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 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: qwen3-8B-sft_0915_likert_lfrs_sampled
+  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. -->
+
+# qwen3-8B-sft_0915_likert_lfrs_sampled
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the rl-rag/sft_0915_likert_lfrs_sampled 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: 4e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 16
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
+- optimizer: Use OptimizerNames.ADAMW_TORCH 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: 5
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.52.4
+- Pytorch 2.8.0+cu128
+- Datasets 3.6.0
+- Tokenizers 0.21.1

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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": 5.0,
+    "total_flos": 717096447639552.0,
+    "train_loss": 0.7372651619247244,
+    "train_runtime": 37731.7684,
+    "train_samples_per_second": 1.34,
+    "train_steps_per_second": 0.01
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# 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' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- 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' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,13 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:024e52c47e05636c24d540398cfa575004da61a0f034f2100a2aa9d2662c70cd
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2e41868d050bc8880e444769d2df1e935c9933ff88e35d06770bfd90ff0a823
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0d9ca735826472472822315d10c94f35bb75529527405f54573aae7ba52e436f
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:433d5dbc9e79b4ee0a0f185445198fd5ddc0e3560d459e8726834b3f50b39843
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,406 @@
+{
+  "metadata": {
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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": 5.0,
+    "total_flos": 717096447639552.0,
+    "train_loss": 0.7372651619247244,
+    "train_runtime": 37731.7684,
+    "train_samples_per_second": 1.34,
+    "train_steps_per_second": 0.01
+}

trainer_log.jsonl

@@ -0,0 +1,80 @@
+{"current_steps": 5, "total_steps": 395, "loss": 1.6528, "lr": 4.000000000000001e-06, "epoch": 0.06329113924050633, "percentage": 1.27, "elapsed_time": "0:08:46", "remaining_time": "11:24:04"}
+{"current_steps": 10, "total_steps": 395, "loss": 1.433, "lr": 9e-06, "epoch": 0.12658227848101267, "percentage": 2.53, "elapsed_time": "0:16:57", "remaining_time": "10:53:00"}
+{"current_steps": 15, "total_steps": 395, "loss": 1.2997, "lr": 1.4e-05, "epoch": 0.189873417721519, "percentage": 3.8, "elapsed_time": "0:24:37", "remaining_time": "10:23:44"}
+{"current_steps": 20, "total_steps": 395, "loss": 1.2252, "lr": 1.9e-05, "epoch": 0.25316455696202533, "percentage": 5.06, "elapsed_time": "0:32:46", "remaining_time": "10:14:37"}
+{"current_steps": 25, "total_steps": 395, "loss": 1.1621, "lr": 2.4e-05, "epoch": 0.31645569620253167, "percentage": 6.33, "elapsed_time": "0:40:38", "remaining_time": "10:01:26"}
+{"current_steps": 30, "total_steps": 395, "loss": 1.1294, "lr": 2.9e-05, "epoch": 0.379746835443038, "percentage": 7.59, "elapsed_time": "0:48:37", "remaining_time": "9:51:31"}
+{"current_steps": 35, "total_steps": 395, "loss": 1.1227, "lr": 3.4e-05, "epoch": 0.4430379746835443, "percentage": 8.86, "elapsed_time": "0:56:26", "remaining_time": "9:40:37"}
+{"current_steps": 40, "total_steps": 395, "loss": 1.0958, "lr": 3.9e-05, "epoch": 0.5063291139240507, "percentage": 10.13, "elapsed_time": "1:04:25", "remaining_time": "9:31:44"}
+{"current_steps": 45, "total_steps": 395, "loss": 1.0891, "lr": 3.998747096355221e-05, "epoch": 0.569620253164557, "percentage": 11.39, "elapsed_time": "1:12:03", "remaining_time": "9:20:26"}
+{"current_steps": 50, "total_steps": 395, "loss": 1.0626, "lr": 3.993659865551998e-05, "epoch": 0.6329113924050633, "percentage": 12.66, "elapsed_time": "1:20:16", "remaining_time": "9:13:55"}
+{"current_steps": 55, "total_steps": 395, "loss": 1.0429, "lr": 3.984669951939583e-05, "epoch": 0.6962025316455697, "percentage": 13.92, "elapsed_time": "1:27:48", "remaining_time": "9:02:51"}
+{"current_steps": 60, "total_steps": 395, "loss": 1.0611, "lr": 3.971794953696041e-05, "epoch": 0.759493670886076, "percentage": 15.19, "elapsed_time": "1:35:40", "remaining_time": "8:54:09"}
+{"current_steps": 65, "total_steps": 395, "loss": 1.0622, "lr": 3.955060074235045e-05, "epoch": 0.8227848101265823, "percentage": 16.46, "elapsed_time": "1:43:50", "remaining_time": "8:47:13"}
+{"current_steps": 70, "total_steps": 395, "loss": 1.0448, "lr": 3.934498072869008e-05, "epoch": 0.8860759493670886, "percentage": 17.72, "elapsed_time": "1:51:59", "remaining_time": "8:39:56"}
+{"current_steps": 75, "total_steps": 395, "loss": 1.0382, "lr": 3.910149200681199e-05, "epoch": 0.9493670886075949, "percentage": 18.99, "elapsed_time": "2:00:06", "remaining_time": "8:32:25"}
+{"current_steps": 80, "total_steps": 395, "loss": 1.0114, "lr": 3.882061121732349e-05, "epoch": 1.0126582278481013, "percentage": 20.25, "elapsed_time": "2:07:56", "remaining_time": "8:23:44"}
+{"current_steps": 85, "total_steps": 395, "loss": 0.8861, "lr": 3.850288819756019e-05, "epoch": 1.0759493670886076, "percentage": 21.52, "elapsed_time": "2:15:46", "remaining_time": "8:15:10"}
+{"current_steps": 90, "total_steps": 395, "loss": 0.929, "lr": 3.814894490525356e-05, "epoch": 1.139240506329114, "percentage": 22.78, "elapsed_time": "2:23:26", "remaining_time": "8:06:07"}
+{"current_steps": 95, "total_steps": 395, "loss": 0.888, "lr": 3.775947420101948e-05, "epoch": 1.2025316455696202, "percentage": 24.05, "elapsed_time": "2:31:08", "remaining_time": "7:57:16"}
+{"current_steps": 100, "total_steps": 395, "loss": 0.8759, "lr": 3.733523849205105e-05, "epoch": 1.2658227848101267, "percentage": 25.32, "elapsed_time": "2:39:12", "remaining_time": "7:49:40"}
+{"current_steps": 105, "total_steps": 395, "loss": 0.9184, "lr": 3.687706823967073e-05, "epoch": 1.3291139240506329, "percentage": 26.58, "elapsed_time": "2:47:17", "remaining_time": "7:42:02"}
+{"current_steps": 110, "total_steps": 395, "loss": 0.8784, "lr": 3.6385860333663236e-05, "epoch": 1.3924050632911391, "percentage": 27.85, "elapsed_time": "2:55:23", "remaining_time": "7:34:24"}
+{"current_steps": 115, "total_steps": 395, "loss": 0.8814, "lr": 3.5862576336571725e-05, "epoch": 1.4556962025316456, "percentage": 29.11, "elapsed_time": "3:03:41", "remaining_time": "7:27:15"}
+{"current_steps": 120, "total_steps": 395, "loss": 0.9016, "lr": 3.530824060139396e-05, "epoch": 1.518987341772152, "percentage": 30.38, "elapsed_time": "3:11:21", "remaining_time": "7:18:30"}
+{"current_steps": 125, "total_steps": 395, "loss": 0.9145, "lr": 3.472393826636317e-05, "epoch": 1.5822784810126582, "percentage": 31.65, "elapsed_time": "3:19:33", "remaining_time": "7:11:03"}
+{"current_steps": 130, "total_steps": 395, "loss": 0.8916, "lr": 3.411081313073906e-05, "epoch": 1.6455696202531644, "percentage": 32.91, "elapsed_time": "3:27:37", "remaining_time": "7:03:15"}
+{"current_steps": 135, "total_steps": 395, "loss": 0.8931, "lr": 3.3470065415767004e-05, "epoch": 1.7088607594936709, "percentage": 34.18, "elapsed_time": "3:35:34", "remaining_time": "6:55:10"}
+{"current_steps": 140, "total_steps": 395, "loss": 0.8628, "lr": 3.28029494151886e-05, "epoch": 1.7721518987341773, "percentage": 35.44, "elapsed_time": "3:43:18", "remaining_time": "6:46:45"}
+{"current_steps": 145, "total_steps": 395, "loss": 0.8668, "lr": 3.211077103990278e-05, "epoch": 1.8354430379746836, "percentage": 36.71, "elapsed_time": "3:51:22", "remaining_time": "6:38:55"}
+{"current_steps": 150, "total_steps": 395, "loss": 0.8731, "lr": 3.13948852615839e-05, "epoch": 1.8987341772151898, "percentage": 37.97, "elapsed_time": "3:59:21", "remaining_time": "6:30:57"}
+{"current_steps": 155, "total_steps": 395, "loss": 0.8877, "lr": 3.065669346026106e-05, "epoch": 1.9620253164556962, "percentage": 39.24, "elapsed_time": "4:07:22", "remaining_time": "6:23:02"}
+{"current_steps": 160, "total_steps": 395, "loss": 0.8092, "lr": 2.9897640681050877e-05, "epoch": 2.0253164556962027, "percentage": 40.51, "elapsed_time": "4:14:53", "remaining_time": "6:14:21"}
+{"current_steps": 165, "total_steps": 395, "loss": 0.7009, "lr": 2.91192128054138e-05, "epoch": 2.088607594936709, "percentage": 41.77, "elapsed_time": "4:22:49", "remaining_time": "6:06:22"}
+{"current_steps": 170, "total_steps": 395, "loss": 0.7011, "lr": 2.832293364247141e-05, "epoch": 2.151898734177215, "percentage": 43.04, "elapsed_time": "4:30:49", "remaining_time": "5:58:27"}
+{"current_steps": 175, "total_steps": 395, "loss": 0.7099, "lr": 2.7510361946078482e-05, "epoch": 2.2151898734177213, "percentage": 44.3, "elapsed_time": "4:38:47", "remaining_time": "5:50:29"}
+{"current_steps": 180, "total_steps": 395, "loss": 0.6843, "lr": 2.6683088363489118e-05, "epoch": 2.278481012658228, "percentage": 45.57, "elapsed_time": "4:46:43", "remaining_time": "5:42:28"}
+{"current_steps": 185, "total_steps": 395, "loss": 0.6784, "lr": 2.5842732321590034e-05, "epoch": 2.3417721518987342, "percentage": 46.84, "elapsed_time": "4:54:45", "remaining_time": "5:34:34"}
+{"current_steps": 190, "total_steps": 395, "loss": 0.6919, "lr": 2.499093885679642e-05, "epoch": 2.4050632911392404, "percentage": 48.1, "elapsed_time": "5:02:25", "remaining_time": "5:26:18"}
+{"current_steps": 195, "total_steps": 395, "loss": 0.6813, "lr": 2.4129375394815878e-05, "epoch": 2.4683544303797467, "percentage": 49.37, "elapsed_time": "5:10:46", "remaining_time": "5:18:44"}
+{"current_steps": 200, "total_steps": 395, "loss": 0.7073, "lr": 2.3259728486584297e-05, "epoch": 2.5316455696202533, "percentage": 50.63, "elapsed_time": "5:18:30", "remaining_time": "5:10:33"}
+{"current_steps": 205, "total_steps": 395, "loss": 0.6961, "lr": 2.2383700506763204e-05, "epoch": 2.5949367088607596, "percentage": 51.9, "elapsed_time": "5:26:24", "remaining_time": "5:02:31"}
+{"current_steps": 210, "total_steps": 395, "loss": 0.6864, "lr": 2.150300632126142e-05, "epoch": 2.6582278481012658, "percentage": 53.16, "elapsed_time": "5:34:02", "remaining_time": "4:54:16"}
+{"current_steps": 215, "total_steps": 395, "loss": 0.6952, "lr": 2.061936993030451e-05, "epoch": 2.721518987341772, "percentage": 54.43, "elapsed_time": "5:41:57", "remaining_time": "4:46:17"}
+{"current_steps": 220, "total_steps": 395, "loss": 0.6829, "lr": 1.9734521093623388e-05, "epoch": 2.7848101265822782, "percentage": 55.7, "elapsed_time": "5:49:58", "remaining_time": "4:38:23"}
+{"current_steps": 225, "total_steps": 395, "loss": 0.6969, "lr": 1.88501919443684e-05, "epoch": 2.848101265822785, "percentage": 56.96, "elapsed_time": "5:57:54", "remaining_time": "4:30:25"}
+{"current_steps": 230, "total_steps": 395, "loss": 0.6984, "lr": 1.7968113598377356e-05, "epoch": 2.911392405063291, "percentage": 58.23, "elapsed_time": "6:06:03", "remaining_time": "4:22:36"}
+{"current_steps": 235, "total_steps": 395, "loss": 0.69, "lr": 1.7090012765434974e-05, "epoch": 2.9746835443037973, "percentage": 59.49, "elapsed_time": "6:14:34", "remaining_time": "4:15:02"}
+{"current_steps": 240, "total_steps": 395, "loss": 0.6373, "lr": 1.6217608369157417e-05, "epoch": 3.037974683544304, "percentage": 60.76, "elapsed_time": "6:22:07", "remaining_time": "4:06:47"}
+{"current_steps": 245, "total_steps": 395, "loss": 0.539, "lr": 1.5352608182118546e-05, "epoch": 3.1012658227848102, "percentage": 62.03, "elapsed_time": "6:30:22", "remaining_time": "3:59:00"}
+{"current_steps": 250, "total_steps": 395, "loss": 0.5206, "lr": 1.4496705482804943e-05, "epoch": 3.1645569620253164, "percentage": 63.29, "elapsed_time": "6:38:10", "remaining_time": "3:50:56"}
+{"current_steps": 255, "total_steps": 395, "loss": 0.5281, "lr": 1.3651575740943746e-05, "epoch": 3.2278481012658227, "percentage": 64.56, "elapsed_time": "6:46:13", "remaining_time": "3:43:01"}
+{"current_steps": 260, "total_steps": 395, "loss": 0.5172, "lr": 1.2818873337691993e-05, "epoch": 3.291139240506329, "percentage": 65.82, "elapsed_time": "6:54:13", "remaining_time": "3:35:04"}
+{"current_steps": 265, "total_steps": 395, "loss": 0.5416, "lr": 1.2000228327107787e-05, "epoch": 3.3544303797468356, "percentage": 67.09, "elapsed_time": "7:02:15", "remaining_time": "3:27:08"}
+{"current_steps": 270, "total_steps": 395, "loss": 0.5105, "lr": 1.1197243245242978e-05, "epoch": 3.4177215189873418, "percentage": 68.35, "elapsed_time": "7:10:17", "remaining_time": "3:19:12"}
+{"current_steps": 275, "total_steps": 395, "loss": 0.526, "lr": 1.0411489973103525e-05, "epoch": 3.481012658227848, "percentage": 69.62, "elapsed_time": "7:18:21", "remaining_time": "3:11:16"}
+{"current_steps": 280, "total_steps": 395, "loss": 0.5052, "lr": 9.64450665961866e-06, "epoch": 3.5443037974683547, "percentage": 70.89, "elapsed_time": "7:26:32", "remaining_time": "3:03:23"}
+{"current_steps": 285, "total_steps": 395, "loss": 0.5141, "lr": 8.897794710642098e-06, "epoch": 3.607594936708861, "percentage": 72.15, "elapsed_time": "7:34:38", "remaining_time": "2:55:28"}
+{"current_steps": 290, "total_steps": 395, "loss": 0.5337, "lr": 8.172815849879607e-06, "epoch": 3.670886075949367, "percentage": 73.42, "elapsed_time": "7:41:57", "remaining_time": "2:47:15"}
+{"current_steps": 295, "total_steps": 395, "loss": 0.5187, "lr": 7.470989257496164e-06, "epoch": 3.7341772151898733, "percentage": 74.68, "elapsed_time": "7:50:09", "remaining_time": "2:39:22"}
+{"current_steps": 300, "total_steps": 395, "loss": 0.5111, "lr": 6.7936887920041825e-06, "epoch": 3.7974683544303796, "percentage": 75.95, "elapsed_time": "7:58:01", "remaining_time": "2:31:22"}
+{"current_steps": 305, "total_steps": 395, "loss": 0.5328, "lr": 6.1422403008709255e-06, "epoch": 3.8607594936708862, "percentage": 77.22, "elapsed_time": "8:06:01", "remaining_time": "2:23:25"}
+{"current_steps": 310, "total_steps": 395, "loss": 0.51, "lr": 5.517919025109839e-06, "epoch": 3.9240506329113924, "percentage": 78.48, "elapsed_time": "8:14:09", "remaining_time": "2:15:29"}
+{"current_steps": 315, "total_steps": 395, "loss": 0.5098, "lr": 4.921947102936388e-06, "epoch": 3.9873417721518987, "percentage": 79.75, "elapsed_time": "8:22:01", "remaining_time": "2:07:29"}
+{"current_steps": 320, "total_steps": 395, "loss": 0.4576, "lr": 4.3554911773751e-06, "epoch": 4.050632911392405, "percentage": 81.01, "elapsed_time": "8:30:09", "remaining_time": "1:59:34"}
+{"current_steps": 325, "total_steps": 395, "loss": 0.4179, "lr": 3.819660112501053e-06, "epoch": 4.113924050632911, "percentage": 82.28, "elapsed_time": "8:37:54", "remaining_time": "1:51:32"}
+{"current_steps": 330, "total_steps": 395, "loss": 0.3929, "lr": 3.315502822786407e-06, "epoch": 4.177215189873418, "percentage": 83.54, "elapsed_time": "8:45:51", "remaining_time": "1:43:34"}
+{"current_steps": 335, "total_steps": 395, "loss": 0.4279, "lr": 2.8440062198010187e-06, "epoch": 4.2405063291139244, "percentage": 84.81, "elapsed_time": "8:53:26", "remaining_time": "1:35:32"}
+{"current_steps": 340, "total_steps": 395, "loss": 0.4249, "lr": 2.4060932802867498e-06, "epoch": 4.30379746835443, "percentage": 86.08, "elapsed_time": "9:01:21", "remaining_time": "1:27:34"}
+{"current_steps": 345, "total_steps": 395, "loss": 0.4119, "lr": 2.0026212393871057e-06, "epoch": 4.367088607594937, "percentage": 87.34, "elapsed_time": "9:09:26", "remaining_time": "1:19:37"}
+{"current_steps": 350, "total_steps": 395, "loss": 0.4302, "lr": 1.6343799125692194e-06, "epoch": 4.430379746835443, "percentage": 88.61, "elapsed_time": "9:17:25", "remaining_time": "1:11:40"}
+{"current_steps": 355, "total_steps": 395, "loss": 0.4067, "lr": 1.3020901495229632e-06, "epoch": 4.493670886075949, "percentage": 89.87, "elapsed_time": "9:25:09", "remaining_time": "1:03:40"}
+{"current_steps": 360, "total_steps": 395, "loss": 0.4346, "lr": 1.0064024230638547e-06, "epoch": 4.556962025316456, "percentage": 91.14, "elapsed_time": "9:33:07", "remaining_time": "0:55:43"}
+{"current_steps": 365, "total_steps": 395, "loss": 0.412, "lr": 7.478955558019408e-07, "epoch": 4.620253164556962, "percentage": 92.41, "elapsed_time": "9:41:12", "remaining_time": "0:47:46"}
+{"current_steps": 370, "total_steps": 395, "loss": 0.4171, "lr": 5.270755870693877e-07, "epoch": 4.6835443037974684, "percentage": 93.67, "elapsed_time": "9:49:20", "remaining_time": "0:39:49"}
+{"current_steps": 375, "total_steps": 395, "loss": 0.4082, "lr": 3.4437478232470123e-07, "epoch": 4.746835443037975, "percentage": 94.94, "elapsed_time": "9:57:04", "remaining_time": "0:31:50"}
+{"current_steps": 380, "total_steps": 395, "loss": 0.4122, "lr": 2.0015078697281477e-07, "epoch": 4.810126582278481, "percentage": 96.2, "elapsed_time": "10:05:29", "remaining_time": "0:23:54"}
+{"current_steps": 385, "total_steps": 395, "loss": 0.4003, "lr": 9.46859262573896e-08, "epoch": 4.8734177215189876, "percentage": 97.47, "elapsed_time": "10:13:10", "remaining_time": "0:15:55"}
+{"current_steps": 390, "total_steps": 395, "loss": 0.4297, "lr": 2.8186652595918464e-08, "epoch": 4.936708860759493, "percentage": 98.73, "elapsed_time": "10:20:51", "remaining_time": "0:07:57"}
+{"current_steps": 395, "total_steps": 395, "loss": 0.4124, "lr": 7.831414393999481e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "10:28:50", "remaining_time": "0:00:00"}
+{"current_steps": 395, "total_steps": 395, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "10:28:50", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,596 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 395,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.06329113924050633,
+      "grad_norm": 8.190221366047021,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 1.6528,
+      "step": 5
+    },
+    {
+      "epoch": 0.12658227848101267,
+      "grad_norm": 2.0302478881380908,
+      "learning_rate": 9e-06,
+      "loss": 1.433,
+      "step": 10
+    },
+    {
+      "epoch": 0.189873417721519,
+      "grad_norm": 0.9035030619527921,
+      "learning_rate": 1.4e-05,
+      "loss": 1.2997,
+      "step": 15
+    },
+    {
+      "epoch": 0.25316455696202533,
+      "grad_norm": 0.6411978704213375,
+      "learning_rate": 1.9e-05,
+      "loss": 1.2252,
+      "step": 20
+    },
+    {
+      "epoch": 0.31645569620253167,
+      "grad_norm": 0.4729734480029101,
+      "learning_rate": 2.4e-05,
+      "loss": 1.1621,
+      "step": 25
+    },
+    {
+      "epoch": 0.379746835443038,
+      "grad_norm": 0.39623906335790865,
+      "learning_rate": 2.9e-05,
+      "loss": 1.1294,
+      "step": 30
+    },
+    {
+      "epoch": 0.4430379746835443,
+      "grad_norm": 0.35838538383752355,
+      "learning_rate": 3.4e-05,
+      "loss": 1.1227,
+      "step": 35
+    },
+    {
+      "epoch": 0.5063291139240507,
+      "grad_norm": 0.3972117468174211,
+      "learning_rate": 3.9e-05,
+      "loss": 1.0958,
+      "step": 40
+    },
+    {
+      "epoch": 0.569620253164557,
+      "grad_norm": 0.38312860456168585,
+      "learning_rate": 3.998747096355221e-05,
+      "loss": 1.0891,
+      "step": 45
+    },
+    {
+      "epoch": 0.6329113924050633,
+      "grad_norm": 0.36710577735917843,
+      "learning_rate": 3.993659865551998e-05,
+      "loss": 1.0626,
+      "step": 50
+    },
+    {
+      "epoch": 0.6962025316455697,
+      "grad_norm": 0.3349682144567762,
+      "learning_rate": 3.984669951939583e-05,
+      "loss": 1.0429,
+      "step": 55
+    },
+    {
+      "epoch": 0.759493670886076,
+      "grad_norm": 0.3620969332045494,
+      "learning_rate": 3.971794953696041e-05,
+      "loss": 1.0611,
+      "step": 60
+    },
+    {
+      "epoch": 0.8227848101265823,
+      "grad_norm": 0.33980748949320766,
+      "learning_rate": 3.955060074235045e-05,
+      "loss": 1.0622,
+      "step": 65
+    },
+    {
+      "epoch": 0.8860759493670886,
+      "grad_norm": 0.35220506114218925,
+      "learning_rate": 3.934498072869008e-05,
+      "loss": 1.0448,
+      "step": 70
+    },
+    {
+      "epoch": 0.9493670886075949,
+      "grad_norm": 0.3345475666867474,
+      "learning_rate": 3.910149200681199e-05,
+      "loss": 1.0382,
+      "step": 75
+    },
+    {
+      "epoch": 1.0126582278481013,
+      "grad_norm": 0.5835942213568852,
+      "learning_rate": 3.882061121732349e-05,
+      "loss": 1.0114,
+      "step": 80
+    },
+    {
+      "epoch": 1.0759493670886076,
+      "grad_norm": 0.490279488075702,
+      "learning_rate": 3.850288819756019e-05,
+      "loss": 0.8861,
+      "step": 85
+    },
+    {
+      "epoch": 1.139240506329114,
+      "grad_norm": 0.36798975076726864,
+      "learning_rate": 3.814894490525356e-05,
+      "loss": 0.929,
+      "step": 90
+    },
+    {
+      "epoch": 1.2025316455696202,
+      "grad_norm": 0.4166137764276443,
+      "learning_rate": 3.775947420101948e-05,
+      "loss": 0.888,
+      "step": 95
+    },
+    {
+      "epoch": 1.2658227848101267,
+      "grad_norm": 0.36773960752890966,
+      "learning_rate": 3.733523849205105e-05,
+      "loss": 0.8759,
+      "step": 100
+    },
+    {
+      "epoch": 1.3291139240506329,
+      "grad_norm": 0.31732076539896936,
+      "learning_rate": 3.687706823967073e-05,
+      "loss": 0.9184,
+      "step": 105
+    },
+    {
+      "epoch": 1.3924050632911391,
+      "grad_norm": 0.35595264578026214,
+      "learning_rate": 3.6385860333663236e-05,
+      "loss": 0.8784,
+      "step": 110
+    },
+    {
+      "epoch": 1.4556962025316456,
+      "grad_norm": 0.33660269368665974,
+      "learning_rate": 3.5862576336571725e-05,
+      "loss": 0.8814,
+      "step": 115
+    },
+    {
+      "epoch": 1.518987341772152,
+      "grad_norm": 0.38557057544668505,
+      "learning_rate": 3.530824060139396e-05,
+      "loss": 0.9016,
+      "step": 120
+    },
+    {
+      "epoch": 1.5822784810126582,
+      "grad_norm": 0.33702770153593836,
+      "learning_rate": 3.472393826636317e-05,
+      "loss": 0.9145,
+      "step": 125
+    },
+    {
+      "epoch": 1.6455696202531644,
+      "grad_norm": 0.3451811525905654,
+      "learning_rate": 3.411081313073906e-05,
+      "loss": 0.8916,
+      "step": 130
+    },
+    {
+      "epoch": 1.7088607594936709,
+      "grad_norm": 0.35839003670208736,
+      "learning_rate": 3.3470065415767004e-05,
+      "loss": 0.8931,
+      "step": 135
+    },
+    {
+      "epoch": 1.7721518987341773,
+      "grad_norm": 0.35474577846302596,
+      "learning_rate": 3.28029494151886e-05,
+      "loss": 0.8628,
+      "step": 140
+    },
+    {
+      "epoch": 1.8354430379746836,
+      "grad_norm": 0.33305048478780597,
+      "learning_rate": 3.211077103990278e-05,
+      "loss": 0.8668,
+      "step": 145
+    },
+    {
+      "epoch": 1.8987341772151898,
+      "grad_norm": 0.3534851157371203,
+      "learning_rate": 3.13948852615839e-05,
+      "loss": 0.8731,
+      "step": 150
+    },
+    {
+      "epoch": 1.9620253164556962,
+      "grad_norm": 0.3314251565751023,
+      "learning_rate": 3.065669346026106e-05,
+      "loss": 0.8877,
+      "step": 155
+    },
+    {
+      "epoch": 2.0253164556962027,
+      "grad_norm": 0.528797556904215,
+      "learning_rate": 2.9897640681050877e-05,
+      "loss": 0.8092,
+      "step": 160
+    },
+    {
+      "epoch": 2.088607594936709,
+      "grad_norm": 0.44442500024474996,
+      "learning_rate": 2.91192128054138e-05,
+      "loss": 0.7009,
+      "step": 165
+    },
+    {
+      "epoch": 2.151898734177215,
+      "grad_norm": 0.416444200678735,
+      "learning_rate": 2.832293364247141e-05,
+      "loss": 0.7011,
+      "step": 170
+    },
+    {
+      "epoch": 2.2151898734177213,
+      "grad_norm": 0.42969912298795,
+      "learning_rate": 2.7510361946078482e-05,
+      "loss": 0.7099,
+      "step": 175
+    },
+    {
+      "epoch": 2.278481012658228,
+      "grad_norm": 0.3916144378079092,
+      "learning_rate": 2.6683088363489118e-05,
+      "loss": 0.6843,
+      "step": 180
+    },
+    {
+      "epoch": 2.3417721518987342,
+      "grad_norm": 0.3513696446056463,
+      "learning_rate": 2.5842732321590034e-05,
+      "loss": 0.6784,
+      "step": 185
+    },
+    {
+      "epoch": 2.4050632911392404,
+      "grad_norm": 0.37722195477379744,
+      "learning_rate": 2.499093885679642e-05,
+      "loss": 0.6919,
+      "step": 190
+    },
+    {
+      "epoch": 2.4683544303797467,
+      "grad_norm": 0.3693875329737844,
+      "learning_rate": 2.4129375394815878e-05,
+      "loss": 0.6813,
+      "step": 195
+    },
+    {
+      "epoch": 2.5316455696202533,
+      "grad_norm": 0.36550476454804565,
+      "learning_rate": 2.3259728486584297e-05,
+      "loss": 0.7073,
+      "step": 200
+    },
+    {
+      "epoch": 2.5949367088607596,
+      "grad_norm": 0.36673126123218974,
+      "learning_rate": 2.2383700506763204e-05,
+      "loss": 0.6961,
+      "step": 205
+    },
+    {
+      "epoch": 2.6582278481012658,
+      "grad_norm": 0.3574666079741072,
+      "learning_rate": 2.150300632126142e-05,
+      "loss": 0.6864,
+      "step": 210
+    },
+    {
+      "epoch": 2.721518987341772,
+      "grad_norm": 0.37617726769282556,
+      "learning_rate": 2.061936993030451e-05,
+      "loss": 0.6952,
+      "step": 215
+    },
+    {
+      "epoch": 2.7848101265822782,
+      "grad_norm": 0.3656388281852626,
+      "learning_rate": 1.9734521093623388e-05,
+      "loss": 0.6829,
+      "step": 220
+    },
+    {
+      "epoch": 2.848101265822785,
+      "grad_norm": 0.33883760060351703,
+      "learning_rate": 1.88501919443684e-05,
+      "loss": 0.6969,
+      "step": 225
+    },
+    {
+      "epoch": 2.911392405063291,
+      "grad_norm": 0.35981527876374314,
+      "learning_rate": 1.7968113598377356e-05,
+      "loss": 0.6984,
+      "step": 230
+    },
+    {
+      "epoch": 2.9746835443037973,
+      "grad_norm": 0.3670812501059382,
+      "learning_rate": 1.7090012765434974e-05,
+      "loss": 0.69,
+      "step": 235
+    },
+    {
+      "epoch": 3.037974683544304,
+      "grad_norm": 0.49917176315512335,
+      "learning_rate": 1.6217608369157417e-05,
+      "loss": 0.6373,
+      "step": 240
+    },
+    {
+      "epoch": 3.1012658227848102,
+      "grad_norm": 0.5918566188787662,
+      "learning_rate": 1.5352608182118546e-05,
+      "loss": 0.539,
+      "step": 245
+    },
+    {
+      "epoch": 3.1645569620253164,
+      "grad_norm": 0.5041512334832167,
+      "learning_rate": 1.4496705482804943e-05,
+      "loss": 0.5206,
+      "step": 250
+    },
+    {
+      "epoch": 3.2278481012658227,
+      "grad_norm": 0.45653261940890033,
+      "learning_rate": 1.3651575740943746e-05,
+      "loss": 0.5281,
+      "step": 255
+    },
+    {
+      "epoch": 3.291139240506329,
+      "grad_norm": 0.43851629336794623,
+      "learning_rate": 1.2818873337691993e-05,
+      "loss": 0.5172,
+      "step": 260
+    },
+    {
+      "epoch": 3.3544303797468356,
+      "grad_norm": 0.40824593110817303,
+      "learning_rate": 1.2000228327107787e-05,
+      "loss": 0.5416,
+      "step": 265
+    },
+    {
+      "epoch": 3.4177215189873418,
+      "grad_norm": 0.4125095093522506,
+      "learning_rate": 1.1197243245242978e-05,
+      "loss": 0.5105,
+      "step": 270
+    },
+    {
+      "epoch": 3.481012658227848,
+      "grad_norm": 0.39546638971159587,
+      "learning_rate": 1.0411489973103525e-05,
+      "loss": 0.526,
+      "step": 275
+    },
+    {
+      "epoch": 3.5443037974683547,
+      "grad_norm": 0.3979523063934119,
+      "learning_rate": 9.64450665961866e-06,
+      "loss": 0.5052,
+      "step": 280
+    },
+    {
+      "epoch": 3.607594936708861,
+      "grad_norm": 0.4007566972264219,
+      "learning_rate": 8.897794710642098e-06,
+      "loss": 0.5141,
+      "step": 285
+    },
+    {
+      "epoch": 3.670886075949367,
+      "grad_norm": 0.39854536610455366,
+      "learning_rate": 8.172815849879607e-06,
+      "loss": 0.5337,
+      "step": 290
+    },
+    {
+      "epoch": 3.7341772151898733,
+      "grad_norm": 0.38032901846122297,
+      "learning_rate": 7.470989257496164e-06,
+      "loss": 0.5187,
+      "step": 295
+    },
+    {
+      "epoch": 3.7974683544303796,
+      "grad_norm": 0.37263622065605867,
+      "learning_rate": 6.7936887920041825e-06,
+      "loss": 0.5111,
+      "step": 300
+    },
+    {
+      "epoch": 3.8607594936708862,
+      "grad_norm": 0.39103621070748484,
+      "learning_rate": 6.1422403008709255e-06,
+      "loss": 0.5328,
+      "step": 305
+    },
+    {
+      "epoch": 3.9240506329113924,
+      "grad_norm": 0.3820249737884236,
+      "learning_rate": 5.517919025109839e-06,
+      "loss": 0.51,
+      "step": 310
+    },
+    {
+      "epoch": 3.9873417721518987,
+      "grad_norm": 0.3819442127092411,
+      "learning_rate": 4.921947102936388e-06,
+      "loss": 0.5098,
+      "step": 315
+    },
+    {
+      "epoch": 4.050632911392405,
+      "grad_norm": 0.45292407093983916,
+      "learning_rate": 4.3554911773751e-06,
+      "loss": 0.4576,
+      "step": 320
+    },
+    {
+      "epoch": 4.113924050632911,
+      "grad_norm": 0.6815364711164434,
+      "learning_rate": 3.819660112501053e-06,
+      "loss": 0.4179,
+      "step": 325
+    },
+    {
+      "epoch": 4.177215189873418,
+      "grad_norm": 0.40656558419724,
+      "learning_rate": 3.315502822786407e-06,
+      "loss": 0.3929,
+      "step": 330
+    },
+    {
+      "epoch": 4.2405063291139244,
+      "grad_norm": 0.44333659988830937,
+      "learning_rate": 2.8440062198010187e-06,
+      "loss": 0.4279,
+      "step": 335
+    },
+    {
+      "epoch": 4.30379746835443,
+      "grad_norm": 0.3979679289743368,
+      "learning_rate": 2.4060932802867498e-06,
+      "loss": 0.4249,
+      "step": 340
+    },
+    {
+      "epoch": 4.367088607594937,
+      "grad_norm": 0.3910383908124771,
+      "learning_rate": 2.0026212393871057e-06,
+      "loss": 0.4119,
+      "step": 345
+    },
+    {
+      "epoch": 4.430379746835443,
+      "grad_norm": 0.41359872762990135,
+      "learning_rate": 1.6343799125692194e-06,
+      "loss": 0.4302,
+      "step": 350
+    },
+    {
+      "epoch": 4.493670886075949,
+      "grad_norm": 0.36837247694605507,
+      "learning_rate": 1.3020901495229632e-06,
+      "loss": 0.4067,
+      "step": 355
+    },
+    {
+      "epoch": 4.556962025316456,
+      "grad_norm": 0.37212695119767214,
+      "learning_rate": 1.0064024230638547e-06,
+      "loss": 0.4346,
+      "step": 360
+    },
+    {
+      "epoch": 4.620253164556962,
+      "grad_norm": 0.3829623334903917,
+      "learning_rate": 7.478955558019408e-07,
+      "loss": 0.412,
+      "step": 365
+    },
+    {
+      "epoch": 4.6835443037974684,
+      "grad_norm": 0.38398801975165414,
+      "learning_rate": 5.270755870693877e-07,
+      "loss": 0.4171,
+      "step": 370
+    },
+    {
+      "epoch": 4.746835443037975,
+      "grad_norm": 0.3902403567855495,
+      "learning_rate": 3.4437478232470123e-07,
+      "loss": 0.4082,
+      "step": 375
+    },
+    {
+      "epoch": 4.810126582278481,
+      "grad_norm": 0.38211563038112484,
+      "learning_rate": 2.0015078697281477e-07,
+      "loss": 0.4122,
+      "step": 380
+    },
+    {
+      "epoch": 4.8734177215189876,
+      "grad_norm": 0.387782528773728,
+      "learning_rate": 9.46859262573896e-08,
+      "loss": 0.4003,
+      "step": 385
+    },
+    {
+      "epoch": 4.936708860759493,
+      "grad_norm": 0.41433765454771804,
+      "learning_rate": 2.8186652595918464e-08,
+      "loss": 0.4297,
+      "step": 390
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.37399343528203305,
+      "learning_rate": 7.831414393999481e-10,
+      "loss": 0.4124,
+      "step": 395
+    },
+    {
+      "epoch": 5.0,
+      "step": 395,
+      "total_flos": 717096447639552.0,
+      "train_loss": 0.7372651619247244,
+      "train_runtime": 37731.7684,
+      "train_samples_per_second": 1.34,
+      "train_steps_per_second": 0.01
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 395,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 717096447639552.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ac826840990d0368a8907f90aed5412be605e1f2c42ccd7eed41911fe1fd076
+size 7953