Training in progress, step 1500

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

chat_template.jinja

@@ -0,0 +1,89 @@
+{%- if tools %}
+    {{- '<|im_start|>system\n' }}
+    {%- if messages[0].role == 'system' %}
+        {{- messages[0].content + '\n\n' }}
+    {%- endif %}
+    {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
+    {%- for tool in tools %}
+        {{- "\n" }}
+        {{- tool | tojson }}
+    {%- endfor %}
+    {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
+{%- else %}
+    {%- if messages[0].role == 'system' %}
+        {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }}
+    {%- endif %}
+{%- endif %}
+{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
+{%- for message in messages[::-1] %}
+    {%- set index = (messages|length - 1) - loop.index0 %}
+    {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}
+        {%- set ns.multi_step_tool = false %}
+        {%- set ns.last_query_index = index %}
+    {%- endif %}
+{%- endfor %}
+{%- for message in messages %}
+    {%- if message.content is string %}
+        {%- set content = message.content %}
+    {%- else %}
+        {%- set content = '' %}
+    {%- endif %}
+    {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
+        {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
+    {%- elif message.role == "assistant" %}
+        {%- set reasoning_content = '' %}
+        {%- if message.reasoning_content is string %}
+            {%- set reasoning_content = message.reasoning_content %}
+        {%- else %}
+            {%- if '</think>' in content %}
+                {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
+                {%- set content = content.split('</think>')[-1].lstrip('\n') %}
+            {%- endif %}
+        {%- endif %}
+        {%- if loop.index0 > ns.last_query_index %}
+            {%- if loop.last or (not loop.last and reasoning_content) %}
+                {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
+            {%- else %}
+                {{- '<|im_start|>' + message.role + '\n' + content }}
+            {%- endif %}
+        {%- else %}
+            {{- '<|im_start|>' + message.role + '\n' + content }}
+        {%- endif %}
+        {%- if message.tool_calls %}
+            {%- for tool_call in message.tool_calls %}
+                {%- if (loop.first and content) or (not loop.first) %}
+                    {{- '\n' }}
+                {%- endif %}
+                {%- if tool_call.function %}
+                    {%- set tool_call = tool_call.function %}
+                {%- endif %}
+                {{- '<tool_call>\n{"name": "' }}
+                {{- tool_call.name }}
+                {{- '", "arguments": ' }}
+                {%- if tool_call.arguments is string %}
+                    {{- tool_call.arguments }}
+                {%- else %}
+                    {{- tool_call.arguments | tojson }}
+                {%- endif %}
+                {{- '}\n</tool_call>' }}
+            {%- endfor %}
+        {%- endif %}
+        {{- '<|im_end|>\n' }}
+    {%- elif message.role == "tool" %}
+        {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
+            {{- '<|im_start|>user' }}
+        {%- endif %}
+        {{- '\n<tool_response>\n' }}
+        {{- content }}
+        {{- '\n</tool_response>' }}
+        {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
+            {{- '<|im_end|>\n' }}
+        {%- endif %}
+    {%- endif %}
+{%- endfor %}
+{%- if add_generation_prompt %}
+    {{- '<|im_start|>assistant\n' }}
+    {%- if enable_thinking is defined and enable_thinking is false %}
+        {{- '<think>\n\n</think>\n\n' }}
+    {%- endif %}
+{%- endif %}

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.3",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

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

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f71dae96f07ec0085786ec5b188b65f019615bec241f3415aa92b714a1104ab8
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9ca692b8666b35473a60f821183a0d356325b88fe5ca3fe41518676337372286
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:482056f801db513dec5edcd23d2acfc48edb5cb1f50c2b7be59ab32a91275741
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:78ff3c79834fa0f244068476a7a025b9208376f03fe14ea0d400ae99f661cdae
+size 1580230264

model.safetensors.index.json

@@ -0,0 +1,407 @@
+{
+  "metadata": {
+    "total_parameters": 308224,
+    "total_size": 16381470720
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

run_summary.json

@@ -0,0 +1,12 @@
+{
+  "agent_name": "terminus-2",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "DCAgent/exp_tas_timeout_multiplier_1.0_traces",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/exp_tas_timeout_multiplier_1_0_traces/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_exp_tas_timeout_multiplier_1-0_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 +1,311 @@
+{"current_steps": 5, "total_steps": 4368, "loss": 0.9655, "lr": 3.661327231121282e-07, "epoch": 0.008012820512820512, "percentage": 0.11, "elapsed_time": "0:00:43", "remaining_time": "10:33:09"}
+{"current_steps": 10, "total_steps": 4368, "loss": 0.9567, "lr": 8.237986270022884e-07, "epoch": 0.016025641025641024, "percentage": 0.23, "elapsed_time": "0:01:19", "remaining_time": "9:35:01"}
+{"current_steps": 15, "total_steps": 4368, "loss": 0.9797, "lr": 1.2814645308924487e-06, "epoch": 0.02403846153846154, "percentage": 0.34, "elapsed_time": "0:01:56", "remaining_time": "9:24:31"}
+{"current_steps": 20, "total_steps": 4368, "loss": 0.9819, "lr": 1.7391304347826088e-06, "epoch": 0.03205128205128205, "percentage": 0.46, "elapsed_time": "0:02:34", "remaining_time": "9:21:28"}
+{"current_steps": 25, "total_steps": 4368, "loss": 0.943, "lr": 2.196796338672769e-06, "epoch": 0.04006410256410257, "percentage": 0.57, "elapsed_time": "0:03:06", "remaining_time": "8:58:40"}
+{"current_steps": 30, "total_steps": 4368, "loss": 0.894, "lr": 2.654462242562929e-06, "epoch": 0.04807692307692308, "percentage": 0.69, "elapsed_time": "0:03:37", "remaining_time": "8:45:05"}
+{"current_steps": 35, "total_steps": 4368, "loss": 0.898, "lr": 3.1121281464530894e-06, "epoch": 0.05608974358974359, "percentage": 0.8, "elapsed_time": "0:04:14", "remaining_time": "8:44:15"}
+{"current_steps": 40, "total_steps": 4368, "loss": 0.8348, "lr": 3.56979405034325e-06, "epoch": 0.0641025641025641, "percentage": 0.92, "elapsed_time": "0:04:48", "remaining_time": "8:40:55"}
+{"current_steps": 45, "total_steps": 4368, "loss": 0.8442, "lr": 4.0274599542334094e-06, "epoch": 0.07211538461538461, "percentage": 1.03, "elapsed_time": "0:05:36", "remaining_time": "8:58:35"}
+{"current_steps": 50, "total_steps": 4368, "loss": 0.8109, "lr": 4.48512585812357e-06, "epoch": 0.08012820512820513, "percentage": 1.14, "elapsed_time": "0:06:09", "remaining_time": "8:51:42"}
+{"current_steps": 55, "total_steps": 4368, "loss": 0.8115, "lr": 4.94279176201373e-06, "epoch": 0.08814102564102565, "percentage": 1.26, "elapsed_time": "0:06:49", "remaining_time": "8:55:32"}
+{"current_steps": 60, "total_steps": 4368, "loss": 0.7536, "lr": 5.400457665903891e-06, "epoch": 0.09615384615384616, "percentage": 1.37, "elapsed_time": "0:07:29", "remaining_time": "8:57:54"}
+{"current_steps": 65, "total_steps": 4368, "loss": 0.7537, "lr": 5.858123569794051e-06, "epoch": 0.10416666666666667, "percentage": 1.49, "elapsed_time": "0:08:05", "remaining_time": "8:55:56"}
+{"current_steps": 70, "total_steps": 4368, "loss": 0.7417, "lr": 6.31578947368421e-06, "epoch": 0.11217948717948718, "percentage": 1.6, "elapsed_time": "0:08:45", "remaining_time": "8:57:34"}
+{"current_steps": 75, "total_steps": 4368, "loss": 0.7748, "lr": 6.773455377574372e-06, "epoch": 0.1201923076923077, "percentage": 1.72, "elapsed_time": "0:09:24", "remaining_time": "8:58:47"}
+{"current_steps": 80, "total_steps": 4368, "loss": 0.7666, "lr": 7.231121281464531e-06, "epoch": 0.1282051282051282, "percentage": 1.83, "elapsed_time": "0:10:03", "remaining_time": "8:59:23"}
+{"current_steps": 85, "total_steps": 4368, "loss": 0.6723, "lr": 7.688787185354691e-06, "epoch": 0.1362179487179487, "percentage": 1.95, "elapsed_time": "0:10:46", "remaining_time": "9:02:57"}
+{"current_steps": 90, "total_steps": 4368, "loss": 0.7063, "lr": 8.146453089244852e-06, "epoch": 0.14423076923076922, "percentage": 2.06, "elapsed_time": "0:11:19", "remaining_time": "8:58:35"}
+{"current_steps": 95, "total_steps": 4368, "loss": 0.7005, "lr": 8.604118993135013e-06, "epoch": 0.15224358974358973, "percentage": 2.17, "elapsed_time": "0:11:50", "remaining_time": "8:52:22"}
+{"current_steps": 100, "total_steps": 4368, "loss": 0.6994, "lr": 9.061784897025172e-06, "epoch": 0.16025641025641027, "percentage": 2.29, "elapsed_time": "0:12:23", "remaining_time": "8:49:08"}
+{"current_steps": 105, "total_steps": 4368, "loss": 0.7064, "lr": 9.519450800915333e-06, "epoch": 0.16826923076923078, "percentage": 2.4, "elapsed_time": "0:12:58", "remaining_time": "8:46:28"}
+{"current_steps": 110, "total_steps": 4368, "loss": 0.6694, "lr": 9.977116704805492e-06, "epoch": 0.1762820512820513, "percentage": 2.52, "elapsed_time": "0:13:42", "remaining_time": "8:50:29"}
+{"current_steps": 115, "total_steps": 4368, "loss": 0.6781, "lr": 1.0434782608695653e-05, "epoch": 0.1842948717948718, "percentage": 2.63, "elapsed_time": "0:14:19", "remaining_time": "8:49:29"}
+{"current_steps": 120, "total_steps": 4368, "loss": 0.6593, "lr": 1.0892448512585814e-05, "epoch": 0.19230769230769232, "percentage": 2.75, "elapsed_time": "0:14:58", "remaining_time": "8:49:53"}
+{"current_steps": 125, "total_steps": 4368, "loss": 0.6411, "lr": 1.1350114416475973e-05, "epoch": 0.20032051282051283, "percentage": 2.86, "elapsed_time": "0:15:32", "remaining_time": "8:47:49"}
+{"current_steps": 130, "total_steps": 4368, "loss": 0.6848, "lr": 1.1807780320366134e-05, "epoch": 0.20833333333333334, "percentage": 2.98, "elapsed_time": "0:16:11", "remaining_time": "8:47:46"}
+{"current_steps": 135, "total_steps": 4368, "loss": 0.6421, "lr": 1.2265446224256295e-05, "epoch": 0.21634615384615385, "percentage": 3.09, "elapsed_time": "0:16:40", "remaining_time": "8:42:51"}
+{"current_steps": 140, "total_steps": 4368, "loss": 0.6348, "lr": 1.2723112128146454e-05, "epoch": 0.22435897435897437, "percentage": 3.21, "elapsed_time": "0:17:10", "remaining_time": "8:38:29"}
+{"current_steps": 145, "total_steps": 4368, "loss": 0.683, "lr": 1.3180778032036615e-05, "epoch": 0.23237179487179488, "percentage": 3.32, "elapsed_time": "0:17:42", "remaining_time": "8:35:44"}
+{"current_steps": 150, "total_steps": 4368, "loss": 0.656, "lr": 1.3638443935926776e-05, "epoch": 0.2403846153846154, "percentage": 3.43, "elapsed_time": "0:18:25", "remaining_time": "8:38:08"}
+{"current_steps": 155, "total_steps": 4368, "loss": 0.6734, "lr": 1.4096109839816933e-05, "epoch": 0.2483974358974359, "percentage": 3.55, "elapsed_time": "0:18:57", "remaining_time": "8:35:29"}
+{"current_steps": 160, "total_steps": 4368, "loss": 0.6344, "lr": 1.4553775743707096e-05, "epoch": 0.2564102564102564, "percentage": 3.66, "elapsed_time": "0:19:33", "remaining_time": "8:34:31"}
+{"current_steps": 165, "total_steps": 4368, "loss": 0.6547, "lr": 1.5011441647597256e-05, "epoch": 0.2644230769230769, "percentage": 3.78, "elapsed_time": "0:20:07", "remaining_time": "8:32:44"}
+{"current_steps": 170, "total_steps": 4368, "loss": 0.6144, "lr": 1.5469107551487414e-05, "epoch": 0.2724358974358974, "percentage": 3.89, "elapsed_time": "0:20:43", "remaining_time": "8:31:37"}
+{"current_steps": 175, "total_steps": 4368, "loss": 0.6454, "lr": 1.5926773455377575e-05, "epoch": 0.28044871794871795, "percentage": 4.01, "elapsed_time": "0:21:24", "remaining_time": "8:32:45"}
+{"current_steps": 180, "total_steps": 4368, "loss": 0.6317, "lr": 1.6384439359267736e-05, "epoch": 0.28846153846153844, "percentage": 4.12, "elapsed_time": "0:21:52", "remaining_time": "8:28:59"}
+{"current_steps": 185, "total_steps": 4368, "loss": 0.6377, "lr": 1.6842105263157896e-05, "epoch": 0.296474358974359, "percentage": 4.24, "elapsed_time": "0:22:31", "remaining_time": "8:29:12"}
+{"current_steps": 190, "total_steps": 4368, "loss": 0.6429, "lr": 1.7299771167048057e-05, "epoch": 0.30448717948717946, "percentage": 4.35, "elapsed_time": "0:23:04", "remaining_time": "8:27:33"}
+{"current_steps": 195, "total_steps": 4368, "loss": 0.6447, "lr": 1.7757437070938218e-05, "epoch": 0.3125, "percentage": 4.46, "elapsed_time": "0:23:41", "remaining_time": "8:27:05"}
+{"current_steps": 200, "total_steps": 4368, "loss": 0.6205, "lr": 1.8215102974828376e-05, "epoch": 0.32051282051282054, "percentage": 4.58, "elapsed_time": "0:24:19", "remaining_time": "8:27:02"}
+{"current_steps": 205, "total_steps": 4368, "loss": 0.611, "lr": 1.8672768878718537e-05, "epoch": 0.328525641025641, "percentage": 4.69, "elapsed_time": "0:24:53", "remaining_time": "8:25:35"}
+{"current_steps": 210, "total_steps": 4368, "loss": 0.6301, "lr": 1.9130434782608697e-05, "epoch": 0.33653846153846156, "percentage": 4.81, "elapsed_time": "0:25:31", "remaining_time": "8:25:32"}
+{"current_steps": 215, "total_steps": 4368, "loss": 0.5953, "lr": 1.9588100686498858e-05, "epoch": 0.34455128205128205, "percentage": 4.92, "elapsed_time": "0:26:07", "remaining_time": "8:24:35"}
+{"current_steps": 220, "total_steps": 4368, "loss": 0.656, "lr": 2.004576659038902e-05, "epoch": 0.3525641025641026, "percentage": 5.04, "elapsed_time": "0:26:36", "remaining_time": "8:21:40"}
+{"current_steps": 225, "total_steps": 4368, "loss": 0.6255, "lr": 2.050343249427918e-05, "epoch": 0.3605769230769231, "percentage": 5.15, "elapsed_time": "0:27:07", "remaining_time": "8:19:24"}
+{"current_steps": 230, "total_steps": 4368, "loss": 0.614, "lr": 2.0961098398169337e-05, "epoch": 0.3685897435897436, "percentage": 5.27, "elapsed_time": "0:27:45", "remaining_time": "8:19:19"}
+{"current_steps": 235, "total_steps": 4368, "loss": 0.6089, "lr": 2.14187643020595e-05, "epoch": 0.3766025641025641, "percentage": 5.38, "elapsed_time": "0:28:12", "remaining_time": "8:16:09"}
+{"current_steps": 240, "total_steps": 4368, "loss": 0.6354, "lr": 2.187643020594966e-05, "epoch": 0.38461538461538464, "percentage": 5.49, "elapsed_time": "0:28:43", "remaining_time": "8:14:01"}
+{"current_steps": 245, "total_steps": 4368, "loss": 0.6026, "lr": 2.2334096109839817e-05, "epoch": 0.3926282051282051, "percentage": 5.61, "elapsed_time": "0:29:22", "remaining_time": "8:14:17"}
+{"current_steps": 250, "total_steps": 4368, "loss": 0.6119, "lr": 2.279176201372998e-05, "epoch": 0.40064102564102566, "percentage": 5.72, "elapsed_time": "0:30:06", "remaining_time": "8:15:50"}
+{"current_steps": 255, "total_steps": 4368, "loss": 0.5854, "lr": 2.3249427917620138e-05, "epoch": 0.40865384615384615, "percentage": 5.84, "elapsed_time": "0:30:34", "remaining_time": "8:13:15"}
+{"current_steps": 260, "total_steps": 4368, "loss": 0.5917, "lr": 2.37070938215103e-05, "epoch": 0.4166666666666667, "percentage": 5.95, "elapsed_time": "0:31:07", "remaining_time": "8:11:42"}
+{"current_steps": 265, "total_steps": 4368, "loss": 0.6211, "lr": 2.4164759725400463e-05, "epoch": 0.42467948717948717, "percentage": 6.07, "elapsed_time": "0:31:33", "remaining_time": "8:08:32"}
+{"current_steps": 270, "total_steps": 4368, "loss": 0.5775, "lr": 2.462242562929062e-05, "epoch": 0.4326923076923077, "percentage": 6.18, "elapsed_time": "0:32:12", "remaining_time": "8:08:47"}
+{"current_steps": 275, "total_steps": 4368, "loss": 0.5995, "lr": 2.508009153318078e-05, "epoch": 0.4407051282051282, "percentage": 6.3, "elapsed_time": "0:32:42", "remaining_time": "8:06:50"}
+{"current_steps": 280, "total_steps": 4368, "loss": 0.5977, "lr": 2.5537757437070943e-05, "epoch": 0.44871794871794873, "percentage": 6.41, "elapsed_time": "0:33:14", "remaining_time": "8:05:17"}
+{"current_steps": 285, "total_steps": 4368, "loss": 0.6142, "lr": 2.59954233409611e-05, "epoch": 0.4567307692307692, "percentage": 6.52, "elapsed_time": "0:33:58", "remaining_time": "8:06:49"}
+{"current_steps": 290, "total_steps": 4368, "loss": 0.5716, "lr": 2.645308924485126e-05, "epoch": 0.46474358974358976, "percentage": 6.64, "elapsed_time": "0:34:32", "remaining_time": "8:05:44"}
+{"current_steps": 295, "total_steps": 4368, "loss": 0.5892, "lr": 2.6910755148741422e-05, "epoch": 0.47275641025641024, "percentage": 6.75, "elapsed_time": "0:35:05", "remaining_time": "8:04:25"}
+{"current_steps": 300, "total_steps": 4368, "loss": 0.6112, "lr": 2.7368421052631583e-05, "epoch": 0.4807692307692308, "percentage": 6.87, "elapsed_time": "0:35:40", "remaining_time": "8:03:47"}
+{"current_steps": 305, "total_steps": 4368, "loss": 0.5587, "lr": 2.782608695652174e-05, "epoch": 0.48878205128205127, "percentage": 6.98, "elapsed_time": "0:36:12", "remaining_time": "8:02:18"}
+{"current_steps": 310, "total_steps": 4368, "loss": 0.6255, "lr": 2.8283752860411904e-05, "epoch": 0.4967948717948718, "percentage": 7.1, "elapsed_time": "0:36:44", "remaining_time": "8:00:54"}
+{"current_steps": 315, "total_steps": 4368, "loss": 0.6187, "lr": 2.8741418764302062e-05, "epoch": 0.5048076923076923, "percentage": 7.21, "elapsed_time": "0:37:12", "remaining_time": "7:58:48"}
+{"current_steps": 320, "total_steps": 4368, "loss": 0.5639, "lr": 2.9199084668192223e-05, "epoch": 0.5128205128205128, "percentage": 7.33, "elapsed_time": "0:37:50", "remaining_time": "7:58:37"}
+{"current_steps": 325, "total_steps": 4368, "loss": 0.5994, "lr": 2.9656750572082384e-05, "epoch": 0.5208333333333334, "percentage": 7.44, "elapsed_time": "0:38:22", "remaining_time": "7:57:23"}
+{"current_steps": 330, "total_steps": 4368, "loss": 0.5855, "lr": 3.0114416475972544e-05, "epoch": 0.5288461538461539, "percentage": 7.55, "elapsed_time": "0:38:55", "remaining_time": "7:56:15"}
+{"current_steps": 335, "total_steps": 4368, "loss": 0.5956, "lr": 3.05720823798627e-05, "epoch": 0.5368589743589743, "percentage": 7.67, "elapsed_time": "0:39:31", "remaining_time": "7:55:48"}
+{"current_steps": 340, "total_steps": 4368, "loss": 0.5798, "lr": 3.102974828375286e-05, "epoch": 0.5448717948717948, "percentage": 7.78, "elapsed_time": "0:40:04", "remaining_time": "7:54:45"}
+{"current_steps": 345, "total_steps": 4368, "loss": 0.5892, "lr": 3.1487414187643024e-05, "epoch": 0.5528846153846154, "percentage": 7.9, "elapsed_time": "0:40:33", "remaining_time": "7:53:01"}
+{"current_steps": 350, "total_steps": 4368, "loss": 0.5648, "lr": 3.1945080091533184e-05, "epoch": 0.5608974358974359, "percentage": 8.01, "elapsed_time": "0:41:14", "remaining_time": "7:53:23"}
+{"current_steps": 355, "total_steps": 4368, "loss": 0.567, "lr": 3.240274599542334e-05, "epoch": 0.5689102564102564, "percentage": 8.13, "elapsed_time": "0:41:48", "remaining_time": "7:52:34"}
+{"current_steps": 360, "total_steps": 4368, "loss": 0.6071, "lr": 3.2860411899313506e-05, "epoch": 0.5769230769230769, "percentage": 8.24, "elapsed_time": "0:42:23", "remaining_time": "7:51:57"}
+{"current_steps": 365, "total_steps": 4368, "loss": 0.6091, "lr": 3.331807780320366e-05, "epoch": 0.5849358974358975, "percentage": 8.36, "elapsed_time": "0:42:51", "remaining_time": "7:50:04"}
+{"current_steps": 370, "total_steps": 4368, "loss": 0.5993, "lr": 3.377574370709382e-05, "epoch": 0.592948717948718, "percentage": 8.47, "elapsed_time": "0:43:23", "remaining_time": "7:48:50"}
+{"current_steps": 375, "total_steps": 4368, "loss": 0.582, "lr": 3.423340961098399e-05, "epoch": 0.6009615384615384, "percentage": 8.59, "elapsed_time": "0:44:05", "remaining_time": "7:49:29"}
+{"current_steps": 380, "total_steps": 4368, "loss": 0.5572, "lr": 3.469107551487414e-05, "epoch": 0.6089743589743589, "percentage": 8.7, "elapsed_time": "0:44:42", "remaining_time": "7:49:09"}
+{"current_steps": 385, "total_steps": 4368, "loss": 0.5954, "lr": 3.5148741418764304e-05, "epoch": 0.6169871794871795, "percentage": 8.81, "elapsed_time": "0:45:14", "remaining_time": "7:48:02"}
+{"current_steps": 390, "total_steps": 4368, "loss": 0.5986, "lr": 3.5606407322654464e-05, "epoch": 0.625, "percentage": 8.93, "elapsed_time": "0:45:47", "remaining_time": "7:47:00"}
+{"current_steps": 395, "total_steps": 4368, "loss": 0.5691, "lr": 3.6064073226544625e-05, "epoch": 0.6330128205128205, "percentage": 9.04, "elapsed_time": "0:46:21", "remaining_time": "7:46:18"}
+{"current_steps": 400, "total_steps": 4368, "loss": 0.5678, "lr": 3.6521739130434786e-05, "epoch": 0.6410256410256411, "percentage": 9.16, "elapsed_time": "0:46:59", "remaining_time": "7:46:06"}
+{"current_steps": 405, "total_steps": 4368, "loss": 0.5637, "lr": 3.697940503432495e-05, "epoch": 0.6490384615384616, "percentage": 9.27, "elapsed_time": "0:47:33", "remaining_time": "7:45:23"}
+{"current_steps": 410, "total_steps": 4368, "loss": 0.5706, "lr": 3.743707093821511e-05, "epoch": 0.657051282051282, "percentage": 9.39, "elapsed_time": "0:48:12", "remaining_time": "7:45:23"}
+{"current_steps": 415, "total_steps": 4368, "loss": 0.6069, "lr": 3.789473684210526e-05, "epoch": 0.6650641025641025, "percentage": 9.5, "elapsed_time": "0:48:49", "remaining_time": "7:45:04"}
+{"current_steps": 420, "total_steps": 4368, "loss": 0.5823, "lr": 3.835240274599543e-05, "epoch": 0.6730769230769231, "percentage": 9.62, "elapsed_time": "0:49:30", "remaining_time": "7:45:22"}
+{"current_steps": 425, "total_steps": 4368, "loss": 0.5661, "lr": 3.8810068649885584e-05, "epoch": 0.6810897435897436, "percentage": 9.73, "elapsed_time": "0:49:58", "remaining_time": "7:43:38"}
+{"current_steps": 430, "total_steps": 4368, "loss": 0.5573, "lr": 3.9267734553775745e-05, "epoch": 0.6891025641025641, "percentage": 9.84, "elapsed_time": "0:50:34", "remaining_time": "7:43:10"}
+{"current_steps": 435, "total_steps": 4368, "loss": 0.5766, "lr": 3.9725400457665905e-05, "epoch": 0.6971153846153846, "percentage": 9.96, "elapsed_time": "0:51:04", "remaining_time": "7:41:43"}
+{"current_steps": 440, "total_steps": 4368, "loss": 0.5625, "lr": 3.999997445219712e-05, "epoch": 0.7051282051282052, "percentage": 10.07, "elapsed_time": "0:51:39", "remaining_time": "7:41:10"}
+{"current_steps": 445, "total_steps": 4368, "loss": 0.5622, "lr": 3.999968704016428e-05, "epoch": 0.7131410256410257, "percentage": 10.19, "elapsed_time": "0:52:10", "remaining_time": "7:39:58"}
+{"current_steps": 450, "total_steps": 4368, "loss": 0.5867, "lr": 3.9999080285949514e-05, "epoch": 0.7211538461538461, "percentage": 10.3, "elapsed_time": "0:52:42", "remaining_time": "7:38:56"}
+{"current_steps": 455, "total_steps": 4368, "loss": 0.545, "lr": 3.999815419924108e-05, "epoch": 0.7291666666666666, "percentage": 10.42, "elapsed_time": "0:53:16", "remaining_time": "7:38:06"}
+{"current_steps": 460, "total_steps": 4368, "loss": 0.6004, "lr": 3.999690879482614e-05, "epoch": 0.7371794871794872, "percentage": 10.53, "elapsed_time": "0:53:44", "remaining_time": "7:36:33"}
+{"current_steps": 465, "total_steps": 4368, "loss": 0.5831, "lr": 3.9995344092590506e-05, "epoch": 0.7451923076923077, "percentage": 10.65, "elapsed_time": "0:54:22", "remaining_time": "7:36:21"}
+{"current_steps": 470, "total_steps": 4368, "loss": 0.5489, "lr": 3.999346011751835e-05, "epoch": 0.7532051282051282, "percentage": 10.76, "elapsed_time": "0:54:49", "remaining_time": "7:34:42"}
+{"current_steps": 475, "total_steps": 4368, "loss": 0.5706, "lr": 3.999125689969176e-05, "epoch": 0.7612179487179487, "percentage": 10.87, "elapsed_time": "0:55:25", "remaining_time": "7:34:17"}
+{"current_steps": 480, "total_steps": 4368, "loss": 0.5563, "lr": 3.9988734474290324e-05, "epoch": 0.7692307692307693, "percentage": 10.99, "elapsed_time": "0:55:55", "remaining_time": "7:33:01"}
+{"current_steps": 485, "total_steps": 4368, "loss": 0.5372, "lr": 3.9985892881590513e-05, "epoch": 0.7772435897435898, "percentage": 11.1, "elapsed_time": "0:56:26", "remaining_time": "7:31:49"}
+{"current_steps": 490, "total_steps": 4368, "loss": 0.6105, "lr": 3.9982732166965054e-05, "epoch": 0.7852564102564102, "percentage": 11.22, "elapsed_time": "0:56:59", "remaining_time": "7:31:00"}
+{"current_steps": 495, "total_steps": 4368, "loss": 0.6127, "lr": 3.997925238088221e-05, "epoch": 0.7932692307692307, "percentage": 11.33, "elapsed_time": "0:57:32", "remaining_time": "7:30:12"}
+{"current_steps": 500, "total_steps": 4368, "loss": 0.5466, "lr": 3.9975453578904975e-05, "epoch": 0.8012820512820513, "percentage": 11.45, "elapsed_time": "0:58:07", "remaining_time": "7:29:37"}
+{"current_steps": 505, "total_steps": 4368, "loss": 0.5801, "lr": 3.997133582169018e-05, "epoch": 0.8092948717948718, "percentage": 11.56, "elapsed_time": "0:58:43", "remaining_time": "7:29:14"}
+{"current_steps": 510, "total_steps": 4368, "loss": 0.5661, "lr": 3.996689917498754e-05, "epoch": 0.8173076923076923, "percentage": 11.68, "elapsed_time": "0:59:13", "remaining_time": "7:28:03"}
+{"current_steps": 515, "total_steps": 4368, "loss": 0.5698, "lr": 3.9962143709638585e-05, "epoch": 0.8253205128205128, "percentage": 11.79, "elapsed_time": "0:59:48", "remaining_time": "7:27:25"}
+{"current_steps": 520, "total_steps": 4368, "loss": 0.5813, "lr": 3.995706950157554e-05, "epoch": 0.8333333333333334, "percentage": 11.9, "elapsed_time": "1:00:15", "remaining_time": "7:25:55"}
+{"current_steps": 525, "total_steps": 4368, "loss": 0.561, "lr": 3.995167663182008e-05, "epoch": 0.8413461538461539, "percentage": 12.02, "elapsed_time": "1:00:47", "remaining_time": "7:25:00"}
+{"current_steps": 530, "total_steps": 4368, "loss": 0.5973, "lr": 3.994596518648214e-05, "epoch": 0.8493589743589743, "percentage": 12.13, "elapsed_time": "1:01:25", "remaining_time": "7:24:47"}
+{"current_steps": 535, "total_steps": 4368, "loss": 0.5672, "lr": 3.993993525675838e-05, "epoch": 0.8573717948717948, "percentage": 12.25, "elapsed_time": "1:02:01", "remaining_time": "7:24:23"}
+{"current_steps": 540, "total_steps": 4368, "loss": 0.5876, "lr": 3.993358693893086e-05, "epoch": 0.8653846153846154, "percentage": 12.36, "elapsed_time": "1:02:38", "remaining_time": "7:24:05"}
+{"current_steps": 545, "total_steps": 4368, "loss": 0.5817, "lr": 3.9926920334365457e-05, "epoch": 0.8733974358974359, "percentage": 12.48, "elapsed_time": "1:03:12", "remaining_time": "7:23:25"}
+{"current_steps": 550, "total_steps": 4368, "loss": 0.5339, "lr": 3.991993554951023e-05, "epoch": 0.8814102564102564, "percentage": 12.59, "elapsed_time": "1:03:50", "remaining_time": "7:23:08"}
+{"current_steps": 555, "total_steps": 4368, "loss": 0.5681, "lr": 3.991263269589376e-05, "epoch": 0.8894230769230769, "percentage": 12.71, "elapsed_time": "1:04:21", "remaining_time": "7:22:11"}
+{"current_steps": 560, "total_steps": 4368, "loss": 0.5348, "lr": 3.990501189012332e-05, "epoch": 0.8974358974358975, "percentage": 12.82, "elapsed_time": "1:05:01", "remaining_time": "7:22:11"}
+{"current_steps": 565, "total_steps": 4368, "loss": 0.5521, "lr": 3.989707325388305e-05, "epoch": 0.905448717948718, "percentage": 12.93, "elapsed_time": "1:05:45", "remaining_time": "7:22:36"}
+{"current_steps": 570, "total_steps": 4368, "loss": 0.5455, "lr": 3.9888816913932016e-05, "epoch": 0.9134615384615384, "percentage": 13.05, "elapsed_time": "1:06:16", "remaining_time": "7:21:37"}
+{"current_steps": 575, "total_steps": 4368, "loss": 0.5792, "lr": 3.988024300210215e-05, "epoch": 0.9214743589743589, "percentage": 13.16, "elapsed_time": "1:06:47", "remaining_time": "7:20:35"}
+{"current_steps": 580, "total_steps": 4368, "loss": 0.5451, "lr": 3.987135165529618e-05, "epoch": 0.9294871794871795, "percentage": 13.28, "elapsed_time": "1:07:20", "remaining_time": "7:19:47"}
+{"current_steps": 585, "total_steps": 4368, "loss": 0.5535, "lr": 3.9862143015485446e-05, "epoch": 0.9375, "percentage": 13.39, "elapsed_time": "1:07:53", "remaining_time": "7:19:04"}
+{"current_steps": 590, "total_steps": 4368, "loss": 0.5085, "lr": 3.985261722970759e-05, "epoch": 0.9455128205128205, "percentage": 13.51, "elapsed_time": "1:08:28", "remaining_time": "7:18:25"}
+{"current_steps": 595, "total_steps": 4368, "loss": 0.5729, "lr": 3.984277445006426e-05, "epoch": 0.9535256410256411, "percentage": 13.62, "elapsed_time": "1:09:01", "remaining_time": "7:17:39"}
+{"current_steps": 600, "total_steps": 4368, "loss": 0.5466, "lr": 3.9832614833718654e-05, "epoch": 0.9615384615384616, "percentage": 13.74, "elapsed_time": "1:09:40", "remaining_time": "7:17:31"}
+{"current_steps": 605, "total_steps": 4368, "loss": 0.5446, "lr": 3.9822138542893005e-05, "epoch": 0.969551282051282, "percentage": 13.85, "elapsed_time": "1:10:15", "remaining_time": "7:16:57"}
+{"current_steps": 610, "total_steps": 4368, "loss": 0.552, "lr": 3.9811345744866014e-05, "epoch": 0.9775641025641025, "percentage": 13.97, "elapsed_time": "1:10:43", "remaining_time": "7:15:40"}
+{"current_steps": 615, "total_steps": 4368, "loss": 0.6033, "lr": 3.980023661197016e-05, "epoch": 0.9855769230769231, "percentage": 14.08, "elapsed_time": "1:11:22", "remaining_time": "7:15:33"}
+{"current_steps": 620, "total_steps": 4368, "loss": 0.5286, "lr": 3.978881132158896e-05, "epoch": 0.9935897435897436, "percentage": 14.19, "elapsed_time": "1:11:54", "remaining_time": "7:14:41"}
+{"current_steps": 625, "total_steps": 4368, "loss": 0.5658, "lr": 3.9777070056154124e-05, "epoch": 1.001602564102564, "percentage": 14.31, "elapsed_time": "1:12:27", "remaining_time": "7:13:57"}
+{"current_steps": 630, "total_steps": 4368, "loss": 0.5828, "lr": 3.976501300314264e-05, "epoch": 1.0096153846153846, "percentage": 14.42, "elapsed_time": "1:12:59", "remaining_time": "7:13:02"}
+{"current_steps": 635, "total_steps": 4368, "loss": 0.541, "lr": 3.9752640355073825e-05, "epoch": 1.017628205128205, "percentage": 14.54, "elapsed_time": "1:13:28", "remaining_time": "7:11:54"}
+{"current_steps": 640, "total_steps": 4368, "loss": 0.5157, "lr": 3.9739952309506175e-05, "epoch": 1.0256410256410255, "percentage": 14.65, "elapsed_time": "1:14:04", "remaining_time": "7:11:29"}
+{"current_steps": 645, "total_steps": 4368, "loss": 0.489, "lr": 3.972694906903427e-05, "epoch": 1.0336538461538463, "percentage": 14.77, "elapsed_time": "1:14:36", "remaining_time": "7:10:35"}
+{"current_steps": 650, "total_steps": 4368, "loss": 0.5247, "lr": 3.971363084128552e-05, "epoch": 1.0416666666666667, "percentage": 14.88, "elapsed_time": "1:15:06", "remaining_time": "7:09:36"}
+{"current_steps": 655, "total_steps": 4368, "loss": 0.5068, "lr": 3.969999783891685e-05, "epoch": 1.0496794871794872, "percentage": 15.0, "elapsed_time": "1:15:41", "remaining_time": "7:09:06"}
+{"current_steps": 660, "total_steps": 4368, "loss": 0.5414, "lr": 3.96860502796113e-05, "epoch": 1.0576923076923077, "percentage": 15.11, "elapsed_time": "1:16:08", "remaining_time": "7:07:47"}
+{"current_steps": 665, "total_steps": 4368, "loss": 0.5552, "lr": 3.967178838607456e-05, "epoch": 1.0657051282051282, "percentage": 15.22, "elapsed_time": "1:16:41", "remaining_time": "7:07:03"}
+{"current_steps": 670, "total_steps": 4368, "loss": 0.5292, "lr": 3.965721238603139e-05, "epoch": 1.0737179487179487, "percentage": 15.34, "elapsed_time": "1:17:13", "remaining_time": "7:06:11"}
+{"current_steps": 675, "total_steps": 4368, "loss": 0.5445, "lr": 3.964232251222203e-05, "epoch": 1.0817307692307692, "percentage": 15.45, "elapsed_time": "1:17:45", "remaining_time": "7:05:27"}
+{"current_steps": 680, "total_steps": 4368, "loss": 0.5318, "lr": 3.962711900239844e-05, "epoch": 1.0897435897435896, "percentage": 15.57, "elapsed_time": "1:18:18", "remaining_time": "7:04:43"}
+{"current_steps": 685, "total_steps": 4368, "loss": 0.5339, "lr": 3.961160209932051e-05, "epoch": 1.0977564102564104, "percentage": 15.68, "elapsed_time": "1:18:49", "remaining_time": "7:03:47"}
+{"current_steps": 690, "total_steps": 4368, "loss": 0.5215, "lr": 3.95957720507522e-05, "epoch": 1.1057692307692308, "percentage": 15.8, "elapsed_time": "1:19:24", "remaining_time": "7:03:15"}
+{"current_steps": 695, "total_steps": 4368, "loss": 0.526, "lr": 3.957962910945759e-05, "epoch": 1.1137820512820513, "percentage": 15.91, "elapsed_time": "1:19:56", "remaining_time": "7:02:26"}
+{"current_steps": 700, "total_steps": 4368, "loss": 0.5335, "lr": 3.9563173533196805e-05, "epoch": 1.1217948717948718, "percentage": 16.03, "elapsed_time": "1:20:33", "remaining_time": "7:02:06"}
+{"current_steps": 705, "total_steps": 4368, "loss": 0.5364, "lr": 3.954640558472195e-05, "epoch": 1.1298076923076923, "percentage": 16.14, "elapsed_time": "1:21:12", "remaining_time": "7:01:54"}
+{"current_steps": 710, "total_steps": 4368, "loss": 0.5172, "lr": 3.952932553177287e-05, "epoch": 1.1378205128205128, "percentage": 16.25, "elapsed_time": "1:21:49", "remaining_time": "7:01:35"}
+{"current_steps": 715, "total_steps": 4368, "loss": 0.5399, "lr": 3.95119336470729e-05, "epoch": 1.1458333333333333, "percentage": 16.37, "elapsed_time": "1:22:19", "remaining_time": "7:00:34"}
+{"current_steps": 720, "total_steps": 4368, "loss": 0.5593, "lr": 3.949423020832451e-05, "epoch": 1.1538461538461537, "percentage": 16.48, "elapsed_time": "1:22:57", "remaining_time": "7:00:19"}
+{"current_steps": 725, "total_steps": 4368, "loss": 0.5088, "lr": 3.947621549820485e-05, "epoch": 1.1618589743589745, "percentage": 16.6, "elapsed_time": "1:23:31", "remaining_time": "6:59:42"}
+{"current_steps": 730, "total_steps": 4368, "loss": 0.5143, "lr": 3.945788980436129e-05, "epoch": 1.169871794871795, "percentage": 16.71, "elapsed_time": "1:24:04", "remaining_time": "6:58:57"}
+{"current_steps": 735, "total_steps": 4368, "loss": 0.5198, "lr": 3.943925341940673e-05, "epoch": 1.1778846153846154, "percentage": 16.83, "elapsed_time": "1:24:34", "remaining_time": "6:58:00"}
+{"current_steps": 740, "total_steps": 4368, "loss": 0.5195, "lr": 3.942030664091503e-05, "epoch": 1.185897435897436, "percentage": 16.94, "elapsed_time": "1:25:05", "remaining_time": "6:57:10"}
+{"current_steps": 745, "total_steps": 4368, "loss": 0.5314, "lr": 3.9401049771416214e-05, "epoch": 1.1939102564102564, "percentage": 17.06, "elapsed_time": "1:25:39", "remaining_time": "6:56:35"}
+{"current_steps": 750, "total_steps": 4368, "loss": 0.5278, "lr": 3.938148311839162e-05, "epoch": 1.2019230769230769, "percentage": 17.17, "elapsed_time": "1:26:13", "remaining_time": "6:55:58"}
+{"current_steps": 755, "total_steps": 4368, "loss": 0.517, "lr": 3.9361606994269014e-05, "epoch": 1.2099358974358974, "percentage": 17.28, "elapsed_time": "1:26:43", "remaining_time": "6:54:59"}
+{"current_steps": 760, "total_steps": 4368, "loss": 0.5336, "lr": 3.934142171641763e-05, "epoch": 1.217948717948718, "percentage": 17.4, "elapsed_time": "1:27:20", "remaining_time": "6:54:38"}
+{"current_steps": 765, "total_steps": 4368, "loss": 0.544, "lr": 3.9320927607143003e-05, "epoch": 1.2259615384615385, "percentage": 17.51, "elapsed_time": "1:27:52", "remaining_time": "6:53:53"}
+{"current_steps": 770, "total_steps": 4368, "loss": 0.5579, "lr": 3.9300124993681976e-05, "epoch": 1.233974358974359, "percentage": 17.63, "elapsed_time": "1:28:25", "remaining_time": "6:53:10"}
+{"current_steps": 775, "total_steps": 4368, "loss": 0.5541, "lr": 3.9279014208197317e-05, "epoch": 1.2419871794871795, "percentage": 17.74, "elapsed_time": "1:28:53", "remaining_time": "6:52:08"}
+{"current_steps": 780, "total_steps": 4368, "loss": 0.5336, "lr": 3.925759558777252e-05, "epoch": 1.25, "percentage": 17.86, "elapsed_time": "1:29:28", "remaining_time": "6:51:33"}
+{"current_steps": 785, "total_steps": 4368, "loss": 0.5268, "lr": 3.923586947440639e-05, "epoch": 1.2580128205128205, "percentage": 17.97, "elapsed_time": "1:30:06", "remaining_time": "6:51:18"}
+{"current_steps": 790, "total_steps": 4368, "loss": 0.5041, "lr": 3.921383621500758e-05, "epoch": 1.266025641025641, "percentage": 18.09, "elapsed_time": "1:30:42", "remaining_time": "6:50:49"}
+{"current_steps": 795, "total_steps": 4368, "loss": 0.5446, "lr": 3.919149616138906e-05, "epoch": 1.2740384615384617, "percentage": 18.2, "elapsed_time": "1:31:11", "remaining_time": "6:49:52"}
+{"current_steps": 800, "total_steps": 4368, "loss": 0.5421, "lr": 3.916884967026246e-05, "epoch": 1.282051282051282, "percentage": 18.32, "elapsed_time": "1:31:47", "remaining_time": "6:49:22"}
+{"current_steps": 805, "total_steps": 4368, "loss": 0.4931, "lr": 3.914589710323245e-05, "epoch": 1.2900641025641026, "percentage": 18.43, "elapsed_time": "1:32:18", "remaining_time": "6:48:35"}
+{"current_steps": 810, "total_steps": 4368, "loss": 0.5118, "lr": 3.912263882679091e-05, "epoch": 1.2980769230769231, "percentage": 18.54, "elapsed_time": "1:32:49", "remaining_time": "6:47:44"}
+{"current_steps": 815, "total_steps": 4368, "loss": 0.5049, "lr": 3.9099075212311076e-05, "epoch": 1.3060897435897436, "percentage": 18.66, "elapsed_time": "1:33:21", "remaining_time": "6:46:59"}
+{"current_steps": 820, "total_steps": 4368, "loss": 0.5442, "lr": 3.9075206636041646e-05, "epoch": 1.314102564102564, "percentage": 18.77, "elapsed_time": "1:33:53", "remaining_time": "6:46:16"}
+{"current_steps": 825, "total_steps": 4368, "loss": 0.5011, "lr": 3.905103347910075e-05, "epoch": 1.3221153846153846, "percentage": 18.89, "elapsed_time": "1:34:33", "remaining_time": "6:46:03"}
+{"current_steps": 830, "total_steps": 4368, "loss": 0.5498, "lr": 3.902655612746985e-05, "epoch": 1.330128205128205, "percentage": 19.0, "elapsed_time": "1:35:04", "remaining_time": "6:45:18"}
+{"current_steps": 835, "total_steps": 4368, "loss": 0.5102, "lr": 3.900177497198761e-05, "epoch": 1.3381410256410255, "percentage": 19.12, "elapsed_time": "1:35:43", "remaining_time": "6:45:03"}
+{"current_steps": 840, "total_steps": 4368, "loss": 0.5582, "lr": 3.8976690408343635e-05, "epoch": 1.3461538461538463, "percentage": 19.23, "elapsed_time": "1:36:20", "remaining_time": "6:44:37"}
+{"current_steps": 845, "total_steps": 4368, "loss": 0.5099, "lr": 3.8951302837072165e-05, "epoch": 1.3541666666666667, "percentage": 19.35, "elapsed_time": "1:37:00", "remaining_time": "6:44:26"}
+{"current_steps": 850, "total_steps": 4368, "loss": 0.5142, "lr": 3.892561266354566e-05, "epoch": 1.3621794871794872, "percentage": 19.46, "elapsed_time": "1:37:42", "remaining_time": "6:44:24"}
+{"current_steps": 855, "total_steps": 4368, "loss": 0.5306, "lr": 3.889962029796833e-05, "epoch": 1.3701923076923077, "percentage": 19.57, "elapsed_time": "1:38:13", "remaining_time": "6:43:35"}
+{"current_steps": 860, "total_steps": 4368, "loss": 0.5239, "lr": 3.887332615536962e-05, "epoch": 1.3782051282051282, "percentage": 19.69, "elapsed_time": "1:38:43", "remaining_time": "6:42:43"}
+{"current_steps": 865, "total_steps": 4368, "loss": 0.5186, "lr": 3.8846730655597535e-05, "epoch": 1.3862179487179487, "percentage": 19.8, "elapsed_time": "1:39:15", "remaining_time": "6:41:59"}
+{"current_steps": 870, "total_steps": 4368, "loss": 0.5468, "lr": 3.881983422331198e-05, "epoch": 1.3942307692307692, "percentage": 19.92, "elapsed_time": "1:39:49", "remaining_time": "6:41:23"}
+{"current_steps": 875, "total_steps": 4368, "loss": 0.5015, "lr": 3.879263728797792e-05, "epoch": 1.4022435897435899, "percentage": 20.03, "elapsed_time": "1:40:27", "remaining_time": "6:41:02"}
+{"current_steps": 880, "total_steps": 4368, "loss": 0.4915, "lr": 3.876514028385861e-05, "epoch": 1.4102564102564101, "percentage": 20.15, "elapsed_time": "1:41:02", "remaining_time": "6:40:28"}
+{"current_steps": 885, "total_steps": 4368, "loss": 0.5515, "lr": 3.873734365000857e-05, "epoch": 1.4182692307692308, "percentage": 20.26, "elapsed_time": "1:41:28", "remaining_time": "6:39:23"}
+{"current_steps": 890, "total_steps": 4368, "loss": 0.515, "lr": 3.870924783026663e-05, "epoch": 1.4262820512820513, "percentage": 20.38, "elapsed_time": "1:41:56", "remaining_time": "6:38:24"}
+{"current_steps": 895, "total_steps": 4368, "loss": 0.5177, "lr": 3.8680853273248826e-05, "epoch": 1.4342948717948718, "percentage": 20.49, "elapsed_time": "1:42:34", "remaining_time": "6:38:01"}
+{"current_steps": 900, "total_steps": 4368, "loss": 0.4936, "lr": 3.865216043234126e-05, "epoch": 1.4423076923076923, "percentage": 20.6, "elapsed_time": "1:43:09", "remaining_time": "6:37:29"}
+{"current_steps": 905, "total_steps": 4368, "loss": 0.5145, "lr": 3.862316976569281e-05, "epoch": 1.4503205128205128, "percentage": 20.72, "elapsed_time": "1:43:38", "remaining_time": "6:36:35"}
+{"current_steps": 910, "total_steps": 4368, "loss": 0.4967, "lr": 3.859388173620785e-05, "epoch": 1.4583333333333333, "percentage": 20.83, "elapsed_time": "1:44:11", "remaining_time": "6:35:55"}
+{"current_steps": 915, "total_steps": 4368, "loss": 0.5083, "lr": 3.8564296811538874e-05, "epoch": 1.4663461538461537, "percentage": 20.95, "elapsed_time": "1:44:44", "remaining_time": "6:35:17"}
+{"current_steps": 920, "total_steps": 4368, "loss": 0.5424, "lr": 3.853441546407898e-05, "epoch": 1.4743589743589745, "percentage": 21.06, "elapsed_time": "1:45:11", "remaining_time": "6:34:13"}
+{"current_steps": 925, "total_steps": 4368, "loss": 0.5221, "lr": 3.850423817095438e-05, "epoch": 1.482371794871795, "percentage": 21.18, "elapsed_time": "1:45:50", "remaining_time": "6:33:55"}
+{"current_steps": 930, "total_steps": 4368, "loss": 0.5446, "lr": 3.847376541401674e-05, "epoch": 1.4903846153846154, "percentage": 21.29, "elapsed_time": "1:46:22", "remaining_time": "6:33:15"}
+{"current_steps": 935, "total_steps": 4368, "loss": 0.5334, "lr": 3.844299767983551e-05, "epoch": 1.498397435897436, "percentage": 21.41, "elapsed_time": "1:46:53", "remaining_time": "6:32:28"}
+{"current_steps": 940, "total_steps": 4368, "loss": 0.5161, "lr": 3.841193545969015e-05, "epoch": 1.5064102564102564, "percentage": 21.52, "elapsed_time": "1:47:23", "remaining_time": "6:31:37"}
+{"current_steps": 945, "total_steps": 4368, "loss": 0.5105, "lr": 3.8380579249562265e-05, "epoch": 1.5144230769230769, "percentage": 21.63, "elapsed_time": "1:47:58", "remaining_time": "6:31:05"}
+{"current_steps": 950, "total_steps": 4368, "loss": 0.4847, "lr": 3.8348929550127734e-05, "epoch": 1.5224358974358974, "percentage": 21.75, "elapsed_time": "1:48:30", "remaining_time": "6:30:23"}
+{"current_steps": 955, "total_steps": 4368, "loss": 0.5687, "lr": 3.831698686674866e-05, "epoch": 1.530448717948718, "percentage": 21.86, "elapsed_time": "1:48:55", "remaining_time": "6:29:16"}
+{"current_steps": 960, "total_steps": 4368, "loss": 0.5203, "lr": 3.828475170946534e-05, "epoch": 1.5384615384615383, "percentage": 21.98, "elapsed_time": "1:49:27", "remaining_time": "6:28:34"}
+{"current_steps": 965, "total_steps": 4368, "loss": 0.5172, "lr": 3.8252224592988087e-05, "epoch": 1.546474358974359, "percentage": 22.09, "elapsed_time": "1:50:04", "remaining_time": "6:28:11"}
+{"current_steps": 970, "total_steps": 4368, "loss": 0.529, "lr": 3.821940603668906e-05, "epoch": 1.5544871794871795, "percentage": 22.21, "elapsed_time": "1:50:34", "remaining_time": "6:27:21"}
+{"current_steps": 975, "total_steps": 4368, "loss": 0.5386, "lr": 3.8186296564593924e-05, "epoch": 1.5625, "percentage": 22.32, "elapsed_time": "1:50:58", "remaining_time": "6:26:11"}
+{"current_steps": 980, "total_steps": 4368, "loss": 0.4983, "lr": 3.815289670537351e-05, "epoch": 1.5705128205128205, "percentage": 22.44, "elapsed_time": "1:51:33", "remaining_time": "6:25:40"}
+{"current_steps": 985, "total_steps": 4368, "loss": 0.5514, "lr": 3.811920699233535e-05, "epoch": 1.578525641025641, "percentage": 22.55, "elapsed_time": "1:52:08", "remaining_time": "6:25:09"}
+{"current_steps": 990, "total_steps": 4368, "loss": 0.5246, "lr": 3.8085227963415186e-05, "epoch": 1.5865384615384617, "percentage": 22.66, "elapsed_time": "1:52:50", "remaining_time": "6:25:00"}
+{"current_steps": 995, "total_steps": 4368, "loss": 0.5319, "lr": 3.805096016116838e-05, "epoch": 1.594551282051282, "percentage": 22.78, "elapsed_time": "1:53:27", "remaining_time": "6:24:36"}
+{"current_steps": 1000, "total_steps": 4368, "loss": 0.5422, "lr": 3.801640413276121e-05, "epoch": 1.6025641025641026, "percentage": 22.89, "elapsed_time": "1:53:57", "remaining_time": "6:23:50"}
+{"current_steps": 1005, "total_steps": 4368, "loss": 0.487, "lr": 3.7981560429962204e-05, "epoch": 1.6105769230769231, "percentage": 23.01, "elapsed_time": "1:54:34", "remaining_time": "6:23:24"}
+{"current_steps": 1010, "total_steps": 4368, "loss": 0.5211, "lr": 3.7946429609133274e-05, "epoch": 1.6185897435897436, "percentage": 23.12, "elapsed_time": "1:55:13", "remaining_time": "6:23:06"}
+{"current_steps": 1015, "total_steps": 4368, "loss": 0.5188, "lr": 3.791101223122084e-05, "epoch": 1.626602564102564, "percentage": 23.24, "elapsed_time": "1:55:40", "remaining_time": "6:22:07"}
+{"current_steps": 1020, "total_steps": 4368, "loss": 0.5088, "lr": 3.787530886174688e-05, "epoch": 1.6346153846153846, "percentage": 23.35, "elapsed_time": "1:56:13", "remaining_time": "6:21:28"}
+{"current_steps": 1025, "total_steps": 4368, "loss": 0.5486, "lr": 3.783932007079992e-05, "epoch": 1.6426282051282053, "percentage": 23.47, "elapsed_time": "1:56:50", "remaining_time": "6:21:04"}
+{"current_steps": 1030, "total_steps": 4368, "loss": 0.4929, "lr": 3.7803046433025905e-05, "epoch": 1.6506410256410255, "percentage": 23.58, "elapsed_time": "1:57:27", "remaining_time": "6:20:40"}
+{"current_steps": 1035, "total_steps": 4368, "loss": 0.52, "lr": 3.7766488527619024e-05, "epoch": 1.6586538461538463, "percentage": 23.7, "elapsed_time": "1:58:00", "remaining_time": "6:20:01"}
+{"current_steps": 1040, "total_steps": 4368, "loss": 0.4955, "lr": 3.772964693831247e-05, "epoch": 1.6666666666666665, "percentage": 23.81, "elapsed_time": "1:58:31", "remaining_time": "6:19:17"}
+{"current_steps": 1045, "total_steps": 4368, "loss": 0.5276, "lr": 3.7692522253369136e-05, "epoch": 1.6746794871794872, "percentage": 23.92, "elapsed_time": "1:59:08", "remaining_time": "6:18:52"}
+{"current_steps": 1050, "total_steps": 4368, "loss": 0.5139, "lr": 3.7655115065572194e-05, "epoch": 1.6826923076923077, "percentage": 24.04, "elapsed_time": "1:59:31", "remaining_time": "6:17:40"}
+{"current_steps": 1055, "total_steps": 4368, "loss": 0.4682, "lr": 3.7617425972215626e-05, "epoch": 1.6907051282051282, "percentage": 24.15, "elapsed_time": "1:59:58", "remaining_time": "6:16:44"}
+{"current_steps": 1060, "total_steps": 4368, "loss": 0.5348, "lr": 3.757945557509472e-05, "epoch": 1.6987179487179487, "percentage": 24.27, "elapsed_time": "2:00:30", "remaining_time": "6:16:05"}
+{"current_steps": 1065, "total_steps": 4368, "loss": 0.5192, "lr": 3.7541204480496444e-05, "epoch": 1.7067307692307692, "percentage": 24.38, "elapsed_time": "2:01:04", "remaining_time": "6:15:30"}
+{"current_steps": 1070, "total_steps": 4368, "loss": 0.5074, "lr": 3.7502673299189745e-05, "epoch": 1.7147435897435899, "percentage": 24.5, "elapsed_time": "2:01:41", "remaining_time": "6:15:04"}
+{"current_steps": 1075, "total_steps": 4368, "loss": 0.5368, "lr": 3.746386264641583e-05, "epoch": 1.7227564102564101, "percentage": 24.61, "elapsed_time": "2:02:14", "remaining_time": "6:14:27"}
+{"current_steps": 1080, "total_steps": 4368, "loss": 0.5334, "lr": 3.7424773141878324e-05, "epoch": 1.7307692307692308, "percentage": 24.73, "elapsed_time": "2:02:48", "remaining_time": "6:13:52"}
+{"current_steps": 1085, "total_steps": 4368, "loss": 0.5129, "lr": 3.738540540973338e-05, "epoch": 1.7387820512820513, "percentage": 24.84, "elapsed_time": "2:03:27", "remaining_time": "6:13:34"}
+{"current_steps": 1090, "total_steps": 4368, "loss": 0.5256, "lr": 3.7345760078579695e-05, "epoch": 1.7467948717948718, "percentage": 24.95, "elapsed_time": "2:04:02", "remaining_time": "6:13:02"}
+{"current_steps": 1095, "total_steps": 4368, "loss": 0.5195, "lr": 3.730583778144852e-05, "epoch": 1.7548076923076923, "percentage": 25.07, "elapsed_time": "2:04:39", "remaining_time": "6:12:36"}
+{"current_steps": 1100, "total_steps": 4368, "loss": 0.522, "lr": 3.7265639155793494e-05, "epoch": 1.7628205128205128, "percentage": 25.18, "elapsed_time": "2:05:10", "remaining_time": "6:11:53"}
+{"current_steps": 1105, "total_steps": 4368, "loss": 0.528, "lr": 3.7225164843480503e-05, "epoch": 1.7708333333333335, "percentage": 25.3, "elapsed_time": "2:05:46", "remaining_time": "6:11:24"}
+{"current_steps": 1110, "total_steps": 4368, "loss": 0.5171, "lr": 3.7184415490777426e-05, "epoch": 1.7788461538461537, "percentage": 25.41, "elapsed_time": "2:06:22", "remaining_time": "6:10:56"}
+{"current_steps": 1115, "total_steps": 4368, "loss": 0.5287, "lr": 3.714339174834379e-05, "epoch": 1.7868589743589745, "percentage": 25.53, "elapsed_time": "2:07:03", "remaining_time": "6:10:42"}
+{"current_steps": 1120, "total_steps": 4368, "loss": 0.493, "lr": 3.710209427122044e-05, "epoch": 1.7948717948717947, "percentage": 25.64, "elapsed_time": "2:07:32", "remaining_time": "6:09:52"}
+{"current_steps": 1125, "total_steps": 4368, "loss": 0.5003, "lr": 3.7060523718819e-05, "epoch": 1.8028846153846154, "percentage": 25.76, "elapsed_time": "2:08:00", "remaining_time": "6:09:01"}
+{"current_steps": 1130, "total_steps": 4368, "loss": 0.5375, "lr": 3.701868075491139e-05, "epoch": 1.810897435897436, "percentage": 25.87, "elapsed_time": "2:08:28", "remaining_time": "6:08:08"}
+{"current_steps": 1135, "total_steps": 4368, "loss": 0.5086, "lr": 3.697656604761926e-05, "epoch": 1.8189102564102564, "percentage": 25.98, "elapsed_time": "2:09:03", "remaining_time": "6:07:36"}
+{"current_steps": 1140, "total_steps": 4368, "loss": 0.5056, "lr": 3.693418026940325e-05, "epoch": 1.8269230769230769, "percentage": 26.1, "elapsed_time": "2:09:41", "remaining_time": "6:07:14"}
+{"current_steps": 1145, "total_steps": 4368, "loss": 0.4896, "lr": 3.689152409705229e-05, "epoch": 1.8349358974358974, "percentage": 26.21, "elapsed_time": "2:10:09", "remaining_time": "6:06:23"}
+{"current_steps": 1150, "total_steps": 4368, "loss": 0.4998, "lr": 3.6848598211672794e-05, "epoch": 1.842948717948718, "percentage": 26.33, "elapsed_time": "2:10:36", "remaining_time": "6:05:28"}
+{"current_steps": 1155, "total_steps": 4368, "loss": 0.4874, "lr": 3.6805403298677797e-05, "epoch": 1.8509615384615383, "percentage": 26.44, "elapsed_time": "2:11:12", "remaining_time": "6:04:58"}
+{"current_steps": 1160, "total_steps": 4368, "loss": 0.5301, "lr": 3.6761940047775966e-05, "epoch": 1.858974358974359, "percentage": 26.56, "elapsed_time": "2:11:44", "remaining_time": "6:04:20"}
+{"current_steps": 1165, "total_steps": 4368, "loss": 0.5226, "lr": 3.671820915296063e-05, "epoch": 1.8669871794871795, "percentage": 26.67, "elapsed_time": "2:12:16", "remaining_time": "6:03:39"}
+{"current_steps": 1170, "total_steps": 4368, "loss": 0.5085, "lr": 3.667421131249869e-05, "epoch": 1.875, "percentage": 26.79, "elapsed_time": "2:12:43", "remaining_time": "6:02:47"}
+{"current_steps": 1175, "total_steps": 4368, "loss": 0.5034, "lr": 3.662994722891946e-05, "epoch": 1.8830128205128205, "percentage": 26.9, "elapsed_time": "2:13:12", "remaining_time": "6:01:58"}
+{"current_steps": 1180, "total_steps": 4368, "loss": 0.5253, "lr": 3.658541760900344e-05, "epoch": 1.891025641025641, "percentage": 27.01, "elapsed_time": "2:13:52", "remaining_time": "6:01:41"}
+{"current_steps": 1185, "total_steps": 4368, "loss": 0.4923, "lr": 3.654062316377106e-05, "epoch": 1.8990384615384617, "percentage": 27.13, "elapsed_time": "2:14:23", "remaining_time": "6:00:59"}
+{"current_steps": 1190, "total_steps": 4368, "loss": 0.4968, "lr": 3.649556460847131e-05, "epoch": 1.907051282051282, "percentage": 27.24, "elapsed_time": "2:14:52", "remaining_time": "6:00:12"}
+{"current_steps": 1195, "total_steps": 4368, "loss": 0.5464, "lr": 3.6450242662570314e-05, "epoch": 1.9150641025641026, "percentage": 27.36, "elapsed_time": "2:15:28", "remaining_time": "5:59:41"}
+{"current_steps": 1200, "total_steps": 4368, "loss": 0.5017, "lr": 3.6404658049739854e-05, "epoch": 1.9230769230769231, "percentage": 27.47, "elapsed_time": "2:16:05", "remaining_time": "5:59:16"}
+{"current_steps": 1205, "total_steps": 4368, "loss": 0.5117, "lr": 3.63588114978458e-05, "epoch": 1.9310897435897436, "percentage": 27.59, "elapsed_time": "2:16:42", "remaining_time": "5:58:51"}
+{"current_steps": 1210, "total_steps": 4368, "loss": 0.4967, "lr": 3.6312703738936504e-05, "epoch": 1.939102564102564, "percentage": 27.7, "elapsed_time": "2:17:19", "remaining_time": "5:58:23"}
+{"current_steps": 1215, "total_steps": 4368, "loss": 0.4842, "lr": 3.626633550923111e-05, "epoch": 1.9471153846153846, "percentage": 27.82, "elapsed_time": "2:17:58", "remaining_time": "5:58:02"}
+{"current_steps": 1220, "total_steps": 4368, "loss": 0.4889, "lr": 3.621970754910778e-05, "epoch": 1.9551282051282053, "percentage": 27.93, "elapsed_time": "2:18:36", "remaining_time": "5:57:40"}
+{"current_steps": 1225, "total_steps": 4368, "loss": 0.4942, "lr": 3.6172820603091885e-05, "epoch": 1.9631410256410255, "percentage": 28.04, "elapsed_time": "2:19:08", "remaining_time": "5:56:58"}
+{"current_steps": 1230, "total_steps": 4368, "loss": 0.4815, "lr": 3.612567541984413e-05, "epoch": 1.9711538461538463, "percentage": 28.16, "elapsed_time": "2:19:44", "remaining_time": "5:56:30"}
+{"current_steps": 1235, "total_steps": 4368, "loss": 0.5211, "lr": 3.6078272752148574e-05, "epoch": 1.9791666666666665, "percentage": 28.27, "elapsed_time": "2:20:24", "remaining_time": "5:56:11"}
+{"current_steps": 1240, "total_steps": 4368, "loss": 0.5182, "lr": 3.6030613356900635e-05, "epoch": 1.9871794871794872, "percentage": 28.39, "elapsed_time": "2:20:57", "remaining_time": "5:55:34"}
+{"current_steps": 1245, "total_steps": 4368, "loss": 0.4999, "lr": 3.598269799509498e-05, "epoch": 1.9951923076923077, "percentage": 28.5, "elapsed_time": "2:21:27", "remaining_time": "5:54:50"}
+{"current_steps": 1250, "total_steps": 4368, "loss": 0.5314, "lr": 3.5934527431813385e-05, "epoch": 2.003205128205128, "percentage": 28.62, "elapsed_time": "2:22:06", "remaining_time": "5:54:29"}
+{"current_steps": 1255, "total_steps": 4368, "loss": 0.4891, "lr": 3.5886102436212536e-05, "epoch": 2.011217948717949, "percentage": 28.73, "elapsed_time": "2:22:34", "remaining_time": "5:53:39"}
+{"current_steps": 1260, "total_steps": 4368, "loss": 0.4868, "lr": 3.583742378151171e-05, "epoch": 2.019230769230769, "percentage": 28.85, "elapsed_time": "2:23:09", "remaining_time": "5:53:07"}
+{"current_steps": 1265, "total_steps": 4368, "loss": 0.4944, "lr": 3.5788492244980464e-05, "epoch": 2.02724358974359, "percentage": 28.96, "elapsed_time": "2:23:42", "remaining_time": "5:52:29"}
+{"current_steps": 1270, "total_steps": 4368, "loss": 0.4826, "lr": 3.573930860792621e-05, "epoch": 2.03525641025641, "percentage": 29.08, "elapsed_time": "2:24:13", "remaining_time": "5:51:48"}
+{"current_steps": 1275, "total_steps": 4368, "loss": 0.4955, "lr": 3.568987365568173e-05, "epoch": 2.043269230769231, "percentage": 29.19, "elapsed_time": "2:24:45", "remaining_time": "5:51:11"}
+{"current_steps": 1280, "total_steps": 4368, "loss": 0.4912, "lr": 3.564018817759266e-05, "epoch": 2.051282051282051, "percentage": 29.3, "elapsed_time": "2:25:17", "remaining_time": "5:50:30"}
+{"current_steps": 1285, "total_steps": 4368, "loss": 0.4789, "lr": 3.559025296700484e-05, "epoch": 2.059294871794872, "percentage": 29.42, "elapsed_time": "2:25:48", "remaining_time": "5:49:49"}
+{"current_steps": 1290, "total_steps": 4368, "loss": 0.4888, "lr": 3.554006882125173e-05, "epoch": 2.0673076923076925, "percentage": 29.53, "elapsed_time": "2:26:20", "remaining_time": "5:49:10"}
+{"current_steps": 1295, "total_steps": 4368, "loss": 0.4921, "lr": 3.5489636541641586e-05, "epoch": 2.0753205128205128, "percentage": 29.65, "elapsed_time": "2:26:47", "remaining_time": "5:48:19"}
+{"current_steps": 1300, "total_steps": 4368, "loss": 0.478, "lr": 3.543895693344472e-05, "epoch": 2.0833333333333335, "percentage": 29.76, "elapsed_time": "2:27:20", "remaining_time": "5:47:44"}
+{"current_steps": 1305, "total_steps": 4368, "loss": 0.4908, "lr": 3.538803080588063e-05, "epoch": 2.0913461538461537, "percentage": 29.88, "elapsed_time": "2:27:52", "remaining_time": "5:47:04"}
+{"current_steps": 1310, "total_steps": 4368, "loss": 0.4789, "lr": 3.5336858972105076e-05, "epoch": 2.0993589743589745, "percentage": 29.99, "elapsed_time": "2:28:22", "remaining_time": "5:46:20"}
+{"current_steps": 1315, "total_steps": 4368, "loss": 0.4858, "lr": 3.528544224919708e-05, "epoch": 2.1073717948717947, "percentage": 30.11, "elapsed_time": "2:28:55", "remaining_time": "5:45:44"}
+{"current_steps": 1320, "total_steps": 4368, "loss": 0.4942, "lr": 3.5233781458145934e-05, "epoch": 2.1153846153846154, "percentage": 30.22, "elapsed_time": "2:29:32", "remaining_time": "5:45:17"}
+{"current_steps": 1325, "total_steps": 4368, "loss": 0.4767, "lr": 3.5181877423838034e-05, "epoch": 2.123397435897436, "percentage": 30.33, "elapsed_time": "2:30:08", "remaining_time": "5:44:49"}
+{"current_steps": 1330, "total_steps": 4368, "loss": 0.4903, "lr": 3.512973097504371e-05, "epoch": 2.1314102564102564, "percentage": 30.45, "elapsed_time": "2:30:39", "remaining_time": "5:44:08"}
+{"current_steps": 1335, "total_steps": 4368, "loss": 0.4905, "lr": 3.507734294440403e-05, "epoch": 2.139423076923077, "percentage": 30.56, "elapsed_time": "2:31:14", "remaining_time": "5:43:35"}
+{"current_steps": 1340, "total_steps": 4368, "loss": 0.4654, "lr": 3.50247141684175e-05, "epoch": 2.1474358974358974, "percentage": 30.68, "elapsed_time": "2:31:41", "remaining_time": "5:42:47"}
+{"current_steps": 1345, "total_steps": 4368, "loss": 0.4741, "lr": 3.497184548742667e-05, "epoch": 2.155448717948718, "percentage": 30.79, "elapsed_time": "2:32:18", "remaining_time": "5:42:19"}
+{"current_steps": 1350, "total_steps": 4368, "loss": 0.4819, "lr": 3.491873774560473e-05, "epoch": 2.1634615384615383, "percentage": 30.91, "elapsed_time": "2:32:48", "remaining_time": "5:41:36"}
+{"current_steps": 1355, "total_steps": 4368, "loss": 0.4889, "lr": 3.486539179094208e-05, "epoch": 2.171474358974359, "percentage": 31.02, "elapsed_time": "2:33:20", "remaining_time": "5:40:57"}
+{"current_steps": 1360, "total_steps": 4368, "loss": 0.496, "lr": 3.481180847523272e-05, "epoch": 2.1794871794871793, "percentage": 31.14, "elapsed_time": "2:33:51", "remaining_time": "5:40:17"}
+{"current_steps": 1365, "total_steps": 4368, "loss": 0.4668, "lr": 3.4757988654060684e-05, "epoch": 2.1875, "percentage": 31.25, "elapsed_time": "2:34:24", "remaining_time": "5:39:40"}
+{"current_steps": 1370, "total_steps": 4368, "loss": 0.4848, "lr": 3.470393318678637e-05, "epoch": 2.1955128205128207, "percentage": 31.36, "elapsed_time": "2:34:53", "remaining_time": "5:38:58"}
+{"current_steps": 1375, "total_steps": 4368, "loss": 0.4529, "lr": 3.4649642936532836e-05, "epoch": 2.203525641025641, "percentage": 31.48, "elapsed_time": "2:35:25", "remaining_time": "5:38:19"}
+{"current_steps": 1380, "total_steps": 4368, "loss": 0.4754, "lr": 3.4595118770171984e-05, "epoch": 2.2115384615384617, "percentage": 31.59, "elapsed_time": "2:35:57", "remaining_time": "5:37:41"}
+{"current_steps": 1385, "total_steps": 4368, "loss": 0.4613, "lr": 3.454036155831077e-05, "epoch": 2.219551282051282, "percentage": 31.71, "elapsed_time": "2:36:39", "remaining_time": "5:37:25"}
+{"current_steps": 1390, "total_steps": 4368, "loss": 0.4866, "lr": 3.4485372175277236e-05, "epoch": 2.2275641025641026, "percentage": 31.82, "elapsed_time": "2:37:11", "remaining_time": "5:36:47"}
+{"current_steps": 1395, "total_steps": 4368, "loss": 0.4799, "lr": 3.44301514991066e-05, "epoch": 2.235576923076923, "percentage": 31.94, "elapsed_time": "2:37:43", "remaining_time": "5:36:09"}
+{"current_steps": 1400, "total_steps": 4368, "loss": 0.4898, "lr": 3.4374700411527225e-05, "epoch": 2.2435897435897436, "percentage": 32.05, "elapsed_time": "2:38:22", "remaining_time": "5:35:44"}
+{"current_steps": 1405, "total_steps": 4368, "loss": 0.5002, "lr": 3.431901979794653e-05, "epoch": 2.251602564102564, "percentage": 32.17, "elapsed_time": "2:38:54", "remaining_time": "5:35:07"}
+{"current_steps": 1410, "total_steps": 4368, "loss": 0.4801, "lr": 3.426311054743685e-05, "epoch": 2.2596153846153846, "percentage": 32.28, "elapsed_time": "2:39:20", "remaining_time": "5:34:16"}
+{"current_steps": 1415, "total_steps": 4368, "loss": 0.4954, "lr": 3.420697355272127e-05, "epoch": 2.2676282051282053, "percentage": 32.39, "elapsed_time": "2:39:57", "remaining_time": "5:33:49"}
+{"current_steps": 1420, "total_steps": 4368, "loss": 0.4855, "lr": 3.415060971015933e-05, "epoch": 2.2756410256410255, "percentage": 32.51, "elapsed_time": "2:40:29", "remaining_time": "5:33:11"}
+{"current_steps": 1425, "total_steps": 4368, "loss": 0.4701, "lr": 3.4094019919732736e-05, "epoch": 2.2836538461538463, "percentage": 32.62, "elapsed_time": "2:40:57", "remaining_time": "5:32:25"}
+{"current_steps": 1430, "total_steps": 4368, "loss": 0.4814, "lr": 3.403720508503098e-05, "epoch": 2.2916666666666665, "percentage": 32.74, "elapsed_time": "2:41:33", "remaining_time": "5:31:56"}
+{"current_steps": 1435, "total_steps": 4368, "loss": 0.4613, "lr": 3.398016611323693e-05, "epoch": 2.2996794871794872, "percentage": 32.85, "elapsed_time": "2:42:03", "remaining_time": "5:31:14"}
+{"current_steps": 1440, "total_steps": 4368, "loss": 0.4826, "lr": 3.392290391511232e-05, "epoch": 2.3076923076923075, "percentage": 32.97, "elapsed_time": "2:42:40", "remaining_time": "5:30:46"}
+{"current_steps": 1445, "total_steps": 4368, "loss": 0.4692, "lr": 3.386541940498322e-05, "epoch": 2.315705128205128, "percentage": 33.08, "elapsed_time": "2:43:14", "remaining_time": "5:30:12"}
+{"current_steps": 1450, "total_steps": 4368, "loss": 0.4883, "lr": 3.380771350072543e-05, "epoch": 2.323717948717949, "percentage": 33.2, "elapsed_time": "2:43:43", "remaining_time": "5:29:28"}
+{"current_steps": 1455, "total_steps": 4368, "loss": 0.4807, "lr": 3.374978712374986e-05, "epoch": 2.331730769230769, "percentage": 33.31, "elapsed_time": "2:44:15", "remaining_time": "5:28:50"}
+{"current_steps": 1460, "total_steps": 4368, "loss": 0.4669, "lr": 3.369164119898774e-05, "epoch": 2.33974358974359, "percentage": 33.42, "elapsed_time": "2:44:51", "remaining_time": "5:28:22"}
+{"current_steps": 1465, "total_steps": 4368, "loss": 0.5001, "lr": 3.363327665487593e-05, "epoch": 2.34775641025641, "percentage": 33.54, "elapsed_time": "2:45:31", "remaining_time": "5:28:00"}
+{"current_steps": 1470, "total_steps": 4368, "loss": 0.5013, "lr": 3.357469442334206e-05, "epoch": 2.355769230769231, "percentage": 33.65, "elapsed_time": "2:46:07", "remaining_time": "5:27:31"}
+{"current_steps": 1475, "total_steps": 4368, "loss": 0.4724, "lr": 3.351589543978965e-05, "epoch": 2.363782051282051, "percentage": 33.77, "elapsed_time": "2:46:34", "remaining_time": "5:26:43"}
+{"current_steps": 1480, "total_steps": 4368, "loss": 0.4442, "lr": 3.345688064308317e-05, "epoch": 2.371794871794872, "percentage": 33.88, "elapsed_time": "2:47:03", "remaining_time": "5:25:59"}
+{"current_steps": 1485, "total_steps": 4368, "loss": 0.4715, "lr": 3.339765097553307e-05, "epoch": 2.3798076923076925, "percentage": 34.0, "elapsed_time": "2:47:39", "remaining_time": "5:25:29"}
+{"current_steps": 1490, "total_steps": 4368, "loss": 0.4965, "lr": 3.33382073828807e-05, "epoch": 2.3878205128205128, "percentage": 34.11, "elapsed_time": "2:48:24", "remaining_time": "5:25:17"}
+{"current_steps": 1495, "total_steps": 4368, "loss": 0.4658, "lr": 3.327855081428326e-05, "epoch": 2.3958333333333335, "percentage": 34.23, "elapsed_time": "2:48:56", "remaining_time": "5:24:39"}
+{"current_steps": 1500, "total_steps": 4368, "loss": 0.4668, "lr": 3.3218682222298584e-05, "epoch": 2.4038461538461537, "percentage": 34.34, "elapsed_time": "2:49:28", "remaining_time": "5:24:01"}
+{"current_steps": 1505, "total_steps": 4368, "loss": 0.4531, "lr": 3.315860256286996e-05, "epoch": 2.4118589743589745, "percentage": 34.46, "elapsed_time": "2:50:38", "remaining_time": "5:24:36"}
+{"current_steps": 1510, "total_steps": 4368, "loss": 0.4799, "lr": 3.3098312795310894e-05, "epoch": 2.4198717948717947, "percentage": 34.57, "elapsed_time": "2:51:11", "remaining_time": "5:24:00"}
+{"current_steps": 1515, "total_steps": 4368, "loss": 0.4576, "lr": 3.303781388228974e-05, "epoch": 2.4278846153846154, "percentage": 34.68, "elapsed_time": "2:51:53", "remaining_time": "5:23:42"}
+{"current_steps": 1520, "total_steps": 4368, "loss": 0.4892, "lr": 3.297710678981435e-05, "epoch": 2.435897435897436, "percentage": 34.8, "elapsed_time": "2:52:27", "remaining_time": "5:23:07"}
+{"current_steps": 1525, "total_steps": 4368, "loss": 0.503, "lr": 3.291619248721667e-05, "epoch": 2.4439102564102564, "percentage": 34.91, "elapsed_time": "2:52:58", "remaining_time": "5:22:29"}
+{"current_steps": 1530, "total_steps": 4368, "loss": 0.4559, "lr": 3.285507194713724e-05, "epoch": 2.451923076923077, "percentage": 35.03, "elapsed_time": "2:53:31", "remaining_time": "5:21:52"}
+{"current_steps": 1535, "total_steps": 4368, "loss": 0.4832, "lr": 3.279374614550966e-05, "epoch": 2.4599358974358974, "percentage": 35.14, "elapsed_time": "2:54:05", "remaining_time": "5:21:18"}
+{"current_steps": 1540, "total_steps": 4368, "loss": 0.4852, "lr": 3.2732216061545e-05, "epoch": 2.467948717948718, "percentage": 35.26, "elapsed_time": "2:54:36", "remaining_time": "5:20:37"}
+{"current_steps": 1545, "total_steps": 4368, "loss": 0.5175, "lr": 3.2670482677716214e-05, "epoch": 2.4759615384615383, "percentage": 35.37, "elapsed_time": "2:55:11", "remaining_time": "5:20:07"}
+{"current_steps": 1550, "total_steps": 4368, "loss": 0.4546, "lr": 3.2608546979742394e-05, "epoch": 2.483974358974359, "percentage": 35.49, "elapsed_time": "2:55:47", "remaining_time": "5:19:35"}
+{"current_steps": 1555, "total_steps": 4368, "loss": 0.498, "lr": 3.254640995657307e-05, "epoch": 2.4919871794871793, "percentage": 35.6, "elapsed_time": "2:56:24", "remaining_time": "5:19:06"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d330997b455901ea10dee2e751aa436c1c61073d9148d3e0a98f4d21f95d1226
+size 8657