Training in progress, step 1500

.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": "4.57.6",
+  "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": "4.57.6"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a0ffd03523aa3e2ed023f586065bcae439cd73cd841cb449a9e270cff0e56a49
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dfe8c4d2eb6d5c961e33745eb813a99bb4fadb70e17c8edfd6e4e907ca45841f
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f0e3ca5fb9db73b3d7ac490e42393dd3981739b7c6c76abb9473d90e2e135458
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:32f8361ef07d1a9d6a128c5107161d9007b31e4c164f88931f4a892389faeb45
+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": "5b1d8b21707162015662fa506ad12998155f4ab9_thinking_preprocessed",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "/data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--DCAgent--exp-psu-stackoverflow-31K_glm_4.7_traces/snapshots/5b1d8b21707162015662fa506ad12998155f4ab9_thinking_preprocessed",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/exp-psu-stackoverflow-31K_glm_4_7_traces/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp-psu-stackoverflow-31K_glm_4-7_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 +1,319 @@
+{"current_steps": 5, "total_steps": 13643, "loss": 0.9401, "lr": 1.1721611721611722e-07, "epoch": 0.0025660764690787785, "percentage": 0.04, "elapsed_time": "0:00:29", "remaining_time": "22:02:34"}
+{"current_steps": 10, "total_steps": 13643, "loss": 0.941, "lr": 2.6373626373626375e-07, "epoch": 0.005132152938157557, "percentage": 0.07, "elapsed_time": "0:00:55", "remaining_time": "20:50:43"}
+{"current_steps": 15, "total_steps": 13643, "loss": 0.9746, "lr": 4.102564102564103e-07, "epoch": 0.007698229407236336, "percentage": 0.11, "elapsed_time": "0:01:20", "remaining_time": "20:22:38"}
+{"current_steps": 20, "total_steps": 13643, "loss": 0.9781, "lr": 5.567765567765568e-07, "epoch": 0.010264305876315114, "percentage": 0.15, "elapsed_time": "0:01:43", "remaining_time": "19:35:52"}
+{"current_steps": 25, "total_steps": 13643, "loss": 0.938, "lr": 7.032967032967034e-07, "epoch": 0.012830382345393894, "percentage": 0.18, "elapsed_time": "0:02:13", "remaining_time": "20:10:32"}
+{"current_steps": 30, "total_steps": 13643, "loss": 0.9434, "lr": 8.498168498168499e-07, "epoch": 0.015396458814472672, "percentage": 0.22, "elapsed_time": "0:02:33", "remaining_time": "19:24:01"}
+{"current_steps": 35, "total_steps": 13643, "loss": 0.8867, "lr": 9.963369963369966e-07, "epoch": 0.01796253528355145, "percentage": 0.26, "elapsed_time": "0:02:58", "remaining_time": "19:16:43"}
+{"current_steps": 40, "total_steps": 13643, "loss": 0.8527, "lr": 1.142857142857143e-06, "epoch": 0.020528611752630228, "percentage": 0.29, "elapsed_time": "0:03:25", "remaining_time": "19:23:14"}
+{"current_steps": 45, "total_steps": 13643, "loss": 0.8743, "lr": 1.2893772893772896e-06, "epoch": 0.023094688221709007, "percentage": 0.33, "elapsed_time": "0:03:49", "remaining_time": "19:14:17"}
+{"current_steps": 50, "total_steps": 13643, "loss": 0.8356, "lr": 1.4358974358974359e-06, "epoch": 0.025660764690787787, "percentage": 0.37, "elapsed_time": "0:04:08", "remaining_time": "18:45:02"}
+{"current_steps": 55, "total_steps": 13643, "loss": 0.7723, "lr": 1.5824175824175825e-06, "epoch": 0.028226841159866563, "percentage": 0.4, "elapsed_time": "0:04:31", "remaining_time": "18:38:52"}
+{"current_steps": 60, "total_steps": 13643, "loss": 0.7319, "lr": 1.7289377289377291e-06, "epoch": 0.030792917628945343, "percentage": 0.44, "elapsed_time": "0:04:58", "remaining_time": "18:44:24"}
+{"current_steps": 65, "total_steps": 13643, "loss": 0.711, "lr": 1.8754578754578756e-06, "epoch": 0.03335899409802412, "percentage": 0.48, "elapsed_time": "0:05:21", "remaining_time": "18:38:00"}
+{"current_steps": 70, "total_steps": 13643, "loss": 0.7177, "lr": 2.021978021978022e-06, "epoch": 0.0359250705671029, "percentage": 0.51, "elapsed_time": "0:05:42", "remaining_time": "18:27:00"}
+{"current_steps": 75, "total_steps": 13643, "loss": 0.7039, "lr": 2.1684981684981687e-06, "epoch": 0.03849114703618168, "percentage": 0.55, "elapsed_time": "0:06:04", "remaining_time": "18:19:01"}
+{"current_steps": 80, "total_steps": 13643, "loss": 0.6815, "lr": 2.3150183150183153e-06, "epoch": 0.041057223505260455, "percentage": 0.59, "elapsed_time": "0:06:28", "remaining_time": "18:18:43"}
+{"current_steps": 85, "total_steps": 13643, "loss": 0.6775, "lr": 2.461538461538462e-06, "epoch": 0.04362329997433924, "percentage": 0.62, "elapsed_time": "0:06:53", "remaining_time": "18:18:45"}
+{"current_steps": 90, "total_steps": 13643, "loss": 0.6246, "lr": 2.6080586080586086e-06, "epoch": 0.046189376443418015, "percentage": 0.66, "elapsed_time": "0:07:19", "remaining_time": "18:23:53"}
+{"current_steps": 95, "total_steps": 13643, "loss": 0.6183, "lr": 2.754578754578755e-06, "epoch": 0.04875545291249679, "percentage": 0.7, "elapsed_time": "0:07:49", "remaining_time": "18:36:11"}
+{"current_steps": 100, "total_steps": 13643, "loss": 0.6269, "lr": 2.9010989010989015e-06, "epoch": 0.051321529381575574, "percentage": 0.73, "elapsed_time": "0:08:11", "remaining_time": "18:29:49"}
+{"current_steps": 105, "total_steps": 13643, "loss": 0.5994, "lr": 3.047619047619048e-06, "epoch": 0.05388760585065435, "percentage": 0.77, "elapsed_time": "0:08:34", "remaining_time": "18:25:28"}
+{"current_steps": 110, "total_steps": 13643, "loss": 0.5942, "lr": 3.1941391941391943e-06, "epoch": 0.05645368231973313, "percentage": 0.81, "elapsed_time": "0:09:00", "remaining_time": "18:28:56"}
+{"current_steps": 115, "total_steps": 13643, "loss": 0.5863, "lr": 3.3406593406593406e-06, "epoch": 0.0590197587888119, "percentage": 0.84, "elapsed_time": "0:09:23", "remaining_time": "18:24:08"}
+{"current_steps": 120, "total_steps": 13643, "loss": 0.562, "lr": 3.487179487179487e-06, "epoch": 0.061585835257890686, "percentage": 0.88, "elapsed_time": "0:09:47", "remaining_time": "18:23:18"}
+{"current_steps": 125, "total_steps": 13643, "loss": 0.5873, "lr": 3.633699633699634e-06, "epoch": 0.06415191172696946, "percentage": 0.92, "elapsed_time": "0:10:08", "remaining_time": "18:17:15"}
+{"current_steps": 130, "total_steps": 13643, "loss": 0.5896, "lr": 3.7802197802197805e-06, "epoch": 0.06671798819604824, "percentage": 0.95, "elapsed_time": "0:10:32", "remaining_time": "18:16:05"}
+{"current_steps": 135, "total_steps": 13643, "loss": 0.5836, "lr": 3.926739926739927e-06, "epoch": 0.06928406466512702, "percentage": 0.99, "elapsed_time": "0:10:58", "remaining_time": "18:17:27"}
+{"current_steps": 140, "total_steps": 13643, "loss": 0.5734, "lr": 4.073260073260074e-06, "epoch": 0.0718501411342058, "percentage": 1.03, "elapsed_time": "0:11:19", "remaining_time": "18:12:42"}
+{"current_steps": 145, "total_steps": 13643, "loss": 0.5635, "lr": 4.21978021978022e-06, "epoch": 0.07441621760328458, "percentage": 1.06, "elapsed_time": "0:11:40", "remaining_time": "18:06:51"}
+{"current_steps": 150, "total_steps": 13643, "loss": 0.5467, "lr": 4.366300366300367e-06, "epoch": 0.07698229407236336, "percentage": 1.1, "elapsed_time": "0:12:07", "remaining_time": "18:11:07"}
+{"current_steps": 155, "total_steps": 13643, "loss": 0.5186, "lr": 4.512820512820513e-06, "epoch": 0.07954837054144213, "percentage": 1.14, "elapsed_time": "0:12:37", "remaining_time": "18:18:19"}
+{"current_steps": 160, "total_steps": 13643, "loss": 0.5259, "lr": 4.6593406593406595e-06, "epoch": 0.08211444701052091, "percentage": 1.17, "elapsed_time": "0:13:08", "remaining_time": "18:28:05"}
+{"current_steps": 165, "total_steps": 13643, "loss": 0.5759, "lr": 4.805860805860807e-06, "epoch": 0.08468052347959969, "percentage": 1.21, "elapsed_time": "0:13:36", "remaining_time": "18:31:16"}
+{"current_steps": 170, "total_steps": 13643, "loss": 0.5093, "lr": 4.952380952380953e-06, "epoch": 0.08724659994867848, "percentage": 1.25, "elapsed_time": "0:14:12", "remaining_time": "18:45:27"}
+{"current_steps": 175, "total_steps": 13643, "loss": 0.5096, "lr": 5.098901098901099e-06, "epoch": 0.08981267641775725, "percentage": 1.28, "elapsed_time": "0:14:32", "remaining_time": "18:39:05"}
+{"current_steps": 180, "total_steps": 13643, "loss": 0.4932, "lr": 5.245421245421246e-06, "epoch": 0.09237875288683603, "percentage": 1.32, "elapsed_time": "0:14:55", "remaining_time": "18:36:15"}
+{"current_steps": 185, "total_steps": 13643, "loss": 0.5304, "lr": 5.391941391941392e-06, "epoch": 0.0949448293559148, "percentage": 1.36, "elapsed_time": "0:15:19", "remaining_time": "18:34:51"}
+{"current_steps": 190, "total_steps": 13643, "loss": 0.5618, "lr": 5.538461538461539e-06, "epoch": 0.09751090582499358, "percentage": 1.39, "elapsed_time": "0:15:35", "remaining_time": "18:23:57"}
+{"current_steps": 195, "total_steps": 13643, "loss": 0.5133, "lr": 5.684981684981686e-06, "epoch": 0.10007698229407236, "percentage": 1.43, "elapsed_time": "0:15:59", "remaining_time": "18:22:17"}
+{"current_steps": 200, "total_steps": 13643, "loss": 0.5055, "lr": 5.831501831501833e-06, "epoch": 0.10264305876315115, "percentage": 1.47, "elapsed_time": "0:16:22", "remaining_time": "18:20:10"}
+{"current_steps": 205, "total_steps": 13643, "loss": 0.5265, "lr": 5.978021978021978e-06, "epoch": 0.10520913523222993, "percentage": 1.5, "elapsed_time": "0:16:38", "remaining_time": "18:10:24"}
+{"current_steps": 210, "total_steps": 13643, "loss": 0.547, "lr": 6.124542124542125e-06, "epoch": 0.1077752117013087, "percentage": 1.54, "elapsed_time": "0:17:00", "remaining_time": "18:07:30"}
+{"current_steps": 215, "total_steps": 13643, "loss": 0.5279, "lr": 6.271062271062271e-06, "epoch": 0.11034128817038748, "percentage": 1.58, "elapsed_time": "0:17:20", "remaining_time": "18:03:29"}
+{"current_steps": 220, "total_steps": 13643, "loss": 0.5342, "lr": 6.417582417582418e-06, "epoch": 0.11290736463946625, "percentage": 1.61, "elapsed_time": "0:17:39", "remaining_time": "17:57:37"}
+{"current_steps": 225, "total_steps": 13643, "loss": 0.5172, "lr": 6.564102564102565e-06, "epoch": 0.11547344110854503, "percentage": 1.65, "elapsed_time": "0:18:08", "remaining_time": "18:02:05"}
+{"current_steps": 230, "total_steps": 13643, "loss": 0.5086, "lr": 6.710622710622711e-06, "epoch": 0.1180395175776238, "percentage": 1.69, "elapsed_time": "0:18:28", "remaining_time": "17:57:04"}
+{"current_steps": 235, "total_steps": 13643, "loss": 0.5305, "lr": 6.857142857142858e-06, "epoch": 0.1206055940467026, "percentage": 1.72, "elapsed_time": "0:18:58", "remaining_time": "18:02:14"}
+{"current_steps": 240, "total_steps": 13643, "loss": 0.4872, "lr": 7.003663003663004e-06, "epoch": 0.12317167051578137, "percentage": 1.76, "elapsed_time": "0:19:18", "remaining_time": "17:58:21"}
+{"current_steps": 245, "total_steps": 13643, "loss": 0.5104, "lr": 7.150183150183151e-06, "epoch": 0.12573774698486015, "percentage": 1.8, "elapsed_time": "0:19:38", "remaining_time": "17:54:10"}
+{"current_steps": 250, "total_steps": 13643, "loss": 0.5191, "lr": 7.296703296703297e-06, "epoch": 0.12830382345393893, "percentage": 1.83, "elapsed_time": "0:19:58", "remaining_time": "17:50:05"}
+{"current_steps": 255, "total_steps": 13643, "loss": 0.5234, "lr": 7.443223443223444e-06, "epoch": 0.1308698999230177, "percentage": 1.87, "elapsed_time": "0:20:21", "remaining_time": "17:49:09"}
+{"current_steps": 260, "total_steps": 13643, "loss": 0.5124, "lr": 7.58974358974359e-06, "epoch": 0.13343597639209648, "percentage": 1.91, "elapsed_time": "0:20:54", "remaining_time": "17:55:53"}
+{"current_steps": 265, "total_steps": 13643, "loss": 0.4991, "lr": 7.736263736263738e-06, "epoch": 0.13600205286117525, "percentage": 1.94, "elapsed_time": "0:21:18", "remaining_time": "17:55:32"}
+{"current_steps": 270, "total_steps": 13643, "loss": 0.5243, "lr": 7.882783882783884e-06, "epoch": 0.13856812933025403, "percentage": 1.98, "elapsed_time": "0:21:38", "remaining_time": "17:52:05"}
+{"current_steps": 275, "total_steps": 13643, "loss": 0.459, "lr": 8.02930402930403e-06, "epoch": 0.1411342057993328, "percentage": 2.02, "elapsed_time": "0:21:58", "remaining_time": "17:48:34"}
+{"current_steps": 280, "total_steps": 13643, "loss": 0.4638, "lr": 8.175824175824176e-06, "epoch": 0.1437002822684116, "percentage": 2.05, "elapsed_time": "0:22:19", "remaining_time": "17:45:15"}
+{"current_steps": 285, "total_steps": 13643, "loss": 0.5103, "lr": 8.322344322344323e-06, "epoch": 0.1462663587374904, "percentage": 2.09, "elapsed_time": "0:22:36", "remaining_time": "17:39:18"}
+{"current_steps": 290, "total_steps": 13643, "loss": 0.5016, "lr": 8.468864468864469e-06, "epoch": 0.14883243520656916, "percentage": 2.13, "elapsed_time": "0:22:57", "remaining_time": "17:37:01"}
+{"current_steps": 295, "total_steps": 13643, "loss": 0.4938, "lr": 8.615384615384617e-06, "epoch": 0.15139851167564794, "percentage": 2.16, "elapsed_time": "0:23:25", "remaining_time": "17:39:44"}
+{"current_steps": 300, "total_steps": 13643, "loss": 0.5, "lr": 8.761904761904763e-06, "epoch": 0.15396458814472672, "percentage": 2.2, "elapsed_time": "0:23:46", "remaining_time": "17:37:15"}
+{"current_steps": 305, "total_steps": 13643, "loss": 0.4967, "lr": 8.90842490842491e-06, "epoch": 0.1565306646138055, "percentage": 2.24, "elapsed_time": "0:24:05", "remaining_time": "17:33:35"}
+{"current_steps": 310, "total_steps": 13643, "loss": 0.4683, "lr": 9.054945054945055e-06, "epoch": 0.15909674108288427, "percentage": 2.27, "elapsed_time": "0:24:29", "remaining_time": "17:33:01"}
+{"current_steps": 315, "total_steps": 13643, "loss": 0.5133, "lr": 9.201465201465202e-06, "epoch": 0.16166281755196305, "percentage": 2.31, "elapsed_time": "0:24:55", "remaining_time": "17:34:27"}
+{"current_steps": 320, "total_steps": 13643, "loss": 0.4876, "lr": 9.34798534798535e-06, "epoch": 0.16422889402104182, "percentage": 2.35, "elapsed_time": "0:25:16", "remaining_time": "17:32:05"}
+{"current_steps": 325, "total_steps": 13643, "loss": 0.4861, "lr": 9.494505494505494e-06, "epoch": 0.1667949704901206, "percentage": 2.38, "elapsed_time": "0:25:36", "remaining_time": "17:29:20"}
+{"current_steps": 330, "total_steps": 13643, "loss": 0.4924, "lr": 9.641025641025642e-06, "epoch": 0.16936104695919937, "percentage": 2.42, "elapsed_time": "0:26:00", "remaining_time": "17:29:24"}
+{"current_steps": 335, "total_steps": 13643, "loss": 0.5181, "lr": 9.787545787545788e-06, "epoch": 0.17192712342827815, "percentage": 2.46, "elapsed_time": "0:26:16", "remaining_time": "17:24:01"}
+{"current_steps": 340, "total_steps": 13643, "loss": 0.4562, "lr": 9.934065934065935e-06, "epoch": 0.17449319989735695, "percentage": 2.49, "elapsed_time": "0:26:39", "remaining_time": "17:22:46"}
+{"current_steps": 345, "total_steps": 13643, "loss": 0.4945, "lr": 1.008058608058608e-05, "epoch": 0.17705927636643573, "percentage": 2.53, "elapsed_time": "0:27:01", "remaining_time": "17:21:54"}
+{"current_steps": 350, "total_steps": 13643, "loss": 0.4758, "lr": 1.0227106227106227e-05, "epoch": 0.1796253528355145, "percentage": 2.57, "elapsed_time": "0:27:24", "remaining_time": "17:21:08"}
+{"current_steps": 355, "total_steps": 13643, "loss": 0.4689, "lr": 1.0373626373626375e-05, "epoch": 0.18219142930459328, "percentage": 2.6, "elapsed_time": "0:27:50", "remaining_time": "17:21:54"}
+{"current_steps": 360, "total_steps": 13643, "loss": 0.4883, "lr": 1.0520146520146521e-05, "epoch": 0.18475750577367206, "percentage": 2.64, "elapsed_time": "0:28:11", "remaining_time": "17:20:08"}
+{"current_steps": 365, "total_steps": 13643, "loss": 0.452, "lr": 1.0666666666666667e-05, "epoch": 0.18732358224275084, "percentage": 2.68, "elapsed_time": "0:28:30", "remaining_time": "17:16:55"}
+{"current_steps": 370, "total_steps": 13643, "loss": 0.4815, "lr": 1.0813186813186814e-05, "epoch": 0.1898896587118296, "percentage": 2.71, "elapsed_time": "0:28:55", "remaining_time": "17:17:28"}
+{"current_steps": 375, "total_steps": 13643, "loss": 0.48, "lr": 1.0959706959706961e-05, "epoch": 0.1924557351809084, "percentage": 2.75, "elapsed_time": "0:29:23", "remaining_time": "17:20:07"}
+{"current_steps": 380, "total_steps": 13643, "loss": 0.4747, "lr": 1.1106227106227108e-05, "epoch": 0.19502181164998716, "percentage": 2.79, "elapsed_time": "0:29:47", "remaining_time": "17:19:41"}
+{"current_steps": 385, "total_steps": 13643, "loss": 0.4913, "lr": 1.1252747252747254e-05, "epoch": 0.19758788811906594, "percentage": 2.82, "elapsed_time": "0:30:12", "remaining_time": "17:20:30"}
+{"current_steps": 390, "total_steps": 13643, "loss": 0.4504, "lr": 1.13992673992674e-05, "epoch": 0.20015396458814472, "percentage": 2.86, "elapsed_time": "0:30:36", "remaining_time": "17:20:04"}
+{"current_steps": 395, "total_steps": 13643, "loss": 0.4645, "lr": 1.1545787545787546e-05, "epoch": 0.2027200410572235, "percentage": 2.9, "elapsed_time": "0:30:56", "remaining_time": "17:17:55"}
+{"current_steps": 400, "total_steps": 13643, "loss": 0.4834, "lr": 1.1692307692307694e-05, "epoch": 0.2052861175263023, "percentage": 2.93, "elapsed_time": "0:31:17", "remaining_time": "17:16:02"}
+{"current_steps": 405, "total_steps": 13643, "loss": 0.4814, "lr": 1.183882783882784e-05, "epoch": 0.20785219399538107, "percentage": 2.97, "elapsed_time": "0:31:42", "remaining_time": "17:16:31"}
+{"current_steps": 410, "total_steps": 13643, "loss": 0.4849, "lr": 1.1985347985347987e-05, "epoch": 0.21041827046445985, "percentage": 3.01, "elapsed_time": "0:31:59", "remaining_time": "17:12:17"}
+{"current_steps": 415, "total_steps": 13643, "loss": 0.4589, "lr": 1.2131868131868131e-05, "epoch": 0.21298434693353863, "percentage": 3.04, "elapsed_time": "0:32:17", "remaining_time": "17:09:26"}
+{"current_steps": 420, "total_steps": 13643, "loss": 0.4506, "lr": 1.227838827838828e-05, "epoch": 0.2155504234026174, "percentage": 3.08, "elapsed_time": "0:32:40", "remaining_time": "17:08:38"}
+{"current_steps": 425, "total_steps": 13643, "loss": 0.4599, "lr": 1.2424908424908425e-05, "epoch": 0.21811649987169618, "percentage": 3.12, "elapsed_time": "0:33:06", "remaining_time": "17:09:41"}
+{"current_steps": 430, "total_steps": 13643, "loss": 0.4674, "lr": 1.2571428571428572e-05, "epoch": 0.22068257634077496, "percentage": 3.15, "elapsed_time": "0:33:29", "remaining_time": "17:09:10"}
+{"current_steps": 435, "total_steps": 13643, "loss": 0.4481, "lr": 1.2717948717948718e-05, "epoch": 0.22324865280985373, "percentage": 3.19, "elapsed_time": "0:33:52", "remaining_time": "17:08:47"}
+{"current_steps": 440, "total_steps": 13643, "loss": 0.4827, "lr": 1.2864468864468866e-05, "epoch": 0.2258147292789325, "percentage": 3.23, "elapsed_time": "0:34:21", "remaining_time": "17:11:11"}
+{"current_steps": 445, "total_steps": 13643, "loss": 0.4531, "lr": 1.3010989010989012e-05, "epoch": 0.22838080574801128, "percentage": 3.26, "elapsed_time": "0:34:43", "remaining_time": "17:09:50"}
+{"current_steps": 450, "total_steps": 13643, "loss": 0.4702, "lr": 1.3157509157509158e-05, "epoch": 0.23094688221709006, "percentage": 3.3, "elapsed_time": "0:35:05", "remaining_time": "17:08:46"}
+{"current_steps": 455, "total_steps": 13643, "loss": 0.464, "lr": 1.3304029304029304e-05, "epoch": 0.23351295868616884, "percentage": 3.34, "elapsed_time": "0:35:24", "remaining_time": "17:06:06"}
+{"current_steps": 460, "total_steps": 13643, "loss": 0.4582, "lr": 1.3450549450549452e-05, "epoch": 0.2360790351552476, "percentage": 3.37, "elapsed_time": "0:35:43", "remaining_time": "17:03:52"}
+{"current_steps": 465, "total_steps": 13643, "loss": 0.4541, "lr": 1.3597069597069599e-05, "epoch": 0.23864511162432642, "percentage": 3.41, "elapsed_time": "0:36:06", "remaining_time": "17:03:17"}
+{"current_steps": 470, "total_steps": 13643, "loss": 0.4729, "lr": 1.3743589743589745e-05, "epoch": 0.2412111880934052, "percentage": 3.44, "elapsed_time": "0:36:29", "remaining_time": "17:02:50"}
+{"current_steps": 475, "total_steps": 13643, "loss": 0.4786, "lr": 1.3890109890109891e-05, "epoch": 0.24377726456248397, "percentage": 3.48, "elapsed_time": "0:36:54", "remaining_time": "17:03:01"}
+{"current_steps": 480, "total_steps": 13643, "loss": 0.4484, "lr": 1.4036630036630037e-05, "epoch": 0.24634334103156275, "percentage": 3.52, "elapsed_time": "0:37:24", "remaining_time": "17:05:41"}
+{"current_steps": 485, "total_steps": 13643, "loss": 0.4911, "lr": 1.4183150183150185e-05, "epoch": 0.24890941750064152, "percentage": 3.55, "elapsed_time": "0:37:45", "remaining_time": "17:04:26"}
+{"current_steps": 490, "total_steps": 13643, "loss": 0.4682, "lr": 1.4329670329670331e-05, "epoch": 0.2514754939697203, "percentage": 3.59, "elapsed_time": "0:38:12", "remaining_time": "17:05:27"}
+{"current_steps": 495, "total_steps": 13643, "loss": 0.4483, "lr": 1.4476190476190478e-05, "epoch": 0.2540415704387991, "percentage": 3.63, "elapsed_time": "0:38:32", "remaining_time": "17:03:31"}
+{"current_steps": 500, "total_steps": 13643, "loss": 0.4369, "lr": 1.4622710622710624e-05, "epoch": 0.25660764690787785, "percentage": 3.66, "elapsed_time": "0:38:52", "remaining_time": "17:01:58"}
+{"current_steps": 505, "total_steps": 13643, "loss": 0.454, "lr": 1.4769230769230772e-05, "epoch": 0.25917372337695666, "percentage": 3.7, "elapsed_time": "0:39:12", "remaining_time": "17:00:07"}
+{"current_steps": 510, "total_steps": 13643, "loss": 0.4702, "lr": 1.4915750915750918e-05, "epoch": 0.2617397998460354, "percentage": 3.74, "elapsed_time": "0:39:34", "remaining_time": "16:59:10"}
+{"current_steps": 515, "total_steps": 13643, "loss": 0.4829, "lr": 1.5062271062271062e-05, "epoch": 0.2643058763151142, "percentage": 3.77, "elapsed_time": "0:39:55", "remaining_time": "16:57:47"}
+{"current_steps": 520, "total_steps": 13643, "loss": 0.4627, "lr": 1.5208791208791209e-05, "epoch": 0.26687195278419296, "percentage": 3.81, "elapsed_time": "0:40:13", "remaining_time": "16:55:12"}
+{"current_steps": 525, "total_steps": 13643, "loss": 0.4774, "lr": 1.5355311355311357e-05, "epoch": 0.26943802925327176, "percentage": 3.85, "elapsed_time": "0:40:35", "remaining_time": "16:54:12"}
+{"current_steps": 530, "total_steps": 13643, "loss": 0.4636, "lr": 1.5501831501831503e-05, "epoch": 0.2720041057223505, "percentage": 3.88, "elapsed_time": "0:40:57", "remaining_time": "16:53:23"}
+{"current_steps": 535, "total_steps": 13643, "loss": 0.4701, "lr": 1.564835164835165e-05, "epoch": 0.2745701821914293, "percentage": 3.92, "elapsed_time": "0:41:24", "remaining_time": "16:54:26"}
+{"current_steps": 540, "total_steps": 13643, "loss": 0.4669, "lr": 1.5794871794871795e-05, "epoch": 0.27713625866050806, "percentage": 3.96, "elapsed_time": "0:41:43", "remaining_time": "16:52:33"}
+{"current_steps": 545, "total_steps": 13643, "loss": 0.4465, "lr": 1.5941391941391945e-05, "epoch": 0.27970233512958687, "percentage": 3.99, "elapsed_time": "0:42:06", "remaining_time": "16:52:06"}
+{"current_steps": 550, "total_steps": 13643, "loss": 0.4743, "lr": 1.608791208791209e-05, "epoch": 0.2822684115986656, "percentage": 4.03, "elapsed_time": "0:42:26", "remaining_time": "16:50:13"}
+{"current_steps": 555, "total_steps": 13643, "loss": 0.4443, "lr": 1.6234432234432237e-05, "epoch": 0.2848344880677444, "percentage": 4.07, "elapsed_time": "0:42:47", "remaining_time": "16:49:03"}
+{"current_steps": 560, "total_steps": 13643, "loss": 0.466, "lr": 1.6380952380952384e-05, "epoch": 0.2874005645368232, "percentage": 4.1, "elapsed_time": "0:43:18", "remaining_time": "16:51:41"}
+{"current_steps": 565, "total_steps": 13643, "loss": 0.4682, "lr": 1.6527472527472526e-05, "epoch": 0.28996664100590197, "percentage": 4.14, "elapsed_time": "0:43:43", "remaining_time": "16:52:08"}
+{"current_steps": 570, "total_steps": 13643, "loss": 0.4452, "lr": 1.6673992673992676e-05, "epoch": 0.2925327174749808, "percentage": 4.18, "elapsed_time": "0:44:11", "remaining_time": "16:53:25"}
+{"current_steps": 575, "total_steps": 13643, "loss": 0.4469, "lr": 1.6820512820512822e-05, "epoch": 0.2950987939440595, "percentage": 4.21, "elapsed_time": "0:44:35", "remaining_time": "16:53:18"}
+{"current_steps": 580, "total_steps": 13643, "loss": 0.4528, "lr": 1.696703296703297e-05, "epoch": 0.2976648704131383, "percentage": 4.25, "elapsed_time": "0:44:54", "remaining_time": "16:51:18"}
+{"current_steps": 585, "total_steps": 13643, "loss": 0.4885, "lr": 1.7113553113553115e-05, "epoch": 0.3002309468822171, "percentage": 4.29, "elapsed_time": "0:45:12", "remaining_time": "16:49:14"}
+{"current_steps": 590, "total_steps": 13643, "loss": 0.416, "lr": 1.726007326007326e-05, "epoch": 0.3027970233512959, "percentage": 4.32, "elapsed_time": "0:45:33", "remaining_time": "16:47:49"}
+{"current_steps": 595, "total_steps": 13643, "loss": 0.4385, "lr": 1.7406593406593407e-05, "epoch": 0.30536309982037463, "percentage": 4.36, "elapsed_time": "0:45:54", "remaining_time": "16:46:45"}
+{"current_steps": 600, "total_steps": 13643, "loss": 0.4574, "lr": 1.7553113553113553e-05, "epoch": 0.30792917628945343, "percentage": 4.4, "elapsed_time": "0:46:15", "remaining_time": "16:45:43"}
+{"current_steps": 605, "total_steps": 13643, "loss": 0.4309, "lr": 1.76996336996337e-05, "epoch": 0.3104952527585322, "percentage": 4.43, "elapsed_time": "0:46:39", "remaining_time": "16:45:34"}
+{"current_steps": 610, "total_steps": 13643, "loss": 0.4126, "lr": 1.784615384615385e-05, "epoch": 0.313061329227611, "percentage": 4.47, "elapsed_time": "0:46:58", "remaining_time": "16:43:38"}
+{"current_steps": 615, "total_steps": 13643, "loss": 0.4282, "lr": 1.7992673992673995e-05, "epoch": 0.3156274056966898, "percentage": 4.51, "elapsed_time": "0:47:25", "remaining_time": "16:44:32"}
+{"current_steps": 620, "total_steps": 13643, "loss": 0.4302, "lr": 1.813919413919414e-05, "epoch": 0.31819348216576854, "percentage": 4.54, "elapsed_time": "0:47:42", "remaining_time": "16:42:15"}
+{"current_steps": 625, "total_steps": 13643, "loss": 0.4314, "lr": 1.8285714285714288e-05, "epoch": 0.32075955863484734, "percentage": 4.58, "elapsed_time": "0:48:10", "remaining_time": "16:43:33"}
+{"current_steps": 630, "total_steps": 13643, "loss": 0.4244, "lr": 1.8432234432234434e-05, "epoch": 0.3233256351039261, "percentage": 4.62, "elapsed_time": "0:48:33", "remaining_time": "16:43:04"}
+{"current_steps": 635, "total_steps": 13643, "loss": 0.4329, "lr": 1.857875457875458e-05, "epoch": 0.3258917115730049, "percentage": 4.65, "elapsed_time": "0:48:53", "remaining_time": "16:41:31"}
+{"current_steps": 640, "total_steps": 13643, "loss": 0.4582, "lr": 1.8725274725274726e-05, "epoch": 0.32845778804208364, "percentage": 4.69, "elapsed_time": "0:49:18", "remaining_time": "16:41:50"}
+{"current_steps": 645, "total_steps": 13643, "loss": 0.4365, "lr": 1.8871794871794873e-05, "epoch": 0.33102386451116245, "percentage": 4.73, "elapsed_time": "0:49:43", "remaining_time": "16:42:08"}
+{"current_steps": 650, "total_steps": 13643, "loss": 0.457, "lr": 1.901831501831502e-05, "epoch": 0.3335899409802412, "percentage": 4.76, "elapsed_time": "0:50:03", "remaining_time": "16:40:41"}
+{"current_steps": 655, "total_steps": 13643, "loss": 0.4312, "lr": 1.916483516483517e-05, "epoch": 0.33615601744932, "percentage": 4.8, "elapsed_time": "0:50:25", "remaining_time": "16:40:02"}
+{"current_steps": 660, "total_steps": 13643, "loss": 0.4323, "lr": 1.9311355311355315e-05, "epoch": 0.33872209391839875, "percentage": 4.84, "elapsed_time": "0:50:51", "remaining_time": "16:40:18"}
+{"current_steps": 665, "total_steps": 13643, "loss": 0.439, "lr": 1.9457875457875458e-05, "epoch": 0.34128817038747755, "percentage": 4.87, "elapsed_time": "0:51:08", "remaining_time": "16:38:04"}
+{"current_steps": 670, "total_steps": 13643, "loss": 0.4533, "lr": 1.9604395604395604e-05, "epoch": 0.3438542468565563, "percentage": 4.91, "elapsed_time": "0:51:29", "remaining_time": "16:36:54"}
+{"current_steps": 675, "total_steps": 13643, "loss": 0.447, "lr": 1.9750915750915753e-05, "epoch": 0.3464203233256351, "percentage": 4.95, "elapsed_time": "0:51:53", "remaining_time": "16:37:02"}
+{"current_steps": 680, "total_steps": 13643, "loss": 0.4534, "lr": 1.98974358974359e-05, "epoch": 0.3489863997947139, "percentage": 4.98, "elapsed_time": "0:52:16", "remaining_time": "16:36:24"}
+{"current_steps": 685, "total_steps": 13643, "loss": 0.4147, "lr": 2.0043956043956046e-05, "epoch": 0.35155247626379266, "percentage": 5.02, "elapsed_time": "0:52:43", "remaining_time": "16:37:15"}
+{"current_steps": 690, "total_steps": 13643, "loss": 0.4292, "lr": 2.0190476190476192e-05, "epoch": 0.35411855273287146, "percentage": 5.06, "elapsed_time": "0:53:08", "remaining_time": "16:37:28"}
+{"current_steps": 695, "total_steps": 13643, "loss": 0.4342, "lr": 2.0336996336996338e-05, "epoch": 0.3566846292019502, "percentage": 5.09, "elapsed_time": "0:53:34", "remaining_time": "16:38:01"}
+{"current_steps": 700, "total_steps": 13643, "loss": 0.4299, "lr": 2.0483516483516485e-05, "epoch": 0.359250705671029, "percentage": 5.13, "elapsed_time": "0:53:57", "remaining_time": "16:37:46"}
+{"current_steps": 705, "total_steps": 13643, "loss": 0.4282, "lr": 2.0630036630036634e-05, "epoch": 0.36181678214010776, "percentage": 5.17, "elapsed_time": "0:54:16", "remaining_time": "16:36:11"}
+{"current_steps": 710, "total_steps": 13643, "loss": 0.45, "lr": 2.077655677655678e-05, "epoch": 0.36438285860918657, "percentage": 5.2, "elapsed_time": "0:54:40", "remaining_time": "16:35:49"}
+{"current_steps": 715, "total_steps": 13643, "loss": 0.4547, "lr": 2.0923076923076927e-05, "epoch": 0.3669489350782653, "percentage": 5.24, "elapsed_time": "0:55:03", "remaining_time": "16:35:29"}
+{"current_steps": 720, "total_steps": 13643, "loss": 0.4131, "lr": 2.1069597069597073e-05, "epoch": 0.3695150115473441, "percentage": 5.28, "elapsed_time": "0:55:32", "remaining_time": "16:36:51"}
+{"current_steps": 725, "total_steps": 13643, "loss": 0.4475, "lr": 2.121611721611722e-05, "epoch": 0.37208108801642287, "percentage": 5.31, "elapsed_time": "0:55:53", "remaining_time": "16:35:50"}
+{"current_steps": 730, "total_steps": 13643, "loss": 0.4326, "lr": 2.1362637362637365e-05, "epoch": 0.37464716448550167, "percentage": 5.35, "elapsed_time": "0:56:17", "remaining_time": "16:35:39"}
+{"current_steps": 735, "total_steps": 13643, "loss": 0.4679, "lr": 2.150915750915751e-05, "epoch": 0.3772132409545804, "percentage": 5.39, "elapsed_time": "0:56:37", "remaining_time": "16:34:34"}
+{"current_steps": 740, "total_steps": 13643, "loss": 0.4408, "lr": 2.1655677655677658e-05, "epoch": 0.3797793174236592, "percentage": 5.42, "elapsed_time": "0:56:53", "remaining_time": "16:32:03"}
+{"current_steps": 745, "total_steps": 13643, "loss": 0.4271, "lr": 2.18021978021978e-05, "epoch": 0.38234539389273803, "percentage": 5.46, "elapsed_time": "0:57:11", "remaining_time": "16:30:10"}
+{"current_steps": 750, "total_steps": 13643, "loss": 0.4437, "lr": 2.1948717948717954e-05, "epoch": 0.3849114703618168, "percentage": 5.5, "elapsed_time": "0:57:31", "remaining_time": "16:28:52"}
+{"current_steps": 755, "total_steps": 13643, "loss": 0.4451, "lr": 2.20952380952381e-05, "epoch": 0.3874775468308956, "percentage": 5.53, "elapsed_time": "0:57:50", "remaining_time": "16:27:18"}
+{"current_steps": 760, "total_steps": 13643, "loss": 0.422, "lr": 2.2241758241758246e-05, "epoch": 0.39004362329997433, "percentage": 5.57, "elapsed_time": "0:58:10", "remaining_time": "16:26:12"}
+{"current_steps": 765, "total_steps": 13643, "loss": 0.402, "lr": 2.2388278388278392e-05, "epoch": 0.39260969976905313, "percentage": 5.61, "elapsed_time": "0:58:35", "remaining_time": "16:26:12"}
+{"current_steps": 770, "total_steps": 13643, "loss": 0.4347, "lr": 2.2534798534798535e-05, "epoch": 0.3951757762381319, "percentage": 5.64, "elapsed_time": "0:58:52", "remaining_time": "16:24:09"}
+{"current_steps": 775, "total_steps": 13643, "loss": 0.4335, "lr": 2.268131868131868e-05, "epoch": 0.3977418527072107, "percentage": 5.68, "elapsed_time": "0:59:16", "remaining_time": "16:24:10"}
+{"current_steps": 780, "total_steps": 13643, "loss": 0.4263, "lr": 2.2827838827838827e-05, "epoch": 0.40030792917628943, "percentage": 5.72, "elapsed_time": "0:59:37", "remaining_time": "16:23:15"}
+{"current_steps": 785, "total_steps": 13643, "loss": 0.4282, "lr": 2.2974358974358974e-05, "epoch": 0.40287400564536824, "percentage": 5.75, "elapsed_time": "0:59:58", "remaining_time": "16:22:14"}
+{"current_steps": 790, "total_steps": 13643, "loss": 0.4317, "lr": 2.312087912087912e-05, "epoch": 0.405440082114447, "percentage": 5.79, "elapsed_time": "1:00:16", "remaining_time": "16:20:33"}
+{"current_steps": 795, "total_steps": 13643, "loss": 0.432, "lr": 2.326739926739927e-05, "epoch": 0.4080061585835258, "percentage": 5.83, "elapsed_time": "1:00:38", "remaining_time": "16:19:58"}
+{"current_steps": 800, "total_steps": 13643, "loss": 0.4486, "lr": 2.3413919413919416e-05, "epoch": 0.4105722350526046, "percentage": 5.86, "elapsed_time": "1:00:57", "remaining_time": "16:18:40"}
+{"current_steps": 805, "total_steps": 13643, "loss": 0.4265, "lr": 2.3560439560439562e-05, "epoch": 0.41313831152168334, "percentage": 5.9, "elapsed_time": "1:01:21", "remaining_time": "16:18:31"}
+{"current_steps": 810, "total_steps": 13643, "loss": 0.439, "lr": 2.3706959706959708e-05, "epoch": 0.41570438799076215, "percentage": 5.94, "elapsed_time": "1:01:40", "remaining_time": "16:17:14"}
+{"current_steps": 815, "total_steps": 13643, "loss": 0.4385, "lr": 2.3853479853479854e-05, "epoch": 0.4182704644598409, "percentage": 5.97, "elapsed_time": "1:01:59", "remaining_time": "16:15:42"}
+{"current_steps": 820, "total_steps": 13643, "loss": 0.4446, "lr": 2.4e-05, "epoch": 0.4208365409289197, "percentage": 6.01, "elapsed_time": "1:02:18", "remaining_time": "16:14:24"}
+{"current_steps": 825, "total_steps": 13643, "loss": 0.4365, "lr": 2.4146520146520147e-05, "epoch": 0.42340261739799845, "percentage": 6.05, "elapsed_time": "1:02:43", "remaining_time": "16:14:32"}
+{"current_steps": 830, "total_steps": 13643, "loss": 0.4368, "lr": 2.4293040293040293e-05, "epoch": 0.42596869386707725, "percentage": 6.08, "elapsed_time": "1:03:11", "remaining_time": "16:15:30"}
+{"current_steps": 835, "total_steps": 13643, "loss": 0.442, "lr": 2.4439560439560443e-05, "epoch": 0.428534770336156, "percentage": 6.12, "elapsed_time": "1:03:31", "remaining_time": "16:14:27"}
+{"current_steps": 840, "total_steps": 13643, "loss": 0.4307, "lr": 2.458608058608059e-05, "epoch": 0.4311008468052348, "percentage": 6.16, "elapsed_time": "1:03:54", "remaining_time": "16:13:59"}
+{"current_steps": 845, "total_steps": 13643, "loss": 0.4297, "lr": 2.4732600732600735e-05, "epoch": 0.43366692327431355, "percentage": 6.19, "elapsed_time": "1:04:17", "remaining_time": "16:13:51"}
+{"current_steps": 850, "total_steps": 13643, "loss": 0.406, "lr": 2.487912087912088e-05, "epoch": 0.43623299974339236, "percentage": 6.23, "elapsed_time": "1:04:46", "remaining_time": "16:14:50"}
+{"current_steps": 855, "total_steps": 13643, "loss": 0.4549, "lr": 2.5025641025641028e-05, "epoch": 0.4387990762124711, "percentage": 6.27, "elapsed_time": "1:05:08", "remaining_time": "16:14:19"}
+{"current_steps": 860, "total_steps": 13643, "loss": 0.4568, "lr": 2.5172161172161174e-05, "epoch": 0.4413651526815499, "percentage": 6.3, "elapsed_time": "1:05:29", "remaining_time": "16:13:24"}
+{"current_steps": 865, "total_steps": 13643, "loss": 0.4376, "lr": 2.531868131868132e-05, "epoch": 0.4439312291506287, "percentage": 6.34, "elapsed_time": "1:05:59", "remaining_time": "16:14:52"}
+{"current_steps": 870, "total_steps": 13643, "loss": 0.4336, "lr": 2.5465201465201466e-05, "epoch": 0.44649730561970746, "percentage": 6.38, "elapsed_time": "1:06:20", "remaining_time": "16:14:06"}
+{"current_steps": 875, "total_steps": 13643, "loss": 0.4354, "lr": 2.5611721611721612e-05, "epoch": 0.44906338208878627, "percentage": 6.41, "elapsed_time": "1:06:40", "remaining_time": "16:12:58"}
+{"current_steps": 880, "total_steps": 13643, "loss": 0.4289, "lr": 2.5758241758241762e-05, "epoch": 0.451629458557865, "percentage": 6.45, "elapsed_time": "1:07:00", "remaining_time": "16:11:44"}
+{"current_steps": 885, "total_steps": 13643, "loss": 0.4742, "lr": 2.5904761904761908e-05, "epoch": 0.4541955350269438, "percentage": 6.49, "elapsed_time": "1:07:22", "remaining_time": "16:11:12"}
+{"current_steps": 890, "total_steps": 13643, "loss": 0.4481, "lr": 2.6051282051282054e-05, "epoch": 0.45676161149602257, "percentage": 6.52, "elapsed_time": "1:07:42", "remaining_time": "16:10:17"}
+{"current_steps": 895, "total_steps": 13643, "loss": 0.4112, "lr": 2.61978021978022e-05, "epoch": 0.45932768796510137, "percentage": 6.56, "elapsed_time": "1:08:12", "remaining_time": "16:11:29"}
+{"current_steps": 900, "total_steps": 13643, "loss": 0.4236, "lr": 2.6344322344322347e-05, "epoch": 0.4618937644341801, "percentage": 6.6, "elapsed_time": "1:08:38", "remaining_time": "16:11:59"}
+{"current_steps": 905, "total_steps": 13643, "loss": 0.4209, "lr": 2.6490842490842493e-05, "epoch": 0.4644598409032589, "percentage": 6.63, "elapsed_time": "1:09:01", "remaining_time": "16:11:32"}
+{"current_steps": 910, "total_steps": 13643, "loss": 0.4322, "lr": 2.663736263736264e-05, "epoch": 0.4670259173723377, "percentage": 6.67, "elapsed_time": "1:09:23", "remaining_time": "16:11:02"}
+{"current_steps": 915, "total_steps": 13643, "loss": 0.4319, "lr": 2.6783882783882786e-05, "epoch": 0.4695919938414165, "percentage": 6.71, "elapsed_time": "1:09:41", "remaining_time": "16:09:23"}
+{"current_steps": 920, "total_steps": 13643, "loss": 0.4479, "lr": 2.6930402930402935e-05, "epoch": 0.4721580703104952, "percentage": 6.74, "elapsed_time": "1:10:09", "remaining_time": "16:10:11"}
+{"current_steps": 925, "total_steps": 13643, "loss": 0.4127, "lr": 2.707692307692308e-05, "epoch": 0.47472414677957403, "percentage": 6.78, "elapsed_time": "1:10:30", "remaining_time": "16:09:21"}
+{"current_steps": 930, "total_steps": 13643, "loss": 0.4209, "lr": 2.7223443223443228e-05, "epoch": 0.47729022324865283, "percentage": 6.82, "elapsed_time": "1:10:53", "remaining_time": "16:09:03"}
+{"current_steps": 935, "total_steps": 13643, "loss": 0.4237, "lr": 2.7369963369963374e-05, "epoch": 0.4798562997177316, "percentage": 6.85, "elapsed_time": "1:11:09", "remaining_time": "16:07:05"}
+{"current_steps": 940, "total_steps": 13643, "loss": 0.4398, "lr": 2.751648351648352e-05, "epoch": 0.4824223761868104, "percentage": 6.89, "elapsed_time": "1:11:29", "remaining_time": "16:06:03"}
+{"current_steps": 945, "total_steps": 13643, "loss": 0.4091, "lr": 2.7663003663003666e-05, "epoch": 0.48498845265588914, "percentage": 6.93, "elapsed_time": "1:11:54", "remaining_time": "16:06:18"}
+{"current_steps": 950, "total_steps": 13643, "loss": 0.4112, "lr": 2.780952380952381e-05, "epoch": 0.48755452912496794, "percentage": 6.96, "elapsed_time": "1:12:18", "remaining_time": "16:06:11"}
+{"current_steps": 955, "total_steps": 13643, "loss": 0.4222, "lr": 2.7956043956043955e-05, "epoch": 0.4901206055940467, "percentage": 7.0, "elapsed_time": "1:12:38", "remaining_time": "16:05:08"}
+{"current_steps": 960, "total_steps": 13643, "loss": 0.4354, "lr": 2.81025641025641e-05, "epoch": 0.4926866820631255, "percentage": 7.04, "elapsed_time": "1:13:01", "remaining_time": "16:04:46"}
+{"current_steps": 965, "total_steps": 13643, "loss": 0.4307, "lr": 2.8249084249084255e-05, "epoch": 0.49525275853220424, "percentage": 7.07, "elapsed_time": "1:13:27", "remaining_time": "16:04:58"}
+{"current_steps": 970, "total_steps": 13643, "loss": 0.4309, "lr": 2.83956043956044e-05, "epoch": 0.49781883500128304, "percentage": 7.11, "elapsed_time": "1:13:49", "remaining_time": "16:04:25"}
+{"current_steps": 975, "total_steps": 13643, "loss": 0.4577, "lr": 2.8542124542124544e-05, "epoch": 0.5003849114703618, "percentage": 7.15, "elapsed_time": "1:14:05", "remaining_time": "16:02:38"}
+{"current_steps": 980, "total_steps": 13643, "loss": 0.4222, "lr": 2.868864468864469e-05, "epoch": 0.5029509879394406, "percentage": 7.18, "elapsed_time": "1:14:24", "remaining_time": "16:01:27"}
+{"current_steps": 985, "total_steps": 13643, "loss": 0.4346, "lr": 2.8835164835164836e-05, "epoch": 0.5055170644085194, "percentage": 7.22, "elapsed_time": "1:14:43", "remaining_time": "16:00:10"}
+{"current_steps": 990, "total_steps": 13643, "loss": 0.4243, "lr": 2.8981684981684982e-05, "epoch": 0.5080831408775982, "percentage": 7.26, "elapsed_time": "1:15:07", "remaining_time": "16:00:08"}
+{"current_steps": 995, "total_steps": 13643, "loss": 0.4173, "lr": 2.912820512820513e-05, "epoch": 0.5106492173466769, "percentage": 7.29, "elapsed_time": "1:15:26", "remaining_time": "15:59:02"}
+{"current_steps": 1000, "total_steps": 13643, "loss": 0.4018, "lr": 2.9274725274725275e-05, "epoch": 0.5132152938157557, "percentage": 7.33, "elapsed_time": "1:15:46", "remaining_time": "15:58:06"}
+{"current_steps": 1005, "total_steps": 13643, "loss": 0.4228, "lr": 2.9421245421245424e-05, "epoch": 0.5157813702848345, "percentage": 7.37, "elapsed_time": "1:16:07", "remaining_time": "15:57:11"}
+{"current_steps": 1010, "total_steps": 13643, "loss": 0.4223, "lr": 2.956776556776557e-05, "epoch": 0.5183474467539133, "percentage": 7.4, "elapsed_time": "1:16:27", "remaining_time": "15:56:18"}
+{"current_steps": 1015, "total_steps": 13643, "loss": 0.4212, "lr": 2.9714285714285717e-05, "epoch": 0.520913523222992, "percentage": 7.44, "elapsed_time": "1:16:50", "remaining_time": "15:55:56"}
+{"current_steps": 1020, "total_steps": 13643, "loss": 0.4308, "lr": 2.9860805860805863e-05, "epoch": 0.5234795996920708, "percentage": 7.48, "elapsed_time": "1:17:18", "remaining_time": "15:56:41"}
+{"current_steps": 1025, "total_steps": 13643, "loss": 0.4105, "lr": 3.000732600732601e-05, "epoch": 0.5260456761611496, "percentage": 7.51, "elapsed_time": "1:17:44", "remaining_time": "15:56:59"}
+{"current_steps": 1030, "total_steps": 13643, "loss": 0.4083, "lr": 3.0153846153846155e-05, "epoch": 0.5286117526302284, "percentage": 7.55, "elapsed_time": "1:18:10", "remaining_time": "15:57:19"}
+{"current_steps": 1035, "total_steps": 13643, "loss": 0.4199, "lr": 3.0300366300366302e-05, "epoch": 0.5311778290993071, "percentage": 7.59, "elapsed_time": "1:18:42", "remaining_time": "15:58:53"}
+{"current_steps": 1040, "total_steps": 13643, "loss": 0.4208, "lr": 3.0446886446886448e-05, "epoch": 0.5337439055683859, "percentage": 7.62, "elapsed_time": "1:19:06", "remaining_time": "15:58:42"}
+{"current_steps": 1045, "total_steps": 13643, "loss": 0.422, "lr": 3.059340659340659e-05, "epoch": 0.5363099820374647, "percentage": 7.66, "elapsed_time": "1:19:26", "remaining_time": "15:57:37"}
+{"current_steps": 1050, "total_steps": 13643, "loss": 0.4388, "lr": 3.073992673992675e-05, "epoch": 0.5388760585065435, "percentage": 7.7, "elapsed_time": "1:19:43", "remaining_time": "15:56:15"}
+{"current_steps": 1055, "total_steps": 13643, "loss": 0.4233, "lr": 3.088644688644689e-05, "epoch": 0.5414421349756223, "percentage": 7.73, "elapsed_time": "1:20:09", "remaining_time": "15:56:29"}
+{"current_steps": 1060, "total_steps": 13643, "loss": 0.4219, "lr": 3.103296703296704e-05, "epoch": 0.544008211444701, "percentage": 7.77, "elapsed_time": "1:20:29", "remaining_time": "15:55:25"}
+{"current_steps": 1065, "total_steps": 13643, "loss": 0.4517, "lr": 3.117948717948718e-05, "epoch": 0.5465742879137798, "percentage": 7.81, "elapsed_time": "1:20:52", "remaining_time": "15:55:10"}
+{"current_steps": 1070, "total_steps": 13643, "loss": 0.4123, "lr": 3.1326007326007325e-05, "epoch": 0.5491403643828586, "percentage": 7.84, "elapsed_time": "1:21:16", "remaining_time": "15:54:56"}
+{"current_steps": 1075, "total_steps": 13643, "loss": 0.4371, "lr": 3.1472527472527475e-05, "epoch": 0.5517064408519374, "percentage": 7.88, "elapsed_time": "1:21:37", "remaining_time": "15:54:19"}
+{"current_steps": 1080, "total_steps": 13643, "loss": 0.4, "lr": 3.161904761904762e-05, "epoch": 0.5542725173210161, "percentage": 7.92, "elapsed_time": "1:22:01", "remaining_time": "15:54:13"}
+{"current_steps": 1085, "total_steps": 13643, "loss": 0.4195, "lr": 3.176556776556777e-05, "epoch": 0.5568385937900949, "percentage": 7.95, "elapsed_time": "1:22:23", "remaining_time": "15:53:35"}
+{"current_steps": 1090, "total_steps": 13643, "loss": 0.4258, "lr": 3.191208791208792e-05, "epoch": 0.5594046702591737, "percentage": 7.99, "elapsed_time": "1:22:44", "remaining_time": "15:52:56"}
+{"current_steps": 1095, "total_steps": 13643, "loss": 0.4201, "lr": 3.205860805860806e-05, "epoch": 0.5619707467282525, "percentage": 8.03, "elapsed_time": "1:23:04", "remaining_time": "15:51:56"}
+{"current_steps": 1100, "total_steps": 13643, "loss": 0.4142, "lr": 3.220512820512821e-05, "epoch": 0.5645368231973312, "percentage": 8.06, "elapsed_time": "1:23:22", "remaining_time": "15:50:38"}
+{"current_steps": 1105, "total_steps": 13643, "loss": 0.4261, "lr": 3.235164835164835e-05, "epoch": 0.56710289966641, "percentage": 8.1, "elapsed_time": "1:23:40", "remaining_time": "15:49:21"}
+{"current_steps": 1110, "total_steps": 13643, "loss": 0.4186, "lr": 3.24981684981685e-05, "epoch": 0.5696689761354888, "percentage": 8.14, "elapsed_time": "1:24:03", "remaining_time": "15:49:11"}
+{"current_steps": 1115, "total_steps": 13643, "loss": 0.4311, "lr": 3.2644688644688645e-05, "epoch": 0.5722350526045676, "percentage": 8.17, "elapsed_time": "1:24:32", "remaining_time": "15:49:52"}
+{"current_steps": 1120, "total_steps": 13643, "loss": 0.4173, "lr": 3.2791208791208794e-05, "epoch": 0.5748011290736464, "percentage": 8.21, "elapsed_time": "1:24:59", "remaining_time": "15:50:19"}
+{"current_steps": 1125, "total_steps": 13643, "loss": 0.4218, "lr": 3.293772893772894e-05, "epoch": 0.5773672055427251, "percentage": 8.25, "elapsed_time": "1:25:21", "remaining_time": "15:49:47"}
+{"current_steps": 1130, "total_steps": 13643, "loss": 0.4379, "lr": 3.308424908424909e-05, "epoch": 0.5799332820118039, "percentage": 8.28, "elapsed_time": "1:25:44", "remaining_time": "15:49:27"}
+{"current_steps": 1135, "total_steps": 13643, "loss": 0.4215, "lr": 3.3230769230769236e-05, "epoch": 0.5824993584808827, "percentage": 8.32, "elapsed_time": "1:26:04", "remaining_time": "15:48:38"}
+{"current_steps": 1140, "total_steps": 13643, "loss": 0.4195, "lr": 3.337728937728938e-05, "epoch": 0.5850654349499615, "percentage": 8.36, "elapsed_time": "1:26:21", "remaining_time": "15:47:11"}
+{"current_steps": 1145, "total_steps": 13643, "loss": 0.4323, "lr": 3.352380952380953e-05, "epoch": 0.5876315114190402, "percentage": 8.39, "elapsed_time": "1:26:42", "remaining_time": "15:46:26"}
+{"current_steps": 1150, "total_steps": 13643, "loss": 0.4315, "lr": 3.367032967032967e-05, "epoch": 0.590197587888119, "percentage": 8.43, "elapsed_time": "1:27:00", "remaining_time": "15:45:15"}
+{"current_steps": 1155, "total_steps": 13643, "loss": 0.4239, "lr": 3.381684981684982e-05, "epoch": 0.5927636643571979, "percentage": 8.47, "elapsed_time": "1:27:24", "remaining_time": "15:45:02"}
+{"current_steps": 1160, "total_steps": 13643, "loss": 0.4416, "lr": 3.3963369963369964e-05, "epoch": 0.5953297408262767, "percentage": 8.5, "elapsed_time": "1:27:49", "remaining_time": "15:45:07"}
+{"current_steps": 1165, "total_steps": 13643, "loss": 0.3978, "lr": 3.4109890109890114e-05, "epoch": 0.5978958172953553, "percentage": 8.54, "elapsed_time": "1:28:16", "remaining_time": "15:45:26"}
+{"current_steps": 1170, "total_steps": 13643, "loss": 0.456, "lr": 3.4256410256410256e-05, "epoch": 0.6004618937644342, "percentage": 8.58, "elapsed_time": "1:28:32", "remaining_time": "15:43:55"}
+{"current_steps": 1175, "total_steps": 13643, "loss": 0.4092, "lr": 3.4402930402930406e-05, "epoch": 0.603027970233513, "percentage": 8.61, "elapsed_time": "1:28:52", "remaining_time": "15:43:03"}
+{"current_steps": 1180, "total_steps": 13643, "loss": 0.4039, "lr": 3.4549450549450556e-05, "epoch": 0.6055940467025918, "percentage": 8.65, "elapsed_time": "1:29:12", "remaining_time": "15:42:07"}
+{"current_steps": 1185, "total_steps": 13643, "loss": 0.4119, "lr": 3.46959706959707e-05, "epoch": 0.6081601231716706, "percentage": 8.69, "elapsed_time": "1:29:33", "remaining_time": "15:41:35"}
+{"current_steps": 1190, "total_steps": 13643, "loss": 0.4062, "lr": 3.484249084249085e-05, "epoch": 0.6107261996407493, "percentage": 8.72, "elapsed_time": "1:29:54", "remaining_time": "15:40:56"}
+{"current_steps": 1195, "total_steps": 13643, "loss": 0.4143, "lr": 3.498901098901099e-05, "epoch": 0.6132922761098281, "percentage": 8.76, "elapsed_time": "1:30:16", "remaining_time": "15:40:23"}
+{"current_steps": 1200, "total_steps": 13643, "loss": 0.4021, "lr": 3.513553113553114e-05, "epoch": 0.6158583525789069, "percentage": 8.8, "elapsed_time": "1:30:37", "remaining_time": "15:39:46"}
+{"current_steps": 1205, "total_steps": 13643, "loss": 0.433, "lr": 3.5282051282051283e-05, "epoch": 0.6184244290479857, "percentage": 8.83, "elapsed_time": "1:30:53", "remaining_time": "15:38:15"}
+{"current_steps": 1210, "total_steps": 13643, "loss": 0.4058, "lr": 3.542857142857143e-05, "epoch": 0.6209905055170644, "percentage": 8.87, "elapsed_time": "1:31:15", "remaining_time": "15:37:40"}
+{"current_steps": 1215, "total_steps": 13643, "loss": 0.4217, "lr": 3.5575091575091576e-05, "epoch": 0.6235565819861432, "percentage": 8.91, "elapsed_time": "1:31:37", "remaining_time": "15:37:07"}
+{"current_steps": 1220, "total_steps": 13643, "loss": 0.4148, "lr": 3.5721611721611725e-05, "epoch": 0.626122658455222, "percentage": 8.94, "elapsed_time": "1:31:58", "remaining_time": "15:36:38"}
+{"current_steps": 1225, "total_steps": 13643, "loss": 0.3989, "lr": 3.5868131868131875e-05, "epoch": 0.6286887349243008, "percentage": 8.98, "elapsed_time": "1:32:25", "remaining_time": "15:36:54"}
+{"current_steps": 1230, "total_steps": 13643, "loss": 0.4316, "lr": 3.601465201465202e-05, "epoch": 0.6312548113933796, "percentage": 9.02, "elapsed_time": "1:32:52", "remaining_time": "15:37:14"}
+{"current_steps": 1235, "total_steps": 13643, "loss": 0.4447, "lr": 3.616117216117217e-05, "epoch": 0.6338208878624583, "percentage": 9.05, "elapsed_time": "1:33:14", "remaining_time": "15:36:43"}
+{"current_steps": 1240, "total_steps": 13643, "loss": 0.4448, "lr": 3.630769230769231e-05, "epoch": 0.6363869643315371, "percentage": 9.09, "elapsed_time": "1:33:39", "remaining_time": "15:36:48"}
+{"current_steps": 1245, "total_steps": 13643, "loss": 0.4145, "lr": 3.645421245421245e-05, "epoch": 0.6389530408006159, "percentage": 9.13, "elapsed_time": "1:34:02", "remaining_time": "15:36:28"}
+{"current_steps": 1250, "total_steps": 13643, "loss": 0.4016, "lr": 3.66007326007326e-05, "epoch": 0.6415191172696947, "percentage": 9.16, "elapsed_time": "1:34:21", "remaining_time": "15:35:26"}
+{"current_steps": 1255, "total_steps": 13643, "loss": 0.4377, "lr": 3.6747252747252746e-05, "epoch": 0.6440851937387734, "percentage": 9.2, "elapsed_time": "1:34:40", "remaining_time": "15:34:31"}
+{"current_steps": 1260, "total_steps": 13643, "loss": 0.4036, "lr": 3.68937728937729e-05, "epoch": 0.6466512702078522, "percentage": 9.24, "elapsed_time": "1:35:01", "remaining_time": "15:33:50"}
+{"current_steps": 1265, "total_steps": 13643, "loss": 0.4037, "lr": 3.7040293040293045e-05, "epoch": 0.649217346676931, "percentage": 9.27, "elapsed_time": "1:35:19", "remaining_time": "15:32:49"}
+{"current_steps": 1270, "total_steps": 13643, "loss": 0.3997, "lr": 3.718681318681319e-05, "epoch": 0.6517834231460098, "percentage": 9.31, "elapsed_time": "1:35:45", "remaining_time": "15:32:53"}
+{"current_steps": 1275, "total_steps": 13643, "loss": 0.4277, "lr": 3.733333333333334e-05, "epoch": 0.6543494996150885, "percentage": 9.35, "elapsed_time": "1:36:07", "remaining_time": "15:32:25"}
+{"current_steps": 1280, "total_steps": 13643, "loss": 0.4235, "lr": 3.747985347985348e-05, "epoch": 0.6569155760841673, "percentage": 9.38, "elapsed_time": "1:36:26", "remaining_time": "15:31:25"}
+{"current_steps": 1285, "total_steps": 13643, "loss": 0.3878, "lr": 3.762637362637363e-05, "epoch": 0.6594816525532461, "percentage": 9.42, "elapsed_time": "1:36:50", "remaining_time": "15:31:17"}
+{"current_steps": 1290, "total_steps": 13643, "loss": 0.4392, "lr": 3.777289377289377e-05, "epoch": 0.6620477290223249, "percentage": 9.46, "elapsed_time": "1:37:20", "remaining_time": "15:32:08"}
+{"current_steps": 1295, "total_steps": 13643, "loss": 0.4169, "lr": 3.791941391941392e-05, "epoch": 0.6646138054914037, "percentage": 9.49, "elapsed_time": "1:37:42", "remaining_time": "15:31:38"}
+{"current_steps": 1300, "total_steps": 13643, "loss": 0.4122, "lr": 3.8065934065934065e-05, "epoch": 0.6671798819604824, "percentage": 9.53, "elapsed_time": "1:38:01", "remaining_time": "15:30:46"}
+{"current_steps": 1305, "total_steps": 13643, "loss": 0.4174, "lr": 3.8212454212454215e-05, "epoch": 0.6697459584295612, "percentage": 9.57, "elapsed_time": "1:38:19", "remaining_time": "15:29:37"}
+{"current_steps": 1310, "total_steps": 13643, "loss": 0.4247, "lr": 3.8358974358974364e-05, "epoch": 0.67231203489864, "percentage": 9.6, "elapsed_time": "1:38:41", "remaining_time": "15:29:04"}
+{"current_steps": 1315, "total_steps": 13643, "loss": 0.4244, "lr": 3.850549450549451e-05, "epoch": 0.6748781113677188, "percentage": 9.64, "elapsed_time": "1:39:07", "remaining_time": "15:29:16"}
+{"current_steps": 1320, "total_steps": 13643, "loss": 0.4386, "lr": 3.865201465201466e-05, "epoch": 0.6774441878367975, "percentage": 9.68, "elapsed_time": "1:39:24", "remaining_time": "15:28:04"}
+{"current_steps": 1325, "total_steps": 13643, "loss": 0.431, "lr": 3.87985347985348e-05, "epoch": 0.6800102643058763, "percentage": 9.71, "elapsed_time": "1:39:48", "remaining_time": "15:27:53"}
+{"current_steps": 1330, "total_steps": 13643, "loss": 0.3949, "lr": 3.894505494505495e-05, "epoch": 0.6825763407749551, "percentage": 9.75, "elapsed_time": "1:40:19", "remaining_time": "15:28:45"}
+{"current_steps": 1335, "total_steps": 13643, "loss": 0.4486, "lr": 3.909157509157509e-05, "epoch": 0.6851424172440339, "percentage": 9.79, "elapsed_time": "1:40:38", "remaining_time": "15:27:51"}
+{"current_steps": 1340, "total_steps": 13643, "loss": 0.4258, "lr": 3.923809523809524e-05, "epoch": 0.6877084937131126, "percentage": 9.82, "elapsed_time": "1:40:59", "remaining_time": "15:27:10"}
+{"current_steps": 1345, "total_steps": 13643, "loss": 0.4051, "lr": 3.938461538461539e-05, "epoch": 0.6902745701821914, "percentage": 9.86, "elapsed_time": "1:41:17", "remaining_time": "15:26:13"}
+{"current_steps": 1350, "total_steps": 13643, "loss": 0.4275, "lr": 3.9531135531135534e-05, "epoch": 0.6928406466512702, "percentage": 9.9, "elapsed_time": "1:41:41", "remaining_time": "15:26:04"}
+{"current_steps": 1355, "total_steps": 13643, "loss": 0.436, "lr": 3.9677655677655684e-05, "epoch": 0.695406723120349, "percentage": 9.93, "elapsed_time": "1:42:03", "remaining_time": "15:25:30"}
+{"current_steps": 1360, "total_steps": 13643, "loss": 0.4051, "lr": 3.9824175824175826e-05, "epoch": 0.6979727995894278, "percentage": 9.97, "elapsed_time": "1:42:23", "remaining_time": "15:24:48"}
+{"current_steps": 1365, "total_steps": 13643, "loss": 0.4407, "lr": 3.9970695970695976e-05, "epoch": 0.7005388760585065, "percentage": 10.01, "elapsed_time": "1:42:39", "remaining_time": "15:23:22"}
+{"current_steps": 1370, "total_steps": 13643, "loss": 0.411, "lr": 3.999998952474915e-05, "epoch": 0.7031049525275853, "percentage": 10.04, "elapsed_time": "1:43:01", "remaining_time": "15:22:58"}
+{"current_steps": 1375, "total_steps": 13643, "loss": 0.4148, "lr": 3.999994696906135e-05, "epoch": 0.7056710289966641, "percentage": 10.08, "elapsed_time": "1:43:22", "remaining_time": "15:22:18"}
+{"current_steps": 1380, "total_steps": 13643, "loss": 0.4056, "lr": 3.9999871678303026e-05, "epoch": 0.7082371054657429, "percentage": 10.12, "elapsed_time": "1:43:46", "remaining_time": "15:22:07"}
+{"current_steps": 1385, "total_steps": 13643, "loss": 0.4178, "lr": 3.9999763652597424e-05, "epoch": 0.7108031819348216, "percentage": 10.15, "elapsed_time": "1:44:09", "remaining_time": "15:21:48"}
+{"current_steps": 1390, "total_steps": 13643, "loss": 0.4111, "lr": 3.999962289212135e-05, "epoch": 0.7133692584039004, "percentage": 10.19, "elapsed_time": "1:44:28", "remaining_time": "15:20:58"}
+{"current_steps": 1395, "total_steps": 13643, "loss": 0.4169, "lr": 3.9999449397105176e-05, "epoch": 0.7159353348729792, "percentage": 10.23, "elapsed_time": "1:44:50", "remaining_time": "15:20:30"}
+{"current_steps": 1400, "total_steps": 13643, "loss": 0.4065, "lr": 3.9999243167832896e-05, "epoch": 0.718501411342058, "percentage": 10.26, "elapsed_time": "1:45:17", "remaining_time": "15:20:43"}
+{"current_steps": 1405, "total_steps": 13643, "loss": 0.4072, "lr": 3.9999004204642054e-05, "epoch": 0.7210674878111367, "percentage": 10.3, "elapsed_time": "1:45:34", "remaining_time": "15:19:39"}
+{"current_steps": 1410, "total_steps": 13643, "loss": 0.4008, "lr": 3.9998732507923755e-05, "epoch": 0.7236335642802155, "percentage": 10.33, "elapsed_time": "1:45:54", "remaining_time": "15:18:50"}
+{"current_steps": 1415, "total_steps": 13643, "loss": 0.423, "lr": 3.9998428078122726e-05, "epoch": 0.7261996407492943, "percentage": 10.37, "elapsed_time": "1:46:13", "remaining_time": "15:17:55"}
+{"current_steps": 1420, "total_steps": 13643, "loss": 0.4142, "lr": 3.999809091573723e-05, "epoch": 0.7287657172183731, "percentage": 10.41, "elapsed_time": "1:46:40", "remaining_time": "15:18:09"}
+{"current_steps": 1425, "total_steps": 13643, "loss": 0.413, "lr": 3.9997721021319124e-05, "epoch": 0.7313317936874519, "percentage": 10.44, "elapsed_time": "1:47:01", "remaining_time": "15:17:38"}
+{"current_steps": 1430, "total_steps": 13643, "loss": 0.4018, "lr": 3.9997318395473835e-05, "epoch": 0.7338978701565306, "percentage": 10.48, "elapsed_time": "1:47:20", "remaining_time": "15:16:49"}
+{"current_steps": 1435, "total_steps": 13643, "loss": 0.4197, "lr": 3.9996883038860364e-05, "epoch": 0.7364639466256094, "percentage": 10.52, "elapsed_time": "1:47:39", "remaining_time": "15:15:51"}
+{"current_steps": 1440, "total_steps": 13643, "loss": 0.3742, "lr": 3.999641495219129e-05, "epoch": 0.7390300230946882, "percentage": 10.55, "elapsed_time": "1:47:58", "remaining_time": "15:15:04"}
+{"current_steps": 1445, "total_steps": 13643, "loss": 0.3965, "lr": 3.999591413623274e-05, "epoch": 0.741596099563767, "percentage": 10.59, "elapsed_time": "1:48:20", "remaining_time": "15:14:35"}
+{"current_steps": 1450, "total_steps": 13643, "loss": 0.4177, "lr": 3.999538059180445e-05, "epoch": 0.7441621760328457, "percentage": 10.63, "elapsed_time": "1:48:44", "remaining_time": "15:14:25"}
+{"current_steps": 1455, "total_steps": 13643, "loss": 0.4246, "lr": 3.999481431977969e-05, "epoch": 0.7467282525019245, "percentage": 10.66, "elapsed_time": "1:49:07", "remaining_time": "15:14:07"}
+{"current_steps": 1460, "total_steps": 13643, "loss": 0.4398, "lr": 3.999421532108532e-05, "epoch": 0.7492943289710033, "percentage": 10.7, "elapsed_time": "1:49:33", "remaining_time": "15:14:09"}
+{"current_steps": 1465, "total_steps": 13643, "loss": 0.4339, "lr": 3.999358359670174e-05, "epoch": 0.7518604054400821, "percentage": 10.74, "elapsed_time": "1:49:47", "remaining_time": "15:12:36"}
+{"current_steps": 1470, "total_steps": 13643, "loss": 0.4264, "lr": 3.999291914766295e-05, "epoch": 0.7544264819091608, "percentage": 10.77, "elapsed_time": "1:50:15", "remaining_time": "15:13:04"}
+{"current_steps": 1475, "total_steps": 13643, "loss": 0.3956, "lr": 3.999222197505647e-05, "epoch": 0.7569925583782396, "percentage": 10.81, "elapsed_time": "1:50:39", "remaining_time": "15:12:53"}
+{"current_steps": 1480, "total_steps": 13643, "loss": 0.3959, "lr": 3.999149208002343e-05, "epoch": 0.7595586348473184, "percentage": 10.85, "elapsed_time": "1:51:04", "remaining_time": "15:12:52"}
+{"current_steps": 1485, "total_steps": 13643, "loss": 0.3849, "lr": 3.999072946375846e-05, "epoch": 0.7621247113163973, "percentage": 10.88, "elapsed_time": "1:51:23", "remaining_time": "15:12:01"}
+{"current_steps": 1490, "total_steps": 13643, "loss": 0.4213, "lr": 3.998993412750981e-05, "epoch": 0.7646907877854761, "percentage": 10.92, "elapsed_time": "1:51:46", "remaining_time": "15:11:42"}
+{"current_steps": 1495, "total_steps": 13643, "loss": 0.4042, "lr": 3.998910607257922e-05, "epoch": 0.7672568642545547, "percentage": 10.96, "elapsed_time": "1:52:08", "remaining_time": "15:11:17"}
+{"current_steps": 1500, "total_steps": 13643, "loss": 0.408, "lr": 3.9988245300322044e-05, "epoch": 0.7698229407236336, "percentage": 10.99, "elapsed_time": "1:52:35", "remaining_time": "15:11:31"}
+{"current_steps": 1505, "total_steps": 13643, "loss": 0.4098, "lr": 3.9987351812147145e-05, "epoch": 0.7723890171927124, "percentage": 11.03, "elapsed_time": "1:53:41", "remaining_time": "15:16:59"}
+{"current_steps": 1510, "total_steps": 13643, "loss": 0.4119, "lr": 3.998642560951694e-05, "epoch": 0.7749550936617912, "percentage": 11.07, "elapsed_time": "1:54:08", "remaining_time": "15:17:06"}
+{"current_steps": 1515, "total_steps": 13643, "loss": 0.4304, "lr": 3.998546669394742e-05, "epoch": 0.7775211701308699, "percentage": 11.1, "elapsed_time": "1:54:25", "remaining_time": "15:15:59"}
+{"current_steps": 1520, "total_steps": 13643, "loss": 0.4165, "lr": 3.998447506700807e-05, "epoch": 0.7800872465999487, "percentage": 11.14, "elapsed_time": "1:54:55", "remaining_time": "15:16:34"}
+{"current_steps": 1525, "total_steps": 13643, "loss": 0.4226, "lr": 3.998345073032197e-05, "epoch": 0.7826533230690275, "percentage": 11.18, "elapsed_time": "1:55:14", "remaining_time": "15:15:42"}
+{"current_steps": 1530, "total_steps": 13643, "loss": 0.4281, "lr": 3.998239368556569e-05, "epoch": 0.7852193995381063, "percentage": 11.21, "elapsed_time": "1:55:36", "remaining_time": "15:15:15"}
+{"current_steps": 1535, "total_steps": 13643, "loss": 0.4167, "lr": 3.998130393446937e-05, "epoch": 0.787785476007185, "percentage": 11.25, "elapsed_time": "1:55:57", "remaining_time": "15:14:38"}
+{"current_steps": 1540, "total_steps": 13643, "loss": 0.404, "lr": 3.998018147881666e-05, "epoch": 0.7903515524762638, "percentage": 11.29, "elapsed_time": "1:56:23", "remaining_time": "15:14:46"}
+{"current_steps": 1545, "total_steps": 13643, "loss": 0.4096, "lr": 3.997902632044476e-05, "epoch": 0.7929176289453426, "percentage": 11.32, "elapsed_time": "1:56:41", "remaining_time": "15:13:42"}
+{"current_steps": 1550, "total_steps": 13643, "loss": 0.4094, "lr": 3.9977838461244364e-05, "epoch": 0.7954837054144214, "percentage": 11.36, "elapsed_time": "1:57:03", "remaining_time": "15:13:20"}
+{"current_steps": 1555, "total_steps": 13643, "loss": 0.4124, "lr": 3.997661790315972e-05, "epoch": 0.7980497818835002, "percentage": 11.4, "elapsed_time": "1:57:23", "remaining_time": "15:12:34"}
+{"current_steps": 1560, "total_steps": 13643, "loss": 0.4032, "lr": 3.99753646481886e-05, "epoch": 0.8006158583525789, "percentage": 11.43, "elapsed_time": "1:57:44", "remaining_time": "15:11:57"}
+{"current_steps": 1565, "total_steps": 13643, "loss": 0.4186, "lr": 3.997407869838226e-05, "epoch": 0.8031819348216577, "percentage": 11.47, "elapsed_time": "1:58:01", "remaining_time": "15:10:50"}
+{"current_steps": 1570, "total_steps": 13643, "loss": 0.4165, "lr": 3.9972760055845494e-05, "epoch": 0.8057480112907365, "percentage": 11.51, "elapsed_time": "1:58:21", "remaining_time": "15:10:06"}
+{"current_steps": 1575, "total_steps": 13643, "loss": 0.3989, "lr": 3.9971408722736605e-05, "epoch": 0.8083140877598153, "percentage": 11.54, "elapsed_time": "1:58:47", "remaining_time": "15:10:08"}
+{"current_steps": 1580, "total_steps": 13643, "loss": 0.3961, "lr": 3.99700247012674e-05, "epoch": 0.810880164228894, "percentage": 11.58, "elapsed_time": "1:59:07", "remaining_time": "15:09:27"}
+{"current_steps": 1585, "total_steps": 13643, "loss": 0.3913, "lr": 3.9968607993703175e-05, "epoch": 0.8134462406979728, "percentage": 11.62, "elapsed_time": "1:59:26", "remaining_time": "15:08:36"}
+{"current_steps": 1590, "total_steps": 13643, "loss": 0.411, "lr": 3.996715860236275e-05, "epoch": 0.8160123171670516, "percentage": 11.65, "elapsed_time": "1:59:47", "remaining_time": "15:08:04"}
+{"current_steps": 1595, "total_steps": 13643, "loss": 0.3881, "lr": 3.996567652961841e-05, "epoch": 0.8185783936361304, "percentage": 11.69, "elapsed_time": "2:00:07", "remaining_time": "15:07:24"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43a2c48cd12018bf8ac2ce7f9c67f4be1c2c3238a0f02ba41a50c53870224b3a
+size 8657