Model save

.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 +1,60 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen3-8B
+tags:
+- llama-factory
+- generated_from_trainer
+model-index:
+- name: swesmith_with_plain_docker-sandboxes-traces-terminus-2
+  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. -->
+
+# swesmith_with_plain_docker-sandboxes-traces-terminus-2
+
+This model is a fine-tuned version of [Qwen/Qwen3-8B](https://huggingface.co/Qwen/Qwen3-8B) on an unknown 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: 16
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 64
+- total_eval_batch_size: 128
+- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 5.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.55.0
+- Pytorch 2.7.0+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
+}

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 +1,68 @@
+{
+  "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,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "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": "4.55.0",
+  "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": "4.55.0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ea19dfdf7fee89b76aa8fce0f964655f65a0376b4e9cdae82ed5d603dacfc04
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6370a7d766d4a905825ee246b3c87c1ae15929b3d50a6f6f93321657bcdddc16
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4c6f1001bc12a79dea48b8b8241152c9bcc4fe5465666f6027f034742add6179
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:316bfc1c636f86fad08ef58b3f538908eebf8cc1f0ec33166cea51ef4c4a6774
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 308224,
+    "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": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,158 @@
+{"current_steps": 5, "total_steps": 785, "loss": 0.7984, "lr": 2.0253164556962026e-06, "epoch": 0.032, "percentage": 0.64, "elapsed_time": "0:02:15", "remaining_time": "5:52:14"}
+{"current_steps": 10, "total_steps": 785, "loss": 0.7726, "lr": 4.556962025316456e-06, "epoch": 0.064, "percentage": 1.27, "elapsed_time": "0:04:22", "remaining_time": "5:39:11"}
+{"current_steps": 15, "total_steps": 785, "loss": 0.7267, "lr": 7.08860759493671e-06, "epoch": 0.096, "percentage": 1.91, "elapsed_time": "0:06:30", "remaining_time": "5:34:01"}
+{"current_steps": 20, "total_steps": 785, "loss": 0.6784, "lr": 9.620253164556963e-06, "epoch": 0.128, "percentage": 2.55, "elapsed_time": "0:08:37", "remaining_time": "5:29:59"}
+{"current_steps": 25, "total_steps": 785, "loss": 0.6379, "lr": 1.2151898734177216e-05, "epoch": 0.16, "percentage": 3.18, "elapsed_time": "0:10:43", "remaining_time": "5:25:53"}
+{"current_steps": 30, "total_steps": 785, "loss": 0.6028, "lr": 1.468354430379747e-05, "epoch": 0.192, "percentage": 3.82, "elapsed_time": "0:12:52", "remaining_time": "5:23:59"}
+{"current_steps": 35, "total_steps": 785, "loss": 0.5818, "lr": 1.7215189873417723e-05, "epoch": 0.224, "percentage": 4.46, "elapsed_time": "0:14:56", "remaining_time": "5:20:05"}
+{"current_steps": 40, "total_steps": 785, "loss": 0.5553, "lr": 1.974683544303798e-05, "epoch": 0.256, "percentage": 5.1, "elapsed_time": "0:17:05", "remaining_time": "5:18:25"}
+{"current_steps": 45, "total_steps": 785, "loss": 0.533, "lr": 2.2278481012658228e-05, "epoch": 0.288, "percentage": 5.73, "elapsed_time": "0:19:15", "remaining_time": "5:16:37"}
+{"current_steps": 50, "total_steps": 785, "loss": 0.5175, "lr": 2.481012658227848e-05, "epoch": 0.32, "percentage": 6.37, "elapsed_time": "0:21:22", "remaining_time": "5:14:06"}
+{"current_steps": 55, "total_steps": 785, "loss": 0.4966, "lr": 2.7341772151898737e-05, "epoch": 0.352, "percentage": 7.01, "elapsed_time": "0:23:26", "remaining_time": "5:11:05"}
+{"current_steps": 60, "total_steps": 785, "loss": 0.4959, "lr": 2.987341772151899e-05, "epoch": 0.384, "percentage": 7.64, "elapsed_time": "0:25:32", "remaining_time": "5:08:33"}
+{"current_steps": 65, "total_steps": 785, "loss": 0.4813, "lr": 3.240506329113924e-05, "epoch": 0.416, "percentage": 8.28, "elapsed_time": "0:27:42", "remaining_time": "5:06:58"}
+{"current_steps": 70, "total_steps": 785, "loss": 0.4741, "lr": 3.49367088607595e-05, "epoch": 0.448, "percentage": 8.92, "elapsed_time": "0:29:47", "remaining_time": "5:04:19"}
+{"current_steps": 75, "total_steps": 785, "loss": 0.4724, "lr": 3.746835443037975e-05, "epoch": 0.48, "percentage": 9.55, "elapsed_time": "0:31:56", "remaining_time": "5:02:25"}
+{"current_steps": 80, "total_steps": 785, "loss": 0.4544, "lr": 4e-05, "epoch": 0.512, "percentage": 10.19, "elapsed_time": "0:33:59", "remaining_time": "4:59:32"}
+{"current_steps": 85, "total_steps": 785, "loss": 0.4435, "lr": 3.999504991751045e-05, "epoch": 0.544, "percentage": 10.83, "elapsed_time": "0:36:08", "remaining_time": "4:57:35"}
+{"current_steps": 90, "total_steps": 785, "loss": 0.4466, "lr": 3.9980202120373464e-05, "epoch": 0.576, "percentage": 11.46, "elapsed_time": "0:38:17", "remaining_time": "4:55:39"}
+{"current_steps": 95, "total_steps": 785, "loss": 0.4435, "lr": 3.995546395837111e-05, "epoch": 0.608, "percentage": 12.1, "elapsed_time": "0:40:21", "remaining_time": "4:53:08"}
+{"current_steps": 100, "total_steps": 785, "loss": 0.4372, "lr": 3.992084767709763e-05, "epoch": 0.64, "percentage": 12.74, "elapsed_time": "0:42:20", "remaining_time": "4:50:04"}
+{"current_steps": 105, "total_steps": 785, "loss": 0.4374, "lr": 3.987637041189781e-05, "epoch": 0.672, "percentage": 13.38, "elapsed_time": "0:44:27", "remaining_time": "4:47:56"}
+{"current_steps": 110, "total_steps": 785, "loss": 0.4294, "lr": 3.982205417938482e-05, "epoch": 0.704, "percentage": 14.01, "elapsed_time": "0:46:37", "remaining_time": "4:46:05"}
+{"current_steps": 115, "total_steps": 785, "loss": 0.4277, "lr": 3.975792586654179e-05, "epoch": 0.736, "percentage": 14.65, "elapsed_time": "0:48:48", "remaining_time": "4:44:23"}
+{"current_steps": 120, "total_steps": 785, "loss": 0.4299, "lr": 3.968401721741259e-05, "epoch": 0.768, "percentage": 15.29, "elapsed_time": "0:50:50", "remaining_time": "4:41:43"}
+{"current_steps": 125, "total_steps": 785, "loss": 0.4271, "lr": 3.960036481738819e-05, "epoch": 0.8, "percentage": 15.92, "elapsed_time": "0:52:55", "remaining_time": "4:39:27"}
+{"current_steps": 130, "total_steps": 785, "loss": 0.443, "lr": 3.950701007509667e-05, "epoch": 0.832, "percentage": 16.56, "elapsed_time": "0:55:01", "remaining_time": "4:37:12"}
+{"current_steps": 135, "total_steps": 785, "loss": 0.4267, "lr": 3.940399920190552e-05, "epoch": 0.864, "percentage": 17.2, "elapsed_time": "0:57:05", "remaining_time": "4:34:55"}
+{"current_steps": 140, "total_steps": 785, "loss": 0.4208, "lr": 3.92913831890467e-05, "epoch": 0.896, "percentage": 17.83, "elapsed_time": "0:59:11", "remaining_time": "4:32:42"}
+{"current_steps": 145, "total_steps": 785, "loss": 0.4191, "lr": 3.916921778237556e-05, "epoch": 0.928, "percentage": 18.47, "elapsed_time": "1:01:24", "remaining_time": "4:31:01"}
+{"current_steps": 150, "total_steps": 785, "loss": 0.432, "lr": 3.903756345477612e-05, "epoch": 0.96, "percentage": 19.11, "elapsed_time": "1:03:31", "remaining_time": "4:28:57"}
+{"current_steps": 155, "total_steps": 785, "loss": 0.4282, "lr": 3.889648537622657e-05, "epoch": 0.992, "percentage": 19.75, "elapsed_time": "1:05:40", "remaining_time": "4:26:55"}
+{"current_steps": 160, "total_steps": 785, "loss": 0.424, "lr": 3.874605338153952e-05, "epoch": 1.0192, "percentage": 20.38, "elapsed_time": "1:07:29", "remaining_time": "4:23:36"}
+{"current_steps": 165, "total_steps": 785, "loss": 0.4193, "lr": 3.8586341935793265e-05, "epoch": 1.0512, "percentage": 21.02, "elapsed_time": "1:09:38", "remaining_time": "4:21:40"}
+{"current_steps": 170, "total_steps": 785, "loss": 0.4142, "lr": 3.841743009747089e-05, "epoch": 1.0832, "percentage": 21.66, "elapsed_time": "1:11:41", "remaining_time": "4:19:21"}
+{"current_steps": 175, "total_steps": 785, "loss": 0.412, "lr": 3.8239401479325714e-05, "epoch": 1.1152, "percentage": 22.29, "elapsed_time": "1:13:47", "remaining_time": "4:17:12"}
+{"current_steps": 180, "total_steps": 785, "loss": 0.4113, "lr": 3.8052344206992276e-05, "epoch": 1.1472, "percentage": 22.93, "elapsed_time": "1:15:53", "remaining_time": "4:15:05"}
+{"current_steps": 185, "total_steps": 785, "loss": 0.4153, "lr": 3.7856350875363396e-05, "epoch": 1.1792, "percentage": 23.57, "elapsed_time": "1:18:03", "remaining_time": "4:13:08"}
+{"current_steps": 190, "total_steps": 785, "loss": 0.4137, "lr": 3.765151850275497e-05, "epoch": 1.2112, "percentage": 24.2, "elapsed_time": "1:20:13", "remaining_time": "4:11:13"}
+{"current_steps": 195, "total_steps": 785, "loss": 0.4116, "lr": 3.7437948482881104e-05, "epoch": 1.2432, "percentage": 24.84, "elapsed_time": "1:22:16", "remaining_time": "4:08:55"}
+{"current_steps": 200, "total_steps": 785, "loss": 0.4124, "lr": 3.721574653466336e-05, "epoch": 1.2752, "percentage": 25.48, "elapsed_time": "1:24:19", "remaining_time": "4:06:38"}
+{"current_steps": 205, "total_steps": 785, "loss": 0.4072, "lr": 3.698502264989903e-05, "epoch": 1.3072, "percentage": 26.11, "elapsed_time": "1:26:23", "remaining_time": "4:04:24"}
+{"current_steps": 210, "total_steps": 785, "loss": 0.4073, "lr": 3.674589103881432e-05, "epoch": 1.3392, "percentage": 26.75, "elapsed_time": "1:28:27", "remaining_time": "4:02:11"}
+{"current_steps": 215, "total_steps": 785, "loss": 0.4012, "lr": 3.64984700735293e-05, "epoch": 1.3712, "percentage": 27.39, "elapsed_time": "1:30:28", "remaining_time": "3:59:52"}
+{"current_steps": 220, "total_steps": 785, "loss": 0.4043, "lr": 3.624288222946273e-05, "epoch": 1.4032, "percentage": 28.03, "elapsed_time": "1:32:31", "remaining_time": "3:57:37"}
+{"current_steps": 225, "total_steps": 785, "loss": 0.4149, "lr": 3.597925402470578e-05, "epoch": 1.4352, "percentage": 28.66, "elapsed_time": "1:34:36", "remaining_time": "3:55:27"}
+{"current_steps": 230, "total_steps": 785, "loss": 0.406, "lr": 3.570771595739445e-05, "epoch": 1.4672, "percentage": 29.3, "elapsed_time": "1:36:38", "remaining_time": "3:53:12"}
+{"current_steps": 235, "total_steps": 785, "loss": 0.4034, "lr": 3.5428402441111964e-05, "epoch": 1.4992, "percentage": 29.94, "elapsed_time": "1:38:47", "remaining_time": "3:51:12"}
+{"current_steps": 240, "total_steps": 785, "loss": 0.397, "lr": 3.5141451738352936e-05, "epoch": 1.5312000000000001, "percentage": 30.57, "elapsed_time": "1:40:55", "remaining_time": "3:49:11"}
+{"current_steps": 245, "total_steps": 785, "loss": 0.4025, "lr": 3.4847005892082266e-05, "epoch": 1.5632000000000001, "percentage": 31.21, "elapsed_time": "1:42:55", "remaining_time": "3:46:50"}
+{"current_steps": 250, "total_steps": 785, "loss": 0.401, "lr": 3.454521065542273e-05, "epoch": 1.5952, "percentage": 31.85, "elapsed_time": "1:45:06", "remaining_time": "3:44:55"}
+{"current_steps": 255, "total_steps": 785, "loss": 0.404, "lr": 3.423621541950597e-05, "epoch": 1.6272, "percentage": 32.48, "elapsed_time": "1:47:08", "remaining_time": "3:42:41"}
+{"current_steps": 260, "total_steps": 785, "loss": 0.4038, "lr": 3.3920173139522664e-05, "epoch": 1.6592, "percentage": 33.12, "elapsed_time": "1:49:10", "remaining_time": "3:40:27"}
+{"current_steps": 265, "total_steps": 785, "loss": 0.3983, "lr": 3.35972402590084e-05, "epoch": 1.6912, "percentage": 33.76, "elapsed_time": "1:51:15", "remaining_time": "3:38:18"}
+{"current_steps": 270, "total_steps": 785, "loss": 0.4023, "lr": 3.326757663240291e-05, "epoch": 1.7231999999999998, "percentage": 34.39, "elapsed_time": "1:53:18", "remaining_time": "3:36:06"}
+{"current_steps": 275, "total_steps": 785, "loss": 0.4038, "lr": 3.293134544592073e-05, "epoch": 1.7551999999999999, "percentage": 35.03, "elapsed_time": "1:55:25", "remaining_time": "3:34:02"}
+{"current_steps": 280, "total_steps": 785, "loss": 0.4006, "lr": 3.258871313677274e-05, "epoch": 1.7872, "percentage": 35.67, "elapsed_time": "1:57:26", "remaining_time": "3:31:49"}
+{"current_steps": 285, "total_steps": 785, "loss": 0.3986, "lr": 3.2239849310778316e-05, "epoch": 1.8192, "percentage": 36.31, "elapsed_time": "1:59:33", "remaining_time": "3:29:44"}
+{"current_steps": 290, "total_steps": 785, "loss": 0.4008, "lr": 3.188492665840909e-05, "epoch": 1.8512, "percentage": 36.94, "elapsed_time": "2:01:39", "remaining_time": "3:27:38"}
+{"current_steps": 295, "total_steps": 785, "loss": 0.3956, "lr": 3.1524120869305726e-05, "epoch": 1.8832, "percentage": 37.58, "elapsed_time": "2:03:47", "remaining_time": "3:25:36"}
+{"current_steps": 300, "total_steps": 785, "loss": 0.4008, "lr": 3.11576105453101e-05, "epoch": 1.9152, "percentage": 38.22, "elapsed_time": "2:05:54", "remaining_time": "3:23:33"}
+{"current_steps": 305, "total_steps": 785, "loss": 0.4029, "lr": 3.0785577112055916e-05, "epoch": 1.9472, "percentage": 38.85, "elapsed_time": "2:07:54", "remaining_time": "3:21:18"}
+{"current_steps": 310, "total_steps": 785, "loss": 0.4006, "lr": 3.040820472916153e-05, "epoch": 1.9792, "percentage": 39.49, "elapsed_time": "2:09:58", "remaining_time": "3:19:08"}
+{"current_steps": 315, "total_steps": 785, "loss": 0.3894, "lr": 3.002568019906939e-05, "epoch": 2.0064, "percentage": 40.13, "elapsed_time": "2:11:46", "remaining_time": "3:16:36"}
+{"current_steps": 320, "total_steps": 785, "loss": 0.394, "lr": 2.963819287457733e-05, "epoch": 2.0384, "percentage": 40.76, "elapsed_time": "2:13:50", "remaining_time": "3:14:28"}
+{"current_steps": 325, "total_steps": 785, "loss": 0.3915, "lr": 2.924593456510733e-05, "epoch": 2.0704, "percentage": 41.4, "elapsed_time": "2:15:49", "remaining_time": "3:12:15"}
+{"current_steps": 330, "total_steps": 785, "loss": 0.3913, "lr": 2.8849099441758306e-05, "epoch": 2.1024, "percentage": 42.04, "elapsed_time": "2:17:53", "remaining_time": "3:10:07"}
+{"current_steps": 335, "total_steps": 785, "loss": 0.3893, "lr": 2.844788394118979e-05, "epoch": 2.1344, "percentage": 42.68, "elapsed_time": "2:19:59", "remaining_time": "3:08:02"}
+{"current_steps": 340, "total_steps": 785, "loss": 0.3887, "lr": 2.8042486668384164e-05, "epoch": 2.1664, "percentage": 43.31, "elapsed_time": "2:22:02", "remaining_time": "3:05:54"}
+{"current_steps": 345, "total_steps": 785, "loss": 0.3946, "lr": 2.7633108298335582e-05, "epoch": 2.1984, "percentage": 43.95, "elapsed_time": "2:24:04", "remaining_time": "3:03:44"}
+{"current_steps": 350, "total_steps": 785, "loss": 0.388, "lr": 2.721995147671416e-05, "epoch": 2.2304, "percentage": 44.59, "elapsed_time": "2:26:08", "remaining_time": "3:01:37"}
+{"current_steps": 355, "total_steps": 785, "loss": 0.387, "lr": 2.68032207195547e-05, "epoch": 2.2624, "percentage": 45.22, "elapsed_time": "2:28:14", "remaining_time": "2:59:33"}
+{"current_steps": 360, "total_steps": 785, "loss": 0.3935, "lr": 2.6383122312019604e-05, "epoch": 2.2944, "percentage": 45.86, "elapsed_time": "2:30:25", "remaining_time": "2:57:34"}
+{"current_steps": 365, "total_steps": 785, "loss": 0.3912, "lr": 2.595986420628597e-05, "epoch": 2.3264, "percentage": 46.5, "elapsed_time": "2:32:31", "remaining_time": "2:55:30"}
+{"current_steps": 370, "total_steps": 785, "loss": 0.3911, "lr": 2.5533655918607573e-05, "epoch": 2.3584, "percentage": 47.13, "elapsed_time": "2:34:35", "remaining_time": "2:53:23"}
+{"current_steps": 375, "total_steps": 785, "loss": 0.3927, "lr": 2.510470842560259e-05, "epoch": 2.3904, "percentage": 47.77, "elapsed_time": "2:36:37", "remaining_time": "2:51:14"}
+{"current_steps": 380, "total_steps": 785, "loss": 0.3884, "lr": 2.467323405981841e-05, "epoch": 2.4224, "percentage": 48.41, "elapsed_time": "2:38:43", "remaining_time": "2:49:09"}
+{"current_steps": 385, "total_steps": 785, "loss": 0.3875, "lr": 2.423944640462533e-05, "epoch": 2.4544, "percentage": 49.04, "elapsed_time": "2:40:48", "remaining_time": "2:47:04"}
+{"current_steps": 390, "total_steps": 785, "loss": 0.3934, "lr": 2.3803560188490968e-05, "epoch": 2.4864, "percentage": 49.68, "elapsed_time": "2:42:50", "remaining_time": "2:44:55"}
+{"current_steps": 395, "total_steps": 785, "loss": 0.3875, "lr": 2.336579117868789e-05, "epoch": 2.5183999999999997, "percentage": 50.32, "elapsed_time": "2:44:57", "remaining_time": "2:42:51"}
+{"current_steps": 400, "total_steps": 785, "loss": 0.3895, "lr": 2.292635607448711e-05, "epoch": 2.5504, "percentage": 50.96, "elapsed_time": "2:47:03", "remaining_time": "2:40:47"}
+{"current_steps": 405, "total_steps": 785, "loss": 0.3827, "lr": 2.248547239989008e-05, "epoch": 2.5824, "percentage": 51.59, "elapsed_time": "2:49:03", "remaining_time": "2:38:37"}
+{"current_steps": 410, "total_steps": 785, "loss": 0.3808, "lr": 2.204335839595255e-05, "epoch": 2.6144, "percentage": 52.23, "elapsed_time": "2:51:03", "remaining_time": "2:36:27"}
+{"current_steps": 415, "total_steps": 785, "loss": 0.3871, "lr": 2.1600232912753452e-05, "epoch": 2.6464, "percentage": 52.87, "elapsed_time": "2:53:15", "remaining_time": "2:34:28"}
+{"current_steps": 420, "total_steps": 785, "loss": 0.388, "lr": 2.1156315301062293e-05, "epoch": 2.6784, "percentage": 53.5, "elapsed_time": "2:55:19", "remaining_time": "2:32:22"}
+{"current_steps": 425, "total_steps": 785, "loss": 0.3892, "lr": 2.0711825303758712e-05, "epoch": 2.7104, "percentage": 54.14, "elapsed_time": "2:57:24", "remaining_time": "2:30:16"}
+{"current_steps": 430, "total_steps": 785, "loss": 0.3903, "lr": 2.0266982947057962e-05, "epoch": 2.7424, "percentage": 54.78, "elapsed_time": "2:59:27", "remaining_time": "2:28:09"}
+{"current_steps": 435, "total_steps": 785, "loss": 0.3911, "lr": 1.9822008431596083e-05, "epoch": 2.7744, "percentage": 55.41, "elapsed_time": "3:01:32", "remaining_time": "2:26:04"}
+{"current_steps": 440, "total_steps": 785, "loss": 0.3891, "lr": 1.937712202342881e-05, "epoch": 2.8064, "percentage": 56.05, "elapsed_time": "3:03:33", "remaining_time": "2:23:55"}
+{"current_steps": 445, "total_steps": 785, "loss": 0.3841, "lr": 1.8932543944998037e-05, "epoch": 2.8384, "percentage": 56.69, "elapsed_time": "3:05:38", "remaining_time": "2:21:50"}
+{"current_steps": 450, "total_steps": 785, "loss": 0.3857, "lr": 1.8488494266119877e-05, "epoch": 2.8704, "percentage": 57.32, "elapsed_time": "3:07:38", "remaining_time": "2:19:41"}
+{"current_steps": 455, "total_steps": 785, "loss": 0.3914, "lr": 1.804519279504834e-05, "epoch": 2.9024, "percentage": 57.96, "elapsed_time": "3:09:44", "remaining_time": "2:17:36"}
+{"current_steps": 460, "total_steps": 785, "loss": 0.3852, "lr": 1.7602858969668365e-05, "epoch": 2.9344, "percentage": 58.6, "elapsed_time": "3:11:48", "remaining_time": "2:15:31"}
+{"current_steps": 465, "total_steps": 785, "loss": 0.389, "lr": 1.716171174887231e-05, "epoch": 2.9664, "percentage": 59.24, "elapsed_time": "3:13:51", "remaining_time": "2:13:24"}
+{"current_steps": 470, "total_steps": 785, "loss": 0.3844, "lr": 1.6721969504173484e-05, "epoch": 2.9984, "percentage": 59.87, "elapsed_time": "3:15:52", "remaining_time": "2:11:16"}
+{"current_steps": 475, "total_steps": 785, "loss": 0.3812, "lr": 1.628384991161041e-05, "epoch": 3.0256, "percentage": 60.51, "elapsed_time": "3:17:33", "remaining_time": "2:08:55"}
+{"current_steps": 480, "total_steps": 785, "loss": 0.3798, "lr": 1.5847569843995452e-05, "epoch": 3.0576, "percentage": 61.15, "elapsed_time": "3:19:32", "remaining_time": "2:06:47"}
+{"current_steps": 485, "total_steps": 785, "loss": 0.3797, "lr": 1.5413345263560922e-05, "epoch": 3.0896, "percentage": 61.78, "elapsed_time": "3:21:38", "remaining_time": "2:04:43"}
+{"current_steps": 490, "total_steps": 785, "loss": 0.3766, "lr": 1.4981391115056032e-05, "epoch": 3.1216, "percentage": 62.42, "elapsed_time": "3:23:39", "remaining_time": "2:02:36"}
+{"current_steps": 495, "total_steps": 785, "loss": 0.3764, "lr": 1.455192121934748e-05, "epoch": 3.1536, "percentage": 63.06, "elapsed_time": "3:25:45", "remaining_time": "2:00:32"}
+{"current_steps": 500, "total_steps": 785, "loss": 0.384, "lr": 1.4125148167576303e-05, "epoch": 3.1856, "percentage": 63.69, "elapsed_time": "3:27:49", "remaining_time": "1:58:27"}
+{"current_steps": 505, "total_steps": 785, "loss": 0.3866, "lr": 1.3701283215923563e-05, "epoch": 3.2176, "percentage": 64.33, "elapsed_time": "3:29:56", "remaining_time": "1:56:24"}
+{"current_steps": 510, "total_steps": 785, "loss": 0.376, "lr": 1.328053618103677e-05, "epoch": 3.2496, "percentage": 64.97, "elapsed_time": "3:32:04", "remaining_time": "1:54:21"}
+{"current_steps": 515, "total_steps": 785, "loss": 0.3849, "lr": 1.2863115336168916e-05, "epoch": 3.2816, "percentage": 65.61, "elapsed_time": "3:34:08", "remaining_time": "1:52:15"}
+{"current_steps": 520, "total_steps": 785, "loss": 0.3805, "lr": 1.2449227308081509e-05, "epoch": 3.3136, "percentage": 66.24, "elapsed_time": "3:36:12", "remaining_time": "1:50:11"}
+{"current_steps": 525, "total_steps": 785, "loss": 0.3846, "lr": 1.2039076974762587e-05, "epoch": 3.3456, "percentage": 66.88, "elapsed_time": "3:38:15", "remaining_time": "1:48:05"}
+{"current_steps": 530, "total_steps": 785, "loss": 0.3812, "lr": 1.163286736401044e-05, "epoch": 3.3776, "percentage": 67.52, "elapsed_time": "3:40:18", "remaining_time": "1:46:00"}
+{"current_steps": 535, "total_steps": 785, "loss": 0.3942, "lr": 1.123079955293322e-05, "epoch": 3.4096, "percentage": 68.15, "elapsed_time": "3:42:25", "remaining_time": "1:43:56"}
+{"current_steps": 540, "total_steps": 785, "loss": 0.3825, "lr": 1.0833072568414037e-05, "epoch": 3.4416, "percentage": 68.79, "elapsed_time": "3:44:28", "remaining_time": "1:41:50"}
+{"current_steps": 545, "total_steps": 785, "loss": 0.3822, "lr": 1.0439883288591057e-05, "epoch": 3.4736000000000002, "percentage": 69.43, "elapsed_time": "3:46:22", "remaining_time": "1:39:41"}
+{"current_steps": 550, "total_steps": 785, "loss": 0.3782, "lr": 1.0051426345401202e-05, "epoch": 3.5056000000000003, "percentage": 70.06, "elapsed_time": "3:48:24", "remaining_time": "1:37:35"}
+{"current_steps": 555, "total_steps": 785, "loss": 0.3784, "lr": 9.667894028235704e-06, "epoch": 3.5376, "percentage": 70.7, "elapsed_time": "3:50:26", "remaining_time": "1:35:29"}
+{"current_steps": 560, "total_steps": 785, "loss": 0.3814, "lr": 9.289476188755315e-06, "epoch": 3.5696, "percentage": 71.34, "elapsed_time": "3:52:31", "remaining_time": "1:33:25"}
+{"current_steps": 565, "total_steps": 785, "loss": 0.3787, "lr": 8.916360146912122e-06, "epoch": 3.6016, "percentage": 71.97, "elapsed_time": "3:54:35", "remaining_time": "1:31:20"}
+{"current_steps": 570, "total_steps": 785, "loss": 0.385, "lr": 8.548730598224646e-06, "epoch": 3.6336, "percentage": 72.61, "elapsed_time": "3:56:37", "remaining_time": "1:29:15"}
+{"current_steps": 575, "total_steps": 785, "loss": 0.3842, "lr": 8.186769522352053e-06, "epoch": 3.6656, "percentage": 73.25, "elapsed_time": "3:58:41", "remaining_time": "1:27:10"}
+{"current_steps": 580, "total_steps": 785, "loss": 0.3839, "lr": 7.830656093012714e-06, "epoch": 3.6976, "percentage": 73.89, "elapsed_time": "4:00:41", "remaining_time": "1:25:04"}
+{"current_steps": 585, "total_steps": 785, "loss": 0.379, "lr": 7.480566589291696e-06, "epoch": 3.7296, "percentage": 74.52, "elapsed_time": "4:02:49", "remaining_time": "1:23:00"}
+{"current_steps": 590, "total_steps": 785, "loss": 0.3801, "lr": 7.1366743083812285e-06, "epoch": 3.7616, "percentage": 75.16, "elapsed_time": "4:04:57", "remaining_time": "1:20:57"}
+{"current_steps": 595, "total_steps": 785, "loss": 0.3751, "lr": 6.799149479797101e-06, "epoch": 3.7936, "percentage": 75.8, "elapsed_time": "4:07:00", "remaining_time": "1:18:52"}
+{"current_steps": 600, "total_steps": 785, "loss": 0.3769, "lr": 6.4681591811137e-06, "epoch": 3.8256, "percentage": 76.43, "elapsed_time": "4:09:05", "remaining_time": "1:16:48"}
+{"current_steps": 605, "total_steps": 785, "loss": 0.3735, "lr": 6.143867255259197e-06, "epoch": 3.8576, "percentage": 77.07, "elapsed_time": "4:11:11", "remaining_time": "1:14:44"}
+{"current_steps": 610, "total_steps": 785, "loss": 0.3821, "lr": 5.8264342294119504e-06, "epoch": 3.8895999999999997, "percentage": 77.71, "elapsed_time": "4:13:19", "remaining_time": "1:12:40"}
+{"current_steps": 615, "total_steps": 785, "loss": 0.3769, "lr": 5.516017235538258e-06, "epoch": 3.9215999999999998, "percentage": 78.34, "elapsed_time": "4:15:17", "remaining_time": "1:10:34"}
+{"current_steps": 620, "total_steps": 785, "loss": 0.3752, "lr": 5.212769932610695e-06, "epoch": 3.9536, "percentage": 78.98, "elapsed_time": "4:17:17", "remaining_time": "1:08:28"}
+{"current_steps": 625, "total_steps": 785, "loss": 0.3734, "lr": 4.916842430545681e-06, "epoch": 3.9856, "percentage": 79.62, "elapsed_time": "4:19:23", "remaining_time": "1:06:24"}
+{"current_steps": 630, "total_steps": 785, "loss": 0.3764, "lr": 4.628381215897837e-06, "epoch": 4.0128, "percentage": 80.25, "elapsed_time": "4:21:02", "remaining_time": "1:04:13"}
+{"current_steps": 635, "total_steps": 785, "loss": 0.3853, "lr": 4.347529079347914e-06, "epoch": 4.0448, "percentage": 80.89, "elapsed_time": "4:23:10", "remaining_time": "1:02:10"}
+{"current_steps": 640, "total_steps": 785, "loss": 0.3785, "lr": 4.074425045020247e-06, "epoch": 4.0768, "percentage": 81.53, "elapsed_time": "4:25:14", "remaining_time": "1:00:05"}
+{"current_steps": 645, "total_steps": 785, "loss": 0.3707, "lr": 3.8092043016646487e-06, "epoch": 4.1088, "percentage": 82.17, "elapsed_time": "4:27:17", "remaining_time": "0:58:00"}
+{"current_steps": 650, "total_steps": 785, "loss": 0.3785, "lr": 3.551998135736867e-06, "epoch": 4.1408, "percentage": 82.8, "elapsed_time": "4:29:21", "remaining_time": "0:55:56"}
+{"current_steps": 655, "total_steps": 785, "loss": 0.3677, "lr": 3.3029338664107267e-06, "epoch": 4.1728, "percentage": 83.44, "elapsed_time": "4:31:20", "remaining_time": "0:53:51"}
+{"current_steps": 660, "total_steps": 785, "loss": 0.373, "lr": 3.0621347825540625e-06, "epoch": 4.2048, "percentage": 84.08, "elapsed_time": "4:33:21", "remaining_time": "0:51:46"}
+{"current_steps": 665, "total_steps": 785, "loss": 0.3715, "lr": 2.8297200816997183e-06, "epoch": 4.2368, "percentage": 84.71, "elapsed_time": "4:35:26", "remaining_time": "0:49:42"}
+{"current_steps": 670, "total_steps": 785, "loss": 0.3787, "lr": 2.605804811041803e-06, "epoch": 4.2688, "percentage": 85.35, "elapsed_time": "4:37:29", "remaining_time": "0:47:37"}
+{"current_steps": 675, "total_steps": 785, "loss": 0.3752, "lr": 2.390499810486351e-06, "epoch": 4.3008, "percentage": 85.99, "elapsed_time": "4:39:32", "remaining_time": "0:45:33"}
+{"current_steps": 680, "total_steps": 785, "loss": 0.3785, "lr": 2.183911657784685e-06, "epoch": 4.3328, "percentage": 86.62, "elapsed_time": "4:41:35", "remaining_time": "0:43:28"}
+{"current_steps": 685, "total_steps": 785, "loss": 0.3774, "lr": 1.986142615776532e-06, "epoch": 4.3648, "percentage": 87.26, "elapsed_time": "4:43:44", "remaining_time": "0:41:25"}
+{"current_steps": 690, "total_steps": 785, "loss": 0.3792, "lr": 1.7972905817690644e-06, "epoch": 4.3968, "percentage": 87.9, "elapsed_time": "4:45:39", "remaining_time": "0:39:19"}
+{"current_steps": 695, "total_steps": 785, "loss": 0.3781, "lr": 1.617449039076955e-06, "epoch": 4.4288, "percentage": 88.54, "elapsed_time": "4:47:41", "remaining_time": "0:37:15"}
+{"current_steps": 700, "total_steps": 785, "loss": 0.3735, "lr": 1.4467070107473413e-06, "epoch": 4.4608, "percentage": 89.17, "elapsed_time": "4:49:44", "remaining_time": "0:35:10"}
+{"current_steps": 705, "total_steps": 785, "loss": 0.3787, "lr": 1.2851490154926816e-06, "epoch": 4.4928, "percentage": 89.81, "elapsed_time": "4:51:45", "remaining_time": "0:33:06"}
+{"current_steps": 710, "total_steps": 785, "loss": 0.3772, "lr": 1.1328550258533211e-06, "epoch": 4.5248, "percentage": 90.45, "elapsed_time": "4:53:50", "remaining_time": "0:31:02"}
+{"current_steps": 715, "total_steps": 785, "loss": 0.3704, "lr": 9.899004286103953e-07, "epoch": 4.5568, "percentage": 91.08, "elapsed_time": "4:55:53", "remaining_time": "0:28:58"}
+{"current_steps": 720, "total_steps": 785, "loss": 0.3742, "lr": 8.5635598746876e-07, "epoch": 4.5888, "percentage": 91.72, "elapsed_time": "4:58:02", "remaining_time": "0:26:54"}
+{"current_steps": 725, "total_steps": 785, "loss": 0.3793, "lr": 7.32287808028389e-07, "epoch": 4.6208, "percentage": 92.36, "elapsed_time": "5:00:01", "remaining_time": "0:24:49"}
+{"current_steps": 730, "total_steps": 785, "loss": 0.3791, "lr": 6.177573050615327e-07, "epoch": 4.6528, "percentage": 92.99, "elapsed_time": "5:02:04", "remaining_time": "0:22:45"}
+{"current_steps": 735, "total_steps": 785, "loss": 0.3718, "lr": 5.128211721119213e-07, "epoch": 4.6848, "percentage": 93.63, "elapsed_time": "5:04:01", "remaining_time": "0:20:40"}
+{"current_steps": 740, "total_steps": 785, "loss": 0.382, "lr": 4.175313534309755e-07, "epoch": 4.7168, "percentage": 94.27, "elapsed_time": "5:06:06", "remaining_time": "0:18:36"}
+{"current_steps": 745, "total_steps": 785, "loss": 0.3774, "lr": 3.319350182649861e-07, "epoch": 4.7488, "percentage": 94.9, "elapsed_time": "5:08:11", "remaining_time": "0:16:32"}
+{"current_steps": 750, "total_steps": 785, "loss": 0.377, "lr": 2.560745375059392e-07, "epoch": 4.7808, "percentage": 95.54, "elapsed_time": "5:10:09", "remaining_time": "0:14:28"}
+{"current_steps": 755, "total_steps": 785, "loss": 0.3754, "lr": 1.8998746271758016e-07, "epoch": 4.8128, "percentage": 96.18, "elapsed_time": "5:12:12", "remaining_time": "0:12:24"}
+{"current_steps": 760, "total_steps": 785, "loss": 0.3809, "lr": 1.337065075470778e-07, "epoch": 4.8448, "percentage": 96.82, "elapsed_time": "5:14:14", "remaining_time": "0:10:20"}
+{"current_steps": 765, "total_steps": 785, "loss": 0.3766, "lr": 8.725953153150279e-08, "epoch": 4.8768, "percentage": 97.45, "elapsed_time": "5:16:19", "remaining_time": "0:08:16"}
+{"current_steps": 770, "total_steps": 785, "loss": 0.3764, "lr": 5.066952630711886e-08, "epoch": 4.9088, "percentage": 98.09, "elapsed_time": "5:18:22", "remaining_time": "0:06:12"}
+{"current_steps": 775, "total_steps": 785, "loss": 0.3744, "lr": 2.3954604228342283e-08, "epoch": 4.9408, "percentage": 98.73, "elapsed_time": "5:20:20", "remaining_time": "0:04:08"}
+{"current_steps": 780, "total_steps": 785, "loss": 0.3799, "lr": 7.12798940197601e-09, "epoch": 4.9728, "percentage": 99.36, "elapsed_time": "5:22:26", "remaining_time": "0:02:04"}
+{"current_steps": 785, "total_steps": 785, "loss": 0.3798, "lr": 1.9801114115480802e-10, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "5:24:10", "remaining_time": "0:00:00"}
+{"current_steps": 785, "total_steps": 785, "epoch": 5.0, "percentage": 100.0, "elapsed_time": "5:24:10", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5353b657e9f946b1538ce5feed338ab5cc3ba10757e0057e9ae1532e65f412c6
+size 8657