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-mix-v20250907-8ep
+  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-mix-v20250907-8ep
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on the rl-rag/sft-mix-v20250907 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: 8
+
+### 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 +1,30 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|eom_id|>": 151670,
+  "<|eot_id|>": 151669,
+  "<|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": 8.0,
+    "total_flos": 718744629805056.0,
+    "train_loss": 0.414989875806939,
+    "train_runtime": 39904.848,
+    "train_samples_per_second": 1.608,
+    "train_steps_per_second": 0.013
+}

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 sha256:0473470a364d7d1a47554861a38294a9dd308c70fc467f22c2fc809b0f2afa2a
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aabad5a7f2288a429f747ffb0eab84a4ed4631f68b07e6ba8d841be0a0b713b9
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2f1b8040d7758018d794b079d6d98c1ac0f197b853e409d19080be42c5b3a3a2
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8cc0bd08b701daf6495c45678905656bbc1d2d4d7aa610e2422587edb2c3f7
+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 +1,38 @@
+{
+  "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|>",
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "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:d54c74d027d5d47beb5d853147790ea13202ee3a9b92711338dcf05b6abf1ba5
+size 11423028

tokenizer_config.json

@@ -0,0 +1,257 @@
+{
+  "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
+    },
+    "151669": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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|>",
+    "<|eom_id|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|eot_id|>",
+  "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": 8.0,
+    "total_flos": 718744629805056.0,
+    "train_loss": 0.414989875806939,
+    "train_runtime": 39904.848,
+    "train_samples_per_second": 1.608,
+    "train_steps_per_second": 0.013
+}

trainer_log.jsonl

@@ -0,0 +1,101 @@
+{"current_steps": 5, "total_steps": 504, "loss": 1.6286, "lr": 3.1372549019607846e-06, "epoch": 0.07976071784646062, "percentage": 0.99, "elapsed_time": "0:07:51", "remaining_time": "13:03:36"}
+{"current_steps": 10, "total_steps": 504, "loss": 1.4082, "lr": 7.058823529411766e-06, "epoch": 0.15952143569292124, "percentage": 1.98, "elapsed_time": "0:14:24", "remaining_time": "11:52:03"}
+{"current_steps": 15, "total_steps": 504, "loss": 1.2277, "lr": 1.0980392156862747e-05, "epoch": 0.23928215353938184, "percentage": 2.98, "elapsed_time": "0:21:14", "remaining_time": "11:32:28"}
+{"current_steps": 20, "total_steps": 504, "loss": 1.1183, "lr": 1.4901960784313726e-05, "epoch": 0.3190428713858425, "percentage": 3.97, "elapsed_time": "0:27:40", "remaining_time": "11:09:49"}
+{"current_steps": 25, "total_steps": 504, "loss": 1.065, "lr": 1.8823529411764708e-05, "epoch": 0.3988035892323031, "percentage": 4.96, "elapsed_time": "0:34:34", "remaining_time": "11:02:27"}
+{"current_steps": 30, "total_steps": 504, "loss": 1.0376, "lr": 2.274509803921569e-05, "epoch": 0.4785643070787637, "percentage": 5.95, "elapsed_time": "0:41:06", "remaining_time": "10:49:29"}
+{"current_steps": 35, "total_steps": 504, "loss": 1.0193, "lr": 2.6666666666666667e-05, "epoch": 0.5583250249252243, "percentage": 6.94, "elapsed_time": "0:47:16", "remaining_time": "10:33:27"}
+{"current_steps": 40, "total_steps": 504, "loss": 1.0101, "lr": 3.0588235294117644e-05, "epoch": 0.638085742771685, "percentage": 7.94, "elapsed_time": "0:53:37", "remaining_time": "10:21:58"}
+{"current_steps": 45, "total_steps": 504, "loss": 0.9855, "lr": 3.450980392156863e-05, "epoch": 0.7178464606181456, "percentage": 8.93, "elapsed_time": "1:00:12", "remaining_time": "10:14:09"}
+{"current_steps": 50, "total_steps": 504, "loss": 0.9472, "lr": 3.8431372549019614e-05, "epoch": 0.7976071784646062, "percentage": 9.92, "elapsed_time": "1:06:56", "remaining_time": "10:07:46"}
+{"current_steps": 55, "total_steps": 504, "loss": 0.9543, "lr": 3.999567157212646e-05, "epoch": 0.8773678963110668, "percentage": 10.91, "elapsed_time": "1:13:43", "remaining_time": "10:01:51"}
+{"current_steps": 60, "total_steps": 504, "loss": 0.9476, "lr": 3.996922685294587e-05, "epoch": 0.9571286141575274, "percentage": 11.9, "elapsed_time": "1:20:20", "remaining_time": "9:54:34"}
+{"current_steps": 65, "total_steps": 504, "loss": 0.897, "lr": 3.991877385171789e-05, "epoch": 1.0319042871385842, "percentage": 12.9, "elapsed_time": "1:26:48", "remaining_time": "9:46:18"}
+{"current_steps": 70, "total_steps": 504, "loss": 0.8082, "lr": 3.9844373226268305e-05, "epoch": 1.111665004985045, "percentage": 13.89, "elapsed_time": "1:33:39", "remaining_time": "9:40:41"}
+{"current_steps": 75, "total_steps": 504, "loss": 0.8094, "lr": 3.97461144257888e-05, "epoch": 1.1914257228315055, "percentage": 14.88, "elapsed_time": "1:39:59", "remaining_time": "9:31:57"}
+{"current_steps": 80, "total_steps": 504, "loss": 0.7905, "lr": 3.9624115583295375e-05, "epoch": 1.271186440677966, "percentage": 15.87, "elapsed_time": "1:46:34", "remaining_time": "9:24:50"}
+{"current_steps": 85, "total_steps": 504, "loss": 0.8298, "lr": 3.9478523373601325e-05, "epoch": 1.3509471585244266, "percentage": 16.87, "elapsed_time": "1:53:23", "remaining_time": "9:18:58"}
+{"current_steps": 90, "total_steps": 504, "loss": 0.7867, "lr": 3.930951283697534e-05, "epoch": 1.4307078763708874, "percentage": 17.86, "elapsed_time": "2:00:02", "remaining_time": "9:12:12"}
+{"current_steps": 95, "total_steps": 504, "loss": 0.8198, "lr": 3.9117287168696956e-05, "epoch": 1.510468594217348, "percentage": 18.85, "elapsed_time": "2:06:40", "remaining_time": "9:05:20"}
+{"current_steps": 100, "total_steps": 504, "loss": 0.7834, "lr": 3.8902077474762155e-05, "epoch": 1.5902293120638085, "percentage": 19.84, "elapsed_time": "2:13:27", "remaining_time": "8:59:10"}
+{"current_steps": 105, "total_steps": 504, "loss": 0.8185, "lr": 3.866414249403295e-05, "epoch": 1.6699900299102692, "percentage": 20.83, "elapsed_time": "2:20:07", "remaining_time": "8:52:28"}
+{"current_steps": 110, "total_steps": 504, "loss": 0.8124, "lr": 3.840376828716499e-05, "epoch": 1.7497507477567298, "percentage": 21.83, "elapsed_time": "2:26:18", "remaining_time": "8:44:04"}
+{"current_steps": 115, "total_steps": 504, "loss": 0.8057, "lr": 3.812126789268712e-05, "epoch": 1.8295114656031903, "percentage": 22.82, "elapsed_time": "2:33:05", "remaining_time": "8:37:50"}
+{"current_steps": 120, "total_steps": 504, "loss": 0.8145, "lr": 3.781698095064647e-05, "epoch": 1.909272183449651, "percentage": 23.81, "elapsed_time": "2:39:31", "remaining_time": "8:30:29"}
+{"current_steps": 125, "total_steps": 504, "loss": 0.7913, "lr": 3.7491273294271386e-05, "epoch": 1.9890329012961117, "percentage": 24.8, "elapsed_time": "2:46:21", "remaining_time": "8:24:22"}
+{"current_steps": 130, "total_steps": 504, "loss": 0.6452, "lr": 3.7144536510143436e-05, "epoch": 2.0638085742771684, "percentage": 25.79, "elapsed_time": "2:52:44", "remaining_time": "8:16:59"}
+{"current_steps": 135, "total_steps": 504, "loss": 0.5773, "lr": 3.6777187467406857e-05, "epoch": 2.143569292123629, "percentage": 26.79, "elapsed_time": "2:59:00", "remaining_time": "8:09:16"}
+{"current_steps": 140, "total_steps": 504, "loss": 0.5875, "lr": 3.638966781658187e-05, "epoch": 2.22333000997009, "percentage": 27.78, "elapsed_time": "3:05:53", "remaining_time": "8:03:18"}
+{"current_steps": 145, "total_steps": 504, "loss": 0.5823, "lr": 3.598244345858412e-05, "epoch": 2.30309072781655, "percentage": 28.77, "elapsed_time": "3:12:27", "remaining_time": "7:56:29"}
+{"current_steps": 150, "total_steps": 504, "loss": 0.582, "lr": 3.555600398458885e-05, "epoch": 2.382851445663011, "percentage": 29.76, "elapsed_time": "3:19:22", "remaining_time": "7:50:31"}
+{"current_steps": 155, "total_steps": 504, "loss": 0.5911, "lr": 3.511086208741303e-05, "epoch": 2.4626121635094718, "percentage": 30.75, "elapsed_time": "3:25:48", "remaining_time": "7:43:23"}
+{"current_steps": 160, "total_steps": 504, "loss": 0.5844, "lr": 3.464755294512325e-05, "epoch": 2.542372881355932, "percentage": 31.75, "elapsed_time": "3:32:32", "remaining_time": "7:36:58"}
+{"current_steps": 165, "total_steps": 504, "loss": 0.5893, "lr": 3.4166633577610425e-05, "epoch": 2.622133599202393, "percentage": 32.74, "elapsed_time": "3:38:53", "remaining_time": "7:29:42"}
+{"current_steps": 170, "total_steps": 504, "loss": 0.5912, "lr": 3.366868217690482e-05, "epoch": 2.701894317048853, "percentage": 33.73, "elapsed_time": "3:45:04", "remaining_time": "7:22:11"}
+{"current_steps": 175, "total_steps": 504, "loss": 0.5813, "lr": 3.315429741203666e-05, "epoch": 2.781655034895314, "percentage": 34.72, "elapsed_time": "3:51:57", "remaining_time": "7:16:04"}
+{"current_steps": 180, "total_steps": 504, "loss": 0.5943, "lr": 3.2624097709277855e-05, "epoch": 2.8614157527417747, "percentage": 35.71, "elapsed_time": "3:58:19", "remaining_time": "7:08:58"}
+{"current_steps": 185, "total_steps": 504, "loss": 0.5924, "lr": 3.2078720508630427e-05, "epoch": 2.9411764705882355, "percentage": 36.71, "elapsed_time": "4:05:15", "remaining_time": "7:02:54"}
+{"current_steps": 190, "total_steps": 504, "loss": 0.5568, "lr": 3.1518821497455326e-05, "epoch": 3.015952143569292, "percentage": 37.7, "elapsed_time": "4:11:34", "remaining_time": "6:55:45"}
+{"current_steps": 195, "total_steps": 504, "loss": 0.3975, "lr": 3.094507382216312e-05, "epoch": 3.0957128614157527, "percentage": 38.69, "elapsed_time": "4:18:22", "remaining_time": "6:49:25"}
+{"current_steps": 200, "total_steps": 504, "loss": 0.3864, "lr": 3.0358167278914387e-05, "epoch": 3.1754735792622135, "percentage": 39.68, "elapsed_time": "4:24:54", "remaining_time": "6:42:40"}
+{"current_steps": 205, "total_steps": 504, "loss": 0.3815, "lr": 2.9758807484302566e-05, "epoch": 3.255234297108674, "percentage": 40.67, "elapsed_time": "4:31:28", "remaining_time": "6:35:57"}
+{"current_steps": 210, "total_steps": 504, "loss": 0.3902, "lr": 2.9147715027016593e-05, "epoch": 3.3349950149551346, "percentage": 41.67, "elapsed_time": "4:38:48", "remaining_time": "6:30:20"}
+{"current_steps": 215, "total_steps": 504, "loss": 0.3884, "lr": 2.8525624601503055e-05, "epoch": 3.4147557328015954, "percentage": 42.66, "elapsed_time": "4:45:36", "remaining_time": "6:23:55"}
+{"current_steps": 220, "total_steps": 504, "loss": 0.4097, "lr": 2.789328412466953e-05, "epoch": 3.4945164506480557, "percentage": 43.65, "elapsed_time": "4:52:03", "remaining_time": "6:17:01"}
+{"current_steps": 225, "total_steps": 504, "loss": 0.3813, "lr": 2.725145383669106e-05, "epoch": 3.5742771684945165, "percentage": 44.64, "elapsed_time": "4:58:35", "remaining_time": "6:10:14"}
+{"current_steps": 230, "total_steps": 504, "loss": 0.3874, "lr": 2.6600905387000716e-05, "epoch": 3.6540378863409773, "percentage": 45.63, "elapsed_time": "5:05:07", "remaining_time": "6:03:29"}
+{"current_steps": 235, "total_steps": 504, "loss": 0.3864, "lr": 2.594242090656335e-05, "epoch": 3.7337986041874376, "percentage": 46.63, "elapsed_time": "5:11:32", "remaining_time": "5:56:37"}
+{"current_steps": 240, "total_steps": 504, "loss": 0.4047, "lr": 2.5276792067547672e-05, "epoch": 3.8135593220338984, "percentage": 47.62, "elapsed_time": "5:17:47", "remaining_time": "5:49:34"}
+{"current_steps": 245, "total_steps": 504, "loss": 0.3849, "lr": 2.460481913152734e-05, "epoch": 3.8933200398803587, "percentage": 48.61, "elapsed_time": "5:24:33", "remaining_time": "5:43:05"}
+{"current_steps": 250, "total_steps": 504, "loss": 0.3827, "lr": 2.392730998735529e-05, "epoch": 3.9730807577268195, "percentage": 49.6, "elapsed_time": "5:31:15", "remaining_time": "5:36:33"}
+{"current_steps": 255, "total_steps": 504, "loss": 0.2996, "lr": 2.3245079179868054e-05, "epoch": 4.047856430707876, "percentage": 50.6, "elapsed_time": "5:37:30", "remaining_time": "5:29:33"}
+{"current_steps": 260, "total_steps": 504, "loss": 0.2318, "lr": 2.2558946930587907e-05, "epoch": 4.127617148554337, "percentage": 51.59, "elapsed_time": "5:44:20", "remaining_time": "5:23:08"}
+{"current_steps": 265, "total_steps": 504, "loss": 0.2264, "lr": 2.18697381516e-05, "epoch": 4.2073778664007975, "percentage": 52.58, "elapsed_time": "5:50:33", "remaining_time": "5:16:09"}
+{"current_steps": 270, "total_steps": 504, "loss": 0.2249, "lr": 2.1178281453790358e-05, "epoch": 4.287138584247258, "percentage": 53.57, "elapsed_time": "5:57:04", "remaining_time": "5:09:27"}
+{"current_steps": 275, "total_steps": 504, "loss": 0.2257, "lr": 2.0485408150636804e-05, "epoch": 4.366899302093719, "percentage": 54.56, "elapsed_time": "6:03:55", "remaining_time": "5:03:03"}
+{"current_steps": 280, "total_steps": 504, "loss": 0.2258, "lr": 1.979195125875072e-05, "epoch": 4.44666001994018, "percentage": 55.56, "elapsed_time": "6:10:37", "remaining_time": "4:56:29"}
+{"current_steps": 285, "total_steps": 504, "loss": 0.2277, "lr": 1.909874449637122e-05, "epoch": 4.526420737786641, "percentage": 56.55, "elapsed_time": "6:17:25", "remaining_time": "4:50:01"}
+{"current_steps": 290, "total_steps": 504, "loss": 0.2263, "lr": 1.84066212810157e-05, "epoch": 4.6061814556331, "percentage": 57.54, "elapsed_time": "6:24:08", "remaining_time": "4:43:28"}
+{"current_steps": 295, "total_steps": 504, "loss": 0.2309, "lr": 1.7716413727492035e-05, "epoch": 4.685942173479561, "percentage": 58.53, "elapsed_time": "6:30:04", "remaining_time": "4:36:21"}
+{"current_steps": 300, "total_steps": 504, "loss": 0.2256, "lr": 1.7028951647476862e-05, "epoch": 4.765702891326022, "percentage": 59.52, "elapsed_time": "6:36:29", "remaining_time": "4:29:37"}
+{"current_steps": 305, "total_steps": 504, "loss": 0.2366, "lr": 1.634506155186295e-05, "epoch": 4.845463609172483, "percentage": 60.52, "elapsed_time": "6:43:42", "remaining_time": "4:23:24"}
+{"current_steps": 310, "total_steps": 504, "loss": 0.2177, "lr": 1.5665565657074874e-05, "epoch": 4.9252243270189435, "percentage": 61.51, "elapsed_time": "6:50:07", "remaining_time": "4:16:39"}
+{"current_steps": 315, "total_steps": 504, "loss": 0.217, "lr": 1.4991280896547893e-05, "epoch": 5.0, "percentage": 62.5, "elapsed_time": "6:56:24", "remaining_time": "4:09:50"}
+{"current_steps": 320, "total_steps": 504, "loss": 0.1192, "lr": 1.4323017938558245e-05, "epoch": 5.079760717846461, "percentage": 63.49, "elapsed_time": "7:03:01", "remaining_time": "4:03:14"}
+{"current_steps": 325, "total_steps": 504, "loss": 0.1174, "lr": 1.3661580211585947e-05, "epoch": 5.1595214356929215, "percentage": 64.48, "elapsed_time": "7:09:56", "remaining_time": "3:56:48"}
+{"current_steps": 330, "total_steps": 504, "loss": 0.1121, "lr": 1.3007762938381619e-05, "epoch": 5.239282153539381, "percentage": 65.48, "elapsed_time": "7:16:40", "remaining_time": "3:50:14"}
+{"current_steps": 335, "total_steps": 504, "loss": 0.1191, "lr": 1.2362352179898855e-05, "epoch": 5.319042871385842, "percentage": 66.47, "elapsed_time": "7:23:20", "remaining_time": "3:43:39"}
+{"current_steps": 340, "total_steps": 504, "loss": 0.1128, "lr": 1.1726123890241439e-05, "epoch": 5.398803589232303, "percentage": 67.46, "elapsed_time": "7:30:03", "remaining_time": "3:37:05"}
+{"current_steps": 345, "total_steps": 504, "loss": 0.1144, "lr": 1.1099842983761712e-05, "epoch": 5.478564307078764, "percentage": 68.45, "elapsed_time": "7:36:28", "remaining_time": "3:30:22"}
+{"current_steps": 350, "total_steps": 504, "loss": 0.1056, "lr": 1.0484262415431536e-05, "epoch": 5.5583250249252245, "percentage": 69.44, "elapsed_time": "7:43:09", "remaining_time": "3:23:47"}
+{"current_steps": 355, "total_steps": 504, "loss": 0.1106, "lr": 9.880122275591752e-06, "epoch": 5.638085742771685, "percentage": 70.44, "elapsed_time": "7:49:47", "remaining_time": "3:17:10"}
+{"current_steps": 360, "total_steps": 504, "loss": 0.1056, "lr": 9.288148900168122e-06, "epoch": 5.717846460618146, "percentage": 71.43, "elapsed_time": "7:56:12", "remaining_time": "3:10:29"}
+{"current_steps": 365, "total_steps": 504, "loss": 0.112, "lr": 8.70905399742389e-06, "epoch": 5.797607178464606, "percentage": 72.42, "elapsed_time": "8:02:29", "remaining_time": "3:03:44"}
+{"current_steps": 370, "total_steps": 504, "loss": 0.1055, "lr": 8.143533792298545e-06, "epoch": 5.877367896311067, "percentage": 73.41, "elapsed_time": "8:08:50", "remaining_time": "2:57:02"}
+{"current_steps": 375, "total_steps": 504, "loss": 0.1054, "lr": 7.59226818936166e-06, "epoch": 5.9571286141575275, "percentage": 74.4, "elapsed_time": "8:15:36", "remaining_time": "2:50:29"}
+{"current_steps": 380, "total_steps": 504, "loss": 0.0903, "lr": 7.055919955388122e-06, "epoch": 6.031904287138584, "percentage": 75.4, "elapsed_time": "8:21:46", "remaining_time": "2:43:44"}
+{"current_steps": 385, "total_steps": 504, "loss": 0.056, "lr": 6.535133922537513e-06, "epoch": 6.111665004985045, "percentage": 76.39, "elapsed_time": "8:28:34", "remaining_time": "2:37:11"}
+{"current_steps": 390, "total_steps": 504, "loss": 0.0553, "lr": 6.0305362130956504e-06, "epoch": 6.1914257228315055, "percentage": 77.38, "elapsed_time": "8:35:12", "remaining_time": "2:30:35"}
+{"current_steps": 395, "total_steps": 504, "loss": 0.0538, "lr": 5.542733486710299e-06, "epoch": 6.271186440677966, "percentage": 78.37, "elapsed_time": "8:41:47", "remaining_time": "2:23:59"}
+{"current_steps": 400, "total_steps": 504, "loss": 0.0533, "lr": 5.072312211026125e-06, "epoch": 6.350947158524427, "percentage": 79.37, "elapsed_time": "8:48:37", "remaining_time": "2:17:26"}
+{"current_steps": 405, "total_steps": 504, "loss": 0.0579, "lr": 4.619837956595825e-06, "epoch": 6.430707876370887, "percentage": 80.36, "elapsed_time": "8:55:50", "remaining_time": "2:10:58"}
+{"current_steps": 410, "total_steps": 504, "loss": 0.0516, "lr": 4.185854716914952e-06, "epoch": 6.510468594217348, "percentage": 81.35, "elapsed_time": "9:02:37", "remaining_time": "2:04:24"}
+{"current_steps": 415, "total_steps": 504, "loss": 0.0522, "lr": 3.7708842543981928e-06, "epoch": 6.5902293120638085, "percentage": 82.34, "elapsed_time": "9:08:39", "remaining_time": "1:57:39"}
+{"current_steps": 420, "total_steps": 504, "loss": 0.0554, "lr": 3.375425473083185e-06, "epoch": 6.669990029910269, "percentage": 83.33, "elapsed_time": "9:15:17", "remaining_time": "1:51:03"}
+{"current_steps": 425, "total_steps": 504, "loss": 0.0536, "lr": 2.9999538188161705e-06, "epoch": 6.74975074775673, "percentage": 84.33, "elapsed_time": "9:21:31", "remaining_time": "1:44:22"}
+{"current_steps": 430, "total_steps": 504, "loss": 0.0511, "lr": 2.6449207076405857e-06, "epoch": 6.829511465603191, "percentage": 85.32, "elapsed_time": "9:27:56", "remaining_time": "1:37:44"}
+{"current_steps": 435, "total_steps": 504, "loss": 0.0531, "lr": 2.310752983075819e-06, "epoch": 6.909272183449651, "percentage": 86.31, "elapsed_time": "9:34:26", "remaining_time": "1:31:07"}
+{"current_steps": 440, "total_steps": 504, "loss": 0.0538, "lr": 1.9978524029386026e-06, "epoch": 6.989032901296111, "percentage": 87.3, "elapsed_time": "9:40:56", "remaining_time": "1:24:30"}
+{"current_steps": 445, "total_steps": 504, "loss": 0.0479, "lr": 1.7065951563241022e-06, "epoch": 7.063808574277169, "percentage": 88.29, "elapsed_time": "9:47:17", "remaining_time": "1:17:51"}
+{"current_steps": 450, "total_steps": 504, "loss": 0.0451, "lr": 1.437331411327274e-06, "epoch": 7.14356929212363, "percentage": 89.29, "elapsed_time": "9:54:11", "remaining_time": "1:11:18"}
+{"current_steps": 455, "total_steps": 504, "loss": 0.0373, "lr": 1.1903848940484241e-06, "epoch": 7.2233300099700894, "percentage": 90.28, "elapsed_time": "10:01:01", "remaining_time": "1:04:43"}
+{"current_steps": 460, "total_steps": 504, "loss": 0.0389, "lr": 9.660524993889386e-07, "epoch": 7.30309072781655, "percentage": 91.27, "elapsed_time": "10:07:13", "remaining_time": "0:58:04"}
+{"current_steps": 465, "total_steps": 504, "loss": 0.0345, "lr": 7.646039341052747e-07, "epoch": 7.382851445663011, "percentage": 92.26, "elapsed_time": "10:13:26", "remaining_time": "0:51:26"}
+{"current_steps": 470, "total_steps": 504, "loss": 0.0335, "lr": 5.862813925502209e-07, "epoch": 7.462612163509472, "percentage": 93.25, "elapsed_time": "10:20:03", "remaining_time": "0:44:51"}
+{"current_steps": 475, "total_steps": 504, "loss": 0.0356, "lr": 4.3129926549136057e-07, "epoch": 7.5423728813559325, "percentage": 94.25, "elapsed_time": "10:26:57", "remaining_time": "0:38:16"}
+{"current_steps": 480, "total_steps": 504, "loss": 0.0352, "lr": 2.99843882356774e-07, "epoch": 7.622133599202392, "percentage": 95.24, "elapsed_time": "10:33:40", "remaining_time": "0:31:41"}
+{"current_steps": 485, "total_steps": 504, "loss": 0.0366, "lr": 1.9207328721788653e-07, "epoch": 7.701894317048853, "percentage": 96.23, "elapsed_time": "10:40:30", "remaining_time": "0:25:05"}
+{"current_steps": 490, "total_steps": 504, "loss": 0.0355, "lr": 1.0811704877875528e-07, "epoch": 7.781655034895314, "percentage": 97.22, "elapsed_time": "10:47:01", "remaining_time": "0:18:29"}
+{"current_steps": 495, "total_steps": 504, "loss": 0.0345, "lr": 4.807610460030976e-08, "epoch": 7.861415752741775, "percentage": 98.21, "elapsed_time": "10:53:35", "remaining_time": "0:11:53"}
+{"current_steps": 500, "total_steps": 504, "loss": 0.0367, "lr": 1.202263974674045e-08, "epoch": 7.9411764705882355, "percentage": 99.21, "elapsed_time": "10:59:55", "remaining_time": "0:05:16"}
+{"current_steps": 504, "total_steps": 504, "epoch": 8.0, "percentage": 100.0, "elapsed_time": "11:05:03", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,743 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 8.0,
+  "eval_steps": 500,
+  "global_step": 504,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.07976071784646062,
+      "grad_norm": 8.951485022406759,
+      "learning_rate": 3.1372549019607846e-06,
+      "loss": 1.6286,
+      "step": 5
+    },
+    {
+      "epoch": 0.15952143569292124,
+      "grad_norm": 1.7911944426834843,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 1.4082,
+      "step": 10
+    },
+    {
+      "epoch": 0.23928215353938184,
+      "grad_norm": 1.188948888919745,
+      "learning_rate": 1.0980392156862747e-05,
+      "loss": 1.2277,
+      "step": 15
+    },
+    {
+      "epoch": 0.3190428713858425,
+      "grad_norm": 0.6895721187833729,
+      "learning_rate": 1.4901960784313726e-05,
+      "loss": 1.1183,
+      "step": 20
+    },
+    {
+      "epoch": 0.3988035892323031,
+      "grad_norm": 0.5800787932266839,
+      "learning_rate": 1.8823529411764708e-05,
+      "loss": 1.065,
+      "step": 25
+    },
+    {
+      "epoch": 0.4785643070787637,
+      "grad_norm": 0.5106042574703776,
+      "learning_rate": 2.274509803921569e-05,
+      "loss": 1.0376,
+      "step": 30
+    },
+    {
+      "epoch": 0.5583250249252243,
+      "grad_norm": 0.5130368281162043,
+      "learning_rate": 2.6666666666666667e-05,
+      "loss": 1.0193,
+      "step": 35
+    },
+    {
+      "epoch": 0.638085742771685,
+      "grad_norm": 0.5048169792373989,
+      "learning_rate": 3.0588235294117644e-05,
+      "loss": 1.0101,
+      "step": 40
+    },
+    {
+      "epoch": 0.7178464606181456,
+      "grad_norm": 0.49100483855991833,
+      "learning_rate": 3.450980392156863e-05,
+      "loss": 0.9855,
+      "step": 45
+    },
+    {
+      "epoch": 0.7976071784646062,
+      "grad_norm": 0.5082070499580861,
+      "learning_rate": 3.8431372549019614e-05,
+      "loss": 0.9472,
+      "step": 50
+    },
+    {
+      "epoch": 0.8773678963110668,
+      "grad_norm": 0.45791310359750687,
+      "learning_rate": 3.999567157212646e-05,
+      "loss": 0.9543,
+      "step": 55
+    },
+    {
+      "epoch": 0.9571286141575274,
+      "grad_norm": 0.45379188386242486,
+      "learning_rate": 3.996922685294587e-05,
+      "loss": 0.9476,
+      "step": 60
+    },
+    {
+      "epoch": 1.0319042871385842,
+      "grad_norm": 0.6240889944377968,
+      "learning_rate": 3.991877385171789e-05,
+      "loss": 0.897,
+      "step": 65
+    },
+    {
+      "epoch": 1.111665004985045,
+      "grad_norm": 0.5440466161961147,
+      "learning_rate": 3.9844373226268305e-05,
+      "loss": 0.8082,
+      "step": 70
+    },
+    {
+      "epoch": 1.1914257228315055,
+      "grad_norm": 0.5107070923561905,
+      "learning_rate": 3.97461144257888e-05,
+      "loss": 0.8094,
+      "step": 75
+    },
+    {
+      "epoch": 1.271186440677966,
+      "grad_norm": 0.4651202387725849,
+      "learning_rate": 3.9624115583295375e-05,
+      "loss": 0.7905,
+      "step": 80
+    },
+    {
+      "epoch": 1.3509471585244266,
+      "grad_norm": 0.4774453312775275,
+      "learning_rate": 3.9478523373601325e-05,
+      "loss": 0.8298,
+      "step": 85
+    },
+    {
+      "epoch": 1.4307078763708874,
+      "grad_norm": 0.4556406153190642,
+      "learning_rate": 3.930951283697534e-05,
+      "loss": 0.7867,
+      "step": 90
+    },
+    {
+      "epoch": 1.510468594217348,
+      "grad_norm": 0.4830106629278,
+      "learning_rate": 3.9117287168696956e-05,
+      "loss": 0.8198,
+      "step": 95
+    },
+    {
+      "epoch": 1.5902293120638085,
+      "grad_norm": 0.5022923875137891,
+      "learning_rate": 3.8902077474762155e-05,
+      "loss": 0.7834,
+      "step": 100
+    },
+    {
+      "epoch": 1.6699900299102692,
+      "grad_norm": 0.44123948565588444,
+      "learning_rate": 3.866414249403295e-05,
+      "loss": 0.8185,
+      "step": 105
+    },
+    {
+      "epoch": 1.7497507477567298,
+      "grad_norm": 0.4430352770475653,
+      "learning_rate": 3.840376828716499e-05,
+      "loss": 0.8124,
+      "step": 110
+    },
+    {
+      "epoch": 1.8295114656031903,
+      "grad_norm": 0.4924851273312515,
+      "learning_rate": 3.812126789268712e-05,
+      "loss": 0.8057,
+      "step": 115
+    },
+    {
+      "epoch": 1.909272183449651,
+      "grad_norm": 0.46057083006170463,
+      "learning_rate": 3.781698095064647e-05,
+      "loss": 0.8145,
+      "step": 120
+    },
+    {
+      "epoch": 1.9890329012961117,
+      "grad_norm": 0.4611804285939624,
+      "learning_rate": 3.7491273294271386e-05,
+      "loss": 0.7913,
+      "step": 125
+    },
+    {
+      "epoch": 2.0638085742771684,
+      "grad_norm": 0.6959783330087537,
+      "learning_rate": 3.7144536510143436e-05,
+      "loss": 0.6452,
+      "step": 130
+    },
+    {
+      "epoch": 2.143569292123629,
+      "grad_norm": 0.5166517982510289,
+      "learning_rate": 3.6777187467406857e-05,
+      "loss": 0.5773,
+      "step": 135
+    },
+    {
+      "epoch": 2.22333000997009,
+      "grad_norm": 0.571267388696848,
+      "learning_rate": 3.638966781658187e-05,
+      "loss": 0.5875,
+      "step": 140
+    },
+    {
+      "epoch": 2.30309072781655,
+      "grad_norm": 0.5939430686190696,
+      "learning_rate": 3.598244345858412e-05,
+      "loss": 0.5823,
+      "step": 145
+    },
+    {
+      "epoch": 2.382851445663011,
+      "grad_norm": 0.5778600291078902,
+      "learning_rate": 3.555600398458885e-05,
+      "loss": 0.582,
+      "step": 150
+    },
+    {
+      "epoch": 2.4626121635094718,
+      "grad_norm": 0.5529898865422133,
+      "learning_rate": 3.511086208741303e-05,
+      "loss": 0.5911,
+      "step": 155
+    },
+    {
+      "epoch": 2.542372881355932,
+      "grad_norm": 0.5081756947326533,
+      "learning_rate": 3.464755294512325e-05,
+      "loss": 0.5844,
+      "step": 160
+    },
+    {
+      "epoch": 2.622133599202393,
+      "grad_norm": 0.4848619192082748,
+      "learning_rate": 3.4166633577610425e-05,
+      "loss": 0.5893,
+      "step": 165
+    },
+    {
+      "epoch": 2.701894317048853,
+      "grad_norm": 0.5322251164040472,
+      "learning_rate": 3.366868217690482e-05,
+      "loss": 0.5912,
+      "step": 170
+    },
+    {
+      "epoch": 2.781655034895314,
+      "grad_norm": 0.48557366731521723,
+      "learning_rate": 3.315429741203666e-05,
+      "loss": 0.5813,
+      "step": 175
+    },
+    {
+      "epoch": 2.8614157527417747,
+      "grad_norm": 0.48422520390869345,
+      "learning_rate": 3.2624097709277855e-05,
+      "loss": 0.5943,
+      "step": 180
+    },
+    {
+      "epoch": 2.9411764705882355,
+      "grad_norm": 0.447236488520265,
+      "learning_rate": 3.2078720508630427e-05,
+      "loss": 0.5924,
+      "step": 185
+    },
+    {
+      "epoch": 3.015952143569292,
+      "grad_norm": 1.2170595347725597,
+      "learning_rate": 3.1518821497455326e-05,
+      "loss": 0.5568,
+      "step": 190
+    },
+    {
+      "epoch": 3.0957128614157527,
+      "grad_norm": 0.9128571202802258,
+      "learning_rate": 3.094507382216312e-05,
+      "loss": 0.3975,
+      "step": 195
+    },
+    {
+      "epoch": 3.1754735792622135,
+      "grad_norm": 0.6352191401696539,
+      "learning_rate": 3.0358167278914387e-05,
+      "loss": 0.3864,
+      "step": 200
+    },
+    {
+      "epoch": 3.255234297108674,
+      "grad_norm": 0.5562946553628527,
+      "learning_rate": 2.9758807484302566e-05,
+      "loss": 0.3815,
+      "step": 205
+    },
+    {
+      "epoch": 3.3349950149551346,
+      "grad_norm": 0.5968079984333592,
+      "learning_rate": 2.9147715027016593e-05,
+      "loss": 0.3902,
+      "step": 210
+    },
+    {
+      "epoch": 3.4147557328015954,
+      "grad_norm": 0.5987175013101326,
+      "learning_rate": 2.8525624601503055e-05,
+      "loss": 0.3884,
+      "step": 215
+    },
+    {
+      "epoch": 3.4945164506480557,
+      "grad_norm": 0.582626716390902,
+      "learning_rate": 2.789328412466953e-05,
+      "loss": 0.4097,
+      "step": 220
+    },
+    {
+      "epoch": 3.5742771684945165,
+      "grad_norm": 0.5696325846022255,
+      "learning_rate": 2.725145383669106e-05,
+      "loss": 0.3813,
+      "step": 225
+    },
+    {
+      "epoch": 3.6540378863409773,
+      "grad_norm": 0.6291341426490248,
+      "learning_rate": 2.6600905387000716e-05,
+      "loss": 0.3874,
+      "step": 230
+    },
+    {
+      "epoch": 3.7337986041874376,
+      "grad_norm": 0.5512196870000226,
+      "learning_rate": 2.594242090656335e-05,
+      "loss": 0.3864,
+      "step": 235
+    },
+    {
+      "epoch": 3.8135593220338984,
+      "grad_norm": 0.5172511656987956,
+      "learning_rate": 2.5276792067547672e-05,
+      "loss": 0.4047,
+      "step": 240
+    },
+    {
+      "epoch": 3.8933200398803587,
+      "grad_norm": 0.5434124466868848,
+      "learning_rate": 2.460481913152734e-05,
+      "loss": 0.3849,
+      "step": 245
+    },
+    {
+      "epoch": 3.9730807577268195,
+      "grad_norm": 0.5364334555823091,
+      "learning_rate": 2.392730998735529e-05,
+      "loss": 0.3827,
+      "step": 250
+    },
+    {
+      "epoch": 4.047856430707876,
+      "grad_norm": 0.6202233480341806,
+      "learning_rate": 2.3245079179868054e-05,
+      "loss": 0.2996,
+      "step": 255
+    },
+    {
+      "epoch": 4.127617148554337,
+      "grad_norm": 0.675034415488875,
+      "learning_rate": 2.2558946930587907e-05,
+      "loss": 0.2318,
+      "step": 260
+    },
+    {
+      "epoch": 4.2073778664007975,
+      "grad_norm": 0.6378422283616842,
+      "learning_rate": 2.18697381516e-05,
+      "loss": 0.2264,
+      "step": 265
+    },
+    {
+      "epoch": 4.287138584247258,
+      "grad_norm": 0.5828333823927044,
+      "learning_rate": 2.1178281453790358e-05,
+      "loss": 0.2249,
+      "step": 270
+    },
+    {
+      "epoch": 4.366899302093719,
+      "grad_norm": 0.5645506561383866,
+      "learning_rate": 2.0485408150636804e-05,
+      "loss": 0.2257,
+      "step": 275
+    },
+    {
+      "epoch": 4.44666001994018,
+      "grad_norm": 0.5286311194195279,
+      "learning_rate": 1.979195125875072e-05,
+      "loss": 0.2258,
+      "step": 280
+    },
+    {
+      "epoch": 4.526420737786641,
+      "grad_norm": 0.5354213636574895,
+      "learning_rate": 1.909874449637122e-05,
+      "loss": 0.2277,
+      "step": 285
+    },
+    {
+      "epoch": 4.6061814556331,
+      "grad_norm": 0.5132597119160957,
+      "learning_rate": 1.84066212810157e-05,
+      "loss": 0.2263,
+      "step": 290
+    },
+    {
+      "epoch": 4.685942173479561,
+      "grad_norm": 0.4992674146867158,
+      "learning_rate": 1.7716413727492035e-05,
+      "loss": 0.2309,
+      "step": 295
+    },
+    {
+      "epoch": 4.765702891326022,
+      "grad_norm": 0.5871955206074188,
+      "learning_rate": 1.7028951647476862e-05,
+      "loss": 0.2256,
+      "step": 300
+    },
+    {
+      "epoch": 4.845463609172483,
+      "grad_norm": 0.5483461557535811,
+      "learning_rate": 1.634506155186295e-05,
+      "loss": 0.2366,
+      "step": 305
+    },
+    {
+      "epoch": 4.9252243270189435,
+      "grad_norm": 0.5615291707528146,
+      "learning_rate": 1.5665565657074874e-05,
+      "loss": 0.2177,
+      "step": 310
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 0.5560610126898546,
+      "learning_rate": 1.4991280896547893e-05,
+      "loss": 0.217,
+      "step": 315
+    },
+    {
+      "epoch": 5.079760717846461,
+      "grad_norm": 0.63285574638701,
+      "learning_rate": 1.4323017938558245e-05,
+      "loss": 0.1192,
+      "step": 320
+    },
+    {
+      "epoch": 5.1595214356929215,
+      "grad_norm": 0.51986072558017,
+      "learning_rate": 1.3661580211585947e-05,
+      "loss": 0.1174,
+      "step": 325
+    },
+    {
+      "epoch": 5.239282153539381,
+      "grad_norm": 0.4103698636395131,
+      "learning_rate": 1.3007762938381619e-05,
+      "loss": 0.1121,
+      "step": 330
+    },
+    {
+      "epoch": 5.319042871385842,
+      "grad_norm": 0.47784813487742994,
+      "learning_rate": 1.2362352179898855e-05,
+      "loss": 0.1191,
+      "step": 335
+    },
+    {
+      "epoch": 5.398803589232303,
+      "grad_norm": 0.424232714663781,
+      "learning_rate": 1.1726123890241439e-05,
+      "loss": 0.1128,
+      "step": 340
+    },
+    {
+      "epoch": 5.478564307078764,
+      "grad_norm": 0.48412806315859497,
+      "learning_rate": 1.1099842983761712e-05,
+      "loss": 0.1144,
+      "step": 345
+    },
+    {
+      "epoch": 5.5583250249252245,
+      "grad_norm": 0.4266976645996111,
+      "learning_rate": 1.0484262415431536e-05,
+      "loss": 0.1056,
+      "step": 350
+    },
+    {
+      "epoch": 5.638085742771685,
+      "grad_norm": 0.3812408369839083,
+      "learning_rate": 9.880122275591752e-06,
+      "loss": 0.1106,
+      "step": 355
+    },
+    {
+      "epoch": 5.717846460618146,
+      "grad_norm": 0.422453041096817,
+      "learning_rate": 9.288148900168122e-06,
+      "loss": 0.1056,
+      "step": 360
+    },
+    {
+      "epoch": 5.797607178464606,
+      "grad_norm": 0.4322042305854276,
+      "learning_rate": 8.70905399742389e-06,
+      "loss": 0.112,
+      "step": 365
+    },
+    {
+      "epoch": 5.877367896311067,
+      "grad_norm": 0.41261441396205645,
+      "learning_rate": 8.143533792298545e-06,
+      "loss": 0.1055,
+      "step": 370
+    },
+    {
+      "epoch": 5.9571286141575275,
+      "grad_norm": 0.4218939861247821,
+      "learning_rate": 7.59226818936166e-06,
+      "loss": 0.1054,
+      "step": 375
+    },
+    {
+      "epoch": 6.031904287138584,
+      "grad_norm": 0.4601781395305167,
+      "learning_rate": 7.055919955388122e-06,
+      "loss": 0.0903,
+      "step": 380
+    },
+    {
+      "epoch": 6.111665004985045,
+      "grad_norm": 0.42572965163147103,
+      "learning_rate": 6.535133922537513e-06,
+      "loss": 0.056,
+      "step": 385
+    },
+    {
+      "epoch": 6.1914257228315055,
+      "grad_norm": 0.39199127923177135,
+      "learning_rate": 6.0305362130956504e-06,
+      "loss": 0.0553,
+      "step": 390
+    },
+    {
+      "epoch": 6.271186440677966,
+      "grad_norm": 0.30614111878955885,
+      "learning_rate": 5.542733486710299e-06,
+      "loss": 0.0538,
+      "step": 395
+    },
+    {
+      "epoch": 6.350947158524427,
+      "grad_norm": 0.2838511806116735,
+      "learning_rate": 5.072312211026125e-06,
+      "loss": 0.0533,
+      "step": 400
+    },
+    {
+      "epoch": 6.430707876370887,
+      "grad_norm": 0.3527112901949325,
+      "learning_rate": 4.619837956595825e-06,
+      "loss": 0.0579,
+      "step": 405
+    },
+    {
+      "epoch": 6.510468594217348,
+      "grad_norm": 0.2802030569387254,
+      "learning_rate": 4.185854716914952e-06,
+      "loss": 0.0516,
+      "step": 410
+    },
+    {
+      "epoch": 6.5902293120638085,
+      "grad_norm": 0.28919103613267777,
+      "learning_rate": 3.7708842543981928e-06,
+      "loss": 0.0522,
+      "step": 415
+    },
+    {
+      "epoch": 6.669990029910269,
+      "grad_norm": 0.28238569460732055,
+      "learning_rate": 3.375425473083185e-06,
+      "loss": 0.0554,
+      "step": 420
+    },
+    {
+      "epoch": 6.74975074775673,
+      "grad_norm": 0.35381160740706563,
+      "learning_rate": 2.9999538188161705e-06,
+      "loss": 0.0536,
+      "step": 425
+    },
+    {
+      "epoch": 6.829511465603191,
+      "grad_norm": 0.27756519386816786,
+      "learning_rate": 2.6449207076405857e-06,
+      "loss": 0.0511,
+      "step": 430
+    },
+    {
+      "epoch": 6.909272183449651,
+      "grad_norm": 0.3349698709554607,
+      "learning_rate": 2.310752983075819e-06,
+      "loss": 0.0531,
+      "step": 435
+    },
+    {
+      "epoch": 6.989032901296111,
+      "grad_norm": 0.3120620614394932,
+      "learning_rate": 1.9978524029386026e-06,
+      "loss": 0.0538,
+      "step": 440
+    },
+    {
+      "epoch": 7.063808574277169,
+      "grad_norm": 0.2631675945808927,
+      "learning_rate": 1.7065951563241022e-06,
+      "loss": 0.0479,
+      "step": 445
+    },
+    {
+      "epoch": 7.14356929212363,
+      "grad_norm": 0.26021291176981515,
+      "learning_rate": 1.437331411327274e-06,
+      "loss": 0.0451,
+      "step": 450
+    },
+    {
+      "epoch": 7.2233300099700894,
+      "grad_norm": 0.2211041691097816,
+      "learning_rate": 1.1903848940484241e-06,
+      "loss": 0.0373,
+      "step": 455
+    },
+    {
+      "epoch": 7.30309072781655,
+      "grad_norm": 0.30062035959934313,
+      "learning_rate": 9.660524993889386e-07,
+      "loss": 0.0389,
+      "step": 460
+    },
+    {
+      "epoch": 7.382851445663011,
+      "grad_norm": 0.24836493024466927,
+      "learning_rate": 7.646039341052747e-07,
+      "loss": 0.0345,
+      "step": 465
+    },
+    {
+      "epoch": 7.462612163509472,
+      "grad_norm": 0.2128207343872171,
+      "learning_rate": 5.862813925502209e-07,
+      "loss": 0.0335,
+      "step": 470
+    },
+    {
+      "epoch": 7.5423728813559325,
+      "grad_norm": 0.22526753960255325,
+      "learning_rate": 4.3129926549136057e-07,
+      "loss": 0.0356,
+      "step": 475
+    },
+    {
+      "epoch": 7.622133599202392,
+      "grad_norm": 0.21640137907033566,
+      "learning_rate": 2.99843882356774e-07,
+      "loss": 0.0352,
+      "step": 480
+    },
+    {
+      "epoch": 7.701894317048853,
+      "grad_norm": 0.22957439567149518,
+      "learning_rate": 1.9207328721788653e-07,
+      "loss": 0.0366,
+      "step": 485
+    },
+    {
+      "epoch": 7.781655034895314,
+      "grad_norm": 0.20281851671161966,
+      "learning_rate": 1.0811704877875528e-07,
+      "loss": 0.0355,
+      "step": 490
+    },
+    {
+      "epoch": 7.861415752741775,
+      "grad_norm": 0.2399792418034644,
+      "learning_rate": 4.807610460030976e-08,
+      "loss": 0.0345,
+      "step": 495
+    },
+    {
+      "epoch": 7.9411764705882355,
+      "grad_norm": 0.2284150095647677,
+      "learning_rate": 1.202263974674045e-08,
+      "loss": 0.0367,
+      "step": 500
+    },
+    {
+      "epoch": 8.0,
+      "step": 504,
+      "total_flos": 718744629805056.0,
+      "train_loss": 0.414989875806939,
+      "train_runtime": 39904.848,
+      "train_samples_per_second": 1.608,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 504,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 8,
+  "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": 718744629805056.0,
+  "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:c4950f8bf5c01fb34f2e097070e76b8df21cb908d9ac2a6d1e9b4d4ffeb1f50b
+size 7953