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 sha256:30b2ef3fa496f9f3f91c3954685b8c48ca513e09228f32f66bb9f72cd7ac3fc5
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:27f6546131d8baa9f1c56b4bc7ca1946a71ca551f476199c7d3affa6dc6d166c
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:33ff30311130eb35f5e10bb2990e5d67f0e94dce791c942254f5988461a1067d
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa6177e2d8f6512e862a827447decf2cab104a21defe423221e555d6f34a4b08
+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": "60d83f48605156a6b9182f9b54c6da2d4dffc061_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--penfever--glm-4.6-r2egym-32ep-32k/snapshots/1b98f51e65d71b6dc9702529884355b93b8b8685_thinking_preprocessed,/data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-nl2bash-verified-32eps-32k/snapshots/61e17458d760f1419c4447abbab4fc93118563dd_thinking_preprocessed,/data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-stackexchange-overflow-sandboxes-32eps-65k/snapshots/1c13e68d92fc88775a6a593c5ca93a4a4bae0a38_thinking_preprocessed,/data/cat/ws/befe330h-befe330h-otagent/huggingface/hub/datasets--penfever--GLM-4.6-inferredbugs-32eps-65k/snapshots/60d83f48605156a6b9182f9b54c6da2d4dffc061_thinking_preprocessed",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/r2egym-nl2bash-stack-bugsseq-fixthink/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_r2egym-nl2bash-stack-bugsseq-fixthink_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": 12698, "loss": 0.5457, "lr": 1.2598425196850394e-07, "epoch": 0.0027563395810363835, "percentage": 0.04, "elapsed_time": "0:01:30", "remaining_time": "2 days, 15:51:00"}
+{"current_steps": 10, "total_steps": 12698, "loss": 0.5804, "lr": 2.8346456692913386e-07, "epoch": 0.005512679162072767, "percentage": 0.08, "elapsed_time": "0:02:42", "remaining_time": "2 days, 9:25:29"}
+{"current_steps": 15, "total_steps": 12698, "loss": 0.5587, "lr": 4.409448818897638e-07, "epoch": 0.008269018743109152, "percentage": 0.12, "elapsed_time": "0:04:01", "remaining_time": "2 days, 8:45:54"}
+{"current_steps": 20, "total_steps": 12698, "loss": 0.5105, "lr": 5.984251968503937e-07, "epoch": 0.011025358324145534, "percentage": 0.16, "elapsed_time": "0:05:23", "remaining_time": "2 days, 8:57:37"}
+{"current_steps": 25, "total_steps": 12698, "loss": 0.5233, "lr": 7.559055118110237e-07, "epoch": 0.013781697905181918, "percentage": 0.2, "elapsed_time": "0:06:45", "remaining_time": "2 days, 9:03:16"}
+{"current_steps": 30, "total_steps": 12698, "loss": 0.5295, "lr": 9.133858267716536e-07, "epoch": 0.016538037486218304, "percentage": 0.24, "elapsed_time": "0:08:07", "remaining_time": "2 days, 9:09:32"}
+{"current_steps": 35, "total_steps": 12698, "loss": 0.5218, "lr": 1.0708661417322836e-06, "epoch": 0.019294377067254686, "percentage": 0.28, "elapsed_time": "0:09:23", "remaining_time": "2 days, 8:37:53"}
+{"current_steps": 40, "total_steps": 12698, "loss": 0.4927, "lr": 1.2283464566929135e-06, "epoch": 0.022050716648291068, "percentage": 0.32, "elapsed_time": "0:10:40", "remaining_time": "2 days, 8:20:28"}
+{"current_steps": 45, "total_steps": 12698, "loss": 0.5003, "lr": 1.3858267716535435e-06, "epoch": 0.024807056229327454, "percentage": 0.35, "elapsed_time": "0:11:42", "remaining_time": "2 days, 6:51:37"}
+{"current_steps": 50, "total_steps": 12698, "loss": 0.4538, "lr": 1.5433070866141734e-06, "epoch": 0.027563395810363836, "percentage": 0.39, "elapsed_time": "0:12:57", "remaining_time": "2 days, 6:36:46"}
+{"current_steps": 55, "total_steps": 12698, "loss": 0.4519, "lr": 1.7007874015748034e-06, "epoch": 0.03031973539140022, "percentage": 0.43, "elapsed_time": "0:14:10", "remaining_time": "2 days, 6:19:19"}
+{"current_steps": 60, "total_steps": 12698, "loss": 0.4359, "lr": 1.8582677165354333e-06, "epoch": 0.03307607497243661, "percentage": 0.47, "elapsed_time": "0:15:22", "remaining_time": "2 days, 5:59:05"}
+{"current_steps": 65, "total_steps": 12698, "loss": 0.4134, "lr": 2.015748031496063e-06, "epoch": 0.03583241455347299, "percentage": 0.51, "elapsed_time": "0:16:35", "remaining_time": "2 days, 5:44:29"}
+{"current_steps": 70, "total_steps": 12698, "loss": 0.4015, "lr": 2.173228346456693e-06, "epoch": 0.03858875413450937, "percentage": 0.55, "elapsed_time": "0:17:50", "remaining_time": "2 days, 5:37:21"}
+{"current_steps": 75, "total_steps": 12698, "loss": 0.4051, "lr": 2.330708661417323e-06, "epoch": 0.041345093715545754, "percentage": 0.59, "elapsed_time": "0:18:58", "remaining_time": "2 days, 5:14:32"}
+{"current_steps": 80, "total_steps": 12698, "loss": 0.4007, "lr": 2.488188976377953e-06, "epoch": 0.044101433296582136, "percentage": 0.63, "elapsed_time": "0:20:07", "remaining_time": "2 days, 4:54:42"}
+{"current_steps": 85, "total_steps": 12698, "loss": 0.387, "lr": 2.645669291338583e-06, "epoch": 0.046857772877618525, "percentage": 0.67, "elapsed_time": "0:21:22", "remaining_time": "2 days, 4:51:10"}
+{"current_steps": 90, "total_steps": 12698, "loss": 0.3853, "lr": 2.803149606299213e-06, "epoch": 0.04961411245865491, "percentage": 0.71, "elapsed_time": "0:22:36", "remaining_time": "2 days, 4:46:18"}
+{"current_steps": 95, "total_steps": 12698, "loss": 0.3967, "lr": 2.9606299212598427e-06, "epoch": 0.05237045203969129, "percentage": 0.75, "elapsed_time": "0:23:50", "remaining_time": "2 days, 4:42:53"}
+{"current_steps": 100, "total_steps": 12698, "loss": 0.3832, "lr": 3.118110236220473e-06, "epoch": 0.05512679162072767, "percentage": 0.79, "elapsed_time": "0:24:53", "remaining_time": "2 days, 4:16:12"}
+{"current_steps": 105, "total_steps": 12698, "loss": 0.3462, "lr": 3.2755905511811026e-06, "epoch": 0.057883131201764054, "percentage": 0.83, "elapsed_time": "0:26:06", "remaining_time": "2 days, 4:12:13"}
+{"current_steps": 110, "total_steps": 12698, "loss": 0.3479, "lr": 3.433070866141733e-06, "epoch": 0.06063947078280044, "percentage": 0.87, "elapsed_time": "0:27:23", "remaining_time": "2 days, 4:15:00"}
+{"current_steps": 115, "total_steps": 12698, "loss": 0.3629, "lr": 3.5905511811023625e-06, "epoch": 0.06339581036383682, "percentage": 0.91, "elapsed_time": "0:28:33", "remaining_time": "2 days, 4:04:31"}
+{"current_steps": 120, "total_steps": 12698, "loss": 0.3495, "lr": 3.748031496062993e-06, "epoch": 0.06615214994487321, "percentage": 0.95, "elapsed_time": "0:29:49", "remaining_time": "2 days, 4:06:58"}
+{"current_steps": 125, "total_steps": 12698, "loss": 0.3432, "lr": 3.905511811023622e-06, "epoch": 0.0689084895259096, "percentage": 0.98, "elapsed_time": "0:31:09", "remaining_time": "2 days, 4:13:45"}
+{"current_steps": 130, "total_steps": 12698, "loss": 0.3031, "lr": 4.062992125984252e-06, "epoch": 0.07166482910694598, "percentage": 1.02, "elapsed_time": "0:32:27", "remaining_time": "2 days, 4:17:40"}
+{"current_steps": 135, "total_steps": 12698, "loss": 0.3019, "lr": 4.220472440944882e-06, "epoch": 0.07442116868798236, "percentage": 1.06, "elapsed_time": "0:33:44", "remaining_time": "2 days, 4:19:38"}
+{"current_steps": 140, "total_steps": 12698, "loss": 0.2898, "lr": 4.377952755905512e-06, "epoch": 0.07717750826901874, "percentage": 1.1, "elapsed_time": "0:35:01", "remaining_time": "2 days, 4:21:49"}
+{"current_steps": 145, "total_steps": 12698, "loss": 0.3532, "lr": 4.535433070866142e-06, "epoch": 0.07993384785005513, "percentage": 1.14, "elapsed_time": "0:36:06", "remaining_time": "2 days, 4:06:30"}
+{"current_steps": 150, "total_steps": 12698, "loss": 0.3398, "lr": 4.692913385826772e-06, "epoch": 0.08269018743109151, "percentage": 1.18, "elapsed_time": "0:37:05", "remaining_time": "2 days, 3:42:45"}
+{"current_steps": 155, "total_steps": 12698, "loss": 0.3342, "lr": 4.850393700787402e-06, "epoch": 0.08544652701212789, "percentage": 1.22, "elapsed_time": "0:38:15", "remaining_time": "2 days, 3:36:28"}
+{"current_steps": 160, "total_steps": 12698, "loss": 0.3406, "lr": 5.007874015748032e-06, "epoch": 0.08820286659316427, "percentage": 1.26, "elapsed_time": "0:39:29", "remaining_time": "2 days, 3:34:35"}
+{"current_steps": 165, "total_steps": 12698, "loss": 0.3324, "lr": 5.1653543307086615e-06, "epoch": 0.09095920617420065, "percentage": 1.3, "elapsed_time": "0:40:41", "remaining_time": "2 days, 3:31:23"}
+{"current_steps": 170, "total_steps": 12698, "loss": 0.3156, "lr": 5.322834645669291e-06, "epoch": 0.09371554575523705, "percentage": 1.34, "elapsed_time": "0:42:00", "remaining_time": "2 days, 3:36:09"}
+{"current_steps": 175, "total_steps": 12698, "loss": 0.3196, "lr": 5.480314960629922e-06, "epoch": 0.09647188533627343, "percentage": 1.38, "elapsed_time": "0:43:17", "remaining_time": "2 days, 3:38:27"}
+{"current_steps": 180, "total_steps": 12698, "loss": 0.3109, "lr": 5.637795275590552e-06, "epoch": 0.09922822491730982, "percentage": 1.42, "elapsed_time": "0:44:34", "remaining_time": "2 days, 3:40:27"}
+{"current_steps": 185, "total_steps": 12698, "loss": 0.3155, "lr": 5.795275590551181e-06, "epoch": 0.1019845644983462, "percentage": 1.46, "elapsed_time": "0:45:53", "remaining_time": "2 days, 3:43:50"}
+{"current_steps": 190, "total_steps": 12698, "loss": 0.3082, "lr": 5.952755905511811e-06, "epoch": 0.10474090407938258, "percentage": 1.5, "elapsed_time": "0:47:13", "remaining_time": "2 days, 3:49:09"}
+{"current_steps": 195, "total_steps": 12698, "loss": 0.312, "lr": 6.110236220472442e-06, "epoch": 0.10749724366041896, "percentage": 1.54, "elapsed_time": "0:48:28", "remaining_time": "2 days, 3:48:09"}
+{"current_steps": 200, "total_steps": 12698, "loss": 0.3119, "lr": 6.2677165354330715e-06, "epoch": 0.11025358324145534, "percentage": 1.58, "elapsed_time": "0:49:37", "remaining_time": "2 days, 3:40:51"}
+{"current_steps": 205, "total_steps": 12698, "loss": 0.3081, "lr": 6.425196850393701e-06, "epoch": 0.11300992282249173, "percentage": 1.61, "elapsed_time": "0:50:49", "remaining_time": "2 days, 3:37:15"}
+{"current_steps": 210, "total_steps": 12698, "loss": 0.3075, "lr": 6.5826771653543306e-06, "epoch": 0.11576626240352811, "percentage": 1.65, "elapsed_time": "0:51:31", "remaining_time": "2 days, 3:04:20"}
+{"current_steps": 215, "total_steps": 12698, "loss": 0.3002, "lr": 6.740157480314962e-06, "epoch": 0.1185226019845645, "percentage": 1.69, "elapsed_time": "0:52:48", "remaining_time": "2 days, 3:06:16"}
+{"current_steps": 220, "total_steps": 12698, "loss": 0.2971, "lr": 6.897637795275591e-06, "epoch": 0.12127894156560089, "percentage": 1.73, "elapsed_time": "0:53:54", "remaining_time": "2 days, 2:57:54"}
+{"current_steps": 225, "total_steps": 12698, "loss": 0.2997, "lr": 7.055118110236221e-06, "epoch": 0.12403528114663727, "percentage": 1.77, "elapsed_time": "0:55:12", "remaining_time": "2 days, 3:00:15"}
+{"current_steps": 230, "total_steps": 12698, "loss": 0.2895, "lr": 7.21259842519685e-06, "epoch": 0.12679162072767364, "percentage": 1.81, "elapsed_time": "0:56:29", "remaining_time": "2 days, 3:02:09"}
+{"current_steps": 235, "total_steps": 12698, "loss": 0.2965, "lr": 7.3700787401574816e-06, "epoch": 0.12954796030871002, "percentage": 1.85, "elapsed_time": "0:57:46", "remaining_time": "2 days, 3:03:58"}
+{"current_steps": 240, "total_steps": 12698, "loss": 0.2966, "lr": 7.527559055118111e-06, "epoch": 0.13230429988974643, "percentage": 1.89, "elapsed_time": "0:59:00", "remaining_time": "2 days, 3:02:53"}
+{"current_steps": 245, "total_steps": 12698, "loss": 0.2748, "lr": 7.68503937007874e-06, "epoch": 0.1350606394707828, "percentage": 1.93, "elapsed_time": "0:59:57", "remaining_time": "2 days, 2:47:36"}
+{"current_steps": 250, "total_steps": 12698, "loss": 0.286, "lr": 7.84251968503937e-06, "epoch": 0.1378169790518192, "percentage": 1.97, "elapsed_time": "1:00:52", "remaining_time": "2 days, 2:31:16"}
+{"current_steps": 255, "total_steps": 12698, "loss": 0.2859, "lr": 8.000000000000001e-06, "epoch": 0.14057331863285558, "percentage": 2.01, "elapsed_time": "1:02:03", "remaining_time": "2 days, 2:27:59"}
+{"current_steps": 260, "total_steps": 12698, "loss": 0.2912, "lr": 8.157480314960631e-06, "epoch": 0.14332965821389196, "percentage": 2.05, "elapsed_time": "1:03:15", "remaining_time": "2 days, 2:26:03"}
+{"current_steps": 265, "total_steps": 12698, "loss": 0.2851, "lr": 8.31496062992126e-06, "epoch": 0.14608599779492834, "percentage": 2.09, "elapsed_time": "1:04:21", "remaining_time": "2 days, 2:19:29"}
+{"current_steps": 270, "total_steps": 12698, "loss": 0.2702, "lr": 8.47244094488189e-06, "epoch": 0.14884233737596472, "percentage": 2.13, "elapsed_time": "1:05:34", "remaining_time": "2 days, 2:18:07"}
+{"current_steps": 275, "total_steps": 12698, "loss": 0.2857, "lr": 8.629921259842521e-06, "epoch": 0.1515986769570011, "percentage": 2.17, "elapsed_time": "1:06:49", "remaining_time": "2 days, 2:18:49"}
+{"current_steps": 280, "total_steps": 12698, "loss": 0.3304, "lr": 8.78740157480315e-06, "epoch": 0.1543550165380375, "percentage": 2.21, "elapsed_time": "1:07:39", "remaining_time": "2 days, 2:00:50"}
+{"current_steps": 285, "total_steps": 12698, "loss": 0.3819, "lr": 8.94488188976378e-06, "epoch": 0.15711135611907387, "percentage": 2.24, "elapsed_time": "1:07:54", "remaining_time": "2 days, 1:17:45"}
+{"current_steps": 290, "total_steps": 12698, "loss": 0.3535, "lr": 9.10236220472441e-06, "epoch": 0.15986769570011025, "percentage": 2.28, "elapsed_time": "1:08:09", "remaining_time": "2 days, 0:36:34"}
+{"current_steps": 295, "total_steps": 12698, "loss": 0.3333, "lr": 9.259842519685041e-06, "epoch": 0.16262403528114663, "percentage": 2.32, "elapsed_time": "1:08:23", "remaining_time": "1 day, 23:55:33"}
+{"current_steps": 300, "total_steps": 12698, "loss": 0.3258, "lr": 9.41732283464567e-06, "epoch": 0.16538037486218302, "percentage": 2.36, "elapsed_time": "1:08:39", "remaining_time": "1 day, 23:17:25"}
+{"current_steps": 305, "total_steps": 12698, "loss": 0.3114, "lr": 9.5748031496063e-06, "epoch": 0.1681367144432194, "percentage": 2.4, "elapsed_time": "1:08:53", "remaining_time": "1 day, 22:39:13"}
+{"current_steps": 310, "total_steps": 12698, "loss": 0.3202, "lr": 9.73228346456693e-06, "epoch": 0.17089305402425578, "percentage": 2.44, "elapsed_time": "1:09:07", "remaining_time": "1 day, 22:02:12"}
+{"current_steps": 315, "total_steps": 12698, "loss": 0.292, "lr": 9.88976377952756e-06, "epoch": 0.17364939360529216, "percentage": 2.48, "elapsed_time": "1:09:20", "remaining_time": "1 day, 21:25:57"}
+{"current_steps": 320, "total_steps": 12698, "loss": 0.3184, "lr": 1.0047244094488188e-05, "epoch": 0.17640573318632854, "percentage": 2.52, "elapsed_time": "1:09:32", "remaining_time": "1 day, 20:50:08"}
+{"current_steps": 325, "total_steps": 12698, "loss": 0.294, "lr": 1.0204724409448821e-05, "epoch": 0.17916207276736493, "percentage": 2.56, "elapsed_time": "1:09:45", "remaining_time": "1 day, 20:15:38"}
+{"current_steps": 330, "total_steps": 12698, "loss": 0.2925, "lr": 1.0362204724409451e-05, "epoch": 0.1819184123484013, "percentage": 2.6, "elapsed_time": "1:10:00", "remaining_time": "1 day, 19:43:57"}
+{"current_steps": 335, "total_steps": 12698, "loss": 0.2934, "lr": 1.051968503937008e-05, "epoch": 0.18467475192943772, "percentage": 2.64, "elapsed_time": "1:10:15", "remaining_time": "1 day, 19:12:43"}
+{"current_steps": 340, "total_steps": 12698, "loss": 0.2882, "lr": 1.067716535433071e-05, "epoch": 0.1874310915104741, "percentage": 2.68, "elapsed_time": "1:10:29", "remaining_time": "1 day, 18:42:19"}
+{"current_steps": 345, "total_steps": 12698, "loss": 0.2659, "lr": 1.083464566929134e-05, "epoch": 0.19018743109151048, "percentage": 2.72, "elapsed_time": "1:10:41", "remaining_time": "1 day, 18:11:13"}
+{"current_steps": 350, "total_steps": 12698, "loss": 0.2666, "lr": 1.0992125984251969e-05, "epoch": 0.19294377067254687, "percentage": 2.76, "elapsed_time": "1:10:53", "remaining_time": "1 day, 17:41:07"}
+{"current_steps": 355, "total_steps": 12698, "loss": 0.2751, "lr": 1.1149606299212599e-05, "epoch": 0.19570011025358325, "percentage": 2.8, "elapsed_time": "1:11:08", "remaining_time": "1 day, 17:13:25"}
+{"current_steps": 360, "total_steps": 12698, "loss": 0.2744, "lr": 1.1307086614173228e-05, "epoch": 0.19845644983461963, "percentage": 2.84, "elapsed_time": "1:11:21", "remaining_time": "1 day, 16:45:24"}
+{"current_steps": 365, "total_steps": 12698, "loss": 0.2838, "lr": 1.1464566929133861e-05, "epoch": 0.201212789415656, "percentage": 2.87, "elapsed_time": "1:11:37", "remaining_time": "1 day, 16:20:15"}
+{"current_steps": 370, "total_steps": 12698, "loss": 0.2708, "lr": 1.162204724409449e-05, "epoch": 0.2039691289966924, "percentage": 2.91, "elapsed_time": "1:11:49", "remaining_time": "1 day, 15:53:19"}
+{"current_steps": 375, "total_steps": 12698, "loss": 0.2778, "lr": 1.177952755905512e-05, "epoch": 0.20672546857772878, "percentage": 2.95, "elapsed_time": "1:12:04", "remaining_time": "1 day, 15:28:27"}
+{"current_steps": 380, "total_steps": 12698, "loss": 0.274, "lr": 1.193700787401575e-05, "epoch": 0.20948180815876516, "percentage": 2.99, "elapsed_time": "1:12:18", "remaining_time": "1 day, 15:04:01"}
+{"current_steps": 385, "total_steps": 12698, "loss": 0.2821, "lr": 1.2094488188976379e-05, "epoch": 0.21223814773980154, "percentage": 3.03, "elapsed_time": "1:12:35", "remaining_time": "1 day, 14:41:41"}
+{"current_steps": 390, "total_steps": 12698, "loss": 0.2797, "lr": 1.2251968503937009e-05, "epoch": 0.21499448732083792, "percentage": 3.07, "elapsed_time": "1:12:48", "remaining_time": "1 day, 14:17:56"}
+{"current_steps": 395, "total_steps": 12698, "loss": 0.2533, "lr": 1.2409448818897638e-05, "epoch": 0.2177508269018743, "percentage": 3.11, "elapsed_time": "1:13:00", "remaining_time": "1 day, 13:54:10"}
+{"current_steps": 400, "total_steps": 12698, "loss": 0.2713, "lr": 1.2566929133858268e-05, "epoch": 0.2205071664829107, "percentage": 3.15, "elapsed_time": "1:13:13", "remaining_time": "1 day, 13:31:28"}
+{"current_steps": 405, "total_steps": 12698, "loss": 0.2678, "lr": 1.2724409448818899e-05, "epoch": 0.22326350606394707, "percentage": 3.19, "elapsed_time": "1:13:26", "remaining_time": "1 day, 13:09:15"}
+{"current_steps": 410, "total_steps": 12698, "loss": 0.2668, "lr": 1.288188976377953e-05, "epoch": 0.22601984564498345, "percentage": 3.23, "elapsed_time": "1:13:39", "remaining_time": "1 day, 12:47:41"}
+{"current_steps": 415, "total_steps": 12698, "loss": 0.2672, "lr": 1.303937007874016e-05, "epoch": 0.22877618522601983, "percentage": 3.27, "elapsed_time": "1:13:55", "remaining_time": "1 day, 12:28:12"}
+{"current_steps": 420, "total_steps": 12698, "loss": 0.2481, "lr": 1.3196850393700789e-05, "epoch": 0.23153252480705622, "percentage": 3.31, "elapsed_time": "1:14:08", "remaining_time": "1 day, 12:07:34"}
+{"current_steps": 425, "total_steps": 12698, "loss": 0.2591, "lr": 1.3354330708661419e-05, "epoch": 0.2342888643880926, "percentage": 3.35, "elapsed_time": "1:14:21", "remaining_time": "1 day, 11:47:18"}
+{"current_steps": 430, "total_steps": 12698, "loss": 0.2624, "lr": 1.3511811023622048e-05, "epoch": 0.237045203969129, "percentage": 3.39, "elapsed_time": "1:14:33", "remaining_time": "1 day, 11:27:05"}
+{"current_steps": 435, "total_steps": 12698, "loss": 0.2628, "lr": 1.3669291338582678e-05, "epoch": 0.2398015435501654, "percentage": 3.43, "elapsed_time": "1:14:46", "remaining_time": "1 day, 11:07:51"}
+{"current_steps": 440, "total_steps": 12698, "loss": 0.2643, "lr": 1.3826771653543307e-05, "epoch": 0.24255788313120177, "percentage": 3.47, "elapsed_time": "1:14:59", "remaining_time": "1 day, 10:49:07"}
+{"current_steps": 445, "total_steps": 12698, "loss": 0.2505, "lr": 1.3984251968503938e-05, "epoch": 0.24531422271223816, "percentage": 3.5, "elapsed_time": "1:15:11", "remaining_time": "1 day, 10:30:12"}
+{"current_steps": 450, "total_steps": 12698, "loss": 0.2351, "lr": 1.4141732283464568e-05, "epoch": 0.24807056229327454, "percentage": 3.54, "elapsed_time": "1:15:23", "remaining_time": "1 day, 10:11:53"}
+{"current_steps": 455, "total_steps": 12698, "loss": 0.2613, "lr": 1.4299212598425199e-05, "epoch": 0.2508269018743109, "percentage": 3.58, "elapsed_time": "1:15:36", "remaining_time": "1 day, 9:54:27"}
+{"current_steps": 460, "total_steps": 12698, "loss": 0.2585, "lr": 1.4456692913385829e-05, "epoch": 0.2535832414553473, "percentage": 3.62, "elapsed_time": "1:15:48", "remaining_time": "1 day, 9:36:46"}
+{"current_steps": 465, "total_steps": 12698, "loss": 0.2439, "lr": 1.4614173228346458e-05, "epoch": 0.25633958103638366, "percentage": 3.66, "elapsed_time": "1:16:01", "remaining_time": "1 day, 9:19:55"}
+{"current_steps": 470, "total_steps": 12698, "loss": 0.2458, "lr": 1.4771653543307088e-05, "epoch": 0.25909592061742004, "percentage": 3.7, "elapsed_time": "1:16:13", "remaining_time": "1 day, 9:03:06"}
+{"current_steps": 475, "total_steps": 12698, "loss": 0.2589, "lr": 1.4929133858267717e-05, "epoch": 0.2618522601984565, "percentage": 3.74, "elapsed_time": "1:16:25", "remaining_time": "1 day, 8:46:43"}
+{"current_steps": 480, "total_steps": 12698, "loss": 0.2433, "lr": 1.5086614173228347e-05, "epoch": 0.26460859977949286, "percentage": 3.78, "elapsed_time": "1:16:38", "remaining_time": "1 day, 8:30:52"}
+{"current_steps": 485, "total_steps": 12698, "loss": 0.2592, "lr": 1.5244094488188978e-05, "epoch": 0.26736493936052924, "percentage": 3.82, "elapsed_time": "1:16:53", "remaining_time": "1 day, 8:16:05"}
+{"current_steps": 490, "total_steps": 12698, "loss": 0.2649, "lr": 1.5401574803149607e-05, "epoch": 0.2701212789415656, "percentage": 3.86, "elapsed_time": "1:17:08", "remaining_time": "1 day, 8:01:49"}
+{"current_steps": 495, "total_steps": 12698, "loss": 0.2642, "lr": 1.555905511811024e-05, "epoch": 0.272877618522602, "percentage": 3.9, "elapsed_time": "1:17:21", "remaining_time": "1 day, 7:47:16"}
+{"current_steps": 500, "total_steps": 12698, "loss": 0.2457, "lr": 1.5716535433070866e-05, "epoch": 0.2756339581036384, "percentage": 3.94, "elapsed_time": "1:17:34", "remaining_time": "1 day, 7:32:36"}
+{"current_steps": 505, "total_steps": 12698, "loss": 0.2483, "lr": 1.5874015748031498e-05, "epoch": 0.27839029768467477, "percentage": 3.98, "elapsed_time": "1:17:48", "remaining_time": "1 day, 7:18:36"}
+{"current_steps": 510, "total_steps": 12698, "loss": 0.2559, "lr": 1.6031496062992126e-05, "epoch": 0.28114663726571115, "percentage": 4.02, "elapsed_time": "1:18:00", "remaining_time": "1 day, 7:04:23"}
+{"current_steps": 515, "total_steps": 12698, "loss": 0.2413, "lr": 1.6188976377952757e-05, "epoch": 0.28390297684674753, "percentage": 4.06, "elapsed_time": "1:18:12", "remaining_time": "1 day, 6:50:18"}
+{"current_steps": 520, "total_steps": 12698, "loss": 0.2391, "lr": 1.6346456692913385e-05, "epoch": 0.2866593164277839, "percentage": 4.1, "elapsed_time": "1:18:24", "remaining_time": "1 day, 6:36:21"}
+{"current_steps": 525, "total_steps": 12698, "loss": 0.2446, "lr": 1.650393700787402e-05, "epoch": 0.2894156560088203, "percentage": 4.13, "elapsed_time": "1:18:39", "remaining_time": "1 day, 6:23:47"}
+{"current_steps": 530, "total_steps": 12698, "loss": 0.2451, "lr": 1.6661417322834647e-05, "epoch": 0.2921719955898567, "percentage": 4.17, "elapsed_time": "1:18:51", "remaining_time": "1 day, 6:10:24"}
+{"current_steps": 535, "total_steps": 12698, "loss": 0.2468, "lr": 1.6818897637795278e-05, "epoch": 0.29492833517089306, "percentage": 4.21, "elapsed_time": "1:19:03", "remaining_time": "1 day, 5:57:27"}
+{"current_steps": 540, "total_steps": 12698, "loss": 0.2406, "lr": 1.6976377952755906e-05, "epoch": 0.29768467475192945, "percentage": 4.25, "elapsed_time": "1:19:16", "remaining_time": "1 day, 5:44:55"}
+{"current_steps": 545, "total_steps": 12698, "loss": 0.2374, "lr": 1.7133858267716537e-05, "epoch": 0.30044101433296583, "percentage": 4.29, "elapsed_time": "1:19:30", "remaining_time": "1 day, 5:33:01"}
+{"current_steps": 550, "total_steps": 12698, "loss": 0.2453, "lr": 1.7291338582677165e-05, "epoch": 0.3031973539140022, "percentage": 4.33, "elapsed_time": "1:19:44", "remaining_time": "1 day, 5:21:13"}
+{"current_steps": 555, "total_steps": 12698, "loss": 0.2426, "lr": 1.7448818897637796e-05, "epoch": 0.3059536934950386, "percentage": 4.37, "elapsed_time": "1:19:56", "remaining_time": "1 day, 5:09:01"}
+{"current_steps": 560, "total_steps": 12698, "loss": 0.2409, "lr": 1.7606299212598424e-05, "epoch": 0.308710033076075, "percentage": 4.41, "elapsed_time": "1:20:09", "remaining_time": "1 day, 4:57:23"}
+{"current_steps": 565, "total_steps": 12698, "loss": 0.2281, "lr": 1.776377952755906e-05, "epoch": 0.31146637265711136, "percentage": 4.45, "elapsed_time": "1:20:21", "remaining_time": "1 day, 4:45:48"}
+{"current_steps": 570, "total_steps": 12698, "loss": 0.2369, "lr": 1.7921259842519687e-05, "epoch": 0.31422271223814774, "percentage": 4.49, "elapsed_time": "1:20:35", "remaining_time": "1 day, 4:34:55"}
+{"current_steps": 575, "total_steps": 12698, "loss": 0.2445, "lr": 1.8078740157480318e-05, "epoch": 0.3169790518191841, "percentage": 4.53, "elapsed_time": "1:20:48", "remaining_time": "1 day, 4:23:49"}
+{"current_steps": 580, "total_steps": 12698, "loss": 0.2336, "lr": 1.8236220472440946e-05, "epoch": 0.3197353914002205, "percentage": 4.57, "elapsed_time": "1:21:02", "remaining_time": "1 day, 4:13:10"}
+{"current_steps": 585, "total_steps": 12698, "loss": 0.2396, "lr": 1.8393700787401577e-05, "epoch": 0.3224917309812569, "percentage": 4.61, "elapsed_time": "1:21:13", "remaining_time": "1 day, 4:01:59"}
+{"current_steps": 590, "total_steps": 12698, "loss": 0.2384, "lr": 1.8551181102362205e-05, "epoch": 0.32524807056229327, "percentage": 4.65, "elapsed_time": "1:21:25", "remaining_time": "1 day, 3:51:07"}
+{"current_steps": 595, "total_steps": 12698, "loss": 0.2411, "lr": 1.8708661417322836e-05, "epoch": 0.32800441014332965, "percentage": 4.69, "elapsed_time": "1:21:38", "remaining_time": "1 day, 3:40:41"}
+{"current_steps": 600, "total_steps": 12698, "loss": 0.2397, "lr": 1.8866141732283464e-05, "epoch": 0.33076074972436603, "percentage": 4.73, "elapsed_time": "1:21:51", "remaining_time": "1 day, 3:30:37"}
+{"current_steps": 605, "total_steps": 12698, "loss": 0.2387, "lr": 1.9023622047244098e-05, "epoch": 0.3335170893054024, "percentage": 4.76, "elapsed_time": "1:22:03", "remaining_time": "1 day, 3:20:12"}
+{"current_steps": 610, "total_steps": 12698, "loss": 0.2442, "lr": 1.9181102362204726e-05, "epoch": 0.3362734288864388, "percentage": 4.8, "elapsed_time": "1:22:16", "remaining_time": "1 day, 3:10:13"}
+{"current_steps": 615, "total_steps": 12698, "loss": 0.2417, "lr": 1.9338582677165357e-05, "epoch": 0.3390297684674752, "percentage": 4.84, "elapsed_time": "1:22:27", "remaining_time": "1 day, 3:00:04"}
+{"current_steps": 620, "total_steps": 12698, "loss": 0.2506, "lr": 1.9496062992125985e-05, "epoch": 0.34178610804851156, "percentage": 4.88, "elapsed_time": "1:22:40", "remaining_time": "1 day, 2:50:33"}
+{"current_steps": 625, "total_steps": 12698, "loss": 0.2511, "lr": 1.9653543307086616e-05, "epoch": 0.34454244762954794, "percentage": 4.92, "elapsed_time": "1:22:56", "remaining_time": "1 day, 2:42:09"}
+{"current_steps": 630, "total_steps": 12698, "loss": 0.2479, "lr": 1.9811023622047244e-05, "epoch": 0.3472987872105843, "percentage": 4.96, "elapsed_time": "1:23:09", "remaining_time": "1 day, 2:32:47"}
+{"current_steps": 635, "total_steps": 12698, "loss": 0.2396, "lr": 1.9968503937007875e-05, "epoch": 0.3500551267916207, "percentage": 5.0, "elapsed_time": "1:23:20", "remaining_time": "1 day, 2:23:19"}
+{"current_steps": 640, "total_steps": 12698, "loss": 0.2354, "lr": 2.0125984251968503e-05, "epoch": 0.3528114663726571, "percentage": 5.04, "elapsed_time": "1:23:33", "remaining_time": "1 day, 2:14:13"}
+{"current_steps": 645, "total_steps": 12698, "loss": 0.235, "lr": 2.0283464566929134e-05, "epoch": 0.35556780595369347, "percentage": 5.08, "elapsed_time": "1:23:45", "remaining_time": "1 day, 2:05:13"}
+{"current_steps": 650, "total_steps": 12698, "loss": 0.2393, "lr": 2.0440944881889762e-05, "epoch": 0.35832414553472985, "percentage": 5.12, "elapsed_time": "1:23:57", "remaining_time": "1 day, 1:56:16"}
+{"current_steps": 655, "total_steps": 12698, "loss": 0.229, "lr": 2.0598425196850393e-05, "epoch": 0.36108048511576624, "percentage": 5.16, "elapsed_time": "1:24:10", "remaining_time": "1 day, 1:47:40"}
+{"current_steps": 660, "total_steps": 12698, "loss": 0.2236, "lr": 2.0755905511811028e-05, "epoch": 0.3638368246968026, "percentage": 5.2, "elapsed_time": "1:24:23", "remaining_time": "1 day, 1:39:07"}
+{"current_steps": 665, "total_steps": 12698, "loss": 0.2425, "lr": 2.0913385826771656e-05, "epoch": 0.36659316427783906, "percentage": 5.24, "elapsed_time": "1:24:35", "remaining_time": "1 day, 1:30:47"}
+{"current_steps": 670, "total_steps": 12698, "loss": 0.2332, "lr": 2.1070866141732287e-05, "epoch": 0.36934950385887544, "percentage": 5.28, "elapsed_time": "1:24:48", "remaining_time": "1 day, 1:22:22"}
+{"current_steps": 675, "total_steps": 12698, "loss": 0.229, "lr": 2.1228346456692915e-05, "epoch": 0.3721058434399118, "percentage": 5.32, "elapsed_time": "1:25:01", "remaining_time": "1 day, 1:14:26"}
+{"current_steps": 680, "total_steps": 12698, "loss": 0.2226, "lr": 2.1385826771653546e-05, "epoch": 0.3748621830209482, "percentage": 5.36, "elapsed_time": "1:25:20", "remaining_time": "1 day, 1:08:09"}
+{"current_steps": 685, "total_steps": 12698, "loss": 0.2157, "lr": 2.1543307086614177e-05, "epoch": 0.3776185226019846, "percentage": 5.39, "elapsed_time": "1:25:32", "remaining_time": "1 day, 1:00:02"}
+{"current_steps": 690, "total_steps": 12698, "loss": 0.2323, "lr": 2.1700787401574805e-05, "epoch": 0.38037486218302097, "percentage": 5.43, "elapsed_time": "1:25:43", "remaining_time": "1 day, 0:51:56"}
+{"current_steps": 695, "total_steps": 12698, "loss": 0.2339, "lr": 2.1858267716535436e-05, "epoch": 0.38313120176405735, "percentage": 5.47, "elapsed_time": "1:25:56", "remaining_time": "1 day, 0:44:08"}
+{"current_steps": 700, "total_steps": 12698, "loss": 0.2351, "lr": 2.2015748031496064e-05, "epoch": 0.38588754134509373, "percentage": 5.51, "elapsed_time": "1:26:11", "remaining_time": "1 day, 0:37:20"}
+{"current_steps": 705, "total_steps": 12698, "loss": 0.2383, "lr": 2.2173228346456695e-05, "epoch": 0.3886438809261301, "percentage": 5.55, "elapsed_time": "1:26:23", "remaining_time": "1 day, 0:29:46"}
+{"current_steps": 710, "total_steps": 12698, "loss": 0.2276, "lr": 2.2330708661417323e-05, "epoch": 0.3914002205071665, "percentage": 5.59, "elapsed_time": "1:26:36", "remaining_time": "1 day, 0:22:19"}
+{"current_steps": 715, "total_steps": 12698, "loss": 0.2391, "lr": 2.2488188976377954e-05, "epoch": 0.3941565600882029, "percentage": 5.63, "elapsed_time": "1:26:48", "remaining_time": "1 day, 0:14:50"}
+{"current_steps": 720, "total_steps": 12698, "loss": 0.3339, "lr": 2.2645669291338582e-05, "epoch": 0.39691289966923926, "percentage": 5.67, "elapsed_time": "1:27:19", "remaining_time": "1 day, 0:12:48"}
+{"current_steps": 725, "total_steps": 12698, "loss": 0.4033, "lr": 2.2803149606299214e-05, "epoch": 0.39966923925027564, "percentage": 5.71, "elapsed_time": "1:28:07", "remaining_time": "1 day, 0:15:22"}
+{"current_steps": 730, "total_steps": 12698, "loss": 0.3959, "lr": 2.296062992125984e-05, "epoch": 0.402425578831312, "percentage": 5.75, "elapsed_time": "1:29:04", "remaining_time": "1 day, 0:20:28"}
+{"current_steps": 735, "total_steps": 12698, "loss": 0.3776, "lr": 2.3118110236220473e-05, "epoch": 0.4051819184123484, "percentage": 5.79, "elapsed_time": "1:29:58", "remaining_time": "1 day, 0:24:21"}
+{"current_steps": 740, "total_steps": 12698, "loss": 0.3748, "lr": 2.3275590551181107e-05, "epoch": 0.4079382579933848, "percentage": 5.83, "elapsed_time": "1:30:52", "remaining_time": "1 day, 0:28:30"}
+{"current_steps": 745, "total_steps": 12698, "loss": 0.3911, "lr": 2.3433070866141735e-05, "epoch": 0.41069459757442117, "percentage": 5.87, "elapsed_time": "1:31:46", "remaining_time": "1 day, 0:32:32"}
+{"current_steps": 750, "total_steps": 12698, "loss": 0.3574, "lr": 2.3590551181102366e-05, "epoch": 0.41345093715545755, "percentage": 5.91, "elapsed_time": "1:32:37", "remaining_time": "1 day, 0:35:35"}
+{"current_steps": 755, "total_steps": 12698, "loss": 0.3705, "lr": 2.3748031496062994e-05, "epoch": 0.41620727673649394, "percentage": 5.95, "elapsed_time": "1:33:32", "remaining_time": "1 day, 0:39:36"}
+{"current_steps": 760, "total_steps": 12698, "loss": 0.3639, "lr": 2.3905511811023625e-05, "epoch": 0.4189636163175303, "percentage": 5.99, "elapsed_time": "1:34:25", "remaining_time": "1 day, 0:43:10"}
+{"current_steps": 765, "total_steps": 12698, "loss": 0.3847, "lr": 2.4062992125984253e-05, "epoch": 0.4217199558985667, "percentage": 6.02, "elapsed_time": "1:35:20", "remaining_time": "1 day, 0:47:06"}
+{"current_steps": 770, "total_steps": 12698, "loss": 0.3646, "lr": 2.4220472440944884e-05, "epoch": 0.4244762954796031, "percentage": 6.06, "elapsed_time": "1:36:09", "remaining_time": "1 day, 0:49:36"}
+{"current_steps": 775, "total_steps": 12698, "loss": 0.3649, "lr": 2.4377952755905516e-05, "epoch": 0.42723263506063947, "percentage": 6.1, "elapsed_time": "1:37:10", "remaining_time": "1 day, 0:55:00"}
+{"current_steps": 780, "total_steps": 12698, "loss": 0.3615, "lr": 2.4535433070866143e-05, "epoch": 0.42998897464167585, "percentage": 6.14, "elapsed_time": "1:38:00", "remaining_time": "1 day, 0:57:25"}
+{"current_steps": 785, "total_steps": 12698, "loss": 0.365, "lr": 2.4692913385826775e-05, "epoch": 0.43274531422271223, "percentage": 6.18, "elapsed_time": "1:38:45", "remaining_time": "1 day, 0:58:39"}
+{"current_steps": 790, "total_steps": 12698, "loss": 0.3753, "lr": 2.4850393700787402e-05, "epoch": 0.4355016538037486, "percentage": 6.22, "elapsed_time": "1:39:14", "remaining_time": "1 day, 0:55:57"}
+{"current_steps": 795, "total_steps": 12698, "loss": 0.3713, "lr": 2.5007874015748034e-05, "epoch": 0.438257993384785, "percentage": 6.26, "elapsed_time": "1:39:42", "remaining_time": "1 day, 0:52:48"}
+{"current_steps": 800, "total_steps": 12698, "loss": 0.3659, "lr": 2.516535433070866e-05, "epoch": 0.4410143329658214, "percentage": 6.3, "elapsed_time": "1:40:11", "remaining_time": "1 day, 0:50:09"}
+{"current_steps": 805, "total_steps": 12698, "loss": 0.3784, "lr": 2.5322834645669293e-05, "epoch": 0.44377067254685776, "percentage": 6.34, "elapsed_time": "1:40:37", "remaining_time": "1 day, 0:46:36"}
+{"current_steps": 810, "total_steps": 12698, "loss": 0.3808, "lr": 2.548031496062992e-05, "epoch": 0.44652701212789414, "percentage": 6.38, "elapsed_time": "1:41:02", "remaining_time": "1 day, 0:42:52"}
+{"current_steps": 815, "total_steps": 12698, "loss": 0.3678, "lr": 2.563779527559055e-05, "epoch": 0.4492833517089305, "percentage": 6.42, "elapsed_time": "1:41:31", "remaining_time": "1 day, 0:40:18"}
+{"current_steps": 820, "total_steps": 12698, "loss": 0.3749, "lr": 2.5795275590551186e-05, "epoch": 0.4520396912899669, "percentage": 6.46, "elapsed_time": "1:42:00", "remaining_time": "1 day, 0:37:40"}
+{"current_steps": 825, "total_steps": 12698, "loss": 0.3521, "lr": 2.5952755905511814e-05, "epoch": 0.4547960308710033, "percentage": 6.5, "elapsed_time": "1:42:29", "remaining_time": "1 day, 0:35:06"}
+{"current_steps": 830, "total_steps": 12698, "loss": 0.3494, "lr": 2.6110236220472445e-05, "epoch": 0.45755237045203967, "percentage": 6.54, "elapsed_time": "1:42:59", "remaining_time": "1 day, 0:32:43"}
+{"current_steps": 835, "total_steps": 12698, "loss": 0.3512, "lr": 2.6267716535433073e-05, "epoch": 0.46030871003307605, "percentage": 6.58, "elapsed_time": "1:43:24", "remaining_time": "1 day, 0:29:12"}
+{"current_steps": 840, "total_steps": 12698, "loss": 0.3652, "lr": 2.6425196850393704e-05, "epoch": 0.46306504961411243, "percentage": 6.62, "elapsed_time": "1:43:51", "remaining_time": "1 day, 0:26:01"}
+{"current_steps": 845, "total_steps": 12698, "loss": 0.3658, "lr": 2.6582677165354332e-05, "epoch": 0.4658213891951488, "percentage": 6.65, "elapsed_time": "1:44:16", "remaining_time": "1 day, 0:22:36"}
+{"current_steps": 850, "total_steps": 12698, "loss": 0.3456, "lr": 2.6740157480314963e-05, "epoch": 0.4685777287761852, "percentage": 6.69, "elapsed_time": "1:44:46", "remaining_time": "1 day, 0:20:25"}
+{"current_steps": 855, "total_steps": 12698, "loss": 0.348, "lr": 2.689763779527559e-05, "epoch": 0.47133406835722164, "percentage": 6.73, "elapsed_time": "1:45:11", "remaining_time": "1 day, 0:17:02"}
+{"current_steps": 860, "total_steps": 12698, "loss": 0.359, "lr": 2.7055118110236222e-05, "epoch": 0.474090407938258, "percentage": 6.77, "elapsed_time": "1:45:38", "remaining_time": "1 day, 0:14:06"}
+{"current_steps": 865, "total_steps": 12698, "loss": 0.3569, "lr": 2.7212598425196854e-05, "epoch": 0.4768467475192944, "percentage": 6.81, "elapsed_time": "1:46:06", "remaining_time": "1 day, 0:11:30"}
+{"current_steps": 870, "total_steps": 12698, "loss": 0.3445, "lr": 2.737007874015748e-05, "epoch": 0.4796030871003308, "percentage": 6.85, "elapsed_time": "1:46:32", "remaining_time": "1 day, 0:08:27"}
+{"current_steps": 875, "total_steps": 12698, "loss": 0.3472, "lr": 2.7527559055118113e-05, "epoch": 0.48235942668136716, "percentage": 6.89, "elapsed_time": "1:46:59", "remaining_time": "1 day, 0:05:40"}
+{"current_steps": 880, "total_steps": 12698, "loss": 0.359, "lr": 2.768503937007874e-05, "epoch": 0.48511576626240355, "percentage": 6.93, "elapsed_time": "1:47:25", "remaining_time": "1 day, 0:02:34"}
+{"current_steps": 885, "total_steps": 12698, "loss": 0.337, "lr": 2.7842519685039372e-05, "epoch": 0.48787210584343993, "percentage": 6.97, "elapsed_time": "1:47:55", "remaining_time": "1 day, 0:00:29"}
+{"current_steps": 890, "total_steps": 12698, "loss": 0.3648, "lr": 2.8e-05, "epoch": 0.4906284454244763, "percentage": 7.01, "elapsed_time": "1:48:18", "remaining_time": "23:56:54"}
+{"current_steps": 895, "total_steps": 12698, "loss": 0.3568, "lr": 2.815748031496063e-05, "epoch": 0.4933847850055127, "percentage": 7.05, "elapsed_time": "1:48:44", "remaining_time": "23:54:00"}
+{"current_steps": 900, "total_steps": 12698, "loss": 0.3506, "lr": 2.8314960629921265e-05, "epoch": 0.4961411245865491, "percentage": 7.09, "elapsed_time": "1:49:10", "remaining_time": "23:51:13"}
+{"current_steps": 905, "total_steps": 12698, "loss": 0.3427, "lr": 2.8472440944881893e-05, "epoch": 0.49889746416758546, "percentage": 7.13, "elapsed_time": "1:49:40", "remaining_time": "23:49:10"}
+{"current_steps": 910, "total_steps": 12698, "loss": 0.3448, "lr": 2.8629921259842524e-05, "epoch": 0.5016538037486218, "percentage": 7.17, "elapsed_time": "1:50:08", "remaining_time": "23:46:45"}
+{"current_steps": 915, "total_steps": 12698, "loss": 0.3404, "lr": 2.8787401574803152e-05, "epoch": 0.5044101433296582, "percentage": 7.21, "elapsed_time": "1:50:38", "remaining_time": "23:44:48"}
+{"current_steps": 920, "total_steps": 12698, "loss": 0.351, "lr": 2.8944881889763783e-05, "epoch": 0.5071664829106945, "percentage": 7.25, "elapsed_time": "1:51:04", "remaining_time": "23:42:05"}
+{"current_steps": 925, "total_steps": 12698, "loss": 0.3504, "lr": 2.910236220472441e-05, "epoch": 0.5099228224917309, "percentage": 7.28, "elapsed_time": "1:51:29", "remaining_time": "23:39:04"}
+{"current_steps": 930, "total_steps": 12698, "loss": 0.3477, "lr": 2.9259842519685043e-05, "epoch": 0.5126791620727673, "percentage": 7.32, "elapsed_time": "1:51:58", "remaining_time": "23:36:52"}
+{"current_steps": 935, "total_steps": 12698, "loss": 0.344, "lr": 2.941732283464567e-05, "epoch": 0.5154355016538037, "percentage": 7.36, "elapsed_time": "1:52:28", "remaining_time": "23:34:58"}
+{"current_steps": 940, "total_steps": 12698, "loss": 0.3371, "lr": 2.95748031496063e-05, "epoch": 0.5181918412348401, "percentage": 7.4, "elapsed_time": "1:52:54", "remaining_time": "23:32:13"}
+{"current_steps": 945, "total_steps": 12698, "loss": 0.3466, "lr": 2.9732283464566933e-05, "epoch": 0.5209481808158766, "percentage": 7.44, "elapsed_time": "1:53:19", "remaining_time": "23:29:23"}
+{"current_steps": 950, "total_steps": 12698, "loss": 0.3388, "lr": 2.988976377952756e-05, "epoch": 0.523704520396913, "percentage": 7.48, "elapsed_time": "1:53:48", "remaining_time": "23:27:23"}
+{"current_steps": 955, "total_steps": 12698, "loss": 0.3554, "lr": 3.0047244094488192e-05, "epoch": 0.5264608599779493, "percentage": 7.52, "elapsed_time": "1:54:14", "remaining_time": "23:24:42"}
+{"current_steps": 960, "total_steps": 12698, "loss": 0.3562, "lr": 3.020472440944882e-05, "epoch": 0.5292171995589857, "percentage": 7.56, "elapsed_time": "1:54:40", "remaining_time": "23:22:11"}
+{"current_steps": 965, "total_steps": 12698, "loss": 0.338, "lr": 3.036220472440945e-05, "epoch": 0.5319735391400221, "percentage": 7.6, "elapsed_time": "1:55:08", "remaining_time": "23:19:52"}
+{"current_steps": 970, "total_steps": 12698, "loss": 0.3415, "lr": 3.051968503937008e-05, "epoch": 0.5347298787210585, "percentage": 7.64, "elapsed_time": "1:55:38", "remaining_time": "23:18:14"}
+{"current_steps": 975, "total_steps": 12698, "loss": 0.3464, "lr": 3.067716535433071e-05, "epoch": 0.5374862183020949, "percentage": 7.68, "elapsed_time": "1:56:02", "remaining_time": "23:15:08"}
+{"current_steps": 980, "total_steps": 12698, "loss": 0.343, "lr": 3.0834645669291345e-05, "epoch": 0.5402425578831312, "percentage": 7.72, "elapsed_time": "1:56:31", "remaining_time": "23:13:17"}
+{"current_steps": 985, "total_steps": 12698, "loss": 0.3218, "lr": 3.099212598425197e-05, "epoch": 0.5429988974641676, "percentage": 7.76, "elapsed_time": "1:57:00", "remaining_time": "23:11:18"}
+{"current_steps": 990, "total_steps": 12698, "loss": 0.3356, "lr": 3.11496062992126e-05, "epoch": 0.545755237045204, "percentage": 7.8, "elapsed_time": "1:57:24", "remaining_time": "23:08:25"}
+{"current_steps": 995, "total_steps": 12698, "loss": 0.3156, "lr": 3.1307086614173235e-05, "epoch": 0.5485115766262404, "percentage": 7.84, "elapsed_time": "1:57:52", "remaining_time": "23:06:24"}
+{"current_steps": 1000, "total_steps": 12698, "loss": 0.3608, "lr": 3.146456692913386e-05, "epoch": 0.5512679162072768, "percentage": 7.88, "elapsed_time": "1:58:20", "remaining_time": "23:04:18"}
+{"current_steps": 1005, "total_steps": 12698, "loss": 0.332, "lr": 3.162204724409449e-05, "epoch": 0.5540242557883132, "percentage": 7.91, "elapsed_time": "1:58:53", "remaining_time": "23:03:18"}
+{"current_steps": 1010, "total_steps": 12698, "loss": 0.3434, "lr": 3.177952755905512e-05, "epoch": 0.5567805953693495, "percentage": 7.95, "elapsed_time": "1:59:23", "remaining_time": "23:01:35"}
+{"current_steps": 1015, "total_steps": 12698, "loss": 0.3432, "lr": 3.193700787401575e-05, "epoch": 0.5595369349503859, "percentage": 7.99, "elapsed_time": "1:59:52", "remaining_time": "22:59:48"}
+{"current_steps": 1020, "total_steps": 12698, "loss": 0.3497, "lr": 3.209448818897638e-05, "epoch": 0.5622932745314223, "percentage": 8.03, "elapsed_time": "2:00:20", "remaining_time": "22:57:49"}
+{"current_steps": 1025, "total_steps": 12698, "loss": 0.3421, "lr": 3.225196850393701e-05, "epoch": 0.5650496141124587, "percentage": 8.07, "elapsed_time": "2:00:48", "remaining_time": "22:55:47"}
+{"current_steps": 1030, "total_steps": 12698, "loss": 0.3221, "lr": 3.240944881889764e-05, "epoch": 0.5678059536934951, "percentage": 8.11, "elapsed_time": "2:01:16", "remaining_time": "22:53:45"}
+{"current_steps": 1035, "total_steps": 12698, "loss": 0.3317, "lr": 3.256692913385827e-05, "epoch": 0.5705622932745315, "percentage": 8.15, "elapsed_time": "2:01:40", "remaining_time": "22:51:02"}
+{"current_steps": 1040, "total_steps": 12698, "loss": 0.3334, "lr": 3.27244094488189e-05, "epoch": 0.5733186328555678, "percentage": 8.19, "elapsed_time": "2:02:05", "remaining_time": "22:48:39"}
+{"current_steps": 1045, "total_steps": 12698, "loss": 0.3258, "lr": 3.2881889763779527e-05, "epoch": 0.5760749724366042, "percentage": 8.23, "elapsed_time": "2:02:34", "remaining_time": "22:46:49"}
+{"current_steps": 1050, "total_steps": 12698, "loss": 0.3111, "lr": 3.303937007874016e-05, "epoch": 0.5788313120176406, "percentage": 8.27, "elapsed_time": "2:03:01", "remaining_time": "22:44:39"}
+{"current_steps": 1055, "total_steps": 12698, "loss": 0.3233, "lr": 3.319685039370079e-05, "epoch": 0.581587651598677, "percentage": 8.31, "elapsed_time": "2:03:26", "remaining_time": "22:42:20"}
+{"current_steps": 1060, "total_steps": 12698, "loss": 0.3352, "lr": 3.3354330708661424e-05, "epoch": 0.5843439911797134, "percentage": 8.35, "elapsed_time": "2:03:52", "remaining_time": "22:40:04"}
+{"current_steps": 1065, "total_steps": 12698, "loss": 0.3592, "lr": 3.351181102362205e-05, "epoch": 0.5871003307607497, "percentage": 8.39, "elapsed_time": "2:04:17", "remaining_time": "22:37:43"}
+{"current_steps": 1070, "total_steps": 12698, "loss": 0.3285, "lr": 3.366929133858268e-05, "epoch": 0.5898566703417861, "percentage": 8.43, "elapsed_time": "2:04:43", "remaining_time": "22:35:23"}
+{"current_steps": 1075, "total_steps": 12698, "loss": 0.3426, "lr": 3.3826771653543314e-05, "epoch": 0.5926130099228225, "percentage": 8.47, "elapsed_time": "2:05:09", "remaining_time": "22:33:16"}
+{"current_steps": 1080, "total_steps": 12698, "loss": 0.3211, "lr": 3.398425196850394e-05, "epoch": 0.5953693495038589, "percentage": 8.51, "elapsed_time": "2:05:37", "remaining_time": "22:31:18"}
+{"current_steps": 1085, "total_steps": 12698, "loss": 0.3337, "lr": 3.414173228346457e-05, "epoch": 0.5981256890848953, "percentage": 8.54, "elapsed_time": "2:06:04", "remaining_time": "22:29:29"}
+{"current_steps": 1090, "total_steps": 12698, "loss": 0.3269, "lr": 3.42992125984252e-05, "epoch": 0.6008820286659317, "percentage": 8.58, "elapsed_time": "2:06:34", "remaining_time": "22:27:54"}
+{"current_steps": 1095, "total_steps": 12698, "loss": 0.3103, "lr": 3.445669291338583e-05, "epoch": 0.603638368246968, "percentage": 8.62, "elapsed_time": "2:07:04", "remaining_time": "22:26:33"}
+{"current_steps": 1100, "total_steps": 12698, "loss": 0.3439, "lr": 3.461417322834646e-05, "epoch": 0.6063947078280044, "percentage": 8.66, "elapsed_time": "2:07:29", "remaining_time": "22:24:14"}
+{"current_steps": 1105, "total_steps": 12698, "loss": 0.3255, "lr": 3.477165354330709e-05, "epoch": 0.6091510474090408, "percentage": 8.7, "elapsed_time": "2:07:57", "remaining_time": "22:22:24"}
+{"current_steps": 1110, "total_steps": 12698, "loss": 0.3413, "lr": 3.4929133858267715e-05, "epoch": 0.6119073869900772, "percentage": 8.74, "elapsed_time": "2:08:25", "remaining_time": "22:20:38"}
+{"current_steps": 1115, "total_steps": 12698, "loss": 0.3403, "lr": 3.508661417322835e-05, "epoch": 0.6146637265711136, "percentage": 8.78, "elapsed_time": "2:08:51", "remaining_time": "22:18:42"}
+{"current_steps": 1120, "total_steps": 12698, "loss": 0.3335, "lr": 3.524409448818898e-05, "epoch": 0.61742006615215, "percentage": 8.82, "elapsed_time": "2:09:19", "remaining_time": "22:16:55"}
+{"current_steps": 1125, "total_steps": 12698, "loss": 0.3699, "lr": 3.5401574803149606e-05, "epoch": 0.6201764057331863, "percentage": 8.86, "elapsed_time": "2:09:45", "remaining_time": "22:14:46"}
+{"current_steps": 1130, "total_steps": 12698, "loss": 0.3329, "lr": 3.555905511811024e-05, "epoch": 0.6229327453142227, "percentage": 8.9, "elapsed_time": "2:10:09", "remaining_time": "22:12:22"}
+{"current_steps": 1135, "total_steps": 12698, "loss": 0.3416, "lr": 3.571653543307087e-05, "epoch": 0.6256890848952591, "percentage": 8.94, "elapsed_time": "2:10:38", "remaining_time": "22:10:53"}
+{"current_steps": 1140, "total_steps": 12698, "loss": 0.3435, "lr": 3.58740157480315e-05, "epoch": 0.6284454244762955, "percentage": 8.98, "elapsed_time": "2:11:06", "remaining_time": "22:09:13"}
+{"current_steps": 1145, "total_steps": 12698, "loss": 0.3394, "lr": 3.603149606299213e-05, "epoch": 0.6312017640573319, "percentage": 9.02, "elapsed_time": "2:11:32", "remaining_time": "22:07:10"}
+{"current_steps": 1150, "total_steps": 12698, "loss": 0.3396, "lr": 3.618897637795276e-05, "epoch": 0.6339581036383682, "percentage": 9.06, "elapsed_time": "2:12:03", "remaining_time": "22:06:05"}
+{"current_steps": 1155, "total_steps": 12698, "loss": 0.3377, "lr": 3.634645669291339e-05, "epoch": 0.6367144432194046, "percentage": 9.1, "elapsed_time": "2:12:29", "remaining_time": "22:04:04"}
+{"current_steps": 1160, "total_steps": 12698, "loss": 0.3379, "lr": 3.650393700787402e-05, "epoch": 0.639470782800441, "percentage": 9.14, "elapsed_time": "2:12:52", "remaining_time": "22:01:43"}
+{"current_steps": 1165, "total_steps": 12698, "loss": 0.3375, "lr": 3.666141732283465e-05, "epoch": 0.6422271223814774, "percentage": 9.17, "elapsed_time": "2:13:18", "remaining_time": "21:59:43"}
+{"current_steps": 1170, "total_steps": 12698, "loss": 0.3282, "lr": 3.6818897637795276e-05, "epoch": 0.6449834619625138, "percentage": 9.21, "elapsed_time": "2:13:45", "remaining_time": "21:57:58"}
+{"current_steps": 1175, "total_steps": 12698, "loss": 0.3141, "lr": 3.697637795275591e-05, "epoch": 0.6477398015435502, "percentage": 9.25, "elapsed_time": "2:14:16", "remaining_time": "21:56:47"}
+{"current_steps": 1180, "total_steps": 12698, "loss": 0.3296, "lr": 3.713385826771654e-05, "epoch": 0.6504961411245865, "percentage": 9.29, "elapsed_time": "2:14:45", "remaining_time": "21:55:18"}
+{"current_steps": 1185, "total_steps": 12698, "loss": 0.321, "lr": 3.729133858267717e-05, "epoch": 0.6532524807056229, "percentage": 9.33, "elapsed_time": "2:15:13", "remaining_time": "21:53:47"}
+{"current_steps": 1190, "total_steps": 12698, "loss": 0.3312, "lr": 3.7448818897637795e-05, "epoch": 0.6560088202866593, "percentage": 9.37, "elapsed_time": "2:15:37", "remaining_time": "21:51:36"}
+{"current_steps": 1195, "total_steps": 12698, "loss": 0.3309, "lr": 3.760629921259843e-05, "epoch": 0.6587651598676957, "percentage": 9.41, "elapsed_time": "2:16:04", "remaining_time": "21:49:52"}
+{"current_steps": 1200, "total_steps": 12698, "loss": 0.3286, "lr": 3.776377952755906e-05, "epoch": 0.6615214994487321, "percentage": 9.45, "elapsed_time": "2:16:31", "remaining_time": "21:48:12"}
+{"current_steps": 1205, "total_steps": 12698, "loss": 0.3349, "lr": 3.7921259842519685e-05, "epoch": 0.6642778390297684, "percentage": 9.49, "elapsed_time": "2:16:54", "remaining_time": "21:45:51"}
+{"current_steps": 1210, "total_steps": 12698, "loss": 0.3297, "lr": 3.807874015748032e-05, "epoch": 0.6670341786108048, "percentage": 9.53, "elapsed_time": "2:17:25", "remaining_time": "21:44:43"}
+{"current_steps": 1215, "total_steps": 12698, "loss": 0.3181, "lr": 3.823622047244095e-05, "epoch": 0.6697905181918412, "percentage": 9.57, "elapsed_time": "2:17:57", "remaining_time": "21:43:54"}
+{"current_steps": 1220, "total_steps": 12698, "loss": 0.3112, "lr": 3.839370078740158e-05, "epoch": 0.6725468577728776, "percentage": 9.61, "elapsed_time": "2:18:27", "remaining_time": "21:42:41"}
+{"current_steps": 1225, "total_steps": 12698, "loss": 0.3147, "lr": 3.855118110236221e-05, "epoch": 0.675303197353914, "percentage": 9.65, "elapsed_time": "2:18:56", "remaining_time": "21:41:16"}
+{"current_steps": 1230, "total_steps": 12698, "loss": 0.3242, "lr": 3.870866141732284e-05, "epoch": 0.6780595369349504, "percentage": 9.69, "elapsed_time": "2:19:23", "remaining_time": "21:39:38"}
+{"current_steps": 1235, "total_steps": 12698, "loss": 0.3134, "lr": 3.886614173228347e-05, "epoch": 0.6808158765159867, "percentage": 9.73, "elapsed_time": "2:19:50", "remaining_time": "21:38:03"}
+{"current_steps": 1240, "total_steps": 12698, "loss": 0.3152, "lr": 3.90236220472441e-05, "epoch": 0.6835722160970231, "percentage": 9.77, "elapsed_time": "2:20:19", "remaining_time": "21:36:34"}
+{"current_steps": 1245, "total_steps": 12698, "loss": 0.3196, "lr": 3.918110236220473e-05, "epoch": 0.6863285556780595, "percentage": 9.8, "elapsed_time": "2:20:44", "remaining_time": "21:34:38"}
+{"current_steps": 1250, "total_steps": 12698, "loss": 0.3152, "lr": 3.9338582677165356e-05, "epoch": 0.6890848952590959, "percentage": 9.84, "elapsed_time": "2:21:12", "remaining_time": "21:33:11"}
+{"current_steps": 1255, "total_steps": 12698, "loss": 0.3443, "lr": 3.949606299212599e-05, "epoch": 0.6918412348401323, "percentage": 9.88, "elapsed_time": "2:21:38", "remaining_time": "21:31:28"}
+{"current_steps": 1260, "total_steps": 12698, "loss": 0.3306, "lr": 3.965354330708662e-05, "epoch": 0.6945975744211687, "percentage": 9.92, "elapsed_time": "2:22:00", "remaining_time": "21:29:10"}
+{"current_steps": 1265, "total_steps": 12698, "loss": 0.3329, "lr": 3.9811023622047246e-05, "epoch": 0.697353914002205, "percentage": 9.96, "elapsed_time": "2:22:29", "remaining_time": "21:27:51"}
+{"current_steps": 1270, "total_steps": 12698, "loss": 0.3101, "lr": 3.9968503937007874e-05, "epoch": 0.7001102535832414, "percentage": 10.0, "elapsed_time": "2:22:54", "remaining_time": "21:25:54"}
+{"current_steps": 1275, "total_steps": 12698, "loss": 0.3257, "lr": 3.9999987908526714e-05, "epoch": 0.7028665931642778, "percentage": 10.04, "elapsed_time": "2:23:19", "remaining_time": "21:24:01"}
+{"current_steps": 1280, "total_steps": 12698, "loss": 0.3202, "lr": 3.999993878694153e-05, "epoch": 0.7056229327453142, "percentage": 10.08, "elapsed_time": "2:23:45", "remaining_time": "21:22:23"}
+{"current_steps": 1285, "total_steps": 12698, "loss": 0.3306, "lr": 3.99998518796201e-05, "epoch": 0.7083792723263506, "percentage": 10.12, "elapsed_time": "2:24:12", "remaining_time": "21:20:52"}
+{"current_steps": 1290, "total_steps": 12698, "loss": 0.3234, "lr": 3.9999727186726634e-05, "epoch": 0.7111356119073869, "percentage": 10.16, "elapsed_time": "2:24:39", "remaining_time": "21:19:15"}
+{"current_steps": 1295, "total_steps": 12698, "loss": 0.3201, "lr": 3.9999564708496694e-05, "epoch": 0.7138919514884233, "percentage": 10.2, "elapsed_time": "2:25:05", "remaining_time": "21:17:35"}
+{"current_steps": 1300, "total_steps": 12698, "loss": 0.3324, "lr": 3.9999364445237255e-05, "epoch": 0.7166482910694597, "percentage": 10.24, "elapsed_time": "2:25:31", "remaining_time": "21:15:57"}
+{"current_steps": 1305, "total_steps": 12698, "loss": 0.2894, "lr": 3.999912639732668e-05, "epoch": 0.7194046306504961, "percentage": 10.28, "elapsed_time": "2:26:02", "remaining_time": "21:14:55"}
+{"current_steps": 1310, "total_steps": 12698, "loss": 0.2016, "lr": 3.99988505652147e-05, "epoch": 0.7221609702315325, "percentage": 10.32, "elapsed_time": "2:26:31", "remaining_time": "21:13:43"}
+{"current_steps": 1315, "total_steps": 12698, "loss": 0.1539, "lr": 3.999853694942246e-05, "epoch": 0.7249173098125689, "percentage": 10.36, "elapsed_time": "2:27:00", "remaining_time": "21:12:32"}
+{"current_steps": 1320, "total_steps": 12698, "loss": 0.148, "lr": 3.999818555054245e-05, "epoch": 0.7276736493936052, "percentage": 10.4, "elapsed_time": "2:27:21", "remaining_time": "21:10:08"}
+{"current_steps": 1325, "total_steps": 12698, "loss": 0.1594, "lr": 3.999779636923858e-05, "epoch": 0.7304299889746417, "percentage": 10.43, "elapsed_time": "2:27:44", "remaining_time": "21:08:07"}
+{"current_steps": 1330, "total_steps": 12698, "loss": 0.148, "lr": 3.9997369406246115e-05, "epoch": 0.7331863285556781, "percentage": 10.47, "elapsed_time": "2:28:13", "remaining_time": "21:06:53"}
+{"current_steps": 1335, "total_steps": 12698, "loss": 0.2039, "lr": 3.9996904662371736e-05, "epoch": 0.7359426681367145, "percentage": 10.51, "elapsed_time": "2:28:39", "remaining_time": "21:05:20"}
+{"current_steps": 1340, "total_steps": 12698, "loss": 0.1894, "lr": 3.999640213849345e-05, "epoch": 0.7386990077177509, "percentage": 10.55, "elapsed_time": "2:29:07", "remaining_time": "21:03:56"}
+{"current_steps": 1345, "total_steps": 12698, "loss": 0.1613, "lr": 3.99958618355607e-05, "epoch": 0.7414553472987873, "percentage": 10.59, "elapsed_time": "2:29:31", "remaining_time": "21:02:06"}
+{"current_steps": 1350, "total_steps": 12698, "loss": 0.2013, "lr": 3.9995283754594256e-05, "epoch": 0.7442116868798236, "percentage": 10.63, "elapsed_time": "2:30:24", "remaining_time": "21:04:22"}
+{"current_steps": 1355, "total_steps": 12698, "loss": 0.122, "lr": 3.999466789668629e-05, "epoch": 0.74696802646086, "percentage": 10.67, "elapsed_time": "2:30:59", "remaining_time": "21:04:00"}
+{"current_steps": 1360, "total_steps": 12698, "loss": 0.1421, "lr": 3.999401426300034e-05, "epoch": 0.7497243660418964, "percentage": 10.71, "elapsed_time": "2:31:38", "remaining_time": "21:04:09"}
+{"current_steps": 1365, "total_steps": 12698, "loss": 0.1388, "lr": 3.99933228547713e-05, "epoch": 0.7524807056229328, "percentage": 10.75, "elapsed_time": "2:32:07", "remaining_time": "21:03:04"}
+{"current_steps": 1370, "total_steps": 12698, "loss": 0.1703, "lr": 3.999259367330546e-05, "epoch": 0.7552370452039692, "percentage": 10.79, "elapsed_time": "2:32:45", "remaining_time": "21:03:06"}
+{"current_steps": 1375, "total_steps": 12698, "loss": 0.1591, "lr": 3.999182671998044e-05, "epoch": 0.7579933847850056, "percentage": 10.83, "elapsed_time": "2:33:10", "remaining_time": "21:01:19"}
+{"current_steps": 1380, "total_steps": 12698, "loss": 0.1419, "lr": 3.9991021996245256e-05, "epoch": 0.7607497243660419, "percentage": 10.87, "elapsed_time": "2:33:39", "remaining_time": "21:00:16"}
+{"current_steps": 1385, "total_steps": 12698, "loss": 0.1329, "lr": 3.9990179503620255e-05, "epoch": 0.7635060639470783, "percentage": 10.91, "elapsed_time": "2:34:02", "remaining_time": "20:58:18"}
+{"current_steps": 1390, "total_steps": 12698, "loss": 0.134, "lr": 3.9989299243697156e-05, "epoch": 0.7662624035281147, "percentage": 10.95, "elapsed_time": "2:34:25", "remaining_time": "20:56:16"}
+{"current_steps": 1395, "total_steps": 12698, "loss": 0.1457, "lr": 3.9988381218139024e-05, "epoch": 0.7690187431091511, "percentage": 10.99, "elapsed_time": "2:34:45", "remaining_time": "20:53:58"}
+{"current_steps": 1400, "total_steps": 12698, "loss": 0.154, "lr": 3.998742542868028e-05, "epoch": 0.7717750826901875, "percentage": 11.03, "elapsed_time": "2:35:22", "remaining_time": "20:53:52"}
+{"current_steps": 1405, "total_steps": 12698, "loss": 0.1578, "lr": 3.998643187712669e-05, "epoch": 0.7745314222712238, "percentage": 11.06, "elapsed_time": "2:35:44", "remaining_time": "20:51:52"}
+{"current_steps": 1410, "total_steps": 12698, "loss": 0.175, "lr": 3.9985400565355365e-05, "epoch": 0.7772877618522602, "percentage": 11.1, "elapsed_time": "2:36:24", "remaining_time": "20:52:08"}
+{"current_steps": 1415, "total_steps": 12698, "loss": 0.1555, "lr": 3.998433149531475e-05, "epoch": 0.7800441014332966, "percentage": 11.14, "elapsed_time": "2:36:47", "remaining_time": "20:50:12"}
+{"current_steps": 1420, "total_steps": 12698, "loss": 0.1385, "lr": 3.998322466902464e-05, "epoch": 0.782800441014333, "percentage": 11.18, "elapsed_time": "2:37:07", "remaining_time": "20:47:56"}
+{"current_steps": 1425, "total_steps": 12698, "loss": 0.1855, "lr": 3.998208008857614e-05, "epoch": 0.7855567805953694, "percentage": 11.22, "elapsed_time": "2:37:32", "remaining_time": "20:46:19"}
+{"current_steps": 1430, "total_steps": 12698, "loss": 0.1634, "lr": 3.9980897756131716e-05, "epoch": 0.7883131201764058, "percentage": 11.26, "elapsed_time": "2:38:10", "remaining_time": "20:46:23"}
+{"current_steps": 1435, "total_steps": 12698, "loss": 0.1453, "lr": 3.9979677673925125e-05, "epoch": 0.7910694597574421, "percentage": 11.3, "elapsed_time": "2:38:34", "remaining_time": "20:44:38"}
+{"current_steps": 1440, "total_steps": 12698, "loss": 0.3529, "lr": 3.997841984426147e-05, "epoch": 0.7938257993384785, "percentage": 11.34, "elapsed_time": "2:39:26", "remaining_time": "20:46:34"}
+{"current_steps": 1445, "total_steps": 12698, "loss": 0.1671, "lr": 3.997712426951715e-05, "epoch": 0.7965821389195149, "percentage": 11.38, "elapsed_time": "2:39:56", "remaining_time": "20:45:33"}
+{"current_steps": 1450, "total_steps": 12698, "loss": 0.1454, "lr": 3.997579095213988e-05, "epoch": 0.7993384785005513, "percentage": 11.42, "elapsed_time": "2:40:27", "remaining_time": "20:44:44"}
+{"current_steps": 1455, "total_steps": 12698, "loss": 0.2544, "lr": 3.997441989464871e-05, "epoch": 0.8020948180815877, "percentage": 11.46, "elapsed_time": "2:41:20", "remaining_time": "20:46:41"}
+{"current_steps": 1460, "total_steps": 12698, "loss": 0.1253, "lr": 3.997301109963393e-05, "epoch": 0.804851157662624, "percentage": 11.5, "elapsed_time": "2:41:47", "remaining_time": "20:45:23"}
+{"current_steps": 1465, "total_steps": 12698, "loss": 0.1419, "lr": 3.997156456975721e-05, "epoch": 0.8076074972436604, "percentage": 11.54, "elapsed_time": "2:42:22", "remaining_time": "20:44:59"}
+{"current_steps": 1470, "total_steps": 12698, "loss": 0.1399, "lr": 3.997008030775144e-05, "epoch": 0.8103638368246968, "percentage": 11.58, "elapsed_time": "2:42:49", "remaining_time": "20:43:39"}
+{"current_steps": 1475, "total_steps": 12698, "loss": 0.1324, "lr": 3.9968558316420834e-05, "epoch": 0.8131201764057332, "percentage": 11.62, "elapsed_time": "2:43:15", "remaining_time": "20:42:14"}
+{"current_steps": 1480, "total_steps": 12698, "loss": 0.1302, "lr": 3.996699859864088e-05, "epoch": 0.8158765159867696, "percentage": 11.66, "elapsed_time": "2:43:45", "remaining_time": "20:41:11"}
+{"current_steps": 1485, "total_steps": 12698, "loss": 0.1291, "lr": 3.996540115735833e-05, "epoch": 0.818632855567806, "percentage": 11.69, "elapsed_time": "2:44:05", "remaining_time": "20:39:03"}
+{"current_steps": 1490, "total_steps": 12698, "loss": 0.1231, "lr": 3.996376599559124e-05, "epoch": 0.8213891951488423, "percentage": 11.73, "elapsed_time": "2:44:26", "remaining_time": "20:37:00"}
+{"current_steps": 1495, "total_steps": 12698, "loss": 0.1305, "lr": 3.996209311642889e-05, "epoch": 0.8241455347298787, "percentage": 11.77, "elapsed_time": "2:44:49", "remaining_time": "20:35:09"}
+{"current_steps": 1500, "total_steps": 12698, "loss": 0.1788, "lr": 3.996038252303184e-05, "epoch": 0.8269018743109151, "percentage": 11.81, "elapsed_time": "2:45:32", "remaining_time": "20:35:50"}
+{"current_steps": 1505, "total_steps": 12698, "loss": 0.1102, "lr": 3.995863421863191e-05, "epoch": 0.8296582138919515, "percentage": 11.85, "elapsed_time": "2:46:32", "remaining_time": "20:38:35"}
+{"current_steps": 1510, "total_steps": 12698, "loss": 0.1327, "lr": 3.995684820653216e-05, "epoch": 0.8324145534729879, "percentage": 11.89, "elapsed_time": "2:46:54", "remaining_time": "20:36:40"}
+{"current_steps": 1515, "total_steps": 12698, "loss": 0.1173, "lr": 3.9955024490106875e-05, "epoch": 0.8351708930540243, "percentage": 11.93, "elapsed_time": "2:47:20", "remaining_time": "20:35:11"}
+{"current_steps": 1520, "total_steps": 12698, "loss": 0.1795, "lr": 3.9953163072801595e-05, "epoch": 0.8379272326350606, "percentage": 11.97, "elapsed_time": "2:48:09", "remaining_time": "20:36:38"}
+{"current_steps": 1525, "total_steps": 12698, "loss": 0.1477, "lr": 3.995126395813309e-05, "epoch": 0.840683572216097, "percentage": 12.01, "elapsed_time": "2:48:41", "remaining_time": "20:35:53"}
+{"current_steps": 1530, "total_steps": 12698, "loss": 0.1614, "lr": 3.994932714968934e-05, "epoch": 0.8434399117971334, "percentage": 12.05, "elapsed_time": "2:49:06", "remaining_time": "20:34:23"}
+{"current_steps": 1535, "total_steps": 12698, "loss": 0.1419, "lr": 3.994735265112954e-05, "epoch": 0.8461962513781698, "percentage": 12.09, "elapsed_time": "2:49:29", "remaining_time": "20:32:34"}
+{"current_steps": 1540, "total_steps": 12698, "loss": 0.2056, "lr": 3.9945340466184086e-05, "epoch": 0.8489525909592062, "percentage": 12.13, "elapsed_time": "2:50:06", "remaining_time": "20:32:31"}
+{"current_steps": 1545, "total_steps": 12698, "loss": 0.1411, "lr": 3.994329059865461e-05, "epoch": 0.8517089305402425, "percentage": 12.17, "elapsed_time": "2:50:31", "remaining_time": "20:30:58"}
+{"current_steps": 1550, "total_steps": 12698, "loss": 0.1706, "lr": 3.994120305241389e-05, "epoch": 0.8544652701212789, "percentage": 12.21, "elapsed_time": "2:50:56", "remaining_time": "20:29:27"}
+{"current_steps": 1555, "total_steps": 12698, "loss": 0.1347, "lr": 3.993907783140591e-05, "epoch": 0.8572216097023153, "percentage": 12.25, "elapsed_time": "2:51:17", "remaining_time": "20:27:27"}
+{"current_steps": 1560, "total_steps": 12698, "loss": 0.1408, "lr": 3.993691493964585e-05, "epoch": 0.8599779492833517, "percentage": 12.29, "elapsed_time": "2:51:48", "remaining_time": "20:26:38"}
+{"current_steps": 1565, "total_steps": 12698, "loss": 0.1399, "lr": 3.993471438122003e-05, "epoch": 0.8627342888643881, "percentage": 12.32, "elapsed_time": "2:52:31", "remaining_time": "20:27:16"}
+{"current_steps": 1570, "total_steps": 12698, "loss": 0.1166, "lr": 3.993247616028596e-05, "epoch": 0.8654906284454245, "percentage": 12.36, "elapsed_time": "2:53:11", "remaining_time": "20:27:34"}
+{"current_steps": 1575, "total_steps": 12698, "loss": 0.1136, "lr": 3.993020028107229e-05, "epoch": 0.8682469680264608, "percentage": 12.4, "elapsed_time": "2:53:35", "remaining_time": "20:25:57"}
+{"current_steps": 1580, "total_steps": 12698, "loss": 0.1267, "lr": 3.9927886747878826e-05, "epoch": 0.8710033076074972, "percentage": 12.44, "elapsed_time": "2:54:01", "remaining_time": "20:24:36"}
+{"current_steps": 1585, "total_steps": 12698, "loss": 0.1431, "lr": 3.99255355650765e-05, "epoch": 0.8737596471885336, "percentage": 12.48, "elapsed_time": "2:54:54", "remaining_time": "20:26:22"}
+{"current_steps": 1590, "total_steps": 12698, "loss": 0.142, "lr": 3.992314673710739e-05, "epoch": 0.87651598676957, "percentage": 12.52, "elapsed_time": "2:55:18", "remaining_time": "20:24:43"}
+{"current_steps": 1595, "total_steps": 12698, "loss": 0.1294, "lr": 3.992072026848469e-05, "epoch": 0.8792723263506064, "percentage": 12.56, "elapsed_time": "2:55:40", "remaining_time": "20:22:51"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:141325128422ce76d6aa035ce803965ed96e345d0b49e39cbd3ff3adf570c329
+size 8657