch": 0.2299668738193665,
+      "grad_norm": 3.2714788913726807,
+      "learning_rate": 9.495681912652486e-06,
+      "loss": 1.7507,
+      "step": 2100
+    },
+    {
+      "epoch": 0.24091767733457442,
+      "grad_norm": 3.6338818073272705,
+      "learning_rate": 9.408761320880292e-06,
+      "loss": 1.7628,
+      "step": 2200
+    },
+    {
+      "epoch": 0.25186848084978236,
+      "grad_norm": 3.466273546218872,
+      "learning_rate": 9.315398574118876e-06,
+      "loss": 1.7299,
+      "step": 2300
+    },
+    {
+      "epoch": 0.2628192843649903,
+      "grad_norm": 3.3957815170288086,
+      "learning_rate": 9.215730095558582e-06,
+      "loss": 1.7188,
+      "step": 2400
+    },
+    {
+      "epoch": 0.2737700878801982,
+      "grad_norm": 3.8373427391052246,
+      "learning_rate": 9.10990152242939e-06,
+      "loss": 1.7139,
+      "step": 2500
+    },
+    {
+      "epoch": 0.28472089139540613,
+      "grad_norm": 3.5663390159606934,
+      "learning_rate": 8.998067493193395e-06,
+      "loss": 1.711,
+      "step": 2600
+    },
+    {
+      "epoch": 0.29567169491061407,
+      "grad_norm": 3.543086290359497,
+      "learning_rate": 8.880391421584511e-06,
+      "loss": 1.7143,
+      "step": 2700
+    },
+    {
+      "epoch": 0.306622498425822,
+      "grad_norm": 3.4232897758483887,
+      "learning_rate": 8.757045257825642e-06,
+      "loss": 1.693,
+      "step": 2800
+    },
+    {
+      "epoch": 0.31757330194102995,
+      "grad_norm": 3.153503179550171,
+      "learning_rate": 8.628209237372148e-06,
+      "loss": 1.6915,
+      "step": 2900
+    },
+    {
+      "epoch": 0.32852410545623784,
+      "grad_norm": 3.6370930671691895,
+      "learning_rate": 8.494071617548831e-06,
+      "loss": 1.6932,
+      "step": 3000
+    },
+    {
+      "epoch": 0.3394749089714458,
+      "grad_norm": 3.5099680423736572,
+      "learning_rate": 8.354828402465215e-06,
+      "loss": 1.6522,
+      "step": 3100
+    },
+    {
+      "epoch": 0.3504257124866537,
+      "grad_norm": 4.088729381561279,
+      "learning_rate": 8.210683056611086e-06,
+      "loss": 1.6759,
+      "step": 3200
+    },
+    {
+      "epoch": 0.36137651600186166,
+      "grad_norm": 4.009633541107178,
+      "learning_rate": 8.06184620755083e-06,
+      "loss": 1.6584,
+      "step": 3300
+    },
+    {
+      "epoch": 0.37232731951706954,
+      "grad_norm": 3.3517208099365234,
+      "learning_rate": 7.90853533815094e-06,
+      "loss": 1.6598,
+      "step": 3400
+    },
+    {
+      "epoch": 0.3832781230322775,
+      "grad_norm": 3.5369486808776855,
+      "learning_rate": 7.750974468790462e-06,
+      "loss": 1.6602,
+      "step": 3500
+    },
+    {
+      "epoch": 0.3942289265474854,
+      "grad_norm": 3.1376800537109375,
+      "learning_rate": 7.589393830018696e-06,
+      "loss": 1.6466,
+      "step": 3600
+    },
+    {
+      "epoch": 0.40517973006269337,
+      "grad_norm": 3.253649950027466,
+      "learning_rate": 7.4240295261385205e-06,
+      "loss": 1.6247,
+      "step": 3700
+    },
+    {
+      "epoch": 0.41613053357790125,
+      "grad_norm": 3.432814359664917,
+      "learning_rate": 7.2551231902068775e-06,
+      "loss": 1.6204,
+      "step": 3800
+    },
+    {
+      "epoch": 0.4270813370931092,
+      "grad_norm": 3.8177409172058105,
+      "learning_rate": 7.082921630956545e-06,
+      "loss": 1.618,
+      "step": 3900
+    },
+    {
+      "epoch": 0.43803214060831713,
+      "grad_norm": 3.866558313369751,
+      "learning_rate": 6.9076764721551385e-06,
+      "loss": 1.6237,
+      "step": 4000
+    },
+    {
+      "epoch": 0.4489829441235251,
+      "grad_norm": 3.8972673416137695,
+      "learning_rate": 6.729643784928295e-06,
+      "loss": 1.6185,
+      "step": 4100
+    },
+    {
+      "epoch": 0.459933747638733,
+      "grad_norm": 3.088886260986328,
+      "learning_rate": 6.549083713584314e-06,
+      "loss": 1.6114,
+      "step": 4200
+    },
+    {
+      "epoch": 0.4708845511539409,
+      "grad_norm": 3.4185397624969482,
+      "learning_rate": 6.366260095486977e-06,
+      "loss": 1.6123,
+      "step": 4300
+    },
+    {
+      "epoch": 0.48183535466914884,
+      "grad_norm": 4.178684234619141,
+      "learning_rate": 6.181440075532042e-06,
+      "loss": 1.5628,
+      "step": 4400
+    },
+    {
+      "epoch": 0.4927861581843568,
+      "grad_norm": 3.807727813720703,
+      "learning_rate": 5.99489371579069e-06,
+      "loss": 1.5712,
+      "step": 4500
+    },
+    {
+      "epoch": 0.5037369616995647,
+      "grad_norm": 3.5558791160583496,
+      "learning_rate": 5.806893600890361e-06,
+      "loss": 1.5599,
+      "step": 4600
+    },
+    {
+      "epoch": 0.5146877652147727,
+      "grad_norm": 3.706101894378662,
+      "learning_rate": 5.617714439709588e-06,
+      "loss": 1.5595,
+      "step": 4700
+    },
+    {
+      "epoch": 0.5256385687299806,
+      "grad_norm": 3.324862003326416,
+      "learning_rate": 5.42763266396884e-06,
+      "loss": 1.5747,
+      "step": 4800
+    },
+    {
+      "epoch": 0.5365893722451885,
+      "grad_norm": 3.485616445541382,
+      "learning_rate": 5.236926024303909e-06,
+      "loss": 1.5547,
+      "step": 4900
+    },
+    {
+      "epoch": 0.5475401757603964,
+      "grad_norm": 3.410731077194214,
+      "learning_rate": 5.045873184412099e-06,
+      "loss": 1.5846,
+      "step": 5000
+    },
+    {
+      "epoch": 0.5584909792756043,
+      "grad_norm": 3.5248425006866455,
+      "learning_rate": 4.854753313864212e-06,
+      "loss": 1.5473,
+      "step": 5100
+    },
+    {
+      "epoch": 0.5694417827908123,
+      "grad_norm": 3.993953227996826,
+      "learning_rate": 4.663845680177349e-06,
+      "loss": 1.5513,
+      "step": 5200
+    },
+    {
+      "epoch": 0.5803925863060202,
+      "grad_norm": 3.5981061458587646,
+      "learning_rate": 4.473429240744606e-06,
+      "loss": 1.5596,
+      "step": 5300
+    },
+    {
+      "epoch": 0.5913433898212281,
+      "grad_norm": 4.107110977172852,
+      "learning_rate": 4.283782235217901e-06,
+      "loss": 1.5334,
+      "step": 5400
+    },
+    {
+      "epoch": 0.6022941933364361,
+      "grad_norm": 3.5353140830993652,
+      "learning_rate": 4.095181778939598e-06,
+      "loss": 1.5183,
+      "step": 5500
+    },
+    {
+      "epoch": 0.613244996851644,
+      "grad_norm": 3.8818717002868652,
+      "learning_rate": 3.90790345801699e-06,
+      "loss": 1.5402,
+      "step": 5600
+    },
+    {
+      "epoch": 0.624195800366852,
+      "grad_norm": 3.5173981189727783,
+      "learning_rate": 3.7222209266313026e-06,
+      "loss": 1.5132,
+      "step": 5700
+    },
+    {
+      "epoch": 0.6351466038820599,
+      "grad_norm": 4.288154602050781,
+      "learning_rate": 3.538405507169692e-06,
+      "loss": 1.5098,
+      "step": 5800
+    },
+    {
+      "epoch": 0.6460974073972677,
+      "grad_norm": 3.918605089187622,
+      "learning_rate": 3.356725793764477e-06,
+      "loss": 1.5147,
+      "step": 5900
+    },
+    {
+      "epoch": 0.6570482109124757,
+      "grad_norm": 4.286097049713135,
+      "learning_rate": 3.1774472598189503e-06,
+      "loss": 1.5384,
+      "step": 6000
+    },
+    {
+      "epoch": 0.6679990144276836,
+      "grad_norm": 3.301164150238037,
+      "learning_rate": 3.0008318700932426e-06,
+      "loss": 1.5411,
+      "step": 6100
+    },
+    {
+      "epoch": 0.6789498179428916,
+      "grad_norm": 3.758004903793335,
+      "learning_rate": 2.827137697917096e-06,
+      "loss": 1.5003,
+      "step": 6200
+    },
+    {
+      "epoch": 0.6899006214580995,
+      "grad_norm": 3.1831018924713135,
+      "learning_rate": 2.6566185480888276e-06,
+      "loss": 1.5175,
+      "step": 6300
+    },
+    {
+      "epoch": 0.7008514249733074,
+      "grad_norm": 3.6004598140716553,
+      "learning_rate": 2.4895235860115652e-06,
+      "loss": 1.4974,
+      "step": 6400
+    },
+    {
+      "epoch": 0.7118022284885154,
+      "grad_norm": 3.951835870742798,
+      "learning_rate": 2.326096973608648e-06,
+      "loss": 1.497,
+      "step": 6500
+    },
+    {
+      "epoch": 0.7227530320037233,
+      "grad_norm": 3.2882447242736816,
+      "learning_rate": 2.166577512550162e-06,
+      "loss": 1.502,
+      "step": 6600
+    },
+    {
+      "epoch": 0.7337038355189311,
+      "grad_norm": 4.077866077423096,
+      "learning_rate": 2.0111982953120073e-06,
+      "loss": 1.5173,
+      "step": 6700
+    },
+    {
+      "epoch": 0.7446546390341391,
+      "grad_norm": 4.122990608215332,
+      "learning_rate": 1.8601863645773128e-06,
+      "loss": 1.4877,
+      "step": 6800
+    },
+    {
+      "epoch": 0.755605442549347,
+      "grad_norm": 3.5521764755249023,
+      "learning_rate": 1.7137623814779036e-06,
+      "loss": 1.4705,
+      "step": 6900
+    },
+    {
+      "epoch": 0.766556246064555,
+      "grad_norm": 3.5683555603027344,
+      "learning_rate": 1.5721403031606048e-06,
+      "loss": 1.4747,
+      "step": 7000
+    },
+    {
+      "epoch": 0.7775070495797629,
+      "grad_norm": 3.852078914642334,
+      "learning_rate": 1.43552707014953e-06,
+      "loss": 1.5005,
+      "step": 7100
+    },
+    {
+      "epoch": 0.7884578530949709,
+      "grad_norm": 3.6315114498138428,
+      "learning_rate": 1.3041223039611489e-06,
+      "loss": 1.5038,
+      "step": 7200
+    },
+    {
+      "epoch": 0.7994086566101788,
+      "grad_norm": 3.6797256469726562,
+      "learning_rate": 1.1781180154140331e-06,
+      "loss": 1.5086,
+      "step": 7300
+    },
+    {
+      "epoch": 0.8103594601253867,
+      "grad_norm": 3.5173234939575195,
+      "learning_rate": 1.057698324059469e-06,
+      "loss": 1.4665,
+      "step": 7400
+    },
+    {
+      "epoch": 0.8213102636405947,
+      "grad_norm": 3.8179659843444824,
+      "learning_rate": 9.43039189142922e-07,
+      "loss": 1.4686,
+      "step": 7500
+    },
+    {
+      "epoch": 0.8322610671558025,
+      "grad_norm": 4.368917942047119,
+      "learning_rate": 8.343081524894763e-07,
+      "loss": 1.4933,
+      "step": 7600
+    },
+    {
+      "epoch": 0.8432118706710104,
+      "grad_norm": 4.125387191772461,
+      "learning_rate": 7.316640936889491e-07,
+      "loss": 1.4976,
+      "step": 7700
+    },
+    {
+      "epoch": 0.8541626741862184,
+      "grad_norm": 4.123210906982422,
+      "learning_rate": 6.352569979384027e-07,
+      "loss": 1.4663,
+      "step": 7800
+    },
+    {
+      "epoch": 0.8651134777014263,
+      "grad_norm": 3.9425387382507324,
+      "learning_rate": 5.452277368812936e-07,
+      "loss": 1.4635,
+      "step": 7900
+    },
+    {
+      "epoch": 0.8760642812166343,
+      "grad_norm": 3.996006727218628,
+      "learning_rate": 4.617078627635019e-07,
+      "loss": 1.4739,
+      "step": 8000
+    },
+    {
+      "epoch": 0.8870150847318422,
+      "grad_norm": 3.8166754245758057,
+      "learning_rate": 3.8481941620700127e-07,
+      "loss": 1.4525,
+      "step": 8100
+    },
+    {
+      "epoch": 0.8979658882470501,
+      "grad_norm": 4.163847923278809,
+      "learning_rate": 3.146747478820938e-07,
+      "loss": 1.4467,
+      "step": 8200
+    },
+    {
+      "epoch": 0.9089166917622581,
+      "grad_norm": 3.3138253688812256,
+      "learning_rate": 2.513763543387465e-07,
+      "loss": 1.4893,
+      "step": 8300
+    },
+    {
+      "epoch": 0.919867495277466,
+      "grad_norm": 3.702721118927002,
+      "learning_rate": 1.9501672823693584e-07,
+      "loss": 1.4246,
+      "step": 8400
+    },
+    {
+      "epoch": 0.9308182987926739,
+      "grad_norm": 3.539092779159546,
+      "learning_rate": 1.4567822319484614e-07,
+      "loss": 1.456,
+      "step": 8500
+    },
+    {
+      "epoch": 0.9417691023078818,
+      "grad_norm": 4.07131814956665,
+      "learning_rate": 1.0343293345239702e-07,
+      "loss": 1.4473,
+      "step": 8600
+    },
+    {
+      "epoch": 0.9527199058230897,
+      "grad_norm": 3.898056745529175,
+      "learning_rate": 6.834258852594866e-08,
+      "loss": 1.4813,
+      "step": 8700
+    },
+    {
+      "epoch": 0.9636707093382977,
+      "grad_norm": 3.525865316390991,
+      "learning_rate": 4.045846300811229e-08,
+      "loss": 1.4259,
+      "step": 8800
+    },
+    {
+      "epoch": 0.9746215128535056,
+      "grad_norm": 3.3846275806427,
+      "learning_rate": 1.9821301644462056e-08,
+      "loss": 1.4595,
+      "step": 8900
+    },
+    {
+      "epoch": 0.9855723163687136,
+      "grad_norm": 3.4979400634765625,
+      "learning_rate": 6.461259796644026e-09,
+      "loss": 1.4601,
+      "step": 9000
+    },
+    {
+      "epoch": 0.9965231198839215,
+      "grad_norm": 3.377657413482666,
+      "learning_rate": 3.978593788622753e-10,
+      "loss": 1.4738,
+      "step": 9100
+    },
+    {
+      "epoch": 1.0,
+      "step": 9132,
+      "total_flos": 1.591591112898773e+18,
+      "train_loss": 1.633884816748293,
+      "train_runtime": 12935.5693,
+      "train_samples_per_second": 45.179,
+      "train_steps_per_second": 0.706
+    }
+  ],
+  "logging_steps": 100,
+  "max_steps": 9132,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 10000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.591591112898773e+18,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:043ba456eb58af1be580530e5f5622c6fe1e03d866d683711c2018cc9ceddd1f
+size 6289