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

added_tokens.json

@@ -0,0 +1,30 @@
+{
+  "</EF>": 151670,
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<EF>": 151669,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 751611206959104.0,
+    "train_loss": 1.246063159232126,
+    "train_runtime": 22456.1595,
+    "train_samples_per_second": 15.986,
+    "train_steps_per_second": 0.031
+}

chat_template.jinja

@@ -0,0 +1,85 @@
+{%- 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 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.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + message.content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set content = message.content %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in message.content %}
+                {%- set content = message.content.split('</think>')[-1].lstrip('\n') %}
+                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\n').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' }}
+        {{- message.content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- 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": 2560,
+  "initializer_range": 0.02,
+  "intermediate_size": 9728,
+  "max_position_embeddings": 32768,
+  "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": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.52.4",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.52.4"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108b24e3cde9aa3c0327ff12386f7c0541bb068fa25b18b57506926b23991a5b
+size 4967215360

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5dc2ef3d689d04de2093ec9e7ddeda448761696f09a3fdc76097b02ba3f49378
+size 3077766632

model.safetensors.index.json

@@ -0,0 +1,405 @@
+{
+  "metadata": {
+    "total_size": 8044936192
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<EF>",
+    "</EF>"
+  ],
+  "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:aa719b43d2986d6819e19be3ab1a64db6c11f27d121719368319d6e97d1204ff
+size 11423017

tokenizer_config.json

@@ -0,0 +1,245 @@
+{
+  "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": "<EF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151670": {
+      "content": "</EF>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<EF>",
+    "</EF>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 751611206959104.0,
+    "train_loss": 1.246063159232126,
+    "train_runtime": 22456.1595,
+    "train_samples_per_second": 15.986,
+    "train_steps_per_second": 0.031
+}

trainer_log.jsonl

@@ -0,0 +1,71 @@
+{"current_steps": 10, "total_steps": 702, "loss": 1.2958, "lr": 6.338028169014085e-07, "epoch": 0.0142602495543672, "percentage": 1.42, "elapsed_time": "0:06:48", "remaining_time": "7:51:31"}
+{"current_steps": 20, "total_steps": 702, "loss": 1.2249, "lr": 1.3380281690140844e-06, "epoch": 0.0285204991087344, "percentage": 2.85, "elapsed_time": "0:12:28", "remaining_time": "7:05:24"}
+{"current_steps": 30, "total_steps": 702, "loss": 1.3057, "lr": 2.0422535211267608e-06, "epoch": 0.0427807486631016, "percentage": 4.27, "elapsed_time": "0:17:56", "remaining_time": "6:41:43"}
+{"current_steps": 40, "total_steps": 702, "loss": 1.2873, "lr": 2.746478873239437e-06, "epoch": 0.0570409982174688, "percentage": 5.7, "elapsed_time": "0:23:26", "remaining_time": "6:27:58"}
+{"current_steps": 50, "total_steps": 702, "loss": 1.2443, "lr": 3.4507042253521127e-06, "epoch": 0.07130124777183601, "percentage": 7.12, "elapsed_time": "0:28:50", "remaining_time": "6:16:10"}
+{"current_steps": 60, "total_steps": 702, "loss": 1.2489, "lr": 4.154929577464789e-06, "epoch": 0.0855614973262032, "percentage": 8.55, "elapsed_time": "0:34:16", "remaining_time": "6:06:39"}
+{"current_steps": 70, "total_steps": 702, "loss": 1.2629, "lr": 4.859154929577465e-06, "epoch": 0.09982174688057041, "percentage": 9.97, "elapsed_time": "0:39:37", "remaining_time": "5:57:43"}
+{"current_steps": 80, "total_steps": 702, "loss": 1.2185, "lr": 4.9980172242518086e-06, "epoch": 0.1140819964349376, "percentage": 11.4, "elapsed_time": "0:44:50", "remaining_time": "5:48:42"}
+{"current_steps": 90, "total_steps": 702, "loss": 1.2993, "lr": 4.989967587789436e-06, "epoch": 0.12834224598930483, "percentage": 12.82, "elapsed_time": "0:50:02", "remaining_time": "5:40:18"}
+{"current_steps": 100, "total_steps": 702, "loss": 1.2558, "lr": 4.97574710106473e-06, "epoch": 0.14260249554367202, "percentage": 14.25, "elapsed_time": "0:55:19", "remaining_time": "5:33:03"}
+{"current_steps": 110, "total_steps": 702, "loss": 1.266, "lr": 4.955391006501997e-06, "epoch": 0.1568627450980392, "percentage": 15.67, "elapsed_time": "1:00:43", "remaining_time": "5:26:46"}
+{"current_steps": 120, "total_steps": 702, "loss": 1.2306, "lr": 4.928949752312725e-06, "epoch": 0.1711229946524064, "percentage": 17.09, "elapsed_time": "1:06:05", "remaining_time": "5:20:32"}
+{"current_steps": 130, "total_steps": 702, "loss": 1.2931, "lr": 4.896488867470524e-06, "epoch": 0.18538324420677363, "percentage": 18.52, "elapsed_time": "1:11:24", "remaining_time": "5:14:12"}
+{"current_steps": 140, "total_steps": 702, "loss": 1.2639, "lr": 4.858088799311629e-06, "epoch": 0.19964349376114082, "percentage": 19.94, "elapsed_time": "1:16:48", "remaining_time": "5:08:19"}
+{"current_steps": 150, "total_steps": 702, "loss": 1.2239, "lr": 4.813844714163437e-06, "epoch": 0.21390374331550802, "percentage": 21.37, "elapsed_time": "1:22:05", "remaining_time": "5:02:04"}
+{"current_steps": 160, "total_steps": 702, "loss": 1.2428, "lr": 4.7638662614951955e-06, "epoch": 0.2281639928698752, "percentage": 22.79, "elapsed_time": "1:27:20", "remaining_time": "4:55:51"}
+{"current_steps": 170, "total_steps": 702, "loss": 1.3028, "lr": 4.708277302175325e-06, "epoch": 0.24242424242424243, "percentage": 24.22, "elapsed_time": "1:32:31", "remaining_time": "4:49:33"}
+{"current_steps": 180, "total_steps": 702, "loss": 1.1976, "lr": 4.647215601508835e-06, "epoch": 0.25668449197860965, "percentage": 25.64, "elapsed_time": "1:37:41", "remaining_time": "4:43:19"}
+{"current_steps": 190, "total_steps": 702, "loss": 1.2187, "lr": 4.580832487815592e-06, "epoch": 0.2709447415329768, "percentage": 27.07, "elapsed_time": "1:42:57", "remaining_time": "4:37:26"}
+{"current_steps": 200, "total_steps": 702, "loss": 1.262, "lr": 4.509292477395548e-06, "epoch": 0.28520499108734404, "percentage": 28.49, "elapsed_time": "1:48:21", "remaining_time": "4:31:59"}
+{"current_steps": 210, "total_steps": 702, "loss": 1.2111, "lr": 4.432772866810408e-06, "epoch": 0.2994652406417112, "percentage": 29.91, "elapsed_time": "1:53:45", "remaining_time": "4:26:31"}
+{"current_steps": 220, "total_steps": 702, "loss": 1.2284, "lr": 4.351463293492148e-06, "epoch": 0.3137254901960784, "percentage": 31.34, "elapsed_time": "1:59:03", "remaining_time": "4:20:51"}
+{"current_steps": 230, "total_steps": 702, "loss": 1.2286, "lr": 4.2655652657673415e-06, "epoch": 0.32798573975044565, "percentage": 32.76, "elapsed_time": "2:04:25", "remaining_time": "4:15:20"}
+{"current_steps": 240, "total_steps": 702, "loss": 1.1805, "lr": 4.175291663462025e-06, "epoch": 0.3422459893048128, "percentage": 34.19, "elapsed_time": "2:09:40", "remaining_time": "4:09:37"}
+{"current_steps": 250, "total_steps": 702, "loss": 1.2224, "lr": 4.08086621032473e-06, "epoch": 0.35650623885918004, "percentage": 35.61, "elapsed_time": "2:14:57", "remaining_time": "4:04:00"}
+{"current_steps": 260, "total_steps": 702, "loss": 1.2474, "lr": 3.982522919575197e-06, "epoch": 0.37076648841354726, "percentage": 37.04, "elapsed_time": "2:20:09", "remaining_time": "3:58:15"}
+{"current_steps": 270, "total_steps": 702, "loss": 1.3148, "lr": 3.880505513952828e-06, "epoch": 0.3850267379679144, "percentage": 38.46, "elapsed_time": "2:25:37", "remaining_time": "3:53:00"}
+{"current_steps": 280, "total_steps": 702, "loss": 1.3046, "lr": 3.7750668217021885e-06, "epoch": 0.39928698752228164, "percentage": 39.89, "elapsed_time": "2:30:55", "remaining_time": "3:47:28"}
+{"current_steps": 290, "total_steps": 702, "loss": 1.3281, "lr": 3.666468149992468e-06, "epoch": 0.41354723707664887, "percentage": 41.31, "elapsed_time": "2:36:01", "remaining_time": "3:41:39"}
+{"current_steps": 300, "total_steps": 702, "loss": 1.2776, "lr": 3.5549786373237387e-06, "epoch": 0.42780748663101603, "percentage": 42.74, "elapsed_time": "2:41:24", "remaining_time": "3:36:17"}
+{"current_steps": 310, "total_steps": 702, "loss": 1.2158, "lr": 3.440874586524951e-06, "epoch": 0.44206773618538325, "percentage": 44.16, "elapsed_time": "2:46:44", "remaining_time": "3:30:50"}
+{"current_steps": 320, "total_steps": 702, "loss": 1.2223, "lr": 3.32443877999667e-06, "epoch": 0.4563279857397504, "percentage": 45.58, "elapsed_time": "2:52:03", "remaining_time": "3:25:23"}
+{"current_steps": 330, "total_steps": 702, "loss": 1.259, "lr": 3.205959778895588e-06, "epoch": 0.47058823529411764, "percentage": 47.01, "elapsed_time": "2:57:21", "remaining_time": "3:19:55"}
+{"current_steps": 340, "total_steps": 702, "loss": 1.2793, "lr": 3.0857312079976314e-06, "epoch": 0.48484848484848486, "percentage": 48.43, "elapsed_time": "3:02:43", "remaining_time": "3:14:33"}
+{"current_steps": 350, "total_steps": 702, "loss": 1.2648, "lr": 2.9640510280119677e-06, "epoch": 0.49910873440285203, "percentage": 49.86, "elapsed_time": "3:08:02", "remaining_time": "3:09:07"}
+{"current_steps": 360, "total_steps": 702, "loss": 1.2427, "lr": 2.841220797149342e-06, "epoch": 0.5133689839572193, "percentage": 51.28, "elapsed_time": "3:13:26", "remaining_time": "3:03:45"}
+{"current_steps": 370, "total_steps": 702, "loss": 1.3069, "lr": 2.7175449237747707e-06, "epoch": 0.5276292335115864, "percentage": 52.71, "elapsed_time": "3:18:42", "remaining_time": "2:58:17"}
+{"current_steps": 380, "total_steps": 702, "loss": 1.2415, "lr": 2.593329911996741e-06, "epoch": 0.5418894830659536, "percentage": 54.13, "elapsed_time": "3:23:58", "remaining_time": "2:52:50"}
+{"current_steps": 390, "total_steps": 702, "loss": 1.2007, "lr": 2.468883602062561e-06, "epoch": 0.5561497326203209, "percentage": 55.56, "elapsed_time": "3:29:11", "remaining_time": "2:47:21"}
+{"current_steps": 400, "total_steps": 702, "loss": 1.2306, "lr": 2.3445144074423782e-06, "epoch": 0.5704099821746881, "percentage": 56.98, "elapsed_time": "3:34:25", "remaining_time": "2:41:53"}
+{"current_steps": 410, "total_steps": 702, "loss": 1.2208, "lr": 2.2205305504925846e-06, "epoch": 0.5846702317290553, "percentage": 58.4, "elapsed_time": "3:39:40", "remaining_time": "2:36:27"}
+{"current_steps": 420, "total_steps": 702, "loss": 1.2111, "lr": 2.097239298592858e-06, "epoch": 0.5989304812834224, "percentage": 59.83, "elapsed_time": "3:44:59", "remaining_time": "2:31:03"}
+{"current_steps": 430, "total_steps": 702, "loss": 1.1947, "lr": 1.9749462026499098e-06, "epoch": 0.6131907308377896, "percentage": 61.25, "elapsed_time": "3:50:18", "remaining_time": "2:25:41"}
+{"current_steps": 440, "total_steps": 702, "loss": 1.2123, "lr": 1.853954339855138e-06, "epoch": 0.6274509803921569, "percentage": 62.68, "elapsed_time": "3:55:40", "remaining_time": "2:20:20"}
+{"current_steps": 450, "total_steps": 702, "loss": 1.2063, "lr": 1.7345635625728586e-06, "epoch": 0.6417112299465241, "percentage": 64.1, "elapsed_time": "4:00:55", "remaining_time": "2:14:55"}
+{"current_steps": 460, "total_steps": 702, "loss": 1.2734, "lr": 1.6170697552205733e-06, "epoch": 0.6559714795008913, "percentage": 65.53, "elapsed_time": "4:06:06", "remaining_time": "2:09:28"}
+{"current_steps": 470, "total_steps": 702, "loss": 1.2574, "lr": 1.5017641009829465e-06, "epoch": 0.6702317290552585, "percentage": 66.95, "elapsed_time": "4:11:24", "remaining_time": "2:04:05"}
+{"current_steps": 480, "total_steps": 702, "loss": 1.2497, "lr": 1.3889323601767737e-06, "epoch": 0.6844919786096256, "percentage": 68.38, "elapsed_time": "4:16:47", "remaining_time": "1:58:46"}
+{"current_steps": 490, "total_steps": 702, "loss": 1.2039, "lr": 1.2788541620553734e-06, "epoch": 0.6987522281639929, "percentage": 69.8, "elapsed_time": "4:22:16", "remaining_time": "1:53:28"}
+{"current_steps": 500, "total_steps": 702, "loss": 1.215, "lr": 1.171802311807487e-06, "epoch": 0.7130124777183601, "percentage": 71.23, "elapsed_time": "4:27:32", "remaining_time": "1:48:05"}
+{"current_steps": 510, "total_steps": 702, "loss": 1.264, "lr": 1.0680421144681808e-06, "epoch": 0.7272727272727273, "percentage": 72.65, "elapsed_time": "4:32:46", "remaining_time": "1:42:41"}
+{"current_steps": 520, "total_steps": 702, "loss": 1.2546, "lr": 9.678307174172455e-07, "epoch": 0.7415329768270945, "percentage": 74.07, "elapsed_time": "4:38:10", "remaining_time": "1:37:21"}
+{"current_steps": 530, "total_steps": 702, "loss": 1.242, "lr": 8.714164730946165e-07, "epoch": 0.7557932263814616, "percentage": 75.5, "elapsed_time": "4:43:34", "remaining_time": "1:32:01"}
+{"current_steps": 540, "total_steps": 702, "loss": 1.222, "lr": 7.790383235121427e-07, "epoch": 0.7700534759358288, "percentage": 76.92, "elapsed_time": "4:48:54", "remaining_time": "1:26:40"}
+{"current_steps": 550, "total_steps": 702, "loss": 1.2349, "lr": 6.909252080871016e-07, "epoch": 0.7843137254901961, "percentage": 78.35, "elapsed_time": "4:54:12", "remaining_time": "1:21:18"}
+{"current_steps": 560, "total_steps": 702, "loss": 1.2328, "lr": 6.072954962649844e-07, "epoch": 0.7985739750445633, "percentage": 79.77, "elapsed_time": "4:59:25", "remaining_time": "1:15:55"}
+{"current_steps": 570, "total_steps": 702, "loss": 1.2652, "lr": 5.283564463376914e-07, "epoch": 0.8128342245989305, "percentage": 81.2, "elapsed_time": "5:04:50", "remaining_time": "1:10:35"}
+{"current_steps": 580, "total_steps": 702, "loss": 1.2485, "lr": 4.5430369179834346e-07, "epoch": 0.8270944741532977, "percentage": 82.62, "elapsed_time": "5:10:11", "remaining_time": "1:05:14"}
+{"current_steps": 590, "total_steps": 702, "loss": 1.2588, "lr": 3.8532075650564966e-07, "epoch": 0.8413547237076648, "percentage": 84.05, "elapsed_time": "5:15:27", "remaining_time": "0:59:53"}
+{"current_steps": 600, "total_steps": 702, "loss": 1.275, "lr": 3.2157859985941816e-07, "epoch": 0.8556149732620321, "percentage": 85.47, "elapsed_time": "5:20:34", "remaining_time": "0:54:29"}
+{"current_steps": 610, "total_steps": 702, "loss": 1.2301, "lr": 2.632351931143709e-07, "epoch": 0.8698752228163993, "percentage": 86.89, "elapsed_time": "5:25:50", "remaining_time": "0:49:08"}
+{"current_steps": 620, "total_steps": 702, "loss": 1.2529, "lr": 2.1043512788229665e-07, "epoch": 0.8841354723707665, "percentage": 88.32, "elapsed_time": "5:31:11", "remaining_time": "0:43:48"}
+{"current_steps": 630, "total_steps": 702, "loss": 1.2475, "lr": 1.633092577927703e-07, "epoch": 0.8983957219251337, "percentage": 89.74, "elapsed_time": "5:36:32", "remaining_time": "0:38:27"}
+{"current_steps": 640, "total_steps": 702, "loss": 1.2438, "lr": 1.2197437420052e-07, "epoch": 0.9126559714795008, "percentage": 91.17, "elapsed_time": "5:41:45", "remaining_time": "0:33:06"}
+{"current_steps": 650, "total_steps": 702, "loss": 1.1976, "lr": 8.65329167431167e-08, "epoch": 0.9269162210338681, "percentage": 92.59, "elapsed_time": "5:47:04", "remaining_time": "0:27:45"}
+{"current_steps": 660, "total_steps": 702, "loss": 1.2714, "lr": 5.707271946632176e-08, "epoch": 0.9411764705882353, "percentage": 94.02, "elapsed_time": "5:52:20", "remaining_time": "0:22:25"}
+{"current_steps": 670, "total_steps": 702, "loss": 1.284, "lr": 3.36667931462531e-08, "epoch": 0.9554367201426025, "percentage": 95.44, "elapsed_time": "5:57:47", "remaining_time": "0:17:05"}
+{"current_steps": 680, "total_steps": 702, "loss": 1.1997, "lr": 1.63731443478482e-08, "epoch": 0.9696969696969697, "percentage": 96.87, "elapsed_time": "6:03:03", "remaining_time": "0:11:44"}
+{"current_steps": 690, "total_steps": 702, "loss": 1.2281, "lr": 5.234631668041001e-09, "epoch": 0.983957219251337, "percentage": 98.29, "elapsed_time": "6:08:20", "remaining_time": "0:06:24"}
+{"current_steps": 700, "total_steps": 702, "loss": 1.2622, "lr": 2.788595199287869e-10, "epoch": 0.9982174688057041, "percentage": 99.72, "elapsed_time": "6:13:33", "remaining_time": "0:01:04"}
+{"current_steps": 702, "total_steps": 702, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "6:14:16", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,533 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 500,
+  "global_step": 702,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0142602495543672,
+      "grad_norm": 0.8139662743228905,
+      "learning_rate": 6.338028169014085e-07,
+      "loss": 1.2958,
+      "step": 10
+    },
+    {
+      "epoch": 0.0285204991087344,
+      "grad_norm": 0.5878309772115767,
+      "learning_rate": 1.3380281690140844e-06,
+      "loss": 1.2249,
+      "step": 20
+    },
+    {
+      "epoch": 0.0427807486631016,
+      "grad_norm": 0.4258025711807589,
+      "learning_rate": 2.0422535211267608e-06,
+      "loss": 1.3057,
+      "step": 30
+    },
+    {
+      "epoch": 0.0570409982174688,
+      "grad_norm": 0.37515882532122125,
+      "learning_rate": 2.746478873239437e-06,
+      "loss": 1.2873,
+      "step": 40
+    },
+    {
+      "epoch": 0.07130124777183601,
+      "grad_norm": 0.3462910228487005,
+      "learning_rate": 3.4507042253521127e-06,
+      "loss": 1.2443,
+      "step": 50
+    },
+    {
+      "epoch": 0.0855614973262032,
+      "grad_norm": 0.3384165902594944,
+      "learning_rate": 4.154929577464789e-06,
+      "loss": 1.2489,
+      "step": 60
+    },
+    {
+      "epoch": 0.09982174688057041,
+      "grad_norm": 0.3209774822611155,
+      "learning_rate": 4.859154929577465e-06,
+      "loss": 1.2629,
+      "step": 70
+    },
+    {
+      "epoch": 0.1140819964349376,
+      "grad_norm": 0.3263743555552157,
+      "learning_rate": 4.9980172242518086e-06,
+      "loss": 1.2185,
+      "step": 80
+    },
+    {
+      "epoch": 0.12834224598930483,
+      "grad_norm": 0.35124281745402863,
+      "learning_rate": 4.989967587789436e-06,
+      "loss": 1.2993,
+      "step": 90
+    },
+    {
+      "epoch": 0.14260249554367202,
+      "grad_norm": 0.3471445263767614,
+      "learning_rate": 4.97574710106473e-06,
+      "loss": 1.2558,
+      "step": 100
+    },
+    {
+      "epoch": 0.1568627450980392,
+      "grad_norm": 0.33034921582114013,
+      "learning_rate": 4.955391006501997e-06,
+      "loss": 1.266,
+      "step": 110
+    },
+    {
+      "epoch": 0.1711229946524064,
+      "grad_norm": 0.3666489160357953,
+      "learning_rate": 4.928949752312725e-06,
+      "loss": 1.2306,
+      "step": 120
+    },
+    {
+      "epoch": 0.18538324420677363,
+      "grad_norm": 0.32245214016759427,
+      "learning_rate": 4.896488867470524e-06,
+      "loss": 1.2931,
+      "step": 130
+    },
+    {
+      "epoch": 0.19964349376114082,
+      "grad_norm": 0.3486070326815883,
+      "learning_rate": 4.858088799311629e-06,
+      "loss": 1.2639,
+      "step": 140
+    },
+    {
+      "epoch": 0.21390374331550802,
+      "grad_norm": 0.3425758583506635,
+      "learning_rate": 4.813844714163437e-06,
+      "loss": 1.2239,
+      "step": 150
+    },
+    {
+      "epoch": 0.2281639928698752,
+      "grad_norm": 0.3373817144763357,
+      "learning_rate": 4.7638662614951955e-06,
+      "loss": 1.2428,
+      "step": 160
+    },
+    {
+      "epoch": 0.24242424242424243,
+      "grad_norm": 0.3223259906187514,
+      "learning_rate": 4.708277302175325e-06,
+      "loss": 1.3028,
+      "step": 170
+    },
+    {
+      "epoch": 0.25668449197860965,
+      "grad_norm": 0.45055208532832197,
+      "learning_rate": 4.647215601508835e-06,
+      "loss": 1.1976,
+      "step": 180
+    },
+    {
+      "epoch": 0.2709447415329768,
+      "grad_norm": 0.40698480657770836,
+      "learning_rate": 4.580832487815592e-06,
+      "loss": 1.2187,
+      "step": 190
+    },
+    {
+      "epoch": 0.28520499108734404,
+      "grad_norm": 0.33221245008702727,
+      "learning_rate": 4.509292477395548e-06,
+      "loss": 1.262,
+      "step": 200
+    },
+    {
+      "epoch": 0.2994652406417112,
+      "grad_norm": 0.3027652748221288,
+      "learning_rate": 4.432772866810408e-06,
+      "loss": 1.2111,
+      "step": 210
+    },
+    {
+      "epoch": 0.3137254901960784,
+      "grad_norm": 0.31768648840973884,
+      "learning_rate": 4.351463293492148e-06,
+      "loss": 1.2284,
+      "step": 220
+    },
+    {
+      "epoch": 0.32798573975044565,
+      "grad_norm": 0.31748879676682273,
+      "learning_rate": 4.2655652657673415e-06,
+      "loss": 1.2286,
+      "step": 230
+    },
+    {
+      "epoch": 0.3422459893048128,
+      "grad_norm": 0.33479138670359,
+      "learning_rate": 4.175291663462025e-06,
+      "loss": 1.1805,
+      "step": 240
+    },
+    {
+      "epoch": 0.35650623885918004,
+      "grad_norm": 0.33484495559890204,
+      "learning_rate": 4.08086621032473e-06,
+      "loss": 1.2224,
+      "step": 250
+    },
+    {
+      "epoch": 0.37076648841354726,
+      "grad_norm": 0.3443979495813948,
+      "learning_rate": 3.982522919575197e-06,
+      "loss": 1.2474,
+      "step": 260
+    },
+    {
+      "epoch": 0.3850267379679144,
+      "grad_norm": 0.31945113434016614,
+      "learning_rate": 3.880505513952828e-06,
+      "loss": 1.3148,
+      "step": 270
+    },
+    {
+      "epoch": 0.39928698752228164,
+      "grad_norm": 0.29765184685999374,
+      "learning_rate": 3.7750668217021885e-06,
+      "loss": 1.3046,
+      "step": 280
+    },
+    {
+      "epoch": 0.41354723707664887,
+      "grad_norm": 0.29921019027730256,
+      "learning_rate": 3.666468149992468e-06,
+      "loss": 1.3281,
+      "step": 290
+    },
+    {
+      "epoch": 0.42780748663101603,
+      "grad_norm": 0.30627530622399407,
+      "learning_rate": 3.5549786373237387e-06,
+      "loss": 1.2776,
+      "step": 300
+    },
+    {
+      "epoch": 0.44206773618538325,
+      "grad_norm": 0.3100699982388048,
+      "learning_rate": 3.440874586524951e-06,
+      "loss": 1.2158,
+      "step": 310
+    },
+    {
+      "epoch": 0.4563279857397504,
+      "grad_norm": 0.2789573612889071,
+      "learning_rate": 3.32443877999667e-06,
+      "loss": 1.2223,
+      "step": 320
+    },
+    {
+      "epoch": 0.47058823529411764,
+      "grad_norm": 0.29437875631872973,
+      "learning_rate": 3.205959778895588e-06,
+      "loss": 1.259,
+      "step": 330
+    },
+    {
+      "epoch": 0.48484848484848486,
+      "grad_norm": 0.3231824620977908,
+      "learning_rate": 3.0857312079976314e-06,
+      "loss": 1.2793,
+      "step": 340
+    },
+    {
+      "epoch": 0.49910873440285203,
+      "grad_norm": 0.30327802755673333,
+      "learning_rate": 2.9640510280119677e-06,
+      "loss": 1.2648,
+      "step": 350
+    },
+    {
+      "epoch": 0.5133689839572193,
+      "grad_norm": 0.30155624864640673,
+      "learning_rate": 2.841220797149342e-06,
+      "loss": 1.2427,
+      "step": 360
+    },
+    {
+      "epoch": 0.5276292335115864,
+      "grad_norm": 0.2964137483438924,
+      "learning_rate": 2.7175449237747707e-06,
+      "loss": 1.3069,
+      "step": 370
+    },
+    {
+      "epoch": 0.5418894830659536,
+      "grad_norm": 0.29825032229903675,
+      "learning_rate": 2.593329911996741e-06,
+      "loss": 1.2415,
+      "step": 380
+    },
+    {
+      "epoch": 0.5561497326203209,
+      "grad_norm": 0.37384919820810736,
+      "learning_rate": 2.468883602062561e-06,
+      "loss": 1.2007,
+      "step": 390
+    },
+    {
+      "epoch": 0.5704099821746881,
+      "grad_norm": 0.29689057995956597,
+      "learning_rate": 2.3445144074423782e-06,
+      "loss": 1.2306,
+      "step": 400
+    },
+    {
+      "epoch": 0.5846702317290553,
+      "grad_norm": 0.29997128185038,
+      "learning_rate": 2.2205305504925846e-06,
+      "loss": 1.2208,
+      "step": 410
+    },
+    {
+      "epoch": 0.5989304812834224,
+      "grad_norm": 0.2780085462886456,
+      "learning_rate": 2.097239298592858e-06,
+      "loss": 1.2111,
+      "step": 420
+    },
+    {
+      "epoch": 0.6131907308377896,
+      "grad_norm": 0.3035885635047166,
+      "learning_rate": 1.9749462026499098e-06,
+      "loss": 1.1947,
+      "step": 430
+    },
+    {
+      "epoch": 0.6274509803921569,
+      "grad_norm": 0.30911875814444223,
+      "learning_rate": 1.853954339855138e-06,
+      "loss": 1.2123,
+      "step": 440
+    },
+    {
+      "epoch": 0.6417112299465241,
+      "grad_norm": 0.2938389041257947,
+      "learning_rate": 1.7345635625728586e-06,
+      "loss": 1.2063,
+      "step": 450
+    },
+    {
+      "epoch": 0.6559714795008913,
+      "grad_norm": 0.35190818144504715,
+      "learning_rate": 1.6170697552205733e-06,
+      "loss": 1.2734,
+      "step": 460
+    },
+    {
+      "epoch": 0.6702317290552585,
+      "grad_norm": 0.29346821374375515,
+      "learning_rate": 1.5017641009829465e-06,
+      "loss": 1.2574,
+      "step": 470
+    },
+    {
+      "epoch": 0.6844919786096256,
+      "grad_norm": 0.292085877465791,
+      "learning_rate": 1.3889323601767737e-06,
+      "loss": 1.2497,
+      "step": 480
+    },
+    {
+      "epoch": 0.6987522281639929,
+      "grad_norm": 0.2804583120366669,
+      "learning_rate": 1.2788541620553734e-06,
+      "loss": 1.2039,
+      "step": 490
+    },
+    {
+      "epoch": 0.7130124777183601,
+      "grad_norm": 0.2898346832915243,
+      "learning_rate": 1.171802311807487e-06,
+      "loss": 1.215,
+      "step": 500
+    },
+    {
+      "epoch": 0.7272727272727273,
+      "grad_norm": 0.2909963040847838,
+      "learning_rate": 1.0680421144681808e-06,
+      "loss": 1.264,
+      "step": 510
+    },
+    {
+      "epoch": 0.7415329768270945,
+      "grad_norm": 0.28505719437236243,
+      "learning_rate": 9.678307174172455e-07,
+      "loss": 1.2546,
+      "step": 520
+    },
+    {
+      "epoch": 0.7557932263814616,
+      "grad_norm": 0.2812476961856926,
+      "learning_rate": 8.714164730946165e-07,
+      "loss": 1.242,
+      "step": 530
+    },
+    {
+      "epoch": 0.7700534759358288,
+      "grad_norm": 0.28852546580089206,
+      "learning_rate": 7.790383235121427e-07,
+      "loss": 1.222,
+      "step": 540
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.27747083462201094,
+      "learning_rate": 6.909252080871016e-07,
+      "loss": 1.2349,
+      "step": 550
+    },
+    {
+      "epoch": 0.7985739750445633,
+      "grad_norm": 0.3022678034471398,
+      "learning_rate": 6.072954962649844e-07,
+      "loss": 1.2328,
+      "step": 560
+    },
+    {
+      "epoch": 0.8128342245989305,
+      "grad_norm": 0.29378513239668563,
+      "learning_rate": 5.283564463376914e-07,
+      "loss": 1.2652,
+      "step": 570
+    },
+    {
+      "epoch": 0.8270944741532977,
+      "grad_norm": 0.3007887559724406,
+      "learning_rate": 4.5430369179834346e-07,
+      "loss": 1.2485,
+      "step": 580
+    },
+    {
+      "epoch": 0.8413547237076648,
+      "grad_norm": 0.305570559185519,
+      "learning_rate": 3.8532075650564966e-07,
+      "loss": 1.2588,
+      "step": 590
+    },
+    {
+      "epoch": 0.8556149732620321,
+      "grad_norm": 0.27496637760726983,
+      "learning_rate": 3.2157859985941816e-07,
+      "loss": 1.275,
+      "step": 600
+    },
+    {
+      "epoch": 0.8698752228163993,
+      "grad_norm": 0.26966760032193265,
+      "learning_rate": 2.632351931143709e-07,
+      "loss": 1.2301,
+      "step": 610
+    },
+    {
+      "epoch": 0.8841354723707665,
+      "grad_norm": 0.2989355305827188,
+      "learning_rate": 2.1043512788229665e-07,
+      "loss": 1.2529,
+      "step": 620
+    },
+    {
+      "epoch": 0.8983957219251337,
+      "grad_norm": 0.2935604409541666,
+      "learning_rate": 1.633092577927703e-07,
+      "loss": 1.2475,
+      "step": 630
+    },
+    {
+      "epoch": 0.9126559714795008,
+      "grad_norm": 0.3049830163981226,
+      "learning_rate": 1.2197437420052e-07,
+      "loss": 1.2438,
+      "step": 640
+    },
+    {
+      "epoch": 0.9269162210338681,
+      "grad_norm": 0.2785318314791894,
+      "learning_rate": 8.65329167431167e-08,
+      "loss": 1.1976,
+      "step": 650
+    },
+    {
+      "epoch": 0.9411764705882353,
+      "grad_norm": 0.2854212896993753,
+      "learning_rate": 5.707271946632176e-08,
+      "loss": 1.2714,
+      "step": 660
+    },
+    {
+      "epoch": 0.9554367201426025,
+      "grad_norm": 0.2853369914754105,
+      "learning_rate": 3.36667931462531e-08,
+      "loss": 1.284,
+      "step": 670
+    },
+    {
+      "epoch": 0.9696969696969697,
+      "grad_norm": 0.2799549896898941,
+      "learning_rate": 1.63731443478482e-08,
+      "loss": 1.1997,
+      "step": 680
+    },
+    {
+      "epoch": 0.983957219251337,
+      "grad_norm": 0.29153000629646353,
+      "learning_rate": 5.234631668041001e-09,
+      "loss": 1.2281,
+      "step": 690
+    },
+    {
+      "epoch": 0.9982174688057041,
+      "grad_norm": 0.5334879263796033,
+      "learning_rate": 2.788595199287869e-10,
+      "loss": 1.2622,
+      "step": 700
+    },
+    {
+      "epoch": 1.0,
+      "step": 702,
+      "total_flos": 751611206959104.0,
+      "train_loss": 1.246063159232126,
+      "train_runtime": 22456.1595,
+      "train_samples_per_second": 15.986,
+      "train_steps_per_second": 0.031
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 702,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 751611206959104.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dcd60b786281f27bd9f23cbad32599b4ba44ed003f33f58c8775b8ad65b39b03
+size 8081