Training in progress, step 500

.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 +1,28 @@
+{
+  "</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
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ec878f779882fb84de8c362ef471a6b4e109cb6073fe61581d5bb0f3d0403aee
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:452efacd33efd99a5a769c01be533d147814ced4b621aa4cc3dc45f865d6f5e7
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9abf3f51243ce6981716e903da4364f267df89094a5182bdf60f6279475b85eb
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c328acd784131e4398783444b91f0f63753226a127121a7994fabc227eae037d
+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"
+  }
+}

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": "terminus-2",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "DCAgent/staqc-ot3-100k-math-subset-traces-terminus-2",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/DCAgent/staqc-ot3-100k-math-subset-traces-terminus-2_save-strategy_steps_Qwen3-8B/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/dc-agent/runs/staqc-ot3-100k-math-subset-traces-terminus-2_save-strategy_steps_Qwen3-8B",
+  "traces_location_s3": null
+}

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 +1,136 @@
+{"current_steps": 5, "total_steps": 6325, "loss": 1.05, "lr": 2.527646129541864e-07, "epoch": 0.003952569169960474, "percentage": 0.08, "elapsed_time": "0:05:49", "remaining_time": "5 days, 2:52:39"}
+{"current_steps": 5, "total_steps": 6325, "loss": 1.05, "lr": 2.527646129541864e-07, "epoch": 0.003952569169960474, "percentage": 0.08, "elapsed_time": "0:02:26", "remaining_time": "2 days, 3:19:02"}
+{"current_steps": 10, "total_steps": 6325, "loss": 1.0377, "lr": 5.687203791469194e-07, "epoch": 0.007905138339920948, "percentage": 0.16, "elapsed_time": "0:03:19", "remaining_time": "1 day, 10:56:49"}
+{"current_steps": 15, "total_steps": 6325, "loss": 1.0298, "lr": 8.846761453396525e-07, "epoch": 0.011857707509881422, "percentage": 0.24, "elapsed_time": "0:04:12", "remaining_time": "1 day, 5:33:31"}
+{"current_steps": 20, "total_steps": 6325, "loss": 1.0171, "lr": 1.2006319115323856e-06, "epoch": 0.015810276679841896, "percentage": 0.32, "elapsed_time": "0:05:11", "remaining_time": "1 day, 3:15:02"}
+{"current_steps": 25, "total_steps": 6325, "loss": 1.0005, "lr": 1.5165876777251187e-06, "epoch": 0.019762845849802372, "percentage": 0.4, "elapsed_time": "0:06:02", "remaining_time": "1 day, 1:22:53"}
+{"current_steps": 30, "total_steps": 6325, "loss": 1.0091, "lr": 1.8325434439178516e-06, "epoch": 0.023715415019762844, "percentage": 0.47, "elapsed_time": "0:06:52", "remaining_time": "1 day, 0:01:05"}
+{"current_steps": 35, "total_steps": 6325, "loss": 0.9801, "lr": 2.148499210110585e-06, "epoch": 0.02766798418972332, "percentage": 0.55, "elapsed_time": "0:07:42", "remaining_time": "23:04:13"}
+{"current_steps": 40, "total_steps": 6325, "loss": 0.9517, "lr": 2.4644549763033174e-06, "epoch": 0.03162055335968379, "percentage": 0.63, "elapsed_time": "0:08:33", "remaining_time": "22:25:48"}
+{"current_steps": 45, "total_steps": 6325, "loss": 0.9378, "lr": 2.7804107424960508e-06, "epoch": 0.03557312252964427, "percentage": 0.71, "elapsed_time": "0:09:25", "remaining_time": "21:54:22"}
+{"current_steps": 50, "total_steps": 6325, "loss": 0.9051, "lr": 3.096366508688784e-06, "epoch": 0.039525691699604744, "percentage": 0.79, "elapsed_time": "0:10:12", "remaining_time": "21:20:38"}
+{"current_steps": 55, "total_steps": 6325, "loss": 0.888, "lr": 3.412322274881517e-06, "epoch": 0.043478260869565216, "percentage": 0.87, "elapsed_time": "0:11:02", "remaining_time": "20:59:12"}
+{"current_steps": 60, "total_steps": 6325, "loss": 0.8903, "lr": 3.72827804107425e-06, "epoch": 0.04743083003952569, "percentage": 0.95, "elapsed_time": "0:11:54", "remaining_time": "20:43:16"}
+{"current_steps": 65, "total_steps": 6325, "loss": 0.8586, "lr": 4.044233807266983e-06, "epoch": 0.05138339920948617, "percentage": 1.03, "elapsed_time": "0:12:44", "remaining_time": "20:27:36"}
+{"current_steps": 70, "total_steps": 6325, "loss": 0.8469, "lr": 4.360189573459716e-06, "epoch": 0.05533596837944664, "percentage": 1.11, "elapsed_time": "0:13:33", "remaining_time": "20:11:42"}
+{"current_steps": 75, "total_steps": 6325, "loss": 0.8357, "lr": 4.676145339652449e-06, "epoch": 0.05928853754940711, "percentage": 1.19, "elapsed_time": "0:14:20", "remaining_time": "19:54:56"}
+{"current_steps": 80, "total_steps": 6325, "loss": 0.8339, "lr": 4.9921011058451815e-06, "epoch": 0.06324110671936758, "percentage": 1.26, "elapsed_time": "0:15:13", "remaining_time": "19:47:58"}
+{"current_steps": 85, "total_steps": 6325, "loss": 0.8302, "lr": 5.308056872037915e-06, "epoch": 0.06719367588932806, "percentage": 1.34, "elapsed_time": "0:16:02", "remaining_time": "19:37:44"}
+{"current_steps": 90, "total_steps": 6325, "loss": 0.8175, "lr": 5.624012638230648e-06, "epoch": 0.07114624505928854, "percentage": 1.42, "elapsed_time": "0:16:52", "remaining_time": "19:29:10"}
+{"current_steps": 95, "total_steps": 6325, "loss": 0.8072, "lr": 5.939968404423381e-06, "epoch": 0.07509881422924901, "percentage": 1.5, "elapsed_time": "0:17:39", "remaining_time": "19:18:10"}
+{"current_steps": 100, "total_steps": 6325, "loss": 0.821, "lr": 6.255924170616115e-06, "epoch": 0.07905138339920949, "percentage": 1.58, "elapsed_time": "0:18:27", "remaining_time": "19:09:07"}
+{"current_steps": 105, "total_steps": 6325, "loss": 0.8118, "lr": 6.571879936808847e-06, "epoch": 0.08300395256916997, "percentage": 1.66, "elapsed_time": "0:19:18", "remaining_time": "19:03:29"}
+{"current_steps": 110, "total_steps": 6325, "loss": 0.8062, "lr": 6.8878357030015805e-06, "epoch": 0.08695652173913043, "percentage": 1.74, "elapsed_time": "0:20:07", "remaining_time": "18:56:56"}
+{"current_steps": 5, "total_steps": 1585, "loss": 1.0368, "lr": 1.0062893081761007e-06, "epoch": 0.015810276679841896, "percentage": 0.32, "elapsed_time": "0:07:05", "remaining_time": "1 day, 13:22:06"}
+{"current_steps": 10, "total_steps": 1585, "loss": 1.0267, "lr": 2.2641509433962266e-06, "epoch": 0.03162055335968379, "percentage": 0.63, "elapsed_time": "0:12:59", "remaining_time": "1 day, 10:07:25"}
+{"current_steps": 15, "total_steps": 1585, "loss": 1.0164, "lr": 3.5220125786163524e-06, "epoch": 0.04743083003952569, "percentage": 0.95, "elapsed_time": "0:18:50", "remaining_time": "1 day, 8:52:26"}
+{"current_steps": 20, "total_steps": 1585, "loss": 0.9707, "lr": 4.779874213836478e-06, "epoch": 0.06324110671936758, "percentage": 1.26, "elapsed_time": "0:24:33", "remaining_time": "1 day, 8:01:24"}
+{"current_steps": 25, "total_steps": 1585, "loss": 0.9242, "lr": 6.037735849056604e-06, "epoch": 0.07905138339920949, "percentage": 1.58, "elapsed_time": "0:30:18", "remaining_time": "1 day, 7:31:26"}
+{"current_steps": 30, "total_steps": 1585, "loss": 0.8884, "lr": 7.29559748427673e-06, "epoch": 0.09486166007905138, "percentage": 1.89, "elapsed_time": "0:35:59", "remaining_time": "1 day, 7:05:59"}
+{"current_steps": 35, "total_steps": 1585, "loss": 0.8632, "lr": 8.553459119496857e-06, "epoch": 0.11067193675889328, "percentage": 2.21, "elapsed_time": "0:41:42", "remaining_time": "1 day, 6:46:44"}
+{"current_steps": 40, "total_steps": 1585, "loss": 0.8463, "lr": 9.811320754716981e-06, "epoch": 0.12648221343873517, "percentage": 2.52, "elapsed_time": "0:47:41", "remaining_time": "1 day, 6:42:00"}
+{"current_steps": 45, "total_steps": 1585, "loss": 0.8267, "lr": 1.1069182389937107e-05, "epoch": 0.1422924901185771, "percentage": 2.84, "elapsed_time": "0:53:32", "remaining_time": "1 day, 6:32:23"}
+{"current_steps": 50, "total_steps": 1585, "loss": 0.8205, "lr": 1.2327044025157234e-05, "epoch": 0.15810276679841898, "percentage": 3.15, "elapsed_time": "0:59:07", "remaining_time": "1 day, 6:15:21"}
+{"current_steps": 55, "total_steps": 1585, "loss": 0.8116, "lr": 1.3584905660377358e-05, "epoch": 0.17391304347826086, "percentage": 3.47, "elapsed_time": "1:04:52", "remaining_time": "1 day, 6:04:52"}
+{"current_steps": 60, "total_steps": 1585, "loss": 0.8103, "lr": 1.4842767295597484e-05, "epoch": 0.18972332015810275, "percentage": 3.79, "elapsed_time": "1:10:29", "remaining_time": "1 day, 5:51:36"}
+{"current_steps": 5, "total_steps": 6325, "loss": 1.05, "lr": 2.527646129541864e-07, "epoch": 0.003952569169960474, "percentage": 0.08, "elapsed_time": "0:02:41", "remaining_time": "2 days, 8:46:23"}
+{"current_steps": 10, "total_steps": 6325, "loss": 1.0377, "lr": 5.687203791469194e-07, "epoch": 0.007905138339920948, "percentage": 0.16, "elapsed_time": "0:04:15", "remaining_time": "1 day, 20:52:16"}
+{"current_steps": 15, "total_steps": 6325, "loss": 1.0299, "lr": 8.846761453396525e-07, "epoch": 0.011857707509881422, "percentage": 0.24, "elapsed_time": "0:05:51", "remaining_time": "1 day, 17:05:04"}
+{"current_steps": 20, "total_steps": 6325, "loss": 1.0176, "lr": 1.2006319115323856e-06, "epoch": 0.015810276679841896, "percentage": 0.32, "elapsed_time": "0:07:29", "remaining_time": "1 day, 15:20:56"}
+{"current_steps": 25, "total_steps": 6325, "loss": 1.0013, "lr": 1.5165876777251187e-06, "epoch": 0.019762845849802372, "percentage": 0.4, "elapsed_time": "0:09:01", "remaining_time": "1 day, 13:56:04"}
+{"current_steps": 30, "total_steps": 6325, "loss": 1.0099, "lr": 1.8325434439178516e-06, "epoch": 0.023715415019762844, "percentage": 0.47, "elapsed_time": "0:10:30", "remaining_time": "1 day, 12:44:39"}
+{"current_steps": 35, "total_steps": 6325, "loss": 0.9813, "lr": 2.148499210110585e-06, "epoch": 0.02766798418972332, "percentage": 0.55, "elapsed_time": "0:11:58", "remaining_time": "1 day, 11:53:32"}
+{"current_steps": 40, "total_steps": 6325, "loss": 0.9529, "lr": 2.4644549763033174e-06, "epoch": 0.03162055335968379, "percentage": 0.63, "elapsed_time": "0:13:29", "remaining_time": "1 day, 11:18:54"}
+{"current_steps": 45, "total_steps": 6325, "loss": 0.9389, "lr": 2.7804107424960508e-06, "epoch": 0.03557312252964427, "percentage": 0.71, "elapsed_time": "0:15:00", "remaining_time": "1 day, 10:54:59"}
+{"current_steps": 50, "total_steps": 6325, "loss": 0.906, "lr": 3.096366508688784e-06, "epoch": 0.039525691699604744, "percentage": 0.79, "elapsed_time": "0:16:26", "remaining_time": "1 day, 10:22:49"}
+{"current_steps": 55, "total_steps": 6325, "loss": 0.8887, "lr": 3.412322274881517e-06, "epoch": 0.043478260869565216, "percentage": 0.87, "elapsed_time": "0:17:54", "remaining_time": "1 day, 10:00:52"}
+{"current_steps": 60, "total_steps": 6325, "loss": 0.8904, "lr": 3.72827804107425e-06, "epoch": 0.04743083003952569, "percentage": 0.95, "elapsed_time": "0:19:26", "remaining_time": "1 day, 9:50:16"}
+{"current_steps": 65, "total_steps": 6325, "loss": 0.8585, "lr": 4.044233807266983e-06, "epoch": 0.05138339920948617, "percentage": 1.03, "elapsed_time": "0:20:54", "remaining_time": "1 day, 9:34:00"}
+{"current_steps": 70, "total_steps": 6325, "loss": 0.8467, "lr": 4.360189573459716e-06, "epoch": 0.05533596837944664, "percentage": 1.11, "elapsed_time": "0:22:20", "remaining_time": "1 day, 9:16:25"}
+{"current_steps": 75, "total_steps": 6325, "loss": 0.8356, "lr": 4.676145339652449e-06, "epoch": 0.05928853754940711, "percentage": 1.19, "elapsed_time": "0:23:45", "remaining_time": "1 day, 8:59:39"}
+{"current_steps": 80, "total_steps": 6325, "loss": 0.8339, "lr": 4.9921011058451815e-06, "epoch": 0.06324110671936758, "percentage": 1.26, "elapsed_time": "0:25:15", "remaining_time": "1 day, 8:51:37"}
+{"current_steps": 85, "total_steps": 6325, "loss": 0.8302, "lr": 5.308056872037915e-06, "epoch": 0.06719367588932806, "percentage": 1.34, "elapsed_time": "0:26:43", "remaining_time": "1 day, 8:41:35"}
+{"current_steps": 90, "total_steps": 6325, "loss": 0.8175, "lr": 5.624012638230648e-06, "epoch": 0.07114624505928854, "percentage": 1.42, "elapsed_time": "0:28:11", "remaining_time": "1 day, 8:33:20"}
+{"current_steps": 95, "total_steps": 6325, "loss": 0.8073, "lr": 5.939968404423381e-06, "epoch": 0.07509881422924901, "percentage": 1.5, "elapsed_time": "0:29:37", "remaining_time": "1 day, 8:22:21"}
+{"current_steps": 100, "total_steps": 6325, "loss": 0.8211, "lr": 6.255924170616115e-06, "epoch": 0.07905138339920949, "percentage": 1.58, "elapsed_time": "0:31:03", "remaining_time": "1 day, 8:13:25"}
+{"current_steps": 105, "total_steps": 6325, "loss": 0.8119, "lr": 6.571879936808847e-06, "epoch": 0.08300395256916997, "percentage": 1.66, "elapsed_time": "0:32:31", "remaining_time": "1 day, 8:06:54"}
+{"current_steps": 110, "total_steps": 6325, "loss": 0.8063, "lr": 6.8878357030015805e-06, "epoch": 0.08695652173913043, "percentage": 1.74, "elapsed_time": "0:33:57", "remaining_time": "1 day, 7:59:06"}
+{"current_steps": 115, "total_steps": 6325, "loss": 0.8148, "lr": 7.203791469194313e-06, "epoch": 0.09090909090909091, "percentage": 1.82, "elapsed_time": "0:35:23", "remaining_time": "1 day, 7:51:01"}
+{"current_steps": 120, "total_steps": 6325, "loss": 0.8119, "lr": 7.519747235387046e-06, "epoch": 0.09486166007905138, "percentage": 1.9, "elapsed_time": "0:36:49", "remaining_time": "1 day, 7:44:13"}
+{"current_steps": 125, "total_steps": 6325, "loss": 0.8155, "lr": 7.83570300157978e-06, "epoch": 0.09881422924901186, "percentage": 1.98, "elapsed_time": "0:38:22", "remaining_time": "1 day, 7:43:19"}
+{"current_steps": 130, "total_steps": 6325, "loss": 0.7985, "lr": 8.151658767772512e-06, "epoch": 0.10276679841897234, "percentage": 2.06, "elapsed_time": "0:39:46", "remaining_time": "1 day, 7:35:06"}
+{"current_steps": 135, "total_steps": 6325, "loss": 0.8008, "lr": 8.467614533965247e-06, "epoch": 0.1067193675889328, "percentage": 2.13, "elapsed_time": "0:41:12", "remaining_time": "1 day, 7:29:30"}
+{"current_steps": 140, "total_steps": 6325, "loss": 0.8036, "lr": 8.783570300157978e-06, "epoch": 0.11067193675889328, "percentage": 2.21, "elapsed_time": "0:42:37", "remaining_time": "1 day, 7:23:16"}
+{"current_steps": 145, "total_steps": 6325, "loss": 0.8203, "lr": 9.09952606635071e-06, "epoch": 0.11462450592885376, "percentage": 2.29, "elapsed_time": "0:44:08", "remaining_time": "1 day, 7:21:40"}
+{"current_steps": 150, "total_steps": 6325, "loss": 0.8046, "lr": 9.415481832543445e-06, "epoch": 0.11857707509881422, "percentage": 2.37, "elapsed_time": "0:45:41", "remaining_time": "1 day, 7:21:16"}
+{"current_steps": 155, "total_steps": 6325, "loss": 0.7968, "lr": 9.731437598736178e-06, "epoch": 0.1225296442687747, "percentage": 2.45, "elapsed_time": "0:47:07", "remaining_time": "1 day, 7:16:12"}
+{"current_steps": 160, "total_steps": 6325, "loss": 0.7782, "lr": 1.004739336492891e-05, "epoch": 0.12648221343873517, "percentage": 2.53, "elapsed_time": "0:48:41", "remaining_time": "1 day, 7:16:13"}
+{"current_steps": 165, "total_steps": 6325, "loss": 0.7809, "lr": 1.0363349131121642e-05, "epoch": 0.13043478260869565, "percentage": 2.61, "elapsed_time": "0:50:05", "remaining_time": "1 day, 7:10:12"}
+{"current_steps": 170, "total_steps": 6325, "loss": 0.8024, "lr": 1.0679304897314377e-05, "epoch": 0.13438735177865613, "percentage": 2.69, "elapsed_time": "0:51:46", "remaining_time": "1 day, 7:14:20"}
+{"current_steps": 175, "total_steps": 6325, "loss": 0.8, "lr": 1.099526066350711e-05, "epoch": 0.1383399209486166, "percentage": 2.77, "elapsed_time": "0:53:12", "remaining_time": "1 day, 7:09:43"}
+{"current_steps": 180, "total_steps": 6325, "loss": 0.7796, "lr": 1.1311216429699843e-05, "epoch": 0.1422924901185771, "percentage": 2.85, "elapsed_time": "0:54:38", "remaining_time": "1 day, 7:05:37"}
+{"current_steps": 185, "total_steps": 6325, "loss": 0.7869, "lr": 1.1627172195892576e-05, "epoch": 0.14624505928853754, "percentage": 2.92, "elapsed_time": "0:56:03", "remaining_time": "1 day, 7:00:28"}
+{"current_steps": 190, "total_steps": 6325, "loss": 0.7844, "lr": 1.1943127962085309e-05, "epoch": 0.15019762845849802, "percentage": 3.0, "elapsed_time": "0:57:28", "remaining_time": "1 day, 6:55:57"}
+{"current_steps": 195, "total_steps": 6325, "loss": 0.808, "lr": 1.2259083728278043e-05, "epoch": 0.1541501976284585, "percentage": 3.08, "elapsed_time": "0:58:53", "remaining_time": "1 day, 6:51:29"}
+{"current_steps": 200, "total_steps": 6325, "loss": 0.791, "lr": 1.2575039494470776e-05, "epoch": 0.15810276679841898, "percentage": 3.16, "elapsed_time": "1:00:20", "remaining_time": "1 day, 6:47:57"}
+{"current_steps": 205, "total_steps": 6325, "loss": 0.8068, "lr": 1.2890995260663507e-05, "epoch": 0.16205533596837945, "percentage": 3.24, "elapsed_time": "1:01:44", "remaining_time": "1 day, 6:43:05"}
+{"current_steps": 210, "total_steps": 6325, "loss": 0.7732, "lr": 1.320695102685624e-05, "epoch": 0.16600790513833993, "percentage": 3.32, "elapsed_time": "1:03:13", "remaining_time": "1 day, 6:41:05"}
+{"current_steps": 215, "total_steps": 6325, "loss": 0.7934, "lr": 1.3522906793048973e-05, "epoch": 0.16996047430830039, "percentage": 3.4, "elapsed_time": "1:04:47", "remaining_time": "1 day, 6:41:05"}
+{"current_steps": 220, "total_steps": 6325, "loss": 0.7808, "lr": 1.3838862559241708e-05, "epoch": 0.17391304347826086, "percentage": 3.48, "elapsed_time": "1:06:11", "remaining_time": "1 day, 6:36:43"}
+{"current_steps": 225, "total_steps": 6325, "loss": 0.7968, "lr": 1.415481832543444e-05, "epoch": 0.17786561264822134, "percentage": 3.56, "elapsed_time": "1:07:34", "remaining_time": "1 day, 6:31:56"}
+{"current_steps": 230, "total_steps": 6325, "loss": 0.7814, "lr": 1.4470774091627173e-05, "epoch": 0.18181818181818182, "percentage": 3.64, "elapsed_time": "1:09:01", "remaining_time": "1 day, 6:29:09"}
+{"current_steps": 235, "total_steps": 6325, "loss": 0.7925, "lr": 1.4786729857819906e-05, "epoch": 0.1857707509881423, "percentage": 3.72, "elapsed_time": "1:10:24", "remaining_time": "1 day, 6:24:36"}
+{"current_steps": 240, "total_steps": 6325, "loss": 0.797, "lr": 1.510268562401264e-05, "epoch": 0.18972332015810275, "percentage": 3.79, "elapsed_time": "1:11:54", "remaining_time": "1 day, 6:23:05"}
+{"current_steps": 245, "total_steps": 6325, "loss": 0.7953, "lr": 1.5418641390205372e-05, "epoch": 0.19367588932806323, "percentage": 3.87, "elapsed_time": "1:13:17", "remaining_time": "1 day, 6:18:52"}
+{"current_steps": 250, "total_steps": 6325, "loss": 0.8037, "lr": 1.5734597156398107e-05, "epoch": 0.1976284584980237, "percentage": 3.95, "elapsed_time": "1:14:42", "remaining_time": "1 day, 6:15:26"}
+{"current_steps": 255, "total_steps": 6325, "loss": 0.789, "lr": 1.6050552922590838e-05, "epoch": 0.2015810276679842, "percentage": 4.03, "elapsed_time": "1:16:13", "remaining_time": "1 day, 6:14:35"}
+{"current_steps": 260, "total_steps": 6325, "loss": 0.8046, "lr": 1.6366508688783572e-05, "epoch": 0.20553359683794467, "percentage": 4.11, "elapsed_time": "1:17:40", "remaining_time": "1 day, 6:12:05"}
+{"current_steps": 265, "total_steps": 6325, "loss": 0.8014, "lr": 1.6682464454976304e-05, "epoch": 0.20948616600790515, "percentage": 4.19, "elapsed_time": "1:19:05", "remaining_time": "1 day, 6:08:42"}
+{"current_steps": 270, "total_steps": 6325, "loss": 0.7937, "lr": 1.6998420221169038e-05, "epoch": 0.2134387351778656, "percentage": 4.27, "elapsed_time": "1:20:42", "remaining_time": "1 day, 6:10:03"}
+{"current_steps": 275, "total_steps": 6325, "loss": 0.79, "lr": 1.731437598736177e-05, "epoch": 0.21739130434782608, "percentage": 4.35, "elapsed_time": "1:22:09", "remaining_time": "1 day, 6:07:21"}
+{"current_steps": 280, "total_steps": 6325, "loss": 0.814, "lr": 1.7630331753554504e-05, "epoch": 0.22134387351778656, "percentage": 4.43, "elapsed_time": "1:23:40", "remaining_time": "1 day, 6:06:34"}
+{"current_steps": 285, "total_steps": 6325, "loss": 0.7915, "lr": 1.7946287519747235e-05, "epoch": 0.22529644268774704, "percentage": 4.51, "elapsed_time": "1:25:03", "remaining_time": "1 day, 6:02:31"}
+{"current_steps": 290, "total_steps": 6325, "loss": 0.7947, "lr": 1.826224328593997e-05, "epoch": 0.22924901185770752, "percentage": 4.58, "elapsed_time": "1:26:29", "remaining_time": "1 day, 5:59:45"}
+{"current_steps": 295, "total_steps": 6325, "loss": 0.8093, "lr": 1.8578199052132704e-05, "epoch": 0.233201581027668, "percentage": 4.66, "elapsed_time": "1:27:54", "remaining_time": "1 day, 5:56:53"}
+{"current_steps": 300, "total_steps": 6325, "loss": 0.7934, "lr": 1.8894154818325436e-05, "epoch": 0.23715415019762845, "percentage": 4.74, "elapsed_time": "1:29:23", "remaining_time": "1 day, 5:55:13"}
+{"current_steps": 305, "total_steps": 6325, "loss": 0.7758, "lr": 1.921011058451817e-05, "epoch": 0.24110671936758893, "percentage": 4.82, "elapsed_time": "1:30:47", "remaining_time": "1 day, 5:51:54"}
+{"current_steps": 310, "total_steps": 6325, "loss": 0.7833, "lr": 1.95260663507109e-05, "epoch": 0.2450592885375494, "percentage": 4.9, "elapsed_time": "1:32:13", "remaining_time": "1 day, 5:49:28"}
+{"current_steps": 315, "total_steps": 6325, "loss": 0.81, "lr": 1.9842022116903633e-05, "epoch": 0.2490118577075099, "percentage": 4.98, "elapsed_time": "1:33:42", "remaining_time": "1 day, 5:47:56"}
+{"current_steps": 320, "total_steps": 6325, "loss": 0.792, "lr": 2.015797788309637e-05, "epoch": 0.25296442687747034, "percentage": 5.06, "elapsed_time": "1:35:12", "remaining_time": "1 day, 5:46:35"}
+{"current_steps": 325, "total_steps": 6325, "loss": 0.7858, "lr": 2.04739336492891e-05, "epoch": 0.25691699604743085, "percentage": 5.14, "elapsed_time": "1:36:38", "remaining_time": "1 day, 5:44:06"}
+{"current_steps": 330, "total_steps": 6325, "loss": 0.783, "lr": 2.0789889415481833e-05, "epoch": 0.2608695652173913, "percentage": 5.22, "elapsed_time": "1:38:26", "remaining_time": "1 day, 5:48:16"}
+{"current_steps": 335, "total_steps": 6325, "loss": 0.7797, "lr": 2.1105845181674568e-05, "epoch": 0.2648221343873518, "percentage": 5.3, "elapsed_time": "1:39:53", "remaining_time": "1 day, 5:46:08"}
+{"current_steps": 340, "total_steps": 6325, "loss": 0.7813, "lr": 2.14218009478673e-05, "epoch": 0.26877470355731226, "percentage": 5.38, "elapsed_time": "1:41:20", "remaining_time": "1 day, 5:43:46"}
+{"current_steps": 345, "total_steps": 6325, "loss": 0.8013, "lr": 2.1737756714060033e-05, "epoch": 0.2727272727272727, "percentage": 5.45, "elapsed_time": "1:42:51", "remaining_time": "1 day, 5:42:59"}
+{"current_steps": 350, "total_steps": 6325, "loss": 0.7848, "lr": 2.2053712480252765e-05, "epoch": 0.2766798418972332, "percentage": 5.53, "elapsed_time": "1:44:15", "remaining_time": "1 day, 5:39:49"}
+{"current_steps": 355, "total_steps": 6325, "loss": 0.8054, "lr": 2.23696682464455e-05, "epoch": 0.28063241106719367, "percentage": 5.61, "elapsed_time": "1:45:39", "remaining_time": "1 day, 5:36:47"}
+{"current_steps": 360, "total_steps": 6325, "loss": 0.7932, "lr": 2.2685624012638234e-05, "epoch": 0.2845849802371542, "percentage": 5.69, "elapsed_time": "1:47:02", "remaining_time": "1 day, 5:33:35"}
+{"current_steps": 365, "total_steps": 6325, "loss": 0.7822, "lr": 2.3001579778830965e-05, "epoch": 0.2885375494071146, "percentage": 5.77, "elapsed_time": "1:48:33", "remaining_time": "1 day, 5:32:42"}
+{"current_steps": 370, "total_steps": 6325, "loss": 0.7928, "lr": 2.33175355450237e-05, "epoch": 0.2924901185770751, "percentage": 5.85, "elapsed_time": "1:49:56", "remaining_time": "1 day, 5:29:29"}
+{"current_steps": 375, "total_steps": 6325, "loss": 0.7832, "lr": 2.363349131121643e-05, "epoch": 0.2964426877470356, "percentage": 5.93, "elapsed_time": "1:51:24", "remaining_time": "1 day, 5:27:33"}
+{"current_steps": 380, "total_steps": 6325, "loss": 0.7921, "lr": 2.3949447077409165e-05, "epoch": 0.30039525691699603, "percentage": 6.01, "elapsed_time": "1:52:55", "remaining_time": "1 day, 5:26:37"}
+{"current_steps": 385, "total_steps": 6325, "loss": 0.8012, "lr": 2.42654028436019e-05, "epoch": 0.30434782608695654, "percentage": 6.09, "elapsed_time": "1:54:17", "remaining_time": "1 day, 5:23:16"}
+{"current_steps": 390, "total_steps": 6325, "loss": 0.7738, "lr": 2.458135860979463e-05, "epoch": 0.308300395256917, "percentage": 6.17, "elapsed_time": "1:55:39", "remaining_time": "1 day, 5:20:01"}
+{"current_steps": 395, "total_steps": 6325, "loss": 0.792, "lr": 2.4897314375987366e-05, "epoch": 0.31225296442687744, "percentage": 6.25, "elapsed_time": "1:57:05", "remaining_time": "1 day, 5:17:57"}
+{"current_steps": 400, "total_steps": 6325, "loss": 0.7908, "lr": 2.5213270142180094e-05, "epoch": 0.31620553359683795, "percentage": 6.32, "elapsed_time": "1:58:33", "remaining_time": "1 day, 5:16:02"}
+{"current_steps": 405, "total_steps": 6325, "loss": 0.7925, "lr": 2.552922590837283e-05, "epoch": 0.3201581027667984, "percentage": 6.4, "elapsed_time": "1:59:54", "remaining_time": "1 day, 5:12:50"}
+{"current_steps": 410, "total_steps": 6325, "loss": 0.7993, "lr": 2.5845181674565566e-05, "epoch": 0.3241106719367589, "percentage": 6.48, "elapsed_time": "2:01:28", "remaining_time": "1 day, 5:12:31"}
+{"current_steps": 415, "total_steps": 6325, "loss": 0.7882, "lr": 2.6161137440758294e-05, "epoch": 0.32806324110671936, "percentage": 6.56, "elapsed_time": "2:02:51", "remaining_time": "1 day, 5:09:38"}
+{"current_steps": 420, "total_steps": 6325, "loss": 0.7933, "lr": 2.647709320695103e-05, "epoch": 0.33201581027667987, "percentage": 6.64, "elapsed_time": "2:04:18", "remaining_time": "1 day, 5:07:36"}
+{"current_steps": 425, "total_steps": 6325, "loss": 0.7859, "lr": 2.679304897314376e-05, "epoch": 0.3359683794466403, "percentage": 6.72, "elapsed_time": "2:05:48", "remaining_time": "1 day, 5:06:27"}
+{"current_steps": 430, "total_steps": 6325, "loss": 0.8074, "lr": 2.7109004739336494e-05, "epoch": 0.33992094861660077, "percentage": 6.8, "elapsed_time": "2:07:18", "remaining_time": "1 day, 5:05:16"}
+{"current_steps": 435, "total_steps": 6325, "loss": 0.7674, "lr": 2.742496050552923e-05, "epoch": 0.3438735177865613, "percentage": 6.88, "elapsed_time": "2:08:44", "remaining_time": "1 day, 5:03:06"}
+{"current_steps": 440, "total_steps": 6325, "loss": 0.7868, "lr": 2.774091627172196e-05, "epoch": 0.34782608695652173, "percentage": 6.96, "elapsed_time": "2:10:06", "remaining_time": "1 day, 5:00:05"}
+{"current_steps": 445, "total_steps": 6325, "loss": 0.7909, "lr": 2.8056872037914695e-05, "epoch": 0.35177865612648224, "percentage": 7.04, "elapsed_time": "2:11:28", "remaining_time": "1 day, 4:57:14"}
+{"current_steps": 450, "total_steps": 6325, "loss": 0.7812, "lr": 2.8372827804107426e-05, "epoch": 0.3557312252964427, "percentage": 7.11, "elapsed_time": "2:12:52", "remaining_time": "1 day, 4:54:49"}
+{"current_steps": 455, "total_steps": 6325, "loss": 0.7985, "lr": 2.868878357030016e-05, "epoch": 0.35968379446640314, "percentage": 7.19, "elapsed_time": "2:14:17", "remaining_time": "1 day, 4:52:36"}
+{"current_steps": 460, "total_steps": 6325, "loss": 0.8025, "lr": 2.9004739336492895e-05, "epoch": 0.36363636363636365, "percentage": 7.27, "elapsed_time": "2:15:42", "remaining_time": "1 day, 4:50:17"}
+{"current_steps": 465, "total_steps": 6325, "loss": 0.8032, "lr": 2.9320695102685626e-05, "epoch": 0.3675889328063241, "percentage": 7.35, "elapsed_time": "2:17:12", "remaining_time": "1 day, 4:49:07"}
+{"current_steps": 470, "total_steps": 6325, "loss": 0.8085, "lr": 2.963665086887836e-05, "epoch": 0.3715415019762846, "percentage": 7.43, "elapsed_time": "2:18:39", "remaining_time": "1 day, 4:47:14"}
+{"current_steps": 475, "total_steps": 6325, "loss": 0.7823, "lr": 2.9952606635071092e-05, "epoch": 0.37549407114624506, "percentage": 7.51, "elapsed_time": "2:20:30", "remaining_time": "1 day, 4:50:24"}
+{"current_steps": 480, "total_steps": 6325, "loss": 0.7872, "lr": 3.0268562401263827e-05, "epoch": 0.3794466403162055, "percentage": 7.59, "elapsed_time": "2:21:57", "remaining_time": "1 day, 4:48:34"}
+{"current_steps": 485, "total_steps": 6325, "loss": 0.8031, "lr": 3.058451816745656e-05, "epoch": 0.383399209486166, "percentage": 7.67, "elapsed_time": "2:23:28", "remaining_time": "1 day, 4:47:37"}
+{"current_steps": 490, "total_steps": 6325, "loss": 0.792, "lr": 3.090047393364929e-05, "epoch": 0.38735177865612647, "percentage": 7.75, "elapsed_time": "2:24:52", "remaining_time": "1 day, 4:45:12"}
+{"current_steps": 495, "total_steps": 6325, "loss": 0.7984, "lr": 3.121642969984203e-05, "epoch": 0.391304347826087, "percentage": 7.83, "elapsed_time": "2:26:24", "remaining_time": "1 day, 4:44:17"}
+{"current_steps": 500, "total_steps": 6325, "loss": 0.7799, "lr": 3.153238546603476e-05, "epoch": 0.3952569169960474, "percentage": 7.91, "elapsed_time": "2:27:52", "remaining_time": "1 day, 4:42:44"}
+{"current_steps": 505, "total_steps": 6325, "loss": 0.79, "lr": 3.184834123222749e-05, "epoch": 0.39920948616600793, "percentage": 7.98, "elapsed_time": "2:30:18", "remaining_time": "1 day, 4:52:11"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f359bea2944d7a42b7912105624fbb72f47d793c32a4d99071d65fe70f2b20fd
+size 8657