Training in progress, step 1379

.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 sha256:5255c88d0d234d4312e4c13706be9aab18454204856cced9cc043d8321b6ae69
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ccba9cae2fb962e9389ac769892f11f663ed40af74d2566e6b180796764ada3
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:58a772e5bb44e2e8b78ed969dd30aa0365b04355046009e1148e957c79d70941
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f3f7cd6d0e8a99b05b2dbd9db5caebb4c94f1b54ab4c27b6b0b1800e4ef3c5d
+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": "exp-psu-stackoverflow-3K_glm_4.7_traces",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "DCAgent/exp-psu-stackoverflow-3K_glm_4.7_traces",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/exp-psu-stackoverflow-3K_glm_4_7_traces/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp-psu-stackoverflow-3K_glm_4-7_traces_Qwen3-8B",
+  "traces_location_s3": null
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_log.jsonl

@@ -0,0 +1,276 @@
+{"current_steps": 5, "total_steps": 1379, "loss": 0.8448, "lr": 1.1594202898550726e-06, "epoch": 0.025380710659898477, "percentage": 0.36, "elapsed_time": "0:00:36", "remaining_time": "2:47:50"}
+{"current_steps": 10, "total_steps": 1379, "loss": 0.8643, "lr": 2.6086956521739132e-06, "epoch": 0.050761421319796954, "percentage": 0.73, "elapsed_time": "0:01:03", "remaining_time": "2:24:03"}
+{"current_steps": 15, "total_steps": 1379, "loss": 0.8132, "lr": 4.057971014492754e-06, "epoch": 0.07614213197969544, "percentage": 1.09, "elapsed_time": "0:01:28", "remaining_time": "2:14:41"}
+{"current_steps": 20, "total_steps": 1379, "loss": 0.7417, "lr": 5.507246376811595e-06, "epoch": 0.10152284263959391, "percentage": 1.45, "elapsed_time": "0:01:54", "remaining_time": "2:09:50"}
+{"current_steps": 25, "total_steps": 1379, "loss": 0.735, "lr": 6.956521739130435e-06, "epoch": 0.12690355329949238, "percentage": 1.81, "elapsed_time": "0:02:30", "remaining_time": "2:15:26"}
+{"current_steps": 30, "total_steps": 1379, "loss": 0.6935, "lr": 8.405797101449275e-06, "epoch": 0.15228426395939088, "percentage": 2.18, "elapsed_time": "0:02:57", "remaining_time": "2:13:02"}
+{"current_steps": 35, "total_steps": 1379, "loss": 0.626, "lr": 9.855072463768118e-06, "epoch": 0.17766497461928935, "percentage": 2.54, "elapsed_time": "0:03:26", "remaining_time": "2:12:02"}
+{"current_steps": 40, "total_steps": 1379, "loss": 0.6444, "lr": 1.1304347826086957e-05, "epoch": 0.20304568527918782, "percentage": 2.9, "elapsed_time": "0:03:53", "remaining_time": "2:10:08"}
+{"current_steps": 45, "total_steps": 1379, "loss": 0.5968, "lr": 1.2753623188405797e-05, "epoch": 0.22842639593908629, "percentage": 3.26, "elapsed_time": "0:04:18", "remaining_time": "2:07:33"}
+{"current_steps": 50, "total_steps": 1379, "loss": 0.5712, "lr": 1.420289855072464e-05, "epoch": 0.25380710659898476, "percentage": 3.63, "elapsed_time": "0:04:53", "remaining_time": "2:09:51"}
+{"current_steps": 55, "total_steps": 1379, "loss": 0.5423, "lr": 1.565217391304348e-05, "epoch": 0.27918781725888325, "percentage": 3.99, "elapsed_time": "0:05:23", "remaining_time": "2:09:40"}
+{"current_steps": 60, "total_steps": 1379, "loss": 0.5736, "lr": 1.710144927536232e-05, "epoch": 0.30456852791878175, "percentage": 4.35, "elapsed_time": "0:05:44", "remaining_time": "2:06:10"}
+{"current_steps": 65, "total_steps": 1379, "loss": 0.5296, "lr": 1.8550724637681162e-05, "epoch": 0.3299492385786802, "percentage": 4.71, "elapsed_time": "0:06:05", "remaining_time": "2:03:10"}
+{"current_steps": 70, "total_steps": 1379, "loss": 0.5151, "lr": 2e-05, "epoch": 0.3553299492385787, "percentage": 5.08, "elapsed_time": "0:06:29", "remaining_time": "2:01:22"}
+{"current_steps": 75, "total_steps": 1379, "loss": 0.5267, "lr": 2.1449275362318844e-05, "epoch": 0.38071065989847713, "percentage": 5.44, "elapsed_time": "0:06:49", "remaining_time": "1:58:40"}
+{"current_steps": 80, "total_steps": 1379, "loss": 0.534, "lr": 2.2898550724637684e-05, "epoch": 0.40609137055837563, "percentage": 5.8, "elapsed_time": "0:07:17", "remaining_time": "1:58:26"}
+{"current_steps": 85, "total_steps": 1379, "loss": 0.5021, "lr": 2.4347826086956526e-05, "epoch": 0.43147208121827413, "percentage": 6.16, "elapsed_time": "0:07:43", "remaining_time": "1:57:40"}
+{"current_steps": 90, "total_steps": 1379, "loss": 0.4829, "lr": 2.5797101449275362e-05, "epoch": 0.45685279187817257, "percentage": 6.53, "elapsed_time": "0:08:06", "remaining_time": "1:56:03"}
+{"current_steps": 95, "total_steps": 1379, "loss": 0.4635, "lr": 2.7246376811594205e-05, "epoch": 0.48223350253807107, "percentage": 6.89, "elapsed_time": "0:08:33", "remaining_time": "1:55:38"}
+{"current_steps": 100, "total_steps": 1379, "loss": 0.4353, "lr": 2.8695652173913044e-05, "epoch": 0.5076142131979695, "percentage": 7.25, "elapsed_time": "0:08:56", "remaining_time": "1:54:23"}
+{"current_steps": 105, "total_steps": 1379, "loss": 0.4693, "lr": 3.0144927536231887e-05, "epoch": 0.5329949238578681, "percentage": 7.61, "elapsed_time": "0:09:18", "remaining_time": "1:52:51"}
+{"current_steps": 110, "total_steps": 1379, "loss": 0.4865, "lr": 3.1594202898550726e-05, "epoch": 0.5583756345177665, "percentage": 7.98, "elapsed_time": "0:09:41", "remaining_time": "1:51:50"}
+{"current_steps": 115, "total_steps": 1379, "loss": 0.4911, "lr": 3.304347826086957e-05, "epoch": 0.583756345177665, "percentage": 8.34, "elapsed_time": "0:10:08", "remaining_time": "1:51:30"}
+{"current_steps": 120, "total_steps": 1379, "loss": 0.4888, "lr": 3.449275362318841e-05, "epoch": 0.6091370558375635, "percentage": 8.7, "elapsed_time": "0:10:32", "remaining_time": "1:50:33"}
+{"current_steps": 125, "total_steps": 1379, "loss": 0.4849, "lr": 3.594202898550725e-05, "epoch": 0.6345177664974619, "percentage": 9.06, "elapsed_time": "0:10:58", "remaining_time": "1:50:02"}
+{"current_steps": 130, "total_steps": 1379, "loss": 0.4522, "lr": 3.739130434782609e-05, "epoch": 0.6598984771573604, "percentage": 9.43, "elapsed_time": "0:11:25", "remaining_time": "1:49:41"}
+{"current_steps": 135, "total_steps": 1379, "loss": 0.4803, "lr": 3.884057971014493e-05, "epoch": 0.6852791878172588, "percentage": 9.79, "elapsed_time": "0:11:46", "remaining_time": "1:48:32"}
+{"current_steps": 140, "total_steps": 1379, "loss": 0.4917, "lr": 3.999993591506466e-05, "epoch": 0.7106598984771574, "percentage": 10.15, "elapsed_time": "0:12:09", "remaining_time": "1:47:35"}
+{"current_steps": 145, "total_steps": 1379, "loss": 0.4831, "lr": 3.99976929854497e-05, "epoch": 0.7360406091370558, "percentage": 10.51, "elapsed_time": "0:12:35", "remaining_time": "1:47:08"}
+{"current_steps": 150, "total_steps": 1379, "loss": 0.4804, "lr": 3.999224621974382e-05, "epoch": 0.7614213197969543, "percentage": 10.88, "elapsed_time": "0:12:56", "remaining_time": "1:46:05"}
+{"current_steps": 155, "total_steps": 1379, "loss": 0.4899, "lr": 3.9983596490574876e-05, "epoch": 0.7868020304568528, "percentage": 11.24, "elapsed_time": "0:13:19", "remaining_time": "1:45:15"}
+{"current_steps": 160, "total_steps": 1379, "loss": 0.4689, "lr": 3.9971745183718484e-05, "epoch": 0.8121827411167513, "percentage": 11.6, "elapsed_time": "0:13:40", "remaining_time": "1:44:12"}
+{"current_steps": 165, "total_steps": 1379, "loss": 0.4777, "lr": 3.995669419787586e-05, "epoch": 0.8375634517766497, "percentage": 11.97, "elapsed_time": "0:14:10", "remaining_time": "1:44:21"}
+{"current_steps": 170, "total_steps": 1379, "loss": 0.447, "lr": 3.9938445944369745e-05, "epoch": 0.8629441624365483, "percentage": 12.33, "elapsed_time": "0:14:38", "remaining_time": "1:44:09"}
+{"current_steps": 175, "total_steps": 1379, "loss": 0.4579, "lr": 3.9917003346758035e-05, "epoch": 0.8883248730964467, "percentage": 12.69, "elapsed_time": "0:14:59", "remaining_time": "1:43:06"}
+{"current_steps": 180, "total_steps": 1379, "loss": 0.452, "lr": 3.989236984036541e-05, "epoch": 0.9137055837563451, "percentage": 13.05, "elapsed_time": "0:15:19", "remaining_time": "1:42:05"}
+{"current_steps": 185, "total_steps": 1379, "loss": 0.4723, "lr": 3.986454937173292e-05, "epoch": 0.9390862944162437, "percentage": 13.42, "elapsed_time": "0:15:40", "remaining_time": "1:41:10"}
+{"current_steps": 190, "total_steps": 1379, "loss": 0.4487, "lr": 3.98335463979858e-05, "epoch": 0.9644670050761421, "percentage": 13.78, "elapsed_time": "0:15:57", "remaining_time": "1:39:50"}
+{"current_steps": 195, "total_steps": 1379, "loss": 0.4553, "lr": 3.9799365886119304e-05, "epoch": 0.9898477157360406, "percentage": 14.14, "elapsed_time": "0:16:17", "remaining_time": "1:38:58"}
+{"current_steps": 200, "total_steps": 1379, "loss": 0.4614, "lr": 3.976201331220296e-05, "epoch": 1.015228426395939, "percentage": 14.5, "elapsed_time": "0:16:41", "remaining_time": "1:38:22"}
+{"current_steps": 205, "total_steps": 1379, "loss": 0.423, "lr": 3.9721494660503295e-05, "epoch": 1.0406091370558375, "percentage": 14.87, "elapsed_time": "0:17:05", "remaining_time": "1:37:54"}
+{"current_steps": 210, "total_steps": 1379, "loss": 0.4655, "lr": 3.9677816422525024e-05, "epoch": 1.0659898477157361, "percentage": 15.23, "elapsed_time": "0:17:24", "remaining_time": "1:36:54"}
+{"current_steps": 215, "total_steps": 1379, "loss": 0.401, "lr": 3.963098559597112e-05, "epoch": 1.0913705583756346, "percentage": 15.59, "elapsed_time": "0:17:48", "remaining_time": "1:36:25"}
+{"current_steps": 220, "total_steps": 1379, "loss": 0.4255, "lr": 3.9581009683621634e-05, "epoch": 1.116751269035533, "percentage": 15.95, "elapsed_time": "0:18:10", "remaining_time": "1:35:43"}
+{"current_steps": 225, "total_steps": 1379, "loss": 0.461, "lr": 3.952789669213173e-05, "epoch": 1.1421319796954315, "percentage": 16.32, "elapsed_time": "0:18:35", "remaining_time": "1:35:19"}
+{"current_steps": 230, "total_steps": 1379, "loss": 0.4043, "lr": 3.9471655130748894e-05, "epoch": 1.16751269035533, "percentage": 16.68, "elapsed_time": "0:19:03", "remaining_time": "1:35:10"}
+{"current_steps": 235, "total_steps": 1379, "loss": 0.4098, "lr": 3.9412294009949716e-05, "epoch": 1.1928934010152283, "percentage": 17.04, "elapsed_time": "0:19:29", "remaining_time": "1:34:53"}
+{"current_steps": 240, "total_steps": 1379, "loss": 0.4323, "lr": 3.9349822839996266e-05, "epoch": 1.218274111675127, "percentage": 17.4, "elapsed_time": "0:19:56", "remaining_time": "1:34:40"}
+{"current_steps": 245, "total_steps": 1379, "loss": 0.4481, "lr": 3.928425162941248e-05, "epoch": 1.2436548223350254, "percentage": 17.77, "elapsed_time": "0:20:16", "remaining_time": "1:33:52"}
+{"current_steps": 250, "total_steps": 1379, "loss": 0.4234, "lr": 3.9215590883380687e-05, "epoch": 1.2690355329949239, "percentage": 18.13, "elapsed_time": "0:20:41", "remaining_time": "1:33:28"}
+{"current_steps": 255, "total_steps": 1379, "loss": 0.4021, "lr": 3.914385160205858e-05, "epoch": 1.2944162436548223, "percentage": 18.49, "elapsed_time": "0:21:09", "remaining_time": "1:33:17"}
+{"current_steps": 260, "total_steps": 1379, "loss": 0.4236, "lr": 3.9069045278816844e-05, "epoch": 1.3197969543147208, "percentage": 18.85, "elapsed_time": "0:21:35", "remaining_time": "1:32:56"}
+{"current_steps": 265, "total_steps": 1379, "loss": 0.4181, "lr": 3.899118389839785e-05, "epoch": 1.3451776649746192, "percentage": 19.22, "elapsed_time": "0:21:57", "remaining_time": "1:32:20"}
+{"current_steps": 270, "total_steps": 1379, "loss": 0.4117, "lr": 3.8910279934995545e-05, "epoch": 1.3705583756345177, "percentage": 19.58, "elapsed_time": "0:22:22", "remaining_time": "1:31:53"}
+{"current_steps": 275, "total_steps": 1379, "loss": 0.398, "lr": 3.8826346350256943e-05, "epoch": 1.3959390862944163, "percentage": 19.94, "elapsed_time": "0:22:48", "remaining_time": "1:31:32"}
+{"current_steps": 280, "total_steps": 1379, "loss": 0.4151, "lr": 3.873939659120558e-05, "epoch": 1.4213197969543148, "percentage": 20.3, "elapsed_time": "0:23:11", "remaining_time": "1:31:00"}
+{"current_steps": 285, "total_steps": 1379, "loss": 0.4056, "lr": 3.864944458808712e-05, "epoch": 1.4467005076142132, "percentage": 20.67, "elapsed_time": "0:23:34", "remaining_time": "1:30:29"}
+{"current_steps": 290, "total_steps": 1379, "loss": 0.4243, "lr": 3.855650475213761e-05, "epoch": 1.4720812182741116, "percentage": 21.03, "elapsed_time": "0:23:52", "remaining_time": "1:29:38"}
+{"current_steps": 295, "total_steps": 1379, "loss": 0.4011, "lr": 3.846059197327466e-05, "epoch": 1.49746192893401, "percentage": 21.39, "elapsed_time": "0:24:22", "remaining_time": "1:29:32"}
+{"current_steps": 300, "total_steps": 1379, "loss": 0.4049, "lr": 3.836172161771189e-05, "epoch": 1.5228426395939088, "percentage": 21.75, "elapsed_time": "0:24:42", "remaining_time": "1:28:51"}
+{"current_steps": 305, "total_steps": 1379, "loss": 0.3955, "lr": 3.8259909525497134e-05, "epoch": 1.548223350253807, "percentage": 22.12, "elapsed_time": "0:25:05", "remaining_time": "1:28:20"}
+{"current_steps": 310, "total_steps": 1379, "loss": 0.4128, "lr": 3.81551720079747e-05, "epoch": 1.5736040609137056, "percentage": 22.48, "elapsed_time": "0:25:27", "remaining_time": "1:27:47"}
+{"current_steps": 315, "total_steps": 1379, "loss": 0.3937, "lr": 3.8047525845172104e-05, "epoch": 1.598984771573604, "percentage": 22.84, "elapsed_time": "0:25:54", "remaining_time": "1:27:29"}
+{"current_steps": 320, "total_steps": 1379, "loss": 0.4031, "lr": 3.7936988283111764e-05, "epoch": 1.6243654822335025, "percentage": 23.21, "elapsed_time": "0:26:18", "remaining_time": "1:27:02"}
+{"current_steps": 325, "total_steps": 1379, "loss": 0.4003, "lr": 3.7823577031048e-05, "epoch": 1.649746192893401, "percentage": 23.57, "elapsed_time": "0:26:39", "remaining_time": "1:26:27"}
+{"current_steps": 330, "total_steps": 1379, "loss": 0.4184, "lr": 3.77073102586298e-05, "epoch": 1.6751269035532994, "percentage": 23.93, "elapsed_time": "0:27:03", "remaining_time": "1:26:00"}
+{"current_steps": 335, "total_steps": 1379, "loss": 0.4147, "lr": 3.758820659298991e-05, "epoch": 1.700507614213198, "percentage": 24.29, "elapsed_time": "0:27:29", "remaining_time": "1:25:41"}
+{"current_steps": 340, "total_steps": 1379, "loss": 0.4208, "lr": 3.746628511576054e-05, "epoch": 1.7258883248730963, "percentage": 24.66, "elapsed_time": "0:27:47", "remaining_time": "1:24:56"}
+{"current_steps": 345, "total_steps": 1379, "loss": 0.4288, "lr": 3.734156536001629e-05, "epoch": 1.751269035532995, "percentage": 25.02, "elapsed_time": "0:28:12", "remaining_time": "1:24:33"}
+{"current_steps": 350, "total_steps": 1379, "loss": 0.4035, "lr": 3.721406730714476e-05, "epoch": 1.7766497461928934, "percentage": 25.38, "elapsed_time": "0:28:33", "remaining_time": "1:23:57"}
+{"current_steps": 355, "total_steps": 1379, "loss": 0.4057, "lr": 3.7083811383645334e-05, "epoch": 1.8020304568527918, "percentage": 25.74, "elapsed_time": "0:28:53", "remaining_time": "1:23:20"}
+{"current_steps": 360, "total_steps": 1379, "loss": 0.4183, "lr": 3.695081845785663e-05, "epoch": 1.8274111675126905, "percentage": 26.11, "elapsed_time": "0:29:15", "remaining_time": "1:22:48"}
+{"current_steps": 365, "total_steps": 1379, "loss": 0.3992, "lr": 3.6815109836613165e-05, "epoch": 1.8527918781725887, "percentage": 26.47, "elapsed_time": "0:29:40", "remaining_time": "1:22:26"}
+{"current_steps": 370, "total_steps": 1379, "loss": 0.3993, "lr": 3.6676707261831836e-05, "epoch": 1.8781725888324874, "percentage": 26.83, "elapsed_time": "0:30:05", "remaining_time": "1:22:04"}
+{"current_steps": 375, "total_steps": 1379, "loss": 0.4198, "lr": 3.6535632907028566e-05, "epoch": 1.9035532994923858, "percentage": 27.19, "elapsed_time": "0:30:24", "remaining_time": "1:21:25"}
+{"current_steps": 380, "total_steps": 1379, "loss": 0.4097, "lr": 3.6391909373765944e-05, "epoch": 1.9289340101522843, "percentage": 27.56, "elapsed_time": "0:30:41", "remaining_time": "1:20:41"}
+{"current_steps": 385, "total_steps": 1379, "loss": 0.3997, "lr": 3.6245559688032176e-05, "epoch": 1.9543147208121827, "percentage": 27.92, "elapsed_time": "0:31:08", "remaining_time": "1:20:24"}
+{"current_steps": 390, "total_steps": 1379, "loss": 0.4187, "lr": 3.609660729655212e-05, "epoch": 1.9796954314720812, "percentage": 28.28, "elapsed_time": "0:31:25", "remaining_time": "1:19:41"}
+{"current_steps": 395, "total_steps": 1379, "loss": 0.3959, "lr": 3.5945076063030835e-05, "epoch": 2.00507614213198, "percentage": 28.64, "elapsed_time": "0:31:46", "remaining_time": "1:19:08"}
+{"current_steps": 400, "total_steps": 1379, "loss": 0.3661, "lr": 3.579099026433044e-05, "epoch": 2.030456852791878, "percentage": 29.01, "elapsed_time": "0:32:07", "remaining_time": "1:18:37"}
+{"current_steps": 405, "total_steps": 1379, "loss": 0.364, "lr": 3.563437458658064e-05, "epoch": 2.0558375634517767, "percentage": 29.37, "elapsed_time": "0:32:29", "remaining_time": "1:18:07"}
+{"current_steps": 410, "total_steps": 1379, "loss": 0.3568, "lr": 3.547525412122378e-05, "epoch": 2.081218274111675, "percentage": 29.73, "elapsed_time": "0:32:50", "remaining_time": "1:17:36"}
+{"current_steps": 415, "total_steps": 1379, "loss": 0.361, "lr": 3.531365436099497e-05, "epoch": 2.1065989847715736, "percentage": 30.09, "elapsed_time": "0:33:13", "remaining_time": "1:17:10"}
+{"current_steps": 420, "total_steps": 1379, "loss": 0.3541, "lr": 3.5149601195837815e-05, "epoch": 2.1319796954314723, "percentage": 30.46, "elapsed_time": "0:33:34", "remaining_time": "1:16:40"}
+{"current_steps": 425, "total_steps": 1379, "loss": 0.3589, "lr": 3.498312090875667e-05, "epoch": 2.1573604060913705, "percentage": 30.82, "elapsed_time": "0:33:52", "remaining_time": "1:16:02"}
+{"current_steps": 430, "total_steps": 1379, "loss": 0.3631, "lr": 3.481424017160574e-05, "epoch": 2.182741116751269, "percentage": 31.18, "elapsed_time": "0:34:18", "remaining_time": "1:15:43"}
+{"current_steps": 435, "total_steps": 1379, "loss": 0.3753, "lr": 3.464298604081607e-05, "epoch": 2.2081218274111674, "percentage": 31.54, "elapsed_time": "0:34:37", "remaining_time": "1:15:07"}
+{"current_steps": 440, "total_steps": 1379, "loss": 0.355, "lr": 3.4469385953060715e-05, "epoch": 2.233502538071066, "percentage": 31.91, "elapsed_time": "0:34:56", "remaining_time": "1:14:34"}
+{"current_steps": 445, "total_steps": 1379, "loss": 0.3607, "lr": 3.429346772085923e-05, "epoch": 2.2588832487309647, "percentage": 32.27, "elapsed_time": "0:35:20", "remaining_time": "1:14:09"}
+{"current_steps": 450, "total_steps": 1379, "loss": 0.3566, "lr": 3.4115259528121685e-05, "epoch": 2.284263959390863, "percentage": 32.63, "elapsed_time": "0:35:40", "remaining_time": "1:13:39"}
+{"current_steps": 455, "total_steps": 1379, "loss": 0.3471, "lr": 3.3934789925633426e-05, "epoch": 2.3096446700507616, "percentage": 32.99, "elapsed_time": "0:36:10", "remaining_time": "1:13:28"}
+{"current_steps": 460, "total_steps": 1379, "loss": 0.3891, "lr": 3.37520878264809e-05, "epoch": 2.33502538071066, "percentage": 33.36, "elapsed_time": "0:36:29", "remaining_time": "1:12:53"}
+{"current_steps": 465, "total_steps": 1379, "loss": 0.3724, "lr": 3.356718250141945e-05, "epoch": 2.3604060913705585, "percentage": 33.72, "elapsed_time": "0:36:55", "remaining_time": "1:12:34"}
+{"current_steps": 470, "total_steps": 1379, "loss": 0.3503, "lr": 3.33801035741839e-05, "epoch": 2.3857868020304567, "percentage": 34.08, "elapsed_time": "0:37:15", "remaining_time": "1:12:03"}
+{"current_steps": 475, "total_steps": 1379, "loss": 0.3606, "lr": 3.3190881016742476e-05, "epoch": 2.4111675126903553, "percentage": 34.45, "elapsed_time": "0:37:36", "remaining_time": "1:11:34"}
+{"current_steps": 480, "total_steps": 1379, "loss": 0.3529, "lr": 3.2999545144495037e-05, "epoch": 2.436548223350254, "percentage": 34.81, "elapsed_time": "0:37:54", "remaining_time": "1:10:59"}
+{"current_steps": 485, "total_steps": 1379, "loss": 0.3768, "lr": 3.280612661141615e-05, "epoch": 2.4619289340101522, "percentage": 35.17, "elapsed_time": "0:38:10", "remaining_time": "1:10:21"}
+{"current_steps": 490, "total_steps": 1379, "loss": 0.3798, "lr": 3.2610656405144155e-05, "epoch": 2.487309644670051, "percentage": 35.53, "elapsed_time": "0:38:33", "remaining_time": "1:09:57"}
+{"current_steps": 495, "total_steps": 1379, "loss": 0.3505, "lr": 3.241316584201647e-05, "epoch": 2.512690355329949, "percentage": 35.9, "elapsed_time": "0:38:55", "remaining_time": "1:09:30"}
+{"current_steps": 500, "total_steps": 1379, "loss": 0.3732, "lr": 3.2213686562052474e-05, "epoch": 2.5380710659898478, "percentage": 36.26, "elapsed_time": "0:39:13", "remaining_time": "1:08:56"}
+{"current_steps": 505, "total_steps": 1379, "loss": 0.334, "lr": 3.201225052388446e-05, "epoch": 2.563451776649746, "percentage": 36.62, "elapsed_time": "0:39:37", "remaining_time": "1:08:34"}
+{"current_steps": 510, "total_steps": 1379, "loss": 0.3468, "lr": 3.1808889999637496e-05, "epoch": 2.5888324873096447, "percentage": 36.98, "elapsed_time": "0:39:58", "remaining_time": "1:08:07"}
+{"current_steps": 515, "total_steps": 1379, "loss": 0.3585, "lr": 3.16036375697591e-05, "epoch": 2.6142131979695433, "percentage": 37.35, "elapsed_time": "0:40:18", "remaining_time": "1:07:36"}
+{"current_steps": 520, "total_steps": 1379, "loss": 0.3765, "lr": 3.1396526117799557e-05, "epoch": 2.6395939086294415, "percentage": 37.71, "elapsed_time": "0:40:40", "remaining_time": "1:07:11"}
+{"current_steps": 525, "total_steps": 1379, "loss": 0.3718, "lr": 3.1187588825143596e-05, "epoch": 2.66497461928934, "percentage": 38.07, "elapsed_time": "0:41:06", "remaining_time": "1:06:51"}
+{"current_steps": 530, "total_steps": 1379, "loss": 0.3475, "lr": 3.097685916569439e-05, "epoch": 2.6903553299492384, "percentage": 38.43, "elapsed_time": "0:41:34", "remaining_time": "1:06:35"}
+{"current_steps": 535, "total_steps": 1379, "loss": 0.3541, "lr": 3.076437090051073e-05, "epoch": 2.715736040609137, "percentage": 38.8, "elapsed_time": "0:41:57", "remaining_time": "1:06:11"}
+{"current_steps": 540, "total_steps": 1379, "loss": 0.3551, "lr": 3.0550158072398125e-05, "epoch": 2.7411167512690353, "percentage": 39.16, "elapsed_time": "0:42:20", "remaining_time": "1:05:46"}
+{"current_steps": 545, "total_steps": 1379, "loss": 0.3348, "lr": 3.0334255000454795e-05, "epoch": 2.766497461928934, "percentage": 39.52, "elapsed_time": "0:42:45", "remaining_time": "1:05:26"}
+{"current_steps": 550, "total_steps": 1379, "loss": 0.3625, "lr": 3.011669627457341e-05, "epoch": 2.7918781725888326, "percentage": 39.88, "elapsed_time": "0:43:13", "remaining_time": "1:05:09"}
+{"current_steps": 555, "total_steps": 1379, "loss": 0.3654, "lr": 2.989751674989943e-05, "epoch": 2.817258883248731, "percentage": 40.25, "elapsed_time": "0:43:33", "remaining_time": "1:04:40"}
+{"current_steps": 560, "total_steps": 1379, "loss": 0.3818, "lr": 2.967675154124696e-05, "epoch": 2.8426395939086295, "percentage": 40.61, "elapsed_time": "0:43:59", "remaining_time": "1:04:19"}
+{"current_steps": 565, "total_steps": 1379, "loss": 0.3504, "lr": 2.945443601747297e-05, "epoch": 2.868020304568528, "percentage": 40.97, "elapsed_time": "0:44:25", "remaining_time": "1:04:00"}
+{"current_steps": 570, "total_steps": 1379, "loss": 0.3567, "lr": 2.923060579581087e-05, "epoch": 2.8934010152284264, "percentage": 41.33, "elapsed_time": "0:44:49", "remaining_time": "1:03:37"}
+{"current_steps": 575, "total_steps": 1379, "loss": 0.3791, "lr": 2.9005296736164246e-05, "epoch": 2.9187817258883246, "percentage": 41.7, "elapsed_time": "0:45:09", "remaining_time": "1:03:08"}
+{"current_steps": 580, "total_steps": 1379, "loss": 0.3747, "lr": 2.8778544935361742e-05, "epoch": 2.9441624365482233, "percentage": 42.06, "elapsed_time": "0:45:29", "remaining_time": "1:02:39"}
+{"current_steps": 585, "total_steps": 1379, "loss": 0.3458, "lr": 2.855038672137396e-05, "epoch": 2.969543147208122, "percentage": 42.42, "elapsed_time": "0:45:55", "remaining_time": "1:02:19"}
+{"current_steps": 590, "total_steps": 1379, "loss": 0.3659, "lr": 2.8320858647493374e-05, "epoch": 2.99492385786802, "percentage": 42.78, "elapsed_time": "0:46:20", "remaining_time": "1:01:58"}
+{"current_steps": 595, "total_steps": 1379, "loss": 0.3371, "lr": 2.8089997486478102e-05, "epoch": 3.020304568527919, "percentage": 43.15, "elapsed_time": "0:46:44", "remaining_time": "1:01:35"}
+{"current_steps": 600, "total_steps": 1379, "loss": 0.3112, "lr": 2.785784022466053e-05, "epoch": 3.045685279187817, "percentage": 43.51, "elapsed_time": "0:47:09", "remaining_time": "1:01:13"}
+{"current_steps": 605, "total_steps": 1379, "loss": 0.3069, "lr": 2.7624424056021707e-05, "epoch": 3.0710659898477157, "percentage": 43.87, "elapsed_time": "0:47:28", "remaining_time": "1:00:44"}
+{"current_steps": 610, "total_steps": 1379, "loss": 0.3277, "lr": 2.738978637623252e-05, "epoch": 3.0964467005076144, "percentage": 44.23, "elapsed_time": "0:47:53", "remaining_time": "1:00:23"}
+{"current_steps": 615, "total_steps": 1379, "loss": 0.2997, "lr": 2.7153964776662517e-05, "epoch": 3.1218274111675126, "percentage": 44.6, "elapsed_time": "0:48:20", "remaining_time": "1:00:02"}
+{"current_steps": 620, "total_steps": 1379, "loss": 0.3111, "lr": 2.691699703835733e-05, "epoch": 3.1472081218274113, "percentage": 44.96, "elapsed_time": "0:48:45", "remaining_time": "0:59:41"}
+{"current_steps": 625, "total_steps": 1379, "loss": 0.3162, "lr": 2.6678921125985845e-05, "epoch": 3.1725888324873095, "percentage": 45.32, "elapsed_time": "0:49:06", "remaining_time": "0:59:14"}
+{"current_steps": 630, "total_steps": 1379, "loss": 0.3114, "lr": 2.6439775181757806e-05, "epoch": 3.197969543147208, "percentage": 45.69, "elapsed_time": "0:49:32", "remaining_time": "0:58:54"}
+{"current_steps": 635, "total_steps": 1379, "loss": 0.3166, "lr": 2.6199597519313092e-05, "epoch": 3.223350253807107, "percentage": 46.05, "elapsed_time": "0:49:57", "remaining_time": "0:58:31"}
+{"current_steps": 640, "total_steps": 1379, "loss": 0.3395, "lr": 2.5958426617583417e-05, "epoch": 3.248730964467005, "percentage": 46.41, "elapsed_time": "0:50:20", "remaining_time": "0:58:08"}
+{"current_steps": 645, "total_steps": 1379, "loss": 0.3072, "lr": 2.5716301114627663e-05, "epoch": 3.2741116751269037, "percentage": 46.77, "elapsed_time": "0:50:43", "remaining_time": "0:57:43"}
+{"current_steps": 650, "total_steps": 1379, "loss": 0.3132, "lr": 2.5473259801441663e-05, "epoch": 3.299492385786802, "percentage": 47.14, "elapsed_time": "0:51:05", "remaining_time": "0:57:17"}
+{"current_steps": 655, "total_steps": 1379, "loss": 0.3155, "lr": 2.5229341615743423e-05, "epoch": 3.3248730964467006, "percentage": 47.5, "elapsed_time": "0:51:30", "remaining_time": "0:56:55"}
+{"current_steps": 660, "total_steps": 1379, "loss": 0.325, "lr": 2.4984585635734995e-05, "epoch": 3.350253807106599, "percentage": 47.86, "elapsed_time": "0:51:52", "remaining_time": "0:56:31"}
+{"current_steps": 665, "total_steps": 1379, "loss": 0.3126, "lr": 2.4739031073841652e-05, "epoch": 3.3756345177664975, "percentage": 48.22, "elapsed_time": "0:52:14", "remaining_time": "0:56:05"}
+{"current_steps": 670, "total_steps": 1379, "loss": 0.3149, "lr": 2.4492717270429736e-05, "epoch": 3.401015228426396, "percentage": 48.59, "elapsed_time": "0:52:32", "remaining_time": "0:55:35"}
+{"current_steps": 675, "total_steps": 1379, "loss": 0.3321, "lr": 2.424568368750385e-05, "epoch": 3.4263959390862944, "percentage": 48.95, "elapsed_time": "0:53:00", "remaining_time": "0:55:17"}
+{"current_steps": 680, "total_steps": 1379, "loss": 0.3168, "lr": 2.3997969902384722e-05, "epoch": 3.451776649746193, "percentage": 49.31, "elapsed_time": "0:53:23", "remaining_time": "0:54:52"}
+{"current_steps": 685, "total_steps": 1379, "loss": 0.309, "lr": 2.3749615601368434e-05, "epoch": 3.4771573604060912, "percentage": 49.67, "elapsed_time": "0:53:44", "remaining_time": "0:54:26"}
+{"current_steps": 690, "total_steps": 1379, "loss": 0.3173, "lr": 2.3500660573368305e-05, "epoch": 3.50253807106599, "percentage": 50.04, "elapsed_time": "0:54:03", "remaining_time": "0:53:58"}
+{"current_steps": 695, "total_steps": 1379, "loss": 0.3074, "lr": 2.3251144703540313e-05, "epoch": 3.527918781725888, "percentage": 50.4, "elapsed_time": "0:54:24", "remaining_time": "0:53:32"}
+{"current_steps": 700, "total_steps": 1379, "loss": 0.3152, "lr": 2.3001107966893054e-05, "epoch": 3.553299492385787, "percentage": 50.76, "elapsed_time": "0:54:43", "remaining_time": "0:53:04"}
+{"current_steps": 705, "total_steps": 1379, "loss": 0.3211, "lr": 2.2750590421883348e-05, "epoch": 3.5786802030456855, "percentage": 51.12, "elapsed_time": "0:55:03", "remaining_time": "0:52:38"}
+{"current_steps": 710, "total_steps": 1379, "loss": 0.292, "lr": 2.2499632203998454e-05, "epoch": 3.6040609137055837, "percentage": 51.49, "elapsed_time": "0:55:27", "remaining_time": "0:52:15"}
+{"current_steps": 715, "total_steps": 1379, "loss": 0.3247, "lr": 2.224827351932596e-05, "epoch": 3.6294416243654823, "percentage": 51.85, "elapsed_time": "0:55:44", "remaining_time": "0:51:45"}
+{"current_steps": 720, "total_steps": 1379, "loss": 0.3082, "lr": 2.1996554638112362e-05, "epoch": 3.6548223350253806, "percentage": 52.21, "elapsed_time": "0:56:07", "remaining_time": "0:51:21"}
+{"current_steps": 725, "total_steps": 1379, "loss": 0.3192, "lr": 2.174451588831134e-05, "epoch": 3.6802030456852792, "percentage": 52.57, "elapsed_time": "0:56:26", "remaining_time": "0:50:54"}
+{"current_steps": 730, "total_steps": 1379, "loss": 0.347, "lr": 2.1492197649122794e-05, "epoch": 3.7055837563451774, "percentage": 52.94, "elapsed_time": "0:56:56", "remaining_time": "0:50:37"}
+{"current_steps": 735, "total_steps": 1379, "loss": 0.3118, "lr": 2.1239640344523735e-05, "epoch": 3.730964467005076, "percentage": 53.3, "elapsed_time": "0:57:18", "remaining_time": "0:50:12"}
+{"current_steps": 740, "total_steps": 1379, "loss": 0.3273, "lr": 2.0986884436791875e-05, "epoch": 3.7563451776649748, "percentage": 53.66, "elapsed_time": "0:57:39", "remaining_time": "0:49:47"}
+{"current_steps": 745, "total_steps": 1379, "loss": 0.307, "lr": 2.073397042002322e-05, "epoch": 3.781725888324873, "percentage": 54.02, "elapsed_time": "0:58:01", "remaining_time": "0:49:23"}
+{"current_steps": 750, "total_steps": 1379, "loss": 0.3049, "lr": 2.0480938813644443e-05, "epoch": 3.8071065989847717, "percentage": 54.39, "elapsed_time": "0:58:22", "remaining_time": "0:48:57"}
+{"current_steps": 755, "total_steps": 1379, "loss": 0.3286, "lr": 2.022783015592132e-05, "epoch": 3.8324873096446703, "percentage": 54.75, "elapsed_time": "0:58:42", "remaining_time": "0:48:31"}
+{"current_steps": 760, "total_steps": 1379, "loss": 0.3126, "lr": 1.9974684997463986e-05, "epoch": 3.8578680203045685, "percentage": 55.11, "elapsed_time": "0:59:01", "remaining_time": "0:48:04"}
+{"current_steps": 765, "total_steps": 1379, "loss": 0.3261, "lr": 1.9721543894730428e-05, "epoch": 3.8832487309644668, "percentage": 55.47, "elapsed_time": "0:59:22", "remaining_time": "0:47:39"}
+{"current_steps": 770, "total_steps": 1379, "loss": 0.3214, "lr": 1.946844740352883e-05, "epoch": 3.9086294416243654, "percentage": 55.84, "elapsed_time": "0:59:47", "remaining_time": "0:47:17"}
+{"current_steps": 775, "total_steps": 1379, "loss": 0.3225, "lr": 1.9215436072520167e-05, "epoch": 3.934010152284264, "percentage": 56.2, "elapsed_time": "1:00:13", "remaining_time": "0:46:55"}
+{"current_steps": 780, "total_steps": 1379, "loss": 0.3207, "lr": 1.8962550436721867e-05, "epoch": 3.9593908629441623, "percentage": 56.56, "elapsed_time": "1:00:32", "remaining_time": "0:46:29"}
+{"current_steps": 785, "total_steps": 1379, "loss": 0.2859, "lr": 1.8709831011013678e-05, "epoch": 3.984771573604061, "percentage": 56.93, "elapsed_time": "1:00:53", "remaining_time": "0:46:04"}
+{"current_steps": 790, "total_steps": 1379, "loss": 0.3028, "lr": 1.8457318283646814e-05, "epoch": 4.01015228426396, "percentage": 57.29, "elapsed_time": "1:01:24", "remaining_time": "0:45:46"}
+{"current_steps": 795, "total_steps": 1379, "loss": 0.2866, "lr": 1.8205052709757263e-05, "epoch": 4.035532994923858, "percentage": 57.65, "elapsed_time": "1:01:45", "remaining_time": "0:45:22"}
+{"current_steps": 800, "total_steps": 1379, "loss": 0.288, "lr": 1.79530747048845e-05, "epoch": 4.060913705583756, "percentage": 58.01, "elapsed_time": "1:02:09", "remaining_time": "0:44:59"}
+{"current_steps": 805, "total_steps": 1379, "loss": 0.2697, "lr": 1.7701424638496473e-05, "epoch": 4.086294416243655, "percentage": 58.38, "elapsed_time": "1:02:36", "remaining_time": "0:44:38"}
+{"current_steps": 810, "total_steps": 1379, "loss": 0.2927, "lr": 1.7450142827522027e-05, "epoch": 4.111675126903553, "percentage": 58.74, "elapsed_time": "1:02:54", "remaining_time": "0:44:11"}
+{"current_steps": 815, "total_steps": 1379, "loss": 0.2745, "lr": 1.719926952989169e-05, "epoch": 4.137055837563452, "percentage": 59.1, "elapsed_time": "1:03:14", "remaining_time": "0:43:46"}
+{"current_steps": 820, "total_steps": 1379, "loss": 0.2827, "lr": 1.694884493808795e-05, "epoch": 4.16243654822335, "percentage": 59.46, "elapsed_time": "1:03:32", "remaining_time": "0:43:19"}
+{"current_steps": 825, "total_steps": 1379, "loss": 0.2767, "lr": 1.6698909172706e-05, "epoch": 4.187817258883249, "percentage": 59.83, "elapsed_time": "1:03:52", "remaining_time": "0:42:53"}
+{"current_steps": 830, "total_steps": 1379, "loss": 0.2829, "lr": 1.644950227602605e-05, "epoch": 4.213197969543147, "percentage": 60.19, "elapsed_time": "1:04:10", "remaining_time": "0:42:26"}
+{"current_steps": 835, "total_steps": 1379, "loss": 0.2632, "lr": 1.620066420559805e-05, "epoch": 4.238578680203045, "percentage": 60.55, "elapsed_time": "1:04:31", "remaining_time": "0:42:02"}
+{"current_steps": 840, "total_steps": 1379, "loss": 0.2929, "lr": 1.5952434827840187e-05, "epoch": 4.2639593908629445, "percentage": 60.91, "elapsed_time": "1:04:50", "remaining_time": "0:41:36"}
+{"current_steps": 845, "total_steps": 1379, "loss": 0.2714, "lr": 1.5704853911651777e-05, "epoch": 4.289340101522843, "percentage": 61.28, "elapsed_time": "1:05:17", "remaining_time": "0:41:15"}
+{"current_steps": 850, "total_steps": 1379, "loss": 0.2672, "lr": 1.545796112204196e-05, "epoch": 4.314720812182741, "percentage": 61.64, "elapsed_time": "1:05:39", "remaining_time": "0:40:51"}
+{"current_steps": 855, "total_steps": 1379, "loss": 0.2767, "lr": 1.5211796013774893e-05, "epoch": 4.340101522842639, "percentage": 62.0, "elapsed_time": "1:05:59", "remaining_time": "0:40:26"}
+{"current_steps": 860, "total_steps": 1379, "loss": 0.2864, "lr": 1.4966398025032706e-05, "epoch": 4.365482233502538, "percentage": 62.36, "elapsed_time": "1:06:20", "remaining_time": "0:40:02"}
+{"current_steps": 865, "total_steps": 1379, "loss": 0.2711, "lr": 1.4721806471097104e-05, "epoch": 4.3908629441624365, "percentage": 62.73, "elapsed_time": "1:06:43", "remaining_time": "0:39:39"}
+{"current_steps": 870, "total_steps": 1379, "loss": 0.3041, "lr": 1.4478060538050622e-05, "epoch": 4.416243654822335, "percentage": 63.09, "elapsed_time": "1:07:03", "remaining_time": "0:39:13"}
+{"current_steps": 875, "total_steps": 1379, "loss": 0.2762, "lr": 1.4235199276498652e-05, "epoch": 4.441624365482234, "percentage": 63.45, "elapsed_time": "1:07:25", "remaining_time": "0:38:50"}
+{"current_steps": 880, "total_steps": 1379, "loss": 0.2726, "lr": 1.3993261595313094e-05, "epoch": 4.467005076142132, "percentage": 63.81, "elapsed_time": "1:07:49", "remaining_time": "0:38:27"}
+{"current_steps": 885, "total_steps": 1379, "loss": 0.2927, "lr": 1.3752286255398794e-05, "epoch": 4.49238578680203, "percentage": 64.18, "elapsed_time": "1:08:13", "remaining_time": "0:38:05"}
+{"current_steps": 890, "total_steps": 1379, "loss": 0.2886, "lr": 1.3512311863483606e-05, "epoch": 4.517766497461929, "percentage": 64.54, "elapsed_time": "1:08:37", "remaining_time": "0:37:42"}
+{"current_steps": 895, "total_steps": 1379, "loss": 0.2746, "lr": 1.3273376865933236e-05, "epoch": 4.543147208121828, "percentage": 64.9, "elapsed_time": "1:09:02", "remaining_time": "0:37:19"}
+{"current_steps": 900, "total_steps": 1379, "loss": 0.263, "lr": 1.303551954259172e-05, "epoch": 4.568527918781726, "percentage": 65.26, "elapsed_time": "1:09:23", "remaining_time": "0:36:56"}
+{"current_steps": 905, "total_steps": 1379, "loss": 0.305, "lr": 1.2798778000648602e-05, "epoch": 4.593908629441624, "percentage": 65.63, "elapsed_time": "1:09:47", "remaining_time": "0:36:33"}
+{"current_steps": 910, "total_steps": 1379, "loss": 0.2869, "lr": 1.2563190168533766e-05, "epoch": 4.619289340101523, "percentage": 65.99, "elapsed_time": "1:10:07", "remaining_time": "0:36:08"}
+{"current_steps": 915, "total_steps": 1379, "loss": 0.2811, "lr": 1.2328793789840926e-05, "epoch": 4.644670050761421, "percentage": 66.35, "elapsed_time": "1:10:33", "remaining_time": "0:35:46"}
+{"current_steps": 920, "total_steps": 1379, "loss": 0.2464, "lr": 1.2095626417280686e-05, "epoch": 4.67005076142132, "percentage": 66.72, "elapsed_time": "1:10:55", "remaining_time": "0:35:22"}
+{"current_steps": 925, "total_steps": 1379, "loss": 0.2708, "lr": 1.1863725406664241e-05, "epoch": 4.695431472081218, "percentage": 67.08, "elapsed_time": "1:11:29", "remaining_time": "0:35:05"}
+{"current_steps": 930, "total_steps": 1379, "loss": 0.276, "lr": 1.163312791091858e-05, "epoch": 4.720812182741117, "percentage": 67.44, "elapsed_time": "1:11:51", "remaining_time": "0:34:41"}
+{"current_steps": 935, "total_steps": 1379, "loss": 0.2969, "lr": 1.1403870874134192e-05, "epoch": 4.746192893401015, "percentage": 67.8, "elapsed_time": "1:12:13", "remaining_time": "0:34:17"}
+{"current_steps": 940, "total_steps": 1379, "loss": 0.2586, "lr": 1.1175991025646267e-05, "epoch": 4.771573604060913, "percentage": 68.17, "elapsed_time": "1:12:38", "remaining_time": "0:33:55"}
+{"current_steps": 945, "total_steps": 1379, "loss": 0.2818, "lr": 1.0949524874150246e-05, "epoch": 4.7969543147208125, "percentage": 68.53, "elapsed_time": "1:13:01", "remaining_time": "0:33:32"}
+{"current_steps": 950, "total_steps": 1379, "loss": 0.2645, "lr": 1.0724508701852807e-05, "epoch": 4.822335025380711, "percentage": 68.89, "elapsed_time": "1:13:30", "remaining_time": "0:33:11"}
+{"current_steps": 955, "total_steps": 1379, "loss": 0.2732, "lr": 1.0500978558659001e-05, "epoch": 4.847715736040609, "percentage": 69.25, "elapsed_time": "1:13:51", "remaining_time": "0:32:47"}
+{"current_steps": 960, "total_steps": 1379, "loss": 0.2978, "lr": 1.0278970256396764e-05, "epoch": 4.873096446700508, "percentage": 69.62, "elapsed_time": "1:14:10", "remaining_time": "0:32:22"}
+{"current_steps": 965, "total_steps": 1379, "loss": 0.29, "lr": 1.0058519363079464e-05, "epoch": 4.898477157360406, "percentage": 69.98, "elapsed_time": "1:14:35", "remaining_time": "0:32:00"}
+{"current_steps": 970, "total_steps": 1379, "loss": 0.2863, "lr": 9.839661197207527e-06, "epoch": 4.9238578680203045, "percentage": 70.34, "elapsed_time": "1:14:59", "remaining_time": "0:31:37"}
+{"current_steps": 975, "total_steps": 1379, "loss": 0.306, "lr": 9.622430822110063e-06, "epoch": 4.949238578680203, "percentage": 70.7, "elapsed_time": "1:15:16", "remaining_time": "0:31:11"}
+{"current_steps": 980, "total_steps": 1379, "loss": 0.2732, "lr": 9.40686304032735e-06, "epoch": 4.974619289340102, "percentage": 71.07, "elapsed_time": "1:15:38", "remaining_time": "0:30:47"}
+{"current_steps": 985, "total_steps": 1379, "loss": 0.2712, "lr": 9.19299238803515e-06, "epoch": 5.0, "percentage": 71.43, "elapsed_time": "1:16:03", "remaining_time": "0:30:25"}
+{"current_steps": 990, "total_steps": 1379, "loss": 0.2557, "lr": 8.980853129511584e-06, "epoch": 5.025380710659898, "percentage": 71.79, "elapsed_time": "1:16:28", "remaining_time": "0:30:03"}
+{"current_steps": 995, "total_steps": 1379, "loss": 0.2549, "lr": 8.770479251647708e-06, "epoch": 5.050761421319797, "percentage": 72.15, "elapsed_time": "1:16:49", "remaining_time": "0:29:38"}
+{"current_steps": 1000, "total_steps": 1379, "loss": 0.2553, "lr": 8.561904458502424e-06, "epoch": 5.0761421319796955, "percentage": 72.52, "elapsed_time": "1:17:11", "remaining_time": "0:29:15"}
+{"current_steps": 1005, "total_steps": 1379, "loss": 0.2701, "lr": 8.355162165902785e-06, "epoch": 5.101522842639594, "percentage": 72.88, "elapsed_time": "1:17:35", "remaining_time": "0:28:52"}
+{"current_steps": 1010, "total_steps": 1379, "loss": 0.2546, "lr": 8.150285496090388e-06, "epoch": 5.126903553299492, "percentage": 73.24, "elapsed_time": "1:17:55", "remaining_time": "0:28:28"}
+{"current_steps": 1015, "total_steps": 1379, "loss": 0.2666, "lr": 7.947307272414874e-06, "epoch": 5.152284263959391, "percentage": 73.6, "elapsed_time": "1:18:14", "remaining_time": "0:28:03"}
+{"current_steps": 1020, "total_steps": 1379, "loss": 0.2658, "lr": 7.746260014075293e-06, "epoch": 5.177664974619289, "percentage": 73.97, "elapsed_time": "1:18:34", "remaining_time": "0:27:39"}
+{"current_steps": 1025, "total_steps": 1379, "loss": 0.2772, "lr": 7.547175930910187e-06, "epoch": 5.2030456852791875, "percentage": 74.33, "elapsed_time": "1:19:03", "remaining_time": "0:27:18"}
+{"current_steps": 1030, "total_steps": 1379, "loss": 0.2441, "lr": 7.350086918237238e-06, "epoch": 5.228426395939087, "percentage": 74.69, "elapsed_time": "1:19:24", "remaining_time": "0:26:54"}
+{"current_steps": 1035, "total_steps": 1379, "loss": 0.2669, "lr": 7.155024551743317e-06, "epoch": 5.253807106598985, "percentage": 75.05, "elapsed_time": "1:19:45", "remaining_time": "0:26:30"}
+{"current_steps": 1040, "total_steps": 1379, "loss": 0.2456, "lr": 6.962020082425749e-06, "epoch": 5.279187817258883, "percentage": 75.42, "elapsed_time": "1:20:17", "remaining_time": "0:26:10"}
+{"current_steps": 1045, "total_steps": 1379, "loss": 0.2519, "lr": 6.771104431585551e-06, "epoch": 5.304568527918782, "percentage": 75.78, "elapsed_time": "1:20:46", "remaining_time": "0:25:49"}
+{"current_steps": 1050, "total_steps": 1379, "loss": 0.2748, "lr": 6.582308185873536e-06, "epoch": 5.32994923857868, "percentage": 76.14, "elapsed_time": "1:21:05", "remaining_time": "0:25:24"}
+{"current_steps": 1055, "total_steps": 1379, "loss": 0.2582, "lr": 6.3956615923900214e-06, "epoch": 5.355329949238579, "percentage": 76.5, "elapsed_time": "1:21:29", "remaining_time": "0:25:01"}
+{"current_steps": 1060, "total_steps": 1379, "loss": 0.2501, "lr": 6.211194553838931e-06, "epoch": 5.380710659898477, "percentage": 76.87, "elapsed_time": "1:21:55", "remaining_time": "0:24:39"}
+{"current_steps": 1065, "total_steps": 1379, "loss": 0.2543, "lr": 6.028936623737067e-06, "epoch": 5.406091370558376, "percentage": 77.23, "elapsed_time": "1:22:18", "remaining_time": "0:24:16"}
+{"current_steps": 1070, "total_steps": 1379, "loss": 0.2579, "lr": 5.848917001679339e-06, "epoch": 5.431472081218274, "percentage": 77.59, "elapsed_time": "1:22:37", "remaining_time": "0:23:51"}
+{"current_steps": 1075, "total_steps": 1379, "loss": 0.2572, "lr": 5.671164528660687e-06, "epoch": 5.456852791878172, "percentage": 77.96, "elapsed_time": "1:22:58", "remaining_time": "0:23:27"}
+{"current_steps": 1080, "total_steps": 1379, "loss": 0.2573, "lr": 5.495707682455464e-06, "epoch": 5.482233502538071, "percentage": 78.32, "elapsed_time": "1:23:17", "remaining_time": "0:23:03"}
+{"current_steps": 1085, "total_steps": 1379, "loss": 0.247, "lr": 5.322574573054991e-06, "epoch": 5.50761421319797, "percentage": 78.68, "elapsed_time": "1:23:42", "remaining_time": "0:22:40"}
+{"current_steps": 1090, "total_steps": 1379, "loss": 0.2527, "lr": 5.151792938164051e-06, "epoch": 5.532994923857868, "percentage": 79.04, "elapsed_time": "1:24:05", "remaining_time": "0:22:17"}
+{"current_steps": 1095, "total_steps": 1379, "loss": 0.249, "lr": 4.983390138757027e-06, "epoch": 5.558375634517766, "percentage": 79.41, "elapsed_time": "1:24:32", "remaining_time": "0:21:55"}
+{"current_steps": 1100, "total_steps": 1379, "loss": 0.2634, "lr": 4.817393154694399e-06, "epoch": 5.583756345177665, "percentage": 79.77, "elapsed_time": "1:24:52", "remaining_time": "0:21:31"}
+{"current_steps": 1105, "total_steps": 1379, "loss": 0.2325, "lr": 4.653828580400275e-06, "epoch": 5.6091370558375635, "percentage": 80.13, "elapsed_time": "1:25:12", "remaining_time": "0:21:07"}
+{"current_steps": 1110, "total_steps": 1379, "loss": 0.2703, "lr": 4.4927226206017e-06, "epoch": 5.634517766497462, "percentage": 80.49, "elapsed_time": "1:25:33", "remaining_time": "0:20:44"}
+{"current_steps": 1115, "total_steps": 1379, "loss": 0.2426, "lr": 4.334101086130409e-06, "epoch": 5.659898477157361, "percentage": 80.86, "elapsed_time": "1:26:00", "remaining_time": "0:20:21"}
+{"current_steps": 1120, "total_steps": 1379, "loss": 0.2505, "lr": 4.177989389787625e-06, "epoch": 5.685279187817259, "percentage": 81.22, "elapsed_time": "1:26:20", "remaining_time": "0:19:57"}
+{"current_steps": 1125, "total_steps": 1379, "loss": 0.249, "lr": 4.024412542272706e-06, "epoch": 5.710659898477157, "percentage": 81.58, "elapsed_time": "1:26:39", "remaining_time": "0:19:33"}
+{"current_steps": 1130, "total_steps": 1379, "loss": 0.2659, "lr": 3.873395148176135e-06, "epoch": 5.7360406091370555, "percentage": 81.94, "elapsed_time": "1:27:01", "remaining_time": "0:19:10"}
+{"current_steps": 1135, "total_steps": 1379, "loss": 0.2473, "lr": 3.724961402037661e-06, "epoch": 5.761421319796955, "percentage": 82.31, "elapsed_time": "1:27:20", "remaining_time": "0:18:46"}
+{"current_steps": 1140, "total_steps": 1379, "loss": 0.2448, "lr": 3.57913508447004e-06, "epoch": 5.786802030456853, "percentage": 82.67, "elapsed_time": "1:27:43", "remaining_time": "0:18:23"}
+{"current_steps": 1145, "total_steps": 1379, "loss": 0.2441, "lr": 3.4359395583491594e-06, "epoch": 5.812182741116751, "percentage": 83.03, "elapsed_time": "1:28:12", "remaining_time": "0:18:01"}
+{"current_steps": 1150, "total_steps": 1379, "loss": 0.2606, "lr": 3.2953977650710513e-06, "epoch": 5.837563451776649, "percentage": 83.39, "elapsed_time": "1:28:30", "remaining_time": "0:17:37"}
+{"current_steps": 1155, "total_steps": 1379, "loss": 0.246, "lr": 3.1575322208764714e-06, "epoch": 5.862944162436548, "percentage": 83.76, "elapsed_time": "1:28:50", "remaining_time": "0:17:13"}
+{"current_steps": 1160, "total_steps": 1379, "loss": 0.2597, "lr": 3.0223650132435335e-06, "epoch": 5.888324873096447, "percentage": 84.12, "elapsed_time": "1:29:17", "remaining_time": "0:16:51"}
+{"current_steps": 1165, "total_steps": 1379, "loss": 0.2564, "lr": 2.8899177973490734e-06, "epoch": 5.913705583756345, "percentage": 84.48, "elapsed_time": "1:29:39", "remaining_time": "0:16:28"}
+{"current_steps": 1170, "total_steps": 1379, "loss": 0.2538, "lr": 2.7602117925992964e-06, "epoch": 5.939086294416244, "percentage": 84.84, "elapsed_time": "1:30:07", "remaining_time": "0:16:05"}
+{"current_steps": 1175, "total_steps": 1379, "loss": 0.234, "lr": 2.6332677792301773e-06, "epoch": 5.964467005076142, "percentage": 85.21, "elapsed_time": "1:30:27", "remaining_time": "0:15:42"}
+{"current_steps": 1180, "total_steps": 1379, "loss": 0.2542, "lr": 2.5091060949782664e-06, "epoch": 5.98984771573604, "percentage": 85.57, "elapsed_time": "1:30:49", "remaining_time": "0:15:18"}
+{"current_steps": 1185, "total_steps": 1379, "loss": 0.2437, "lr": 2.3877466318223698e-06, "epoch": 6.0152284263959395, "percentage": 85.93, "elapsed_time": "1:31:08", "remaining_time": "0:14:55"}
+{"current_steps": 1190, "total_steps": 1379, "loss": 0.2396, "lr": 2.2692088327966655e-06, "epoch": 6.040609137055838, "percentage": 86.29, "elapsed_time": "1:31:28", "remaining_time": "0:14:31"}
+{"current_steps": 1195, "total_steps": 1379, "loss": 0.2258, "lr": 2.153511688875707e-06, "epoch": 6.065989847715736, "percentage": 86.66, "elapsed_time": "1:31:50", "remaining_time": "0:14:08"}
+{"current_steps": 1200, "total_steps": 1379, "loss": 0.2629, "lr": 2.0406737359318797e-06, "epoch": 6.091370558375634, "percentage": 87.02, "elapsed_time": "1:32:10", "remaining_time": "0:13:45"}
+{"current_steps": 1205, "total_steps": 1379, "loss": 0.2483, "lr": 1.930713051765776e-06, "epoch": 6.116751269035533, "percentage": 87.38, "elapsed_time": "1:32:30", "remaining_time": "0:13:21"}
+{"current_steps": 1210, "total_steps": 1379, "loss": 0.2653, "lr": 1.8236472532099413e-06, "epoch": 6.1421319796954315, "percentage": 87.74, "elapsed_time": "1:32:51", "remaining_time": "0:12:58"}
+{"current_steps": 1215, "total_steps": 1379, "loss": 0.2467, "lr": 1.7194934933064654e-06, "epoch": 6.16751269035533, "percentage": 88.11, "elapsed_time": "1:33:18", "remaining_time": "0:12:35"}
+{"current_steps": 1220, "total_steps": 1379, "loss": 0.2391, "lr": 1.6182684585588981e-06, "epoch": 6.192893401015229, "percentage": 88.47, "elapsed_time": "1:33:43", "remaining_time": "0:12:12"}
+{"current_steps": 1225, "total_steps": 1379, "loss": 0.2351, "lr": 1.5199883662588954e-06, "epoch": 6.218274111675127, "percentage": 88.83, "elapsed_time": "1:34:01", "remaining_time": "0:11:49"}
+{"current_steps": 1230, "total_steps": 1379, "loss": 0.2509, "lr": 1.4246689618880472e-06, "epoch": 6.243654822335025, "percentage": 89.2, "elapsed_time": "1:34:26", "remaining_time": "0:11:26"}
+{"current_steps": 1235, "total_steps": 1379, "loss": 0.2452, "lr": 1.3323255165952875e-06, "epoch": 6.269035532994923, "percentage": 89.56, "elapsed_time": "1:34:53", "remaining_time": "0:11:03"}
+{"current_steps": 1240, "total_steps": 1379, "loss": 0.2372, "lr": 1.2429728247502926e-06, "epoch": 6.2944162436548226, "percentage": 89.92, "elapsed_time": "1:35:16", "remaining_time": "0:10:40"}
+{"current_steps": 1245, "total_steps": 1379, "loss": 0.2529, "lr": 1.156625201573287e-06, "epoch": 6.319796954314721, "percentage": 90.28, "elapsed_time": "1:35:42", "remaining_time": "0:10:18"}
+{"current_steps": 1250, "total_steps": 1379, "loss": 0.2599, "lr": 1.0732964808415792e-06, "epoch": 6.345177664974619, "percentage": 90.65, "elapsed_time": "1:36:03", "remaining_time": "0:09:54"}
+{"current_steps": 1255, "total_steps": 1379, "loss": 0.228, "lr": 9.93000012673262e-07, "epoch": 6.370558375634518, "percentage": 91.01, "elapsed_time": "1:36:26", "remaining_time": "0:09:31"}
+{"current_steps": 1260, "total_steps": 1379, "loss": 0.2437, "lr": 9.157486613883759e-07, "epoch": 6.395939086294416, "percentage": 91.37, "elapsed_time": "1:36:45", "remaining_time": "0:09:08"}
+{"current_steps": 1265, "total_steps": 1379, "loss": 0.255, "lr": 8.415548034479215e-07, "epoch": 6.4213197969543145, "percentage": 91.73, "elapsed_time": "1:37:02", "remaining_time": "0:08:44"}
+{"current_steps": 1270, "total_steps": 1379, "loss": 0.2317, "lr": 7.704303254710188e-07, "epoch": 6.446700507614214, "percentage": 92.1, "elapsed_time": "1:37:24", "remaining_time": "0:08:21"}
+{"current_steps": 1275, "total_steps": 1379, "loss": 0.2469, "lr": 7.023866223305487e-07, "epoch": 6.472081218274112, "percentage": 92.46, "elapsed_time": "1:37:42", "remaining_time": "0:07:58"}
+{"current_steps": 1280, "total_steps": 1379, "loss": 0.2456, "lr": 6.374345953275773e-07, "epoch": 6.49746192893401, "percentage": 92.82, "elapsed_time": "1:38:04", "remaining_time": "0:07:35"}
+{"current_steps": 1285, "total_steps": 1379, "loss": 0.2371, "lr": 5.755846504448604e-07, "epoch": 6.522842639593908, "percentage": 93.18, "elapsed_time": "1:38:24", "remaining_time": "0:07:11"}
+{"current_steps": 1290, "total_steps": 1379, "loss": 0.2582, "lr": 5.16846696679687e-07, "epoch": 6.548223350253807, "percentage": 93.55, "elapsed_time": "1:38:47", "remaining_time": "0:06:48"}
+{"current_steps": 1295, "total_steps": 1379, "loss": 0.2443, "lr": 4.6123014445636605e-07, "epoch": 6.573604060913706, "percentage": 93.91, "elapsed_time": "1:39:11", "remaining_time": "0:06:26"}
+{"current_steps": 1300, "total_steps": 1379, "loss": 0.2393, "lr": 4.087439041185781e-07, "epoch": 6.598984771573604, "percentage": 94.27, "elapsed_time": "1:39:36", "remaining_time": "0:06:03"}
+{"current_steps": 1305, "total_steps": 1379, "loss": 0.2574, "lr": 3.5939638450183776e-07, "epoch": 6.624365482233502, "percentage": 94.63, "elapsed_time": "1:40:01", "remaining_time": "0:05:40"}
+{"current_steps": 1310, "total_steps": 1379, "loss": 0.2342, "lr": 3.1319549158632444e-07, "epoch": 6.649746192893401, "percentage": 95.0, "elapsed_time": "1:40:19", "remaining_time": "0:05:17"}
+{"current_steps": 1315, "total_steps": 1379, "loss": 0.2364, "lr": 2.701486272302534e-07, "epoch": 6.675126903553299, "percentage": 95.36, "elapsed_time": "1:40:42", "remaining_time": "0:04:54"}
+{"current_steps": 1320, "total_steps": 1379, "loss": 0.2565, "lr": 2.302626879840353e-07, "epoch": 6.700507614213198, "percentage": 95.72, "elapsed_time": "1:41:04", "remaining_time": "0:04:31"}
+{"current_steps": 1325, "total_steps": 1379, "loss": 0.2309, "lr": 1.9354406398535363e-07, "epoch": 6.725888324873097, "percentage": 96.08, "elapsed_time": "1:41:31", "remaining_time": "0:04:08"}
+{"current_steps": 1330, "total_steps": 1379, "loss": 0.2524, "lr": 1.599986379354257e-07, "epoch": 6.751269035532995, "percentage": 96.45, "elapsed_time": "1:41:54", "remaining_time": "0:03:45"}
+{"current_steps": 1335, "total_steps": 1379, "loss": 0.2246, "lr": 1.29631784156512e-07, "epoch": 6.776649746192893, "percentage": 96.81, "elapsed_time": "1:42:15", "remaining_time": "0:03:22"}
+{"current_steps": 1340, "total_steps": 1379, "loss": 0.2299, "lr": 1.0244836773091182e-07, "epoch": 6.802030456852792, "percentage": 97.17, "elapsed_time": "1:42:41", "remaining_time": "0:02:59"}
+{"current_steps": 1345, "total_steps": 1379, "loss": 0.2366, "lr": 7.845274372151767e-08, "epoch": 6.8274111675126905, "percentage": 97.53, "elapsed_time": "1:43:05", "remaining_time": "0:02:36"}
+{"current_steps": 1350, "total_steps": 1379, "loss": 0.2389, "lr": 5.7648756474084636e-08, "epoch": 6.852791878172589, "percentage": 97.9, "elapsed_time": "1:43:25", "remaining_time": "0:02:13"}
+{"current_steps": 1355, "total_steps": 1379, "loss": 0.2403, "lr": 4.003973900133851e-08, "epoch": 6.878172588832487, "percentage": 98.26, "elapsed_time": "1:43:52", "remaining_time": "0:01:50"}
+{"current_steps": 1360, "total_steps": 1379, "loss": 0.2497, "lr": 2.5628512448987453e-08, "epoch": 6.903553299492386, "percentage": 98.62, "elapsed_time": "1:44:10", "remaining_time": "0:01:27"}
+{"current_steps": 1365, "total_steps": 1379, "loss": 0.2481, "lr": 1.4417385643741289e-08, "epoch": 6.928934010152284, "percentage": 98.98, "elapsed_time": "1:44:37", "remaining_time": "0:01:04"}
+{"current_steps": 1370, "total_steps": 1379, "loss": 0.2395, "lr": 6.408154723420712e-09, "epoch": 6.9543147208121825, "percentage": 99.35, "elapsed_time": "1:44:58", "remaining_time": "0:00:41"}
+{"current_steps": 1375, "total_steps": 1379, "loss": 0.2374, "lr": 1.6021028491941538e-09, "epoch": 6.979695431472082, "percentage": 99.71, "elapsed_time": "1:45:17", "remaining_time": "0:00:18"}
+{"current_steps": 1379, "total_steps": 1379, "epoch": 7.0, "percentage": 100.0, "elapsed_time": "1:46:12", "remaining_time": "0:00:00"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a92d334f0f0e666f4ea1062428472fe45921f2dddc8e71a473f3dce3da03cea
+size 8657