Training in progress, step 1000

.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,
+  "dtype": "bfloat16",
+  "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,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db6d558b739caff9396aa3c92fb85801e95e3a0322528422a86e2d4127ebaafa
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7e15941a0d37586f1ea50cc0da14f200dab917d39367d6cf59ea2b288af2eb0f
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:36c299d8626563982d2fedd71b0f94f1db522e0bd828db625954fcb13720363e
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e55432e7371a29d1305fdef9d0b0ffd9ef04a7a55e842c40e75b1e4e43fd26bc
+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": null,
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "DCAgent/exp_tas_high_diversity_traces",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/exp_tas_high_diversity_traces/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/exp_tas_high_diversity_traces_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 +1,215 @@
+{"current_steps": 5, "total_steps": 4018, "loss": 4.7729, "lr": 3.9800995024875624e-07, "epoch": 0.008718395815170008, "percentage": 0.12, "elapsed_time": "0:00:31", "remaining_time": "7:03:29"}
+{"current_steps": 10, "total_steps": 4018, "loss": 4.716, "lr": 8.955223880597015e-07, "epoch": 0.017436791630340016, "percentage": 0.25, "elapsed_time": "0:01:00", "remaining_time": "6:41:11"}
+{"current_steps": 15, "total_steps": 4018, "loss": 4.6929, "lr": 1.393034825870647e-06, "epoch": 0.026155187445510025, "percentage": 0.37, "elapsed_time": "0:01:27", "remaining_time": "6:27:15"}
+{"current_steps": 20, "total_steps": 4018, "loss": 4.6455, "lr": 1.8905472636815921e-06, "epoch": 0.03487358326068003, "percentage": 0.5, "elapsed_time": "0:01:55", "remaining_time": "6:25:32"}
+{"current_steps": 25, "total_steps": 4018, "loss": 4.6069, "lr": 2.3880597014925373e-06, "epoch": 0.043591979075850044, "percentage": 0.62, "elapsed_time": "0:02:25", "remaining_time": "6:28:20"}
+{"current_steps": 30, "total_steps": 4018, "loss": 4.514, "lr": 2.885572139303483e-06, "epoch": 0.05231037489102005, "percentage": 0.75, "elapsed_time": "0:02:54", "remaining_time": "6:26:42"}
+{"current_steps": 35, "total_steps": 4018, "loss": 4.4292, "lr": 3.3830845771144283e-06, "epoch": 0.06102877070619006, "percentage": 0.87, "elapsed_time": "0:03:23", "remaining_time": "6:26:22"}
+{"current_steps": 40, "total_steps": 4018, "loss": 4.4098, "lr": 3.8805970149253735e-06, "epoch": 0.06974716652136007, "percentage": 1.0, "elapsed_time": "0:03:52", "remaining_time": "6:25:09"}
+{"current_steps": 45, "total_steps": 4018, "loss": 4.3788, "lr": 4.378109452736319e-06, "epoch": 0.07846556233653008, "percentage": 1.12, "elapsed_time": "0:04:19", "remaining_time": "6:22:06"}
+{"current_steps": 50, "total_steps": 4018, "loss": 4.3267, "lr": 4.875621890547264e-06, "epoch": 0.08718395815170009, "percentage": 1.24, "elapsed_time": "0:04:48", "remaining_time": "6:21:22"}
+{"current_steps": 55, "total_steps": 4018, "loss": 4.2416, "lr": 5.37313432835821e-06, "epoch": 0.0959023539668701, "percentage": 1.37, "elapsed_time": "0:05:18", "remaining_time": "6:22:57"}
+{"current_steps": 60, "total_steps": 4018, "loss": 4.2489, "lr": 5.870646766169155e-06, "epoch": 0.1046207497820401, "percentage": 1.49, "elapsed_time": "0:05:47", "remaining_time": "6:21:37"}
+{"current_steps": 65, "total_steps": 4018, "loss": 4.1726, "lr": 6.3681592039801e-06, "epoch": 0.11333914559721012, "percentage": 1.62, "elapsed_time": "0:06:15", "remaining_time": "6:20:44"}
+{"current_steps": 70, "total_steps": 4018, "loss": 4.1358, "lr": 6.865671641791045e-06, "epoch": 0.12205754141238012, "percentage": 1.74, "elapsed_time": "0:06:44", "remaining_time": "6:20:03"}
+{"current_steps": 75, "total_steps": 4018, "loss": 4.1037, "lr": 7.36318407960199e-06, "epoch": 0.13077593722755013, "percentage": 1.87, "elapsed_time": "0:07:11", "remaining_time": "6:18:27"}
+{"current_steps": 80, "total_steps": 4018, "loss": 4.1097, "lr": 7.860696517412935e-06, "epoch": 0.13949433304272013, "percentage": 1.99, "elapsed_time": "0:07:42", "remaining_time": "6:19:21"}
+{"current_steps": 85, "total_steps": 4018, "loss": 4.0417, "lr": 8.35820895522388e-06, "epoch": 0.14821272885789014, "percentage": 2.12, "elapsed_time": "0:08:09", "remaining_time": "6:17:32"}
+{"current_steps": 90, "total_steps": 4018, "loss": 4.0488, "lr": 8.855721393034826e-06, "epoch": 0.15693112467306017, "percentage": 2.24, "elapsed_time": "0:08:38", "remaining_time": "6:17:27"}
+{"current_steps": 95, "total_steps": 4018, "loss": 4.0098, "lr": 9.353233830845772e-06, "epoch": 0.16564952048823017, "percentage": 2.36, "elapsed_time": "0:09:05", "remaining_time": "6:15:18"}
+{"current_steps": 100, "total_steps": 4018, "loss": 3.9684, "lr": 9.850746268656717e-06, "epoch": 0.17436791630340018, "percentage": 2.49, "elapsed_time": "0:09:34", "remaining_time": "6:15:10"}
+{"current_steps": 105, "total_steps": 4018, "loss": 3.9848, "lr": 1.0348258706467663e-05, "epoch": 0.18308631211857018, "percentage": 2.61, "elapsed_time": "0:10:04", "remaining_time": "6:15:18"}
+{"current_steps": 110, "total_steps": 4018, "loss": 3.9844, "lr": 1.0845771144278608e-05, "epoch": 0.1918047079337402, "percentage": 2.74, "elapsed_time": "0:10:32", "remaining_time": "6:14:45"}
+{"current_steps": 115, "total_steps": 4018, "loss": 3.9752, "lr": 1.1343283582089553e-05, "epoch": 0.2005231037489102, "percentage": 2.86, "elapsed_time": "0:11:00", "remaining_time": "6:13:50"}
+{"current_steps": 120, "total_steps": 4018, "loss": 3.9129, "lr": 1.1840796019900498e-05, "epoch": 0.2092414995640802, "percentage": 2.99, "elapsed_time": "0:11:29", "remaining_time": "6:13:14"}
+{"current_steps": 125, "total_steps": 4018, "loss": 3.9377, "lr": 1.2338308457711443e-05, "epoch": 0.21795989537925023, "percentage": 3.11, "elapsed_time": "0:11:58", "remaining_time": "6:12:51"}
+{"current_steps": 130, "total_steps": 4018, "loss": 3.9285, "lr": 1.2835820895522388e-05, "epoch": 0.22667829119442023, "percentage": 3.24, "elapsed_time": "0:12:28", "remaining_time": "6:13:17"}
+{"current_steps": 135, "total_steps": 4018, "loss": 3.9053, "lr": 1.3333333333333333e-05, "epoch": 0.23539668700959024, "percentage": 3.36, "elapsed_time": "0:12:54", "remaining_time": "6:11:13"}
+{"current_steps": 140, "total_steps": 4018, "loss": 3.8877, "lr": 1.3830845771144278e-05, "epoch": 0.24411508282476024, "percentage": 3.48, "elapsed_time": "0:13:26", "remaining_time": "6:12:10"}
+{"current_steps": 145, "total_steps": 4018, "loss": 3.8956, "lr": 1.4328358208955224e-05, "epoch": 0.2528334786399303, "percentage": 3.61, "elapsed_time": "0:13:53", "remaining_time": "6:10:59"}
+{"current_steps": 150, "total_steps": 4018, "loss": 3.8827, "lr": 1.4825870646766169e-05, "epoch": 0.26155187445510025, "percentage": 3.73, "elapsed_time": "0:14:20", "remaining_time": "6:09:55"}
+{"current_steps": 155, "total_steps": 4018, "loss": 3.8875, "lr": 1.5323383084577114e-05, "epoch": 0.2702702702702703, "percentage": 3.86, "elapsed_time": "0:14:49", "remaining_time": "6:09:20"}
+{"current_steps": 160, "total_steps": 4018, "loss": 3.867, "lr": 1.582089552238806e-05, "epoch": 0.27898866608544026, "percentage": 3.98, "elapsed_time": "0:15:17", "remaining_time": "6:08:46"}
+{"current_steps": 165, "total_steps": 4018, "loss": 3.8986, "lr": 1.6318407960199004e-05, "epoch": 0.2877070619006103, "percentage": 4.11, "elapsed_time": "0:15:47", "remaining_time": "6:08:38"}
+{"current_steps": 170, "total_steps": 4018, "loss": 3.8708, "lr": 1.681592039800995e-05, "epoch": 0.29642545771578027, "percentage": 4.23, "elapsed_time": "0:16:12", "remaining_time": "6:06:58"}
+{"current_steps": 175, "total_steps": 4018, "loss": 3.8842, "lr": 1.7313432835820894e-05, "epoch": 0.3051438535309503, "percentage": 4.36, "elapsed_time": "0:16:41", "remaining_time": "6:06:30"}
+{"current_steps": 180, "total_steps": 4018, "loss": 3.8387, "lr": 1.7810945273631844e-05, "epoch": 0.31386224934612034, "percentage": 4.48, "elapsed_time": "0:17:10", "remaining_time": "6:06:04"}
+{"current_steps": 185, "total_steps": 4018, "loss": 3.855, "lr": 1.8308457711442788e-05, "epoch": 0.3225806451612903, "percentage": 4.6, "elapsed_time": "0:17:37", "remaining_time": "6:05:09"}
+{"current_steps": 190, "total_steps": 4018, "loss": 3.8634, "lr": 1.8805970149253735e-05, "epoch": 0.33129904097646035, "percentage": 4.73, "elapsed_time": "0:18:07", "remaining_time": "6:05:12"}
+{"current_steps": 195, "total_steps": 4018, "loss": 3.8226, "lr": 1.9303482587064678e-05, "epoch": 0.3400174367916303, "percentage": 4.85, "elapsed_time": "0:18:35", "remaining_time": "6:04:28"}
+{"current_steps": 200, "total_steps": 4018, "loss": 3.806, "lr": 1.9800995024875625e-05, "epoch": 0.34873583260680036, "percentage": 4.98, "elapsed_time": "0:19:04", "remaining_time": "6:04:05"}
+{"current_steps": 205, "total_steps": 4018, "loss": 3.8144, "lr": 2.029850746268657e-05, "epoch": 0.35745422842197033, "percentage": 5.1, "elapsed_time": "0:19:31", "remaining_time": "6:03:01"}
+{"current_steps": 210, "total_steps": 4018, "loss": 3.8372, "lr": 2.0796019900497515e-05, "epoch": 0.36617262423714037, "percentage": 5.23, "elapsed_time": "0:20:00", "remaining_time": "6:02:48"}
+{"current_steps": 215, "total_steps": 4018, "loss": 3.824, "lr": 2.129353233830846e-05, "epoch": 0.3748910200523104, "percentage": 5.35, "elapsed_time": "0:20:30", "remaining_time": "6:02:37"}
+{"current_steps": 220, "total_steps": 4018, "loss": 3.8353, "lr": 2.1791044776119405e-05, "epoch": 0.3836094158674804, "percentage": 5.48, "elapsed_time": "0:20:59", "remaining_time": "6:02:26"}
+{"current_steps": 225, "total_steps": 4018, "loss": 3.7991, "lr": 2.2288557213930352e-05, "epoch": 0.3923278116826504, "percentage": 5.6, "elapsed_time": "0:21:27", "remaining_time": "6:01:50"}
+{"current_steps": 230, "total_steps": 4018, "loss": 3.8024, "lr": 2.2786069651741296e-05, "epoch": 0.4010462074978204, "percentage": 5.72, "elapsed_time": "0:21:55", "remaining_time": "6:01:10"}
+{"current_steps": 235, "total_steps": 4018, "loss": 3.8355, "lr": 2.3283582089552242e-05, "epoch": 0.4097646033129904, "percentage": 5.85, "elapsed_time": "0:22:25", "remaining_time": "6:01:02"}
+{"current_steps": 240, "total_steps": 4018, "loss": 3.8145, "lr": 2.3781094527363186e-05, "epoch": 0.4184829991281604, "percentage": 5.97, "elapsed_time": "0:22:53", "remaining_time": "6:00:20"}
+{"current_steps": 245, "total_steps": 4018, "loss": 3.8, "lr": 2.4278606965174133e-05, "epoch": 0.4272013949433304, "percentage": 6.1, "elapsed_time": "0:23:20", "remaining_time": "5:59:30"}
+{"current_steps": 250, "total_steps": 4018, "loss": 3.8196, "lr": 2.4776119402985076e-05, "epoch": 0.43591979075850046, "percentage": 6.22, "elapsed_time": "0:23:50", "remaining_time": "5:59:12"}
+{"current_steps": 255, "total_steps": 4018, "loss": 3.8234, "lr": 2.5273631840796023e-05, "epoch": 0.44463818657367044, "percentage": 6.35, "elapsed_time": "0:24:18", "remaining_time": "5:58:41"}
+{"current_steps": 260, "total_steps": 4018, "loss": 3.7958, "lr": 2.5771144278606966e-05, "epoch": 0.45335658238884047, "percentage": 6.47, "elapsed_time": "0:24:45", "remaining_time": "5:57:58"}
+{"current_steps": 265, "total_steps": 4018, "loss": 3.7932, "lr": 2.6268656716417913e-05, "epoch": 0.46207497820401044, "percentage": 6.6, "elapsed_time": "0:25:15", "remaining_time": "5:57:41"}
+{"current_steps": 270, "total_steps": 4018, "loss": 3.7987, "lr": 2.6766169154228857e-05, "epoch": 0.4707933740191805, "percentage": 6.72, "elapsed_time": "0:25:44", "remaining_time": "5:57:16"}
+{"current_steps": 275, "total_steps": 4018, "loss": 3.7882, "lr": 2.7263681592039803e-05, "epoch": 0.47951176983435045, "percentage": 6.84, "elapsed_time": "0:26:12", "remaining_time": "5:56:44"}
+{"current_steps": 280, "total_steps": 4018, "loss": 3.8192, "lr": 2.776119402985075e-05, "epoch": 0.4882301656495205, "percentage": 6.97, "elapsed_time": "0:26:41", "remaining_time": "5:56:25"}
+{"current_steps": 285, "total_steps": 4018, "loss": 3.8126, "lr": 2.8258706467661694e-05, "epoch": 0.4969485614646905, "percentage": 7.09, "elapsed_time": "0:27:10", "remaining_time": "5:55:57"}
+{"current_steps": 290, "total_steps": 4018, "loss": 3.7915, "lr": 2.875621890547264e-05, "epoch": 0.5056669572798606, "percentage": 7.22, "elapsed_time": "0:27:37", "remaining_time": "5:55:08"}
+{"current_steps": 295, "total_steps": 4018, "loss": 3.7974, "lr": 2.9253731343283584e-05, "epoch": 0.5143853530950305, "percentage": 7.34, "elapsed_time": "0:28:07", "remaining_time": "5:55:01"}
+{"current_steps": 300, "total_steps": 4018, "loss": 3.7774, "lr": 2.975124378109453e-05, "epoch": 0.5231037489102005, "percentage": 7.47, "elapsed_time": "0:28:36", "remaining_time": "5:54:37"}
+{"current_steps": 305, "total_steps": 4018, "loss": 3.8164, "lr": 3.0248756218905474e-05, "epoch": 0.5318221447253705, "percentage": 7.59, "elapsed_time": "0:29:04", "remaining_time": "5:54:02"}
+{"current_steps": 310, "total_steps": 4018, "loss": 3.766, "lr": 3.074626865671642e-05, "epoch": 0.5405405405405406, "percentage": 7.72, "elapsed_time": "0:29:34", "remaining_time": "5:53:46"}
+{"current_steps": 315, "total_steps": 4018, "loss": 3.7746, "lr": 3.124378109452737e-05, "epoch": 0.5492589363557105, "percentage": 7.84, "elapsed_time": "0:30:03", "remaining_time": "5:53:26"}
+{"current_steps": 320, "total_steps": 4018, "loss": 3.7912, "lr": 3.174129353233831e-05, "epoch": 0.5579773321708805, "percentage": 7.96, "elapsed_time": "0:30:33", "remaining_time": "5:53:03"}
+{"current_steps": 325, "total_steps": 4018, "loss": 3.7749, "lr": 3.2238805970149255e-05, "epoch": 0.5666957279860506, "percentage": 8.09, "elapsed_time": "0:31:01", "remaining_time": "5:52:37"}
+{"current_steps": 330, "total_steps": 4018, "loss": 3.8041, "lr": 3.27363184079602e-05, "epoch": 0.5754141238012206, "percentage": 8.21, "elapsed_time": "0:31:30", "remaining_time": "5:52:02"}
+{"current_steps": 335, "total_steps": 4018, "loss": 3.7799, "lr": 3.323383084577115e-05, "epoch": 0.5841325196163906, "percentage": 8.34, "elapsed_time": "0:32:00", "remaining_time": "5:51:51"}
+{"current_steps": 340, "total_steps": 4018, "loss": 3.7867, "lr": 3.3731343283582095e-05, "epoch": 0.5928509154315605, "percentage": 8.46, "elapsed_time": "0:32:28", "remaining_time": "5:51:15"}
+{"current_steps": 345, "total_steps": 4018, "loss": 3.7276, "lr": 3.4228855721393035e-05, "epoch": 0.6015693112467306, "percentage": 8.59, "elapsed_time": "0:32:54", "remaining_time": "5:50:22"}
+{"current_steps": 350, "total_steps": 4018, "loss": 3.7424, "lr": 3.472636815920398e-05, "epoch": 0.6102877070619006, "percentage": 8.71, "elapsed_time": "0:33:19", "remaining_time": "5:49:16"}
+{"current_steps": 355, "total_steps": 4018, "loss": 3.7952, "lr": 3.522388059701493e-05, "epoch": 0.6190061028770706, "percentage": 8.84, "elapsed_time": "0:33:47", "remaining_time": "5:48:35"}
+{"current_steps": 360, "total_steps": 4018, "loss": 3.7465, "lr": 3.5721393034825876e-05, "epoch": 0.6277244986922407, "percentage": 8.96, "elapsed_time": "0:34:16", "remaining_time": "5:48:13"}
+{"current_steps": 365, "total_steps": 4018, "loss": 3.7716, "lr": 3.6218905472636816e-05, "epoch": 0.6364428945074107, "percentage": 9.08, "elapsed_time": "0:34:46", "remaining_time": "5:47:57"}
+{"current_steps": 370, "total_steps": 4018, "loss": 3.7807, "lr": 3.671641791044776e-05, "epoch": 0.6451612903225806, "percentage": 9.21, "elapsed_time": "0:35:15", "remaining_time": "5:47:37"}
+{"current_steps": 375, "total_steps": 4018, "loss": 3.7484, "lr": 3.721393034825871e-05, "epoch": 0.6538796861377506, "percentage": 9.33, "elapsed_time": "0:35:42", "remaining_time": "5:46:48"}
+{"current_steps": 380, "total_steps": 4018, "loss": 3.7592, "lr": 3.7711442786069656e-05, "epoch": 0.6625980819529207, "percentage": 9.46, "elapsed_time": "0:36:10", "remaining_time": "5:46:22"}
+{"current_steps": 385, "total_steps": 4018, "loss": 3.7751, "lr": 3.8208955223880596e-05, "epoch": 0.6713164777680907, "percentage": 9.58, "elapsed_time": "0:36:39", "remaining_time": "5:45:53"}
+{"current_steps": 390, "total_steps": 4018, "loss": 3.786, "lr": 3.870646766169154e-05, "epoch": 0.6800348735832606, "percentage": 9.71, "elapsed_time": "0:37:06", "remaining_time": "5:45:15"}
+{"current_steps": 395, "total_steps": 4018, "loss": 3.7702, "lr": 3.920398009950249e-05, "epoch": 0.6887532693984307, "percentage": 9.83, "elapsed_time": "0:37:34", "remaining_time": "5:44:37"}
+{"current_steps": 400, "total_steps": 4018, "loss": 3.791, "lr": 3.9701492537313437e-05, "epoch": 0.6974716652136007, "percentage": 9.96, "elapsed_time": "0:38:04", "remaining_time": "5:44:19"}
+{"current_steps": 405, "total_steps": 4018, "loss": 3.7427, "lr": 3.999996980724216e-05, "epoch": 0.7061900610287707, "percentage": 10.08, "elapsed_time": "0:38:30", "remaining_time": "5:43:29"}
+{"current_steps": 410, "total_steps": 4018, "loss": 3.7762, "lr": 3.999963013976333e-05, "epoch": 0.7149084568439407, "percentage": 10.2, "elapsed_time": "0:38:57", "remaining_time": "5:42:49"}
+{"current_steps": 415, "total_steps": 4018, "loss": 3.7398, "lr": 3.99989130702894e-05, "epoch": 0.7236268526591108, "percentage": 10.33, "elapsed_time": "0:39:26", "remaining_time": "5:42:23"}
+{"current_steps": 420, "total_steps": 4018, "loss": 3.7315, "lr": 3.9997818612351804e-05, "epoch": 0.7323452484742807, "percentage": 10.45, "elapsed_time": "0:39:53", "remaining_time": "5:41:48"}
+{"current_steps": 425, "total_steps": 4018, "loss": 3.7754, "lr": 3.999634678660344e-05, "epoch": 0.7410636442894507, "percentage": 10.58, "elapsed_time": "0:40:22", "remaining_time": "5:41:22"}
+{"current_steps": 430, "total_steps": 4018, "loss": 3.7565, "lr": 3.999449762081835e-05, "epoch": 0.7497820401046208, "percentage": 10.7, "elapsed_time": "0:40:50", "remaining_time": "5:40:49"}
+{"current_steps": 435, "total_steps": 4018, "loss": 3.7508, "lr": 3.9992271149891086e-05, "epoch": 0.7585004359197908, "percentage": 10.83, "elapsed_time": "0:41:15", "remaining_time": "5:39:47"}
+{"current_steps": 440, "total_steps": 4018, "loss": 3.7501, "lr": 3.9989667415836166e-05, "epoch": 0.7672188317349607, "percentage": 10.95, "elapsed_time": "0:41:45", "remaining_time": "5:39:34"}
+{"current_steps": 445, "total_steps": 4018, "loss": 3.7865, "lr": 3.998668646778723e-05, "epoch": 0.7759372275501307, "percentage": 11.08, "elapsed_time": "0:42:13", "remaining_time": "5:39:00"}
+{"current_steps": 450, "total_steps": 4018, "loss": 3.7266, "lr": 3.99833283619961e-05, "epoch": 0.7846556233653008, "percentage": 11.2, "elapsed_time": "0:42:39", "remaining_time": "5:38:10"}
+{"current_steps": 455, "total_steps": 4018, "loss": 3.7359, "lr": 3.997959316183173e-05, "epoch": 0.7933740191804708, "percentage": 11.32, "elapsed_time": "0:43:08", "remaining_time": "5:37:49"}
+{"current_steps": 460, "total_steps": 4018, "loss": 3.7581, "lr": 3.997548093777904e-05, "epoch": 0.8020924149956408, "percentage": 11.45, "elapsed_time": "0:43:35", "remaining_time": "5:37:08"}
+{"current_steps": 465, "total_steps": 4018, "loss": 3.7646, "lr": 3.997099176743753e-05, "epoch": 0.8108108108108109, "percentage": 11.57, "elapsed_time": "0:44:04", "remaining_time": "5:36:48"}
+{"current_steps": 470, "total_steps": 4018, "loss": 3.7386, "lr": 3.996612573551986e-05, "epoch": 0.8195292066259808, "percentage": 11.7, "elapsed_time": "0:44:33", "remaining_time": "5:36:24"}
+{"current_steps": 475, "total_steps": 4018, "loss": 3.7659, "lr": 3.9960882933850236e-05, "epoch": 0.8282476024411508, "percentage": 11.82, "elapsed_time": "0:45:01", "remaining_time": "5:35:52"}
+{"current_steps": 480, "total_steps": 4018, "loss": 3.7423, "lr": 3.995526346136269e-05, "epoch": 0.8369659982563208, "percentage": 11.95, "elapsed_time": "0:45:31", "remaining_time": "5:35:33"}
+{"current_steps": 485, "total_steps": 4018, "loss": 3.7589, "lr": 3.9949267424099175e-05, "epoch": 0.8456843940714909, "percentage": 12.07, "elapsed_time": "0:46:03", "remaining_time": "5:35:28"}
+{"current_steps": 490, "total_steps": 4018, "loss": 3.7107, "lr": 3.994289493520761e-05, "epoch": 0.8544027898866609, "percentage": 12.2, "elapsed_time": "0:46:31", "remaining_time": "5:35:01"}
+{"current_steps": 495, "total_steps": 4018, "loss": 3.7587, "lr": 3.993614611493971e-05, "epoch": 0.8631211857018308, "percentage": 12.32, "elapsed_time": "0:47:00", "remaining_time": "5:34:35"}
+{"current_steps": 500, "total_steps": 4018, "loss": 3.7493, "lr": 3.992902109064876e-05, "epoch": 0.8718395815170009, "percentage": 12.44, "elapsed_time": "0:47:29", "remaining_time": "5:34:12"}
+{"current_steps": 505, "total_steps": 4018, "loss": 3.7529, "lr": 3.992151999678716e-05, "epoch": 0.8805579773321709, "percentage": 12.57, "elapsed_time": "0:47:58", "remaining_time": "5:33:43"}
+{"current_steps": 510, "total_steps": 4018, "loss": 3.7404, "lr": 3.9913642974903906e-05, "epoch": 0.8892763731473409, "percentage": 12.69, "elapsed_time": "0:48:25", "remaining_time": "5:33:03"}
+{"current_steps": 515, "total_steps": 4018, "loss": 3.7429, "lr": 3.990539017364195e-05, "epoch": 0.8979947689625108, "percentage": 12.82, "elapsed_time": "0:48:52", "remaining_time": "5:32:27"}
+{"current_steps": 520, "total_steps": 4018, "loss": 3.7566, "lr": 3.989676174873535e-05, "epoch": 0.9067131647776809, "percentage": 12.94, "elapsed_time": "0:49:22", "remaining_time": "5:32:06"}
+{"current_steps": 525, "total_steps": 4018, "loss": 3.7265, "lr": 3.988775786300635e-05, "epoch": 0.9154315605928509, "percentage": 13.07, "elapsed_time": "0:49:49", "remaining_time": "5:31:27"}
+{"current_steps": 530, "total_steps": 4018, "loss": 3.7298, "lr": 3.987837868636232e-05, "epoch": 0.9241499564080209, "percentage": 13.19, "elapsed_time": "0:50:17", "remaining_time": "5:31:00"}
+{"current_steps": 535, "total_steps": 4018, "loss": 3.7357, "lr": 3.986862439579253e-05, "epoch": 0.932868352223191, "percentage": 13.32, "elapsed_time": "0:50:47", "remaining_time": "5:30:36"}
+{"current_steps": 540, "total_steps": 4018, "loss": 3.7472, "lr": 3.985849517536481e-05, "epoch": 0.941586748038361, "percentage": 13.44, "elapsed_time": "0:51:15", "remaining_time": "5:30:08"}
+{"current_steps": 545, "total_steps": 4018, "loss": 3.7033, "lr": 3.984799121622212e-05, "epoch": 0.9503051438535309, "percentage": 13.56, "elapsed_time": "0:51:42", "remaining_time": "5:29:30"}
+{"current_steps": 550, "total_steps": 4018, "loss": 3.7327, "lr": 3.983711271657886e-05, "epoch": 0.9590235396687009, "percentage": 13.69, "elapsed_time": "0:52:09", "remaining_time": "5:28:55"}
+{"current_steps": 555, "total_steps": 4018, "loss": 3.7347, "lr": 3.9825859881717214e-05, "epoch": 0.967741935483871, "percentage": 13.81, "elapsed_time": "0:52:39", "remaining_time": "5:28:35"}
+{"current_steps": 560, "total_steps": 4018, "loss": 3.7302, "lr": 3.981423292398321e-05, "epoch": 0.976460331299041, "percentage": 13.94, "elapsed_time": "0:53:07", "remaining_time": "5:28:03"}
+{"current_steps": 565, "total_steps": 4018, "loss": 3.7177, "lr": 3.980223206278278e-05, "epoch": 0.985178727114211, "percentage": 14.06, "elapsed_time": "0:53:37", "remaining_time": "5:27:44"}
+{"current_steps": 570, "total_steps": 4018, "loss": 3.7383, "lr": 3.978985752457753e-05, "epoch": 0.993897122929381, "percentage": 14.19, "elapsed_time": "0:54:06", "remaining_time": "5:27:16"}
+{"current_steps": 575, "total_steps": 4018, "loss": 3.7287, "lr": 3.9777109542880574e-05, "epoch": 1.001743679163034, "percentage": 14.31, "elapsed_time": "0:54:33", "remaining_time": "5:26:39"}
+{"current_steps": 580, "total_steps": 4018, "loss": 3.6854, "lr": 3.976398835825204e-05, "epoch": 1.010462074978204, "percentage": 14.44, "elapsed_time": "0:55:00", "remaining_time": "5:26:06"}
+{"current_steps": 585, "total_steps": 4018, "loss": 3.7346, "lr": 3.975049421829456e-05, "epoch": 1.019180470793374, "percentage": 14.56, "elapsed_time": "0:55:27", "remaining_time": "5:25:29"}
+{"current_steps": 590, "total_steps": 4018, "loss": 3.7215, "lr": 3.973662737764862e-05, "epoch": 1.027898866608544, "percentage": 14.68, "elapsed_time": "0:55:56", "remaining_time": "5:25:02"}
+{"current_steps": 595, "total_steps": 4018, "loss": 3.7144, "lr": 3.972238809798773e-05, "epoch": 1.036617262423714, "percentage": 14.81, "elapsed_time": "0:56:24", "remaining_time": "5:24:31"}
+{"current_steps": 600, "total_steps": 4018, "loss": 3.7305, "lr": 3.970777664801347e-05, "epoch": 1.045335658238884, "percentage": 14.93, "elapsed_time": "0:56:52", "remaining_time": "5:23:57"}
+{"current_steps": 605, "total_steps": 4018, "loss": 3.7172, "lr": 3.9692793303450476e-05, "epoch": 1.054054054054054, "percentage": 15.06, "elapsed_time": "0:57:21", "remaining_time": "5:23:34"}
+{"current_steps": 610, "total_steps": 4018, "loss": 3.7179, "lr": 3.967743834704117e-05, "epoch": 1.0627724498692241, "percentage": 15.18, "elapsed_time": "0:57:50", "remaining_time": "5:23:10"}
+{"current_steps": 615, "total_steps": 4018, "loss": 3.7488, "lr": 3.966171206854047e-05, "epoch": 1.0714908456843941, "percentage": 15.31, "elapsed_time": "0:58:17", "remaining_time": "5:22:31"}
+{"current_steps": 620, "total_steps": 4018, "loss": 3.7269, "lr": 3.964561476471033e-05, "epoch": 1.080209241499564, "percentage": 15.43, "elapsed_time": "0:58:43", "remaining_time": "5:21:53"}
+{"current_steps": 625, "total_steps": 4018, "loss": 3.7047, "lr": 3.9629146739314055e-05, "epoch": 1.088927637314734, "percentage": 15.56, "elapsed_time": "0:59:10", "remaining_time": "5:21:16"}
+{"current_steps": 630, "total_steps": 4018, "loss": 3.7263, "lr": 3.9612308303110715e-05, "epoch": 1.097646033129904, "percentage": 15.68, "elapsed_time": "0:59:39", "remaining_time": "5:20:50"}
+{"current_steps": 635, "total_steps": 4018, "loss": 3.7248, "lr": 3.959509977384914e-05, "epoch": 1.106364428945074, "percentage": 15.8, "elapsed_time": "1:00:06", "remaining_time": "5:20:15"}
+{"current_steps": 640, "total_steps": 4018, "loss": 3.719, "lr": 3.957752147626199e-05, "epoch": 1.1150828247602442, "percentage": 15.93, "elapsed_time": "1:00:34", "remaining_time": "5:19:40"}
+{"current_steps": 645, "total_steps": 4018, "loss": 3.6777, "lr": 3.955957374205964e-05, "epoch": 1.1238012205754142, "percentage": 16.05, "elapsed_time": "1:01:03", "remaining_time": "5:19:16"}
+{"current_steps": 650, "total_steps": 4018, "loss": 3.7344, "lr": 3.954125690992389e-05, "epoch": 1.1325196163905842, "percentage": 16.18, "elapsed_time": "1:01:32", "remaining_time": "5:18:50"}
+{"current_steps": 655, "total_steps": 4018, "loss": 3.7333, "lr": 3.9522571325501576e-05, "epoch": 1.1412380122057542, "percentage": 16.3, "elapsed_time": "1:01:58", "remaining_time": "5:18:09"}
+{"current_steps": 660, "total_steps": 4018, "loss": 3.7151, "lr": 3.950351734139806e-05, "epoch": 1.1499564080209241, "percentage": 16.43, "elapsed_time": "1:02:26", "remaining_time": "5:17:39"}
+{"current_steps": 665, "total_steps": 4018, "loss": 3.7037, "lr": 3.948409531717057e-05, "epoch": 1.1586748038360941, "percentage": 16.55, "elapsed_time": "1:02:54", "remaining_time": "5:17:09"}
+{"current_steps": 670, "total_steps": 4018, "loss": 3.6905, "lr": 3.9464305619321436e-05, "epoch": 1.167393199651264, "percentage": 16.67, "elapsed_time": "1:03:18", "remaining_time": "5:16:22"}
+{"current_steps": 675, "total_steps": 4018, "loss": 3.7271, "lr": 3.9444148621291107e-05, "epoch": 1.176111595466434, "percentage": 16.8, "elapsed_time": "1:03:48", "remaining_time": "5:16:01"}
+{"current_steps": 680, "total_steps": 4018, "loss": 3.7285, "lr": 3.9423624703451205e-05, "epoch": 1.1848299912816043, "percentage": 16.92, "elapsed_time": "1:04:15", "remaining_time": "5:15:28"}
+{"current_steps": 685, "total_steps": 4018, "loss": 3.7081, "lr": 3.940273425309726e-05, "epoch": 1.1935483870967742, "percentage": 17.05, "elapsed_time": "1:04:44", "remaining_time": "5:14:59"}
+{"current_steps": 690, "total_steps": 4018, "loss": 3.7257, "lr": 3.9381477664441436e-05, "epoch": 1.2022667829119442, "percentage": 17.17, "elapsed_time": "1:05:13", "remaining_time": "5:14:36"}
+{"current_steps": 695, "total_steps": 4018, "loss": 3.7329, "lr": 3.935985533860512e-05, "epoch": 1.2109851787271142, "percentage": 17.3, "elapsed_time": "1:05:42", "remaining_time": "5:14:09"}
+{"current_steps": 700, "total_steps": 4018, "loss": 3.6945, "lr": 3.933786768361129e-05, "epoch": 1.2197035745422842, "percentage": 17.42, "elapsed_time": "1:06:10", "remaining_time": "5:13:38"}
+{"current_steps": 705, "total_steps": 4018, "loss": 3.7365, "lr": 3.931551511437686e-05, "epoch": 1.2284219703574542, "percentage": 17.55, "elapsed_time": "1:06:38", "remaining_time": "5:13:12"}
+{"current_steps": 710, "total_steps": 4018, "loss": 3.7219, "lr": 3.929279805270485e-05, "epoch": 1.2371403661726244, "percentage": 17.67, "elapsed_time": "1:07:09", "remaining_time": "5:12:52"}
+{"current_steps": 715, "total_steps": 4018, "loss": 3.6677, "lr": 3.92697169272764e-05, "epoch": 1.2458587619877943, "percentage": 17.79, "elapsed_time": "1:07:34", "remaining_time": "5:12:10"}
+{"current_steps": 720, "total_steps": 4018, "loss": 3.7196, "lr": 3.9246272173642704e-05, "epoch": 1.2545771578029643, "percentage": 17.92, "elapsed_time": "1:08:03", "remaining_time": "5:11:43"}
+{"current_steps": 725, "total_steps": 4018, "loss": 3.7114, "lr": 3.922246423421679e-05, "epoch": 1.2632955536181343, "percentage": 18.04, "elapsed_time": "1:08:32", "remaining_time": "5:11:20"}
+{"current_steps": 730, "total_steps": 4018, "loss": 3.7238, "lr": 3.919829355826515e-05, "epoch": 1.2720139494333043, "percentage": 18.17, "elapsed_time": "1:09:00", "remaining_time": "5:10:48"}
+{"current_steps": 735, "total_steps": 4018, "loss": 3.7014, "lr": 3.9173760601899286e-05, "epoch": 1.2807323452484742, "percentage": 18.29, "elapsed_time": "1:09:26", "remaining_time": "5:10:09"}
+{"current_steps": 740, "total_steps": 4018, "loss": 3.7279, "lr": 3.914886582806711e-05, "epoch": 1.2894507410636442, "percentage": 18.42, "elapsed_time": "1:09:54", "remaining_time": "5:09:38"}
+{"current_steps": 745, "total_steps": 4018, "loss": 3.7007, "lr": 3.9123609706544155e-05, "epoch": 1.2981691368788142, "percentage": 18.54, "elapsed_time": "1:10:23", "remaining_time": "5:09:13"}
+{"current_steps": 750, "total_steps": 4018, "loss": 3.7444, "lr": 3.909799271392477e-05, "epoch": 1.3068875326939844, "percentage": 18.67, "elapsed_time": "1:10:54", "remaining_time": "5:08:56"}
+{"current_steps": 755, "total_steps": 4018, "loss": 3.7133, "lr": 3.907201533361311e-05, "epoch": 1.3156059285091544, "percentage": 18.79, "elapsed_time": "1:11:22", "remaining_time": "5:08:29"}
+{"current_steps": 760, "total_steps": 4018, "loss": 3.7214, "lr": 3.9045678055813994e-05, "epoch": 1.3243243243243243, "percentage": 18.91, "elapsed_time": "1:11:49", "remaining_time": "5:07:54"}
+{"current_steps": 765, "total_steps": 4018, "loss": 3.7284, "lr": 3.9018981377523664e-05, "epoch": 1.3330427201394943, "percentage": 19.04, "elapsed_time": "1:12:17", "remaining_time": "5:07:25"}
+{"current_steps": 770, "total_steps": 4018, "loss": 3.7218, "lr": 3.8991925802520434e-05, "epoch": 1.3417611159546643, "percentage": 19.16, "elapsed_time": "1:12:45", "remaining_time": "5:06:54"}
+{"current_steps": 775, "total_steps": 4018, "loss": 3.698, "lr": 3.8964511841355136e-05, "epoch": 1.3504795117698343, "percentage": 19.29, "elapsed_time": "1:13:15", "remaining_time": "5:06:31"}
+{"current_steps": 780, "total_steps": 4018, "loss": 3.7118, "lr": 3.893674001134152e-05, "epoch": 1.3591979075850045, "percentage": 19.41, "elapsed_time": "1:13:40", "remaining_time": "5:05:48"}
+{"current_steps": 785, "total_steps": 4018, "loss": 3.6918, "lr": 3.890861083654647e-05, "epoch": 1.3679163034001744, "percentage": 19.54, "elapsed_time": "1:14:08", "remaining_time": "5:05:21"}
+{"current_steps": 790, "total_steps": 4018, "loss": 3.6911, "lr": 3.888012484778016e-05, "epoch": 1.3766346992153444, "percentage": 19.66, "elapsed_time": "1:14:36", "remaining_time": "5:04:50"}
+{"current_steps": 795, "total_steps": 4018, "loss": 3.6899, "lr": 3.885128258258596e-05, "epoch": 1.3853530950305144, "percentage": 19.79, "elapsed_time": "1:15:05", "remaining_time": "5:04:26"}
+{"current_steps": 800, "total_steps": 4018, "loss": 3.7126, "lr": 3.882208458523036e-05, "epoch": 1.3940714908456844, "percentage": 19.91, "elapsed_time": "1:15:31", "remaining_time": "5:03:46"}
+{"current_steps": 805, "total_steps": 4018, "loss": 3.6863, "lr": 3.879253140669268e-05, "epoch": 1.4027898866608544, "percentage": 20.03, "elapsed_time": "1:15:56", "remaining_time": "5:03:08"}
+{"current_steps": 810, "total_steps": 4018, "loss": 3.7151, "lr": 3.8762623604654656e-05, "epoch": 1.4115082824760243, "percentage": 20.16, "elapsed_time": "1:16:24", "remaining_time": "5:02:37"}
+{"current_steps": 815, "total_steps": 4018, "loss": 3.6986, "lr": 3.8732361743489934e-05, "epoch": 1.4202266782911943, "percentage": 20.28, "elapsed_time": "1:16:53", "remaining_time": "5:02:11"}
+{"current_steps": 820, "total_steps": 4018, "loss": 3.6925, "lr": 3.870174639425341e-05, "epoch": 1.4289450741063645, "percentage": 20.41, "elapsed_time": "1:17:20", "remaining_time": "5:01:38"}
+{"current_steps": 825, "total_steps": 4018, "loss": 3.7001, "lr": 3.867077813467046e-05, "epoch": 1.4376634699215345, "percentage": 20.53, "elapsed_time": "1:17:48", "remaining_time": "5:01:09"}
+{"current_steps": 830, "total_steps": 4018, "loss": 3.7271, "lr": 3.863945754912605e-05, "epoch": 1.4463818657367045, "percentage": 20.66, "elapsed_time": "1:18:17", "remaining_time": "5:00:43"}
+{"current_steps": 835, "total_steps": 4018, "loss": 3.7039, "lr": 3.860778522865367e-05, "epoch": 1.4551002615518744, "percentage": 20.78, "elapsed_time": "1:18:47", "remaining_time": "5:00:20"}
+{"current_steps": 840, "total_steps": 4018, "loss": 3.6795, "lr": 3.857576177092423e-05, "epoch": 1.4638186573670444, "percentage": 20.91, "elapsed_time": "1:19:13", "remaining_time": "4:59:44"}
+{"current_steps": 845, "total_steps": 4018, "loss": 3.7006, "lr": 3.854338778023475e-05, "epoch": 1.4725370531822144, "percentage": 21.03, "elapsed_time": "1:19:44", "remaining_time": "4:59:26"}
+{"current_steps": 850, "total_steps": 4018, "loss": 3.6762, "lr": 3.851066386749694e-05, "epoch": 1.4812554489973846, "percentage": 21.15, "elapsed_time": "1:20:12", "remaining_time": "4:58:55"}
+{"current_steps": 855, "total_steps": 4018, "loss": 3.748, "lr": 3.8477590650225735e-05, "epoch": 1.4899738448125546, "percentage": 21.28, "elapsed_time": "1:20:41", "remaining_time": "4:58:29"}
+{"current_steps": 860, "total_steps": 4018, "loss": 3.6975, "lr": 3.844416875252759e-05, "epoch": 1.4986922406277245, "percentage": 21.4, "elapsed_time": "1:21:10", "remaining_time": "4:58:05"}
+{"current_steps": 865, "total_steps": 4018, "loss": 3.6856, "lr": 3.84103988050887e-05, "epoch": 1.5074106364428945, "percentage": 21.53, "elapsed_time": "1:21:39", "remaining_time": "4:57:38"}
+{"current_steps": 870, "total_steps": 4018, "loss": 3.6812, "lr": 3.837628144516313e-05, "epoch": 1.5161290322580645, "percentage": 21.65, "elapsed_time": "1:22:04", "remaining_time": "4:56:58"}
+{"current_steps": 875, "total_steps": 4018, "loss": 3.674, "lr": 3.8341817316560776e-05, "epoch": 1.5248474280732345, "percentage": 21.78, "elapsed_time": "1:22:32", "remaining_time": "4:56:27"}
+{"current_steps": 880, "total_steps": 4018, "loss": 3.7189, "lr": 3.83070070696352e-05, "epoch": 1.5335658238884045, "percentage": 21.9, "elapsed_time": "1:23:00", "remaining_time": "4:56:00"}
+{"current_steps": 885, "total_steps": 4018, "loss": 3.6694, "lr": 3.827185136127139e-05, "epoch": 1.5422842197035744, "percentage": 22.03, "elapsed_time": "1:23:29", "remaining_time": "4:55:33"}
+{"current_steps": 890, "total_steps": 4018, "loss": 3.6748, "lr": 3.823635085487334e-05, "epoch": 1.5510026155187444, "percentage": 22.15, "elapsed_time": "1:23:54", "remaining_time": "4:54:55"}
+{"current_steps": 895, "total_steps": 4018, "loss": 3.689, "lr": 3.820050622035152e-05, "epoch": 1.5597210113339146, "percentage": 22.27, "elapsed_time": "1:24:20", "remaining_time": "4:54:18"}
+{"current_steps": 900, "total_steps": 4018, "loss": 3.6932, "lr": 3.8164318134110285e-05, "epoch": 1.5684394071490846, "percentage": 22.4, "elapsed_time": "1:24:49", "remaining_time": "4:53:51"}
+{"current_steps": 905, "total_steps": 4018, "loss": 3.7077, "lr": 3.812778727903506e-05, "epoch": 1.5771578029642546, "percentage": 22.52, "elapsed_time": "1:25:18", "remaining_time": "4:53:26"}
+{"current_steps": 910, "total_steps": 4018, "loss": 3.6874, "lr": 3.809091434447946e-05, "epoch": 1.5858761987794245, "percentage": 22.65, "elapsed_time": "1:25:43", "remaining_time": "4:52:45"}
+{"current_steps": 915, "total_steps": 4018, "loss": 3.6894, "lr": 3.805370002625232e-05, "epoch": 1.5945945945945947, "percentage": 22.77, "elapsed_time": "1:26:11", "remaining_time": "4:52:16"}
+{"current_steps": 920, "total_steps": 4018, "loss": 3.6988, "lr": 3.801614502660451e-05, "epoch": 1.6033129904097647, "percentage": 22.9, "elapsed_time": "1:26:40", "remaining_time": "4:51:50"}
+{"current_steps": 925, "total_steps": 4018, "loss": 3.7077, "lr": 3.7978250054215745e-05, "epoch": 1.6120313862249347, "percentage": 23.02, "elapsed_time": "1:27:08", "remaining_time": "4:51:22"}
+{"current_steps": 930, "total_steps": 4018, "loss": 3.6899, "lr": 3.794001582418113e-05, "epoch": 1.6207497820401047, "percentage": 23.15, "elapsed_time": "1:27:36", "remaining_time": "4:50:54"}
+{"current_steps": 935, "total_steps": 4018, "loss": 3.6965, "lr": 3.790144305799777e-05, "epoch": 1.6294681778552746, "percentage": 23.27, "elapsed_time": "1:28:04", "remaining_time": "4:50:25"}
+{"current_steps": 940, "total_steps": 4018, "loss": 3.6902, "lr": 3.786253248355106e-05, "epoch": 1.6381865736704446, "percentage": 23.39, "elapsed_time": "1:28:34", "remaining_time": "4:50:03"}
+{"current_steps": 945, "total_steps": 4018, "loss": 3.7148, "lr": 3.7823284835100994e-05, "epoch": 1.6469049694856146, "percentage": 23.52, "elapsed_time": "1:29:02", "remaining_time": "4:49:34"}
+{"current_steps": 950, "total_steps": 4018, "loss": 3.7052, "lr": 3.7783700853268325e-05, "epoch": 1.6556233653007846, "percentage": 23.64, "elapsed_time": "1:29:28", "remaining_time": "4:48:58"}
+{"current_steps": 955, "total_steps": 4018, "loss": 3.6939, "lr": 3.774378128502054e-05, "epoch": 1.6643417611159546, "percentage": 23.77, "elapsed_time": "1:29:59", "remaining_time": "4:48:38"}
+{"current_steps": 960, "total_steps": 4018, "loss": 3.6937, "lr": 3.7703526883657805e-05, "epoch": 1.6730601569311245, "percentage": 23.89, "elapsed_time": "1:30:27", "remaining_time": "4:48:09"}
+{"current_steps": 965, "total_steps": 4018, "loss": 3.6775, "lr": 3.766293840879874e-05, "epoch": 1.6817785527462947, "percentage": 24.02, "elapsed_time": "1:30:53", "remaining_time": "4:47:33"}
+{"current_steps": 970, "total_steps": 4018, "loss": 3.6861, "lr": 3.762201662636608e-05, "epoch": 1.6904969485614647, "percentage": 24.14, "elapsed_time": "1:31:21", "remaining_time": "4:47:05"}
+{"current_steps": 975, "total_steps": 4018, "loss": 3.7005, "lr": 3.7580762308572226e-05, "epoch": 1.6992153443766347, "percentage": 24.27, "elapsed_time": "1:31:50", "remaining_time": "4:46:37"}
+{"current_steps": 980, "total_steps": 4018, "loss": 3.6906, "lr": 3.7539176233904654e-05, "epoch": 1.7079337401918047, "percentage": 24.39, "elapsed_time": "1:32:17", "remaining_time": "4:46:05"}
+{"current_steps": 985, "total_steps": 4018, "loss": 3.7064, "lr": 3.749725918711127e-05, "epoch": 1.7166521360069749, "percentage": 24.51, "elapsed_time": "1:32:46", "remaining_time": "4:45:39"}
+{"current_steps": 990, "total_steps": 4018, "loss": 3.6635, "lr": 3.745501195918554e-05, "epoch": 1.7253705318221448, "percentage": 24.64, "elapsed_time": "1:33:14", "remaining_time": "4:45:10"}
+{"current_steps": 995, "total_steps": 4018, "loss": 3.6998, "lr": 3.741243534735163e-05, "epoch": 1.7340889276373148, "percentage": 24.76, "elapsed_time": "1:33:42", "remaining_time": "4:44:42"}
+{"current_steps": 1000, "total_steps": 4018, "loss": 3.6863, "lr": 3.736953015504929e-05, "epoch": 1.7428073234524848, "percentage": 24.89, "elapsed_time": "1:34:13", "remaining_time": "4:44:22"}
+{"current_steps": 1005, "total_steps": 4018, "loss": 3.7055, "lr": 3.732629719191876e-05, "epoch": 1.7515257192676548, "percentage": 25.01, "elapsed_time": "1:35:20", "remaining_time": "4:45:50"}
+{"current_steps": 1010, "total_steps": 4018, "loss": 3.6879, "lr": 3.7282737273785466e-05, "epoch": 1.7602441150828247, "percentage": 25.14, "elapsed_time": "1:35:48", "remaining_time": "4:45:19"}
+{"current_steps": 1015, "total_steps": 4018, "loss": 3.6878, "lr": 3.72388512226446e-05, "epoch": 1.7689625108979947, "percentage": 25.26, "elapsed_time": "1:36:19", "remaining_time": "4:44:58"}
+{"current_steps": 1020, "total_steps": 4018, "loss": 3.7028, "lr": 3.719463986664563e-05, "epoch": 1.7776809067131647, "percentage": 25.39, "elapsed_time": "1:36:49", "remaining_time": "4:44:34"}
+{"current_steps": 1025, "total_steps": 4018, "loss": 3.6787, "lr": 3.71501040400767e-05, "epoch": 1.7863993025283347, "percentage": 25.51, "elapsed_time": "1:37:16", "remaining_time": "4:44:02"}
+{"current_steps": 1030, "total_steps": 4018, "loss": 3.6823, "lr": 3.710524458334883e-05, "epoch": 1.7951176983435047, "percentage": 25.63, "elapsed_time": "1:37:43", "remaining_time": "4:43:31"}
+{"current_steps": 1035, "total_steps": 4018, "loss": 3.7168, "lr": 3.706006234298011e-05, "epoch": 1.8038360941586749, "percentage": 25.76, "elapsed_time": "1:38:15", "remaining_time": "4:43:12"}
+{"current_steps": 1040, "total_steps": 4018, "loss": 3.6905, "lr": 3.701455817157967e-05, "epoch": 1.8125544899738448, "percentage": 25.88, "elapsed_time": "1:38:47", "remaining_time": "4:42:52"}
+{"current_steps": 1045, "total_steps": 4018, "loss": 3.7221, "lr": 3.696873292783166e-05, "epoch": 1.8212728857890148, "percentage": 26.01, "elapsed_time": "1:39:17", "remaining_time": "4:42:29"}
+{"current_steps": 1050, "total_steps": 4018, "loss": 3.6732, "lr": 3.692258747647899e-05, "epoch": 1.8299912816041848, "percentage": 26.13, "elapsed_time": "1:39:43", "remaining_time": "4:41:54"}
+{"current_steps": 1055, "total_steps": 4018, "loss": 3.7094, "lr": 3.6876122688307034e-05, "epoch": 1.838709677419355, "percentage": 26.26, "elapsed_time": "1:40:11", "remaining_time": "4:41:23"}
+{"current_steps": 1060, "total_steps": 4018, "loss": 3.6777, "lr": 3.6829339440127186e-05, "epoch": 1.847428073234525, "percentage": 26.38, "elapsed_time": "1:40:38", "remaining_time": "4:40:51"}
+{"current_steps": 1065, "total_steps": 4018, "loss": 3.6792, "lr": 3.6782238614760344e-05, "epoch": 1.856146469049695, "percentage": 26.51, "elapsed_time": "1:41:08", "remaining_time": "4:40:27"}
+{"current_steps": 1070, "total_steps": 4018, "loss": 3.6749, "lr": 3.673482110102021e-05, "epoch": 1.864864864864865, "percentage": 26.63, "elapsed_time": "1:41:37", "remaining_time": "4:39:58"}
+{"current_steps": 1075, "total_steps": 4018, "loss": 3.6447, "lr": 3.668708779369655e-05, "epoch": 1.873583260680035, "percentage": 26.75, "elapsed_time": "1:42:02", "remaining_time": "4:39:22"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed102b149e738efc2a9d815fe7913e1970d9d079624633c695ea53a00c475ef
+size 8593