Training in progress, step 1500

.gitattributes

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

added_tokens.json

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

chat_template.jinja

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

config.json

@@ -0,0 +1,68 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "dtype": "bfloat16",
+  "eos_token_id": 151645,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 12288,
+  "layer_types": [
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention",
+    "full_attention"
+  ],
+  "max_position_embeddings": 40960,
+  "max_window_layers": 36,
+  "model_type": "qwen3",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 8,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "transformers_version": "4.57.6",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "temperature": 0.6,
+  "top_k": 20,
+  "top_p": 0.95,
+  "transformers_version": "4.57.6"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e3e7405195d9535cbcc2e40bfdda086e3a1ce768425b8a2b19bcef9a00659886
+size 4902257696

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a267463f9ecb79f35ee12130c7e3658cd29d9e33482265491de317fb7a49a9d5
+size 4915960368

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:95c0f7234ee1208bd929499611fa99e2d808746fdb0c56c70ea186329b02339e
+size 4983068496

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:162c72a25c01fa49c26992c2ee5aeb7bd514eb2f51b175991c023a63473bdc6b
+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": "glm46-bash-textbook-traces",
+  "training_start": null,
+  "training_end": null,
+  "created_by": "DCAgent",
+  "base_model_name": "Qwen/Qwen3-8B",
+  "dataset_name": "DCAgent/glm46-bash-textbook-traces",
+  "training_type": "SFT",
+  "training_parameters": "https://huggingface.co/laion/glm46-bash-textbook-traces/blob/main/config.json",
+  "wandb_link": "https://wandb.ai/dogml/OpenThoughts-Agent/runs/sft_glm46-bash-textbook-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 +1,320 @@
+{"current_steps": 5, "total_steps": 2884, "loss": 0.6964, "lr": 5.536332179930796e-07, "epoch": 0.012135922330097087, "percentage": 0.17, "elapsed_time": "0:00:48", "remaining_time": "7:43:40"}
+{"current_steps": 10, "total_steps": 2884, "loss": 0.6879, "lr": 1.2456747404844292e-06, "epoch": 0.024271844660194174, "percentage": 0.35, "elapsed_time": "0:01:39", "remaining_time": "7:57:28"}
+{"current_steps": 15, "total_steps": 2884, "loss": 0.6731, "lr": 1.9377162629757786e-06, "epoch": 0.03640776699029126, "percentage": 0.52, "elapsed_time": "0:02:22", "remaining_time": "7:33:09"}
+{"current_steps": 20, "total_steps": 2884, "loss": 0.6458, "lr": 2.629757785467128e-06, "epoch": 0.04854368932038835, "percentage": 0.69, "elapsed_time": "0:02:56", "remaining_time": "7:02:04"}
+{"current_steps": 25, "total_steps": 2884, "loss": 0.612, "lr": 3.3217993079584777e-06, "epoch": 0.06067961165048544, "percentage": 0.87, "elapsed_time": "0:03:32", "remaining_time": "6:44:22"}
+{"current_steps": 30, "total_steps": 2884, "loss": 0.5331, "lr": 4.0138408304498275e-06, "epoch": 0.07281553398058252, "percentage": 1.04, "elapsed_time": "0:04:15", "remaining_time": "6:44:51"}
+{"current_steps": 35, "total_steps": 2884, "loss": 0.4874, "lr": 4.705882352941177e-06, "epoch": 0.08495145631067962, "percentage": 1.21, "elapsed_time": "0:05:02", "remaining_time": "6:49:55"}
+{"current_steps": 40, "total_steps": 2884, "loss": 0.4341, "lr": 5.397923875432527e-06, "epoch": 0.0970873786407767, "percentage": 1.39, "elapsed_time": "0:05:54", "remaining_time": "6:59:31"}
+{"current_steps": 45, "total_steps": 2884, "loss": 0.4436, "lr": 6.089965397923876e-06, "epoch": 0.10922330097087378, "percentage": 1.56, "elapsed_time": "0:06:28", "remaining_time": "6:48:31"}
+{"current_steps": 50, "total_steps": 2884, "loss": 0.4312, "lr": 6.782006920415225e-06, "epoch": 0.12135922330097088, "percentage": 1.73, "elapsed_time": "0:07:04", "remaining_time": "6:40:50"}
+{"current_steps": 55, "total_steps": 2884, "loss": 0.392, "lr": 7.474048442906575e-06, "epoch": 0.13349514563106796, "percentage": 1.91, "elapsed_time": "0:07:59", "remaining_time": "6:51:10"}
+{"current_steps": 60, "total_steps": 2884, "loss": 0.4005, "lr": 8.166089965397924e-06, "epoch": 0.14563106796116504, "percentage": 2.08, "elapsed_time": "0:08:45", "remaining_time": "6:52:08"}
+{"current_steps": 65, "total_steps": 2884, "loss": 0.3801, "lr": 8.858131487889274e-06, "epoch": 0.15776699029126215, "percentage": 2.25, "elapsed_time": "0:09:24", "remaining_time": "6:48:19"}
+{"current_steps": 70, "total_steps": 2884, "loss": 0.3712, "lr": 9.550173010380624e-06, "epoch": 0.16990291262135923, "percentage": 2.43, "elapsed_time": "0:10:06", "remaining_time": "6:46:27"}
+{"current_steps": 75, "total_steps": 2884, "loss": 0.3625, "lr": 1.0242214532871973e-05, "epoch": 0.1820388349514563, "percentage": 2.6, "elapsed_time": "0:10:48", "remaining_time": "6:44:50"}
+{"current_steps": 80, "total_steps": 2884, "loss": 0.3576, "lr": 1.0934256055363323e-05, "epoch": 0.1941747572815534, "percentage": 2.77, "elapsed_time": "0:11:34", "remaining_time": "6:45:33"}
+{"current_steps": 85, "total_steps": 2884, "loss": 0.3622, "lr": 1.1626297577854673e-05, "epoch": 0.20631067961165048, "percentage": 2.95, "elapsed_time": "0:12:20", "remaining_time": "6:46:40"}
+{"current_steps": 90, "total_steps": 2884, "loss": 0.3631, "lr": 1.2318339100346022e-05, "epoch": 0.21844660194174756, "percentage": 3.12, "elapsed_time": "0:12:52", "remaining_time": "6:39:45"}
+{"current_steps": 95, "total_steps": 2884, "loss": 0.358, "lr": 1.301038062283737e-05, "epoch": 0.23058252427184467, "percentage": 3.29, "elapsed_time": "0:13:40", "remaining_time": "6:41:33"}
+{"current_steps": 100, "total_steps": 2884, "loss": 0.341, "lr": 1.370242214532872e-05, "epoch": 0.24271844660194175, "percentage": 3.47, "elapsed_time": "0:14:17", "remaining_time": "6:37:52"}
+{"current_steps": 105, "total_steps": 2884, "loss": 0.3404, "lr": 1.439446366782007e-05, "epoch": 0.25485436893203883, "percentage": 3.64, "elapsed_time": "0:15:02", "remaining_time": "6:38:18"}
+{"current_steps": 110, "total_steps": 2884, "loss": 0.3364, "lr": 1.5086505190311421e-05, "epoch": 0.2669902912621359, "percentage": 3.81, "elapsed_time": "0:15:46", "remaining_time": "6:37:41"}
+{"current_steps": 115, "total_steps": 2884, "loss": 0.3295, "lr": 1.577854671280277e-05, "epoch": 0.279126213592233, "percentage": 3.99, "elapsed_time": "0:16:21", "remaining_time": "6:34:01"}
+{"current_steps": 120, "total_steps": 2884, "loss": 0.342, "lr": 1.647058823529412e-05, "epoch": 0.2912621359223301, "percentage": 4.16, "elapsed_time": "0:16:54", "remaining_time": "6:29:32"}
+{"current_steps": 125, "total_steps": 2884, "loss": 0.3209, "lr": 1.716262975778547e-05, "epoch": 0.30339805825242716, "percentage": 4.33, "elapsed_time": "0:17:36", "remaining_time": "6:28:47"}
+{"current_steps": 130, "total_steps": 2884, "loss": 0.3122, "lr": 1.785467128027682e-05, "epoch": 0.3155339805825243, "percentage": 4.51, "elapsed_time": "0:18:04", "remaining_time": "6:22:54"}
+{"current_steps": 135, "total_steps": 2884, "loss": 0.3184, "lr": 1.8546712802768167e-05, "epoch": 0.3276699029126214, "percentage": 4.68, "elapsed_time": "0:18:36", "remaining_time": "6:19:02"}
+{"current_steps": 140, "total_steps": 2884, "loss": 0.3057, "lr": 1.9238754325259517e-05, "epoch": 0.33980582524271846, "percentage": 4.85, "elapsed_time": "0:19:11", "remaining_time": "6:16:18"}
+{"current_steps": 145, "total_steps": 2884, "loss": 0.3047, "lr": 1.9930795847750867e-05, "epoch": 0.35194174757281554, "percentage": 5.03, "elapsed_time": "0:19:54", "remaining_time": "6:16:05"}
+{"current_steps": 150, "total_steps": 2884, "loss": 0.3139, "lr": 2.0622837370242218e-05, "epoch": 0.3640776699029126, "percentage": 5.2, "elapsed_time": "0:20:43", "remaining_time": "6:17:52"}
+{"current_steps": 155, "total_steps": 2884, "loss": 0.3155, "lr": 2.1314878892733564e-05, "epoch": 0.3762135922330097, "percentage": 5.37, "elapsed_time": "0:21:26", "remaining_time": "6:17:28"}
+{"current_steps": 160, "total_steps": 2884, "loss": 0.3206, "lr": 2.2006920415224915e-05, "epoch": 0.3883495145631068, "percentage": 5.55, "elapsed_time": "0:22:05", "remaining_time": "6:16:03"}
+{"current_steps": 165, "total_steps": 2884, "loss": 0.3166, "lr": 2.2698961937716265e-05, "epoch": 0.40048543689320387, "percentage": 5.72, "elapsed_time": "0:22:47", "remaining_time": "6:15:35"}
+{"current_steps": 170, "total_steps": 2884, "loss": 0.313, "lr": 2.339100346020761e-05, "epoch": 0.41262135922330095, "percentage": 5.89, "elapsed_time": "0:23:44", "remaining_time": "6:19:04"}
+{"current_steps": 175, "total_steps": 2884, "loss": 0.3092, "lr": 2.4083044982698965e-05, "epoch": 0.42475728155339804, "percentage": 6.07, "elapsed_time": "0:24:31", "remaining_time": "6:19:31"}
+{"current_steps": 180, "total_steps": 2884, "loss": 0.2915, "lr": 2.4775086505190315e-05, "epoch": 0.4368932038834951, "percentage": 6.24, "elapsed_time": "0:25:13", "remaining_time": "6:18:56"}
+{"current_steps": 185, "total_steps": 2884, "loss": 0.309, "lr": 2.5467128027681662e-05, "epoch": 0.44902912621359226, "percentage": 6.41, "elapsed_time": "0:25:55", "remaining_time": "6:18:18"}
+{"current_steps": 190, "total_steps": 2884, "loss": 0.2829, "lr": 2.6159169550173012e-05, "epoch": 0.46116504854368934, "percentage": 6.59, "elapsed_time": "0:26:38", "remaining_time": "6:17:49"}
+{"current_steps": 195, "total_steps": 2884, "loss": 0.3158, "lr": 2.685121107266436e-05, "epoch": 0.4733009708737864, "percentage": 6.76, "elapsed_time": "0:27:26", "remaining_time": "6:18:24"}
+{"current_steps": 200, "total_steps": 2884, "loss": 0.2954, "lr": 2.7543252595155713e-05, "epoch": 0.4854368932038835, "percentage": 6.93, "elapsed_time": "0:28:27", "remaining_time": "6:21:55"}
+{"current_steps": 205, "total_steps": 2884, "loss": 0.3014, "lr": 2.8235294117647063e-05, "epoch": 0.4975728155339806, "percentage": 7.11, "elapsed_time": "0:29:08", "remaining_time": "6:20:52"}
+{"current_steps": 210, "total_steps": 2884, "loss": 0.2974, "lr": 2.892733564013841e-05, "epoch": 0.5097087378640777, "percentage": 7.28, "elapsed_time": "0:29:47", "remaining_time": "6:19:23"}
+{"current_steps": 215, "total_steps": 2884, "loss": 0.2768, "lr": 2.961937716262976e-05, "epoch": 0.5218446601941747, "percentage": 7.45, "elapsed_time": "0:30:37", "remaining_time": "6:20:12"}
+{"current_steps": 220, "total_steps": 2884, "loss": 0.3005, "lr": 3.0311418685121107e-05, "epoch": 0.5339805825242718, "percentage": 7.63, "elapsed_time": "0:31:13", "remaining_time": "6:18:03"}
+{"current_steps": 225, "total_steps": 2884, "loss": 0.2932, "lr": 3.100346020761246e-05, "epoch": 0.5461165048543689, "percentage": 7.8, "elapsed_time": "0:31:50", "remaining_time": "6:16:15"}
+{"current_steps": 230, "total_steps": 2884, "loss": 0.2929, "lr": 3.169550173010381e-05, "epoch": 0.558252427184466, "percentage": 7.98, "elapsed_time": "0:32:26", "remaining_time": "6:14:21"}
+{"current_steps": 235, "total_steps": 2884, "loss": 0.2844, "lr": 3.238754325259516e-05, "epoch": 0.5703883495145631, "percentage": 8.15, "elapsed_time": "0:33:17", "remaining_time": "6:15:15"}
+{"current_steps": 240, "total_steps": 2884, "loss": 0.3013, "lr": 3.307958477508651e-05, "epoch": 0.5825242718446602, "percentage": 8.32, "elapsed_time": "0:33:52", "remaining_time": "6:13:13"}
+{"current_steps": 245, "total_steps": 2884, "loss": 0.2822, "lr": 3.377162629757786e-05, "epoch": 0.5946601941747572, "percentage": 8.5, "elapsed_time": "0:34:29", "remaining_time": "6:11:30"}
+{"current_steps": 250, "total_steps": 2884, "loss": 0.2775, "lr": 3.446366782006921e-05, "epoch": 0.6067961165048543, "percentage": 8.67, "elapsed_time": "0:35:05", "remaining_time": "6:09:45"}
+{"current_steps": 255, "total_steps": 2884, "loss": 0.2912, "lr": 3.515570934256056e-05, "epoch": 0.6189320388349514, "percentage": 8.84, "elapsed_time": "0:35:44", "remaining_time": "6:08:25"}
+{"current_steps": 260, "total_steps": 2884, "loss": 0.2649, "lr": 3.58477508650519e-05, "epoch": 0.6310679611650486, "percentage": 9.02, "elapsed_time": "0:36:26", "remaining_time": "6:07:48"}
+{"current_steps": 265, "total_steps": 2884, "loss": 0.28, "lr": 3.653979238754326e-05, "epoch": 0.6432038834951457, "percentage": 9.19, "elapsed_time": "0:37:07", "remaining_time": "6:06:58"}
+{"current_steps": 270, "total_steps": 2884, "loss": 0.2774, "lr": 3.723183391003461e-05, "epoch": 0.6553398058252428, "percentage": 9.36, "elapsed_time": "0:37:52", "remaining_time": "6:06:42"}
+{"current_steps": 275, "total_steps": 2884, "loss": 0.268, "lr": 3.792387543252595e-05, "epoch": 0.6674757281553398, "percentage": 9.54, "elapsed_time": "0:38:25", "remaining_time": "6:04:37"}
+{"current_steps": 280, "total_steps": 2884, "loss": 0.2799, "lr": 3.86159169550173e-05, "epoch": 0.6796116504854369, "percentage": 9.71, "elapsed_time": "0:39:01", "remaining_time": "6:02:59"}
+{"current_steps": 285, "total_steps": 2884, "loss": 0.2723, "lr": 3.930795847750865e-05, "epoch": 0.691747572815534, "percentage": 9.88, "elapsed_time": "0:39:38", "remaining_time": "6:01:34"}
+{"current_steps": 290, "total_steps": 2884, "loss": 0.2709, "lr": 4e-05, "epoch": 0.7038834951456311, "percentage": 10.06, "elapsed_time": "0:40:16", "remaining_time": "6:00:15"}
+{"current_steps": 295, "total_steps": 2884, "loss": 0.2746, "lr": 3.9999633593049284e-05, "epoch": 0.7160194174757282, "percentage": 10.23, "elapsed_time": "0:40:55", "remaining_time": "5:59:07"}
+{"current_steps": 300, "total_steps": 2884, "loss": 0.2801, "lr": 3.999853438562254e-05, "epoch": 0.7281553398058253, "percentage": 10.4, "elapsed_time": "0:41:41", "remaining_time": "5:59:03"}
+{"current_steps": 305, "total_steps": 2884, "loss": 0.2764, "lr": 3.999670241799547e-05, "epoch": 0.7402912621359223, "percentage": 10.58, "elapsed_time": "0:42:18", "remaining_time": "5:57:47"}
+{"current_steps": 310, "total_steps": 2884, "loss": 0.2706, "lr": 3.9994137757292664e-05, "epoch": 0.7524271844660194, "percentage": 10.75, "elapsed_time": "0:42:59", "remaining_time": "5:56:59"}
+{"current_steps": 315, "total_steps": 2884, "loss": 0.2704, "lr": 3.999084049748507e-05, "epoch": 0.7645631067961165, "percentage": 10.92, "elapsed_time": "0:43:32", "remaining_time": "5:55:04"}
+{"current_steps": 320, "total_steps": 2884, "loss": 0.2619, "lr": 3.998681075938658e-05, "epoch": 0.7766990291262136, "percentage": 11.1, "elapsed_time": "0:44:20", "remaining_time": "5:55:14"}
+{"current_steps": 325, "total_steps": 2884, "loss": 0.2871, "lr": 3.998204869064959e-05, "epoch": 0.7888349514563107, "percentage": 11.27, "elapsed_time": "0:44:54", "remaining_time": "5:53:34"}
+{"current_steps": 330, "total_steps": 2884, "loss": 0.2799, "lr": 3.997655446575961e-05, "epoch": 0.8009708737864077, "percentage": 11.44, "elapsed_time": "0:45:46", "remaining_time": "5:54:13"}
+{"current_steps": 335, "total_steps": 2884, "loss": 0.2925, "lr": 3.9970328286028866e-05, "epoch": 0.8131067961165048, "percentage": 11.62, "elapsed_time": "0:46:13", "remaining_time": "5:51:46"}
+{"current_steps": 340, "total_steps": 2884, "loss": 0.2713, "lr": 3.9963370379588914e-05, "epoch": 0.8252427184466019, "percentage": 11.79, "elapsed_time": "0:46:42", "remaining_time": "5:49:32"}
+{"current_steps": 345, "total_steps": 2884, "loss": 0.2848, "lr": 3.9955681001382265e-05, "epoch": 0.837378640776699, "percentage": 11.96, "elapsed_time": "0:47:20", "remaining_time": "5:48:23"}
+{"current_steps": 350, "total_steps": 2884, "loss": 0.2767, "lr": 3.994726043315309e-05, "epoch": 0.8495145631067961, "percentage": 12.14, "elapsed_time": "0:47:56", "remaining_time": "5:47:08"}
+{"current_steps": 355, "total_steps": 2884, "loss": 0.2624, "lr": 3.9938108983436875e-05, "epoch": 0.8616504854368932, "percentage": 12.31, "elapsed_time": "0:48:37", "remaining_time": "5:46:26"}
+{"current_steps": 360, "total_steps": 2884, "loss": 0.2575, "lr": 3.992822698754908e-05, "epoch": 0.8737864077669902, "percentage": 12.48, "elapsed_time": "0:49:21", "remaining_time": "5:46:05"}
+{"current_steps": 365, "total_steps": 2884, "loss": 0.2758, "lr": 3.9917614807572905e-05, "epoch": 0.8859223300970874, "percentage": 12.66, "elapsed_time": "0:50:00", "remaining_time": "5:45:04"}
+{"current_steps": 370, "total_steps": 2884, "loss": 0.2704, "lr": 3.990627283234601e-05, "epoch": 0.8980582524271845, "percentage": 12.83, "elapsed_time": "0:50:32", "remaining_time": "5:43:23"}
+{"current_steps": 375, "total_steps": 2884, "loss": 0.2742, "lr": 3.989420147744625e-05, "epoch": 0.9101941747572816, "percentage": 13.0, "elapsed_time": "0:51:10", "remaining_time": "5:42:22"}
+{"current_steps": 380, "total_steps": 2884, "loss": 0.2691, "lr": 3.9881401185176456e-05, "epoch": 0.9223300970873787, "percentage": 13.18, "elapsed_time": "0:51:39", "remaining_time": "5:40:27"}
+{"current_steps": 385, "total_steps": 2884, "loss": 0.271, "lr": 3.986787242454823e-05, "epoch": 0.9344660194174758, "percentage": 13.35, "elapsed_time": "0:52:08", "remaining_time": "5:38:28"}
+{"current_steps": 390, "total_steps": 2884, "loss": 0.2674, "lr": 3.985361569126477e-05, "epoch": 0.9466019417475728, "percentage": 13.52, "elapsed_time": "0:52:49", "remaining_time": "5:37:47"}
+{"current_steps": 395, "total_steps": 2884, "loss": 0.2639, "lr": 3.9838631507702685e-05, "epoch": 0.9587378640776699, "percentage": 13.7, "elapsed_time": "0:53:27", "remaining_time": "5:36:52"}
+{"current_steps": 400, "total_steps": 2884, "loss": 0.2712, "lr": 3.982292042289289e-05, "epoch": 0.970873786407767, "percentage": 13.87, "elapsed_time": "0:54:06", "remaining_time": "5:36:01"}
+{"current_steps": 405, "total_steps": 2884, "loss": 0.2647, "lr": 3.980648301250044e-05, "epoch": 0.9830097087378641, "percentage": 14.04, "elapsed_time": "0:54:53", "remaining_time": "5:35:58"}
+{"current_steps": 410, "total_steps": 2884, "loss": 0.2718, "lr": 3.978931987880348e-05, "epoch": 0.9951456310679612, "percentage": 14.22, "elapsed_time": "0:55:32", "remaining_time": "5:35:09"}
+{"current_steps": 415, "total_steps": 2884, "loss": 0.2551, "lr": 3.977143165067117e-05, "epoch": 1.0072815533980584, "percentage": 14.39, "elapsed_time": "0:56:12", "remaining_time": "5:34:26"}
+{"current_steps": 420, "total_steps": 2884, "loss": 0.2575, "lr": 3.97528189835406e-05, "epoch": 1.0194174757281553, "percentage": 14.56, "elapsed_time": "0:56:49", "remaining_time": "5:33:20"}
+{"current_steps": 425, "total_steps": 2884, "loss": 0.2384, "lr": 3.973348255939284e-05, "epoch": 1.0315533980582525, "percentage": 14.74, "elapsed_time": "0:57:24", "remaining_time": "5:32:06"}
+{"current_steps": 430, "total_steps": 2884, "loss": 0.2408, "lr": 3.971342308672792e-05, "epoch": 1.0436893203883495, "percentage": 14.91, "elapsed_time": "0:57:55", "remaining_time": "5:30:31"}
+{"current_steps": 435, "total_steps": 2884, "loss": 0.2496, "lr": 3.969264130053886e-05, "epoch": 1.0558252427184467, "percentage": 15.08, "elapsed_time": "0:58:36", "remaining_time": "5:29:56"}
+{"current_steps": 440, "total_steps": 2884, "loss": 0.2568, "lr": 3.967113796228475e-05, "epoch": 1.0679611650485437, "percentage": 15.26, "elapsed_time": "0:59:17", "remaining_time": "5:29:20"}
+{"current_steps": 445, "total_steps": 2884, "loss": 0.2336, "lr": 3.9648913859862835e-05, "epoch": 1.0800970873786409, "percentage": 15.43, "elapsed_time": "0:59:59", "remaining_time": "5:28:49"}
+{"current_steps": 450, "total_steps": 2884, "loss": 0.2571, "lr": 3.962596980757969e-05, "epoch": 1.0922330097087378, "percentage": 15.6, "elapsed_time": "1:00:35", "remaining_time": "5:27:42"}
+{"current_steps": 455, "total_steps": 2884, "loss": 0.2473, "lr": 3.9602306646121335e-05, "epoch": 1.104368932038835, "percentage": 15.78, "elapsed_time": "1:01:09", "remaining_time": "5:26:27"}
+{"current_steps": 460, "total_steps": 2884, "loss": 0.2546, "lr": 3.957792524252245e-05, "epoch": 1.116504854368932, "percentage": 15.95, "elapsed_time": "1:01:32", "remaining_time": "5:24:16"}
+{"current_steps": 465, "total_steps": 2884, "loss": 0.2344, "lr": 3.9552826490134615e-05, "epoch": 1.1286407766990292, "percentage": 16.12, "elapsed_time": "1:02:09", "remaining_time": "5:23:22"}
+{"current_steps": 470, "total_steps": 2884, "loss": 0.2311, "lr": 3.9527011308593564e-05, "epoch": 1.1407766990291262, "percentage": 16.3, "elapsed_time": "1:02:49", "remaining_time": "5:22:41"}
+{"current_steps": 475, "total_steps": 2884, "loss": 0.2527, "lr": 3.9500480643785485e-05, "epoch": 1.1529126213592233, "percentage": 16.47, "elapsed_time": "1:03:26", "remaining_time": "5:21:45"}
+{"current_steps": 480, "total_steps": 2884, "loss": 0.249, "lr": 3.947323546781238e-05, "epoch": 1.1650485436893203, "percentage": 16.64, "elapsed_time": "1:04:12", "remaining_time": "5:21:33"}
+{"current_steps": 485, "total_steps": 2884, "loss": 0.2498, "lr": 3.9445276778956436e-05, "epoch": 1.1771844660194175, "percentage": 16.82, "elapsed_time": "1:04:45", "remaining_time": "5:20:20"}
+{"current_steps": 490, "total_steps": 2884, "loss": 0.2486, "lr": 3.941660560164345e-05, "epoch": 1.1893203883495145, "percentage": 16.99, "elapsed_time": "1:05:16", "remaining_time": "5:18:53"}
+{"current_steps": 495, "total_steps": 2884, "loss": 0.2572, "lr": 3.9387222986405275e-05, "epoch": 1.2014563106796117, "percentage": 17.16, "elapsed_time": "1:06:06", "remaining_time": "5:19:04"}
+{"current_steps": 500, "total_steps": 2884, "loss": 0.2455, "lr": 3.935713000984136e-05, "epoch": 1.2135922330097086, "percentage": 17.34, "elapsed_time": "1:06:32", "remaining_time": "5:17:15"}
+{"current_steps": 505, "total_steps": 2884, "loss": 0.2557, "lr": 3.93263277745793e-05, "epoch": 1.2257281553398058, "percentage": 17.51, "elapsed_time": "1:07:19", "remaining_time": "5:17:09"}
+{"current_steps": 510, "total_steps": 2884, "loss": 0.2426, "lr": 3.929481740923438e-05, "epoch": 1.237864077669903, "percentage": 17.68, "elapsed_time": "1:07:53", "remaining_time": "5:16:02"}
+{"current_steps": 515, "total_steps": 2884, "loss": 0.2531, "lr": 3.926260006836831e-05, "epoch": 1.25, "percentage": 17.86, "elapsed_time": "1:08:34", "remaining_time": "5:15:25"}
+{"current_steps": 520, "total_steps": 2884, "loss": 0.2407, "lr": 3.922967693244683e-05, "epoch": 1.262135922330097, "percentage": 18.03, "elapsed_time": "1:09:11", "remaining_time": "5:14:35"}
+{"current_steps": 525, "total_steps": 2884, "loss": 0.2589, "lr": 3.9196049207796545e-05, "epoch": 1.2742718446601942, "percentage": 18.2, "elapsed_time": "1:09:54", "remaining_time": "5:14:09"}
+{"current_steps": 530, "total_steps": 2884, "loss": 0.2353, "lr": 3.916171812656065e-05, "epoch": 1.2864077669902914, "percentage": 18.38, "elapsed_time": "1:10:29", "remaining_time": "5:13:06"}
+{"current_steps": 535, "total_steps": 2884, "loss": 0.2459, "lr": 3.912668494665383e-05, "epoch": 1.2985436893203883, "percentage": 18.55, "elapsed_time": "1:11:04", "remaining_time": "5:12:05"}
+{"current_steps": 540, "total_steps": 2884, "loss": 0.2365, "lr": 3.9090950951716135e-05, "epoch": 1.3106796116504853, "percentage": 18.72, "elapsed_time": "1:11:42", "remaining_time": "5:11:17"}
+{"current_steps": 545, "total_steps": 2884, "loss": 0.2324, "lr": 3.905451745106598e-05, "epoch": 1.3228155339805825, "percentage": 18.9, "elapsed_time": "1:12:28", "remaining_time": "5:11:01"}
+{"current_steps": 550, "total_steps": 2884, "loss": 0.2346, "lr": 3.901738577965217e-05, "epoch": 1.3349514563106797, "percentage": 19.07, "elapsed_time": "1:13:08", "remaining_time": "5:10:22"}
+{"current_steps": 555, "total_steps": 2884, "loss": 0.2538, "lr": 3.897955729800494e-05, "epoch": 1.3470873786407767, "percentage": 19.24, "elapsed_time": "1:13:51", "remaining_time": "5:09:54"}
+{"current_steps": 560, "total_steps": 2884, "loss": 0.2381, "lr": 3.894103339218615e-05, "epoch": 1.3592233009708738, "percentage": 19.42, "elapsed_time": "1:14:40", "remaining_time": "5:09:52"}
+{"current_steps": 565, "total_steps": 2884, "loss": 0.2347, "lr": 3.890181547373849e-05, "epoch": 1.3713592233009708, "percentage": 19.59, "elapsed_time": "1:15:14", "remaining_time": "5:08:47"}
+{"current_steps": 570, "total_steps": 2884, "loss": 0.2308, "lr": 3.886190497963375e-05, "epoch": 1.383495145631068, "percentage": 19.76, "elapsed_time": "1:15:45", "remaining_time": "5:07:34"}
+{"current_steps": 575, "total_steps": 2884, "loss": 0.2433, "lr": 3.882130337222018e-05, "epoch": 1.395631067961165, "percentage": 19.94, "elapsed_time": "1:16:27", "remaining_time": "5:07:01"}
+{"current_steps": 580, "total_steps": 2884, "loss": 0.2544, "lr": 3.8780012139168886e-05, "epoch": 1.4077669902912622, "percentage": 20.11, "elapsed_time": "1:17:07", "remaining_time": "5:06:21"}
+{"current_steps": 585, "total_steps": 2884, "loss": 0.2267, "lr": 3.873803279341936e-05, "epoch": 1.4199029126213591, "percentage": 20.28, "elapsed_time": "1:17:39", "remaining_time": "5:05:13"}
+{"current_steps": 590, "total_steps": 2884, "loss": 0.2539, "lr": 3.8695366873124e-05, "epoch": 1.4320388349514563, "percentage": 20.46, "elapsed_time": "1:18:14", "remaining_time": "5:04:12"}
+{"current_steps": 595, "total_steps": 2884, "loss": 0.2491, "lr": 3.865201594159178e-05, "epoch": 1.4441747572815533, "percentage": 20.63, "elapsed_time": "1:18:56", "remaining_time": "5:03:40"}
+{"current_steps": 600, "total_steps": 2884, "loss": 0.2481, "lr": 3.860798158723097e-05, "epoch": 1.4563106796116505, "percentage": 20.8, "elapsed_time": "1:19:31", "remaining_time": "5:02:43"}
+{"current_steps": 605, "total_steps": 2884, "loss": 0.2535, "lr": 3.856326542349092e-05, "epoch": 1.4684466019417477, "percentage": 20.98, "elapsed_time": "1:20:13", "remaining_time": "5:02:13"}
+{"current_steps": 610, "total_steps": 2884, "loss": 0.2476, "lr": 3.851786908880295e-05, "epoch": 1.4805825242718447, "percentage": 21.15, "elapsed_time": "1:20:59", "remaining_time": "5:01:55"}
+{"current_steps": 615, "total_steps": 2884, "loss": 0.2344, "lr": 3.847179424652031e-05, "epoch": 1.4927184466019416, "percentage": 21.32, "elapsed_time": "1:21:40", "remaining_time": "5:01:19"}
+{"current_steps": 620, "total_steps": 2884, "loss": 0.2246, "lr": 3.842504258485726e-05, "epoch": 1.5048543689320388, "percentage": 21.5, "elapsed_time": "1:22:28", "remaining_time": "5:01:10"}
+{"current_steps": 625, "total_steps": 2884, "loss": 0.2411, "lr": 3.837761581682716e-05, "epoch": 1.516990291262136, "percentage": 21.67, "elapsed_time": "1:23:02", "remaining_time": "5:00:09"}
+{"current_steps": 630, "total_steps": 2884, "loss": 0.2487, "lr": 3.8329515680179776e-05, "epoch": 1.529126213592233, "percentage": 21.84, "elapsed_time": "1:23:43", "remaining_time": "4:59:34"}
+{"current_steps": 635, "total_steps": 2884, "loss": 0.2395, "lr": 3.8280743937337534e-05, "epoch": 1.54126213592233, "percentage": 22.02, "elapsed_time": "1:24:19", "remaining_time": "4:58:37"}
+{"current_steps": 640, "total_steps": 2884, "loss": 0.2361, "lr": 3.823130237533099e-05, "epoch": 1.5533980582524272, "percentage": 22.19, "elapsed_time": "1:24:54", "remaining_time": "4:57:41"}
+{"current_steps": 645, "total_steps": 2884, "loss": 0.2342, "lr": 3.818119280573336e-05, "epoch": 1.5655339805825244, "percentage": 22.36, "elapsed_time": "1:25:38", "remaining_time": "4:57:17"}
+{"current_steps": 650, "total_steps": 2884, "loss": 0.2359, "lr": 3.8130417064594085e-05, "epoch": 1.5776699029126213, "percentage": 22.54, "elapsed_time": "1:26:28", "remaining_time": "4:57:11"}
+{"current_steps": 655, "total_steps": 2884, "loss": 0.2474, "lr": 3.807897701237162e-05, "epoch": 1.5898058252427183, "percentage": 22.71, "elapsed_time": "1:27:03", "remaining_time": "4:56:14"}
+{"current_steps": 660, "total_steps": 2884, "loss": 0.2344, "lr": 3.802687453386523e-05, "epoch": 1.6019417475728155, "percentage": 22.88, "elapsed_time": "1:27:43", "remaining_time": "4:55:36"}
+{"current_steps": 665, "total_steps": 2884, "loss": 0.2555, "lr": 3.797411153814595e-05, "epoch": 1.6140776699029127, "percentage": 23.06, "elapsed_time": "1:28:29", "remaining_time": "4:55:15"}
+{"current_steps": 670, "total_steps": 2884, "loss": 0.2342, "lr": 3.79206899584866e-05, "epoch": 1.6262135922330097, "percentage": 23.23, "elapsed_time": "1:29:01", "remaining_time": "4:54:09"}
+{"current_steps": 675, "total_steps": 2884, "loss": 0.2439, "lr": 3.7866611752291016e-05, "epoch": 1.6383495145631068, "percentage": 23.4, "elapsed_time": "1:29:40", "remaining_time": "4:53:26"}
+{"current_steps": 680, "total_steps": 2884, "loss": 0.2339, "lr": 3.7811878901022234e-05, "epoch": 1.650485436893204, "percentage": 23.58, "elapsed_time": "1:30:22", "remaining_time": "4:52:55"}
+{"current_steps": 685, "total_steps": 2884, "loss": 0.2521, "lr": 3.775649341012999e-05, "epoch": 1.662621359223301, "percentage": 23.75, "elapsed_time": "1:31:08", "remaining_time": "4:52:35"}
+{"current_steps": 690, "total_steps": 2884, "loss": 0.2354, "lr": 3.770045730897716e-05, "epoch": 1.674757281553398, "percentage": 23.93, "elapsed_time": "1:31:57", "remaining_time": "4:52:24"}
+{"current_steps": 695, "total_steps": 2884, "loss": 0.2274, "lr": 3.7643772650765436e-05, "epoch": 1.6868932038834952, "percentage": 24.1, "elapsed_time": "1:32:41", "remaining_time": "4:51:57"}
+{"current_steps": 700, "total_steps": 2884, "loss": 0.2352, "lr": 3.75864415124601e-05, "epoch": 1.6990291262135924, "percentage": 24.27, "elapsed_time": "1:33:21", "remaining_time": "4:51:15"}
+{"current_steps": 705, "total_steps": 2884, "loss": 0.227, "lr": 3.75284659947139e-05, "epoch": 1.7111650485436893, "percentage": 24.45, "elapsed_time": "1:34:06", "remaining_time": "4:50:52"}
+{"current_steps": 710, "total_steps": 2884, "loss": 0.2359, "lr": 3.746984822179011e-05, "epoch": 1.7233009708737863, "percentage": 24.62, "elapsed_time": "1:34:54", "remaining_time": "4:50:35"}
+{"current_steps": 715, "total_steps": 2884, "loss": 0.2434, "lr": 3.741059034148468e-05, "epoch": 1.7354368932038835, "percentage": 24.79, "elapsed_time": "1:35:37", "remaining_time": "4:50:06"}
+{"current_steps": 720, "total_steps": 2884, "loss": 0.2266, "lr": 3.735069452504751e-05, "epoch": 1.7475728155339807, "percentage": 24.97, "elapsed_time": "1:36:14", "remaining_time": "4:49:16"}
+{"current_steps": 725, "total_steps": 2884, "loss": 0.2229, "lr": 3.729016296710298e-05, "epoch": 1.7597087378640777, "percentage": 25.14, "elapsed_time": "1:37:07", "remaining_time": "4:49:14"}
+{"current_steps": 730, "total_steps": 2884, "loss": 0.2357, "lr": 3.722899788556942e-05, "epoch": 1.7718446601941746, "percentage": 25.31, "elapsed_time": "1:37:46", "remaining_time": "4:48:31"}
+{"current_steps": 735, "total_steps": 2884, "loss": 0.2389, "lr": 3.7167201521577934e-05, "epoch": 1.7839805825242718, "percentage": 25.49, "elapsed_time": "1:38:25", "remaining_time": "4:47:47"}
+{"current_steps": 740, "total_steps": 2884, "loss": 0.2435, "lr": 3.710477613939026e-05, "epoch": 1.796116504854369, "percentage": 25.66, "elapsed_time": "1:38:54", "remaining_time": "4:46:35"}
+{"current_steps": 745, "total_steps": 2884, "loss": 0.2298, "lr": 3.7041724026315796e-05, "epoch": 1.808252427184466, "percentage": 25.83, "elapsed_time": "1:39:32", "remaining_time": "4:45:48"}
+{"current_steps": 750, "total_steps": 2884, "loss": 0.2297, "lr": 3.697804749262778e-05, "epoch": 1.820388349514563, "percentage": 26.01, "elapsed_time": "1:40:12", "remaining_time": "4:45:07"}
+{"current_steps": 755, "total_steps": 2884, "loss": 0.2314, "lr": 3.6913748871478674e-05, "epoch": 1.8325242718446602, "percentage": 26.18, "elapsed_time": "1:40:51", "remaining_time": "4:44:25"}
+{"current_steps": 760, "total_steps": 2884, "loss": 0.2338, "lr": 3.684883051881463e-05, "epoch": 1.8446601941747574, "percentage": 26.35, "elapsed_time": "1:41:40", "remaining_time": "4:44:10"}
+{"current_steps": 765, "total_steps": 2884, "loss": 0.2406, "lr": 3.678329481328924e-05, "epoch": 1.8567961165048543, "percentage": 26.53, "elapsed_time": "1:42:26", "remaining_time": "4:43:46"}
+{"current_steps": 770, "total_steps": 2884, "loss": 0.2192, "lr": 3.671714415617629e-05, "epoch": 1.8689320388349513, "percentage": 26.7, "elapsed_time": "1:43:05", "remaining_time": "4:43:01"}
+{"current_steps": 775, "total_steps": 2884, "loss": 0.2358, "lr": 3.665038097128185e-05, "epoch": 1.8810679611650487, "percentage": 26.87, "elapsed_time": "1:43:43", "remaining_time": "4:42:16"}
+{"current_steps": 780, "total_steps": 2884, "loss": 0.2336, "lr": 3.6583007704855395e-05, "epoch": 1.8932038834951457, "percentage": 27.05, "elapsed_time": "1:44:20", "remaining_time": "4:41:27"}
+{"current_steps": 785, "total_steps": 2884, "loss": 0.2389, "lr": 3.651502682550026e-05, "epoch": 1.9053398058252426, "percentage": 27.22, "elapsed_time": "1:44:59", "remaining_time": "4:40:42"}
+{"current_steps": 790, "total_steps": 2884, "loss": 0.2399, "lr": 3.6446440824083105e-05, "epoch": 1.9174757281553398, "percentage": 27.39, "elapsed_time": "1:45:25", "remaining_time": "4:39:27"}
+{"current_steps": 795, "total_steps": 2884, "loss": 0.2266, "lr": 3.637725221364269e-05, "epoch": 1.929611650485437, "percentage": 27.57, "elapsed_time": "1:46:11", "remaining_time": "4:39:03"}
+{"current_steps": 800, "total_steps": 2884, "loss": 0.2385, "lr": 3.6307463529297814e-05, "epoch": 1.941747572815534, "percentage": 27.74, "elapsed_time": "1:46:47", "remaining_time": "4:38:11"}
+{"current_steps": 805, "total_steps": 2884, "loss": 0.2335, "lr": 3.623707732815435e-05, "epoch": 1.953883495145631, "percentage": 27.91, "elapsed_time": "1:47:20", "remaining_time": "4:37:13"}
+{"current_steps": 810, "total_steps": 2884, "loss": 0.2397, "lr": 3.616609618921165e-05, "epoch": 1.9660194174757282, "percentage": 28.09, "elapsed_time": "1:48:02", "remaining_time": "4:36:38"}
+{"current_steps": 815, "total_steps": 2884, "loss": 0.2301, "lr": 3.609452271326798e-05, "epoch": 1.9781553398058254, "percentage": 28.26, "elapsed_time": "1:48:47", "remaining_time": "4:36:10"}
+{"current_steps": 820, "total_steps": 2884, "loss": 0.2352, "lr": 3.602235952282524e-05, "epoch": 1.9902912621359223, "percentage": 28.43, "elapsed_time": "1:49:25", "remaining_time": "4:35:27"}
+{"current_steps": 825, "total_steps": 2884, "loss": 0.2349, "lr": 3.59496092619929e-05, "epoch": 2.0024271844660193, "percentage": 28.61, "elapsed_time": "1:50:01", "remaining_time": "4:34:35"}
+{"current_steps": 830, "total_steps": 2884, "loss": 0.205, "lr": 3.587627459639106e-05, "epoch": 2.0145631067961167, "percentage": 28.78, "elapsed_time": "1:50:33", "remaining_time": "4:33:37"}
+{"current_steps": 835, "total_steps": 2884, "loss": 0.2073, "lr": 3.5802358213052876e-05, "epoch": 2.0266990291262137, "percentage": 28.95, "elapsed_time": "1:51:14", "remaining_time": "4:32:59"}
+{"current_steps": 840, "total_steps": 2884, "loss": 0.2056, "lr": 3.5727862820325975e-05, "epoch": 2.0388349514563107, "percentage": 29.13, "elapsed_time": "1:52:01", "remaining_time": "4:32:36"}
+{"current_steps": 845, "total_steps": 2884, "loss": 0.2203, "lr": 3.565279114777334e-05, "epoch": 2.0509708737864076, "percentage": 29.3, "elapsed_time": "1:52:44", "remaining_time": "4:32:02"}
+{"current_steps": 850, "total_steps": 2884, "loss": 0.2003, "lr": 3.557714594607324e-05, "epoch": 2.063106796116505, "percentage": 29.47, "elapsed_time": "1:53:11", "remaining_time": "4:30:52"}
+{"current_steps": 855, "total_steps": 2884, "loss": 0.2138, "lr": 3.550092998691844e-05, "epoch": 2.075242718446602, "percentage": 29.65, "elapsed_time": "1:53:45", "remaining_time": "4:29:58"}
+{"current_steps": 860, "total_steps": 2884, "loss": 0.2125, "lr": 3.5424146062914664e-05, "epoch": 2.087378640776699, "percentage": 29.82, "elapsed_time": "1:54:22", "remaining_time": "4:29:11"}
+{"current_steps": 865, "total_steps": 2884, "loss": 0.208, "lr": 3.534679698747824e-05, "epoch": 2.099514563106796, "percentage": 29.99, "elapsed_time": "1:55:04", "remaining_time": "4:28:36"}
+{"current_steps": 870, "total_steps": 2884, "loss": 0.2074, "lr": 3.5268885594733074e-05, "epoch": 2.1116504854368934, "percentage": 30.17, "elapsed_time": "1:55:34", "remaining_time": "4:27:31"}
+{"current_steps": 875, "total_steps": 2884, "loss": 0.2114, "lr": 3.519041473940674e-05, "epoch": 2.1237864077669903, "percentage": 30.34, "elapsed_time": "1:56:09", "remaining_time": "4:26:41"}
+{"current_steps": 880, "total_steps": 2884, "loss": 0.2024, "lr": 3.511138729672592e-05, "epoch": 2.1359223300970873, "percentage": 30.51, "elapsed_time": "1:56:52", "remaining_time": "4:26:09"}
+{"current_steps": 885, "total_steps": 2884, "loss": 0.2083, "lr": 3.503180616231105e-05, "epoch": 2.1480582524271843, "percentage": 30.69, "elapsed_time": "1:57:26", "remaining_time": "4:25:15"}
+{"current_steps": 890, "total_steps": 2884, "loss": 0.2238, "lr": 3.495167425207021e-05, "epoch": 2.1601941747572817, "percentage": 30.86, "elapsed_time": "1:57:59", "remaining_time": "4:24:20"}
+{"current_steps": 895, "total_steps": 2884, "loss": 0.2234, "lr": 3.487099450209228e-05, "epoch": 2.1723300970873787, "percentage": 31.03, "elapsed_time": "1:58:42", "remaining_time": "4:23:47"}
+{"current_steps": 900, "total_steps": 2884, "loss": 0.2125, "lr": 3.478976986853939e-05, "epoch": 2.1844660194174756, "percentage": 31.21, "elapsed_time": "1:59:23", "remaining_time": "4:23:10"}
+{"current_steps": 905, "total_steps": 2884, "loss": 0.2129, "lr": 3.4708003327538556e-05, "epoch": 2.1966019417475726, "percentage": 31.38, "elapsed_time": "1:59:56", "remaining_time": "4:22:17"}
+{"current_steps": 910, "total_steps": 2884, "loss": 0.1996, "lr": 3.462569787507268e-05, "epoch": 2.20873786407767, "percentage": 31.55, "elapsed_time": "2:00:37", "remaining_time": "4:21:39"}
+{"current_steps": 915, "total_steps": 2884, "loss": 0.2132, "lr": 3.454285652687075e-05, "epoch": 2.220873786407767, "percentage": 31.73, "elapsed_time": "2:01:14", "remaining_time": "4:20:54"}
+{"current_steps": 920, "total_steps": 2884, "loss": 0.2088, "lr": 3.445948231829735e-05, "epoch": 2.233009708737864, "percentage": 31.9, "elapsed_time": "2:02:02", "remaining_time": "4:20:32"}
+{"current_steps": 925, "total_steps": 2884, "loss": 0.2032, "lr": 3.4375578304241424e-05, "epoch": 2.2451456310679614, "percentage": 32.07, "elapsed_time": "2:02:46", "remaining_time": "4:20:00"}
+{"current_steps": 930, "total_steps": 2884, "loss": 0.2013, "lr": 3.429114755900437e-05, "epoch": 2.2572815533980584, "percentage": 32.25, "elapsed_time": "2:03:19", "remaining_time": "4:19:06"}
+{"current_steps": 935, "total_steps": 2884, "loss": 0.2131, "lr": 3.420619317618737e-05, "epoch": 2.2694174757281553, "percentage": 32.42, "elapsed_time": "2:03:55", "remaining_time": "4:18:18"}
+{"current_steps": 940, "total_steps": 2884, "loss": 0.2031, "lr": 3.412071826857808e-05, "epoch": 2.2815533980582523, "percentage": 32.59, "elapsed_time": "2:04:39", "remaining_time": "4:17:48"}
+{"current_steps": 945, "total_steps": 2884, "loss": 0.2023, "lr": 3.403472596803651e-05, "epoch": 2.2936893203883493, "percentage": 32.77, "elapsed_time": "2:05:16", "remaining_time": "4:17:02"}
+{"current_steps": 950, "total_steps": 2884, "loss": 0.2096, "lr": 3.3948219425380326e-05, "epoch": 2.3058252427184467, "percentage": 32.94, "elapsed_time": "2:05:46", "remaining_time": "4:16:02"}
+{"current_steps": 955, "total_steps": 2884, "loss": 0.2058, "lr": 3.3861201810269376e-05, "epoch": 2.3179611650485437, "percentage": 33.11, "elapsed_time": "2:06:20", "remaining_time": "4:15:11"}
+{"current_steps": 960, "total_steps": 2884, "loss": 0.222, "lr": 3.377367631108957e-05, "epoch": 2.3300970873786406, "percentage": 33.29, "elapsed_time": "2:07:12", "remaining_time": "4:14:56"}
+{"current_steps": 965, "total_steps": 2884, "loss": 0.2206, "lr": 3.368564613483604e-05, "epoch": 2.342233009708738, "percentage": 33.46, "elapsed_time": "2:07:52", "remaining_time": "4:14:18"}
+{"current_steps": 970, "total_steps": 2884, "loss": 0.209, "lr": 3.3597114506995605e-05, "epoch": 2.354368932038835, "percentage": 33.63, "elapsed_time": "2:08:40", "remaining_time": "4:13:53"}
+{"current_steps": 975, "total_steps": 2884, "loss": 0.2074, "lr": 3.350808467142867e-05, "epoch": 2.366504854368932, "percentage": 33.81, "elapsed_time": "2:09:15", "remaining_time": "4:13:04"}
+{"current_steps": 980, "total_steps": 2884, "loss": 0.2046, "lr": 3.341855989025028e-05, "epoch": 2.378640776699029, "percentage": 33.98, "elapsed_time": "2:09:57", "remaining_time": "4:12:29"}
+{"current_steps": 985, "total_steps": 2884, "loss": 0.1994, "lr": 3.332854344371065e-05, "epoch": 2.3907766990291264, "percentage": 34.15, "elapsed_time": "2:10:50", "remaining_time": "4:12:15"}
+{"current_steps": 990, "total_steps": 2884, "loss": 0.2024, "lr": 3.3238038630074944e-05, "epoch": 2.4029126213592233, "percentage": 34.33, "elapsed_time": "2:11:24", "remaining_time": "4:11:24"}
+{"current_steps": 995, "total_steps": 2884, "loss": 0.2033, "lr": 3.314704876550244e-05, "epoch": 2.4150485436893203, "percentage": 34.5, "elapsed_time": "2:12:05", "remaining_time": "4:10:45"}
+{"current_steps": 1000, "total_steps": 2884, "loss": 0.2047, "lr": 3.305557718392503e-05, "epoch": 2.4271844660194173, "percentage": 34.67, "elapsed_time": "2:12:46", "remaining_time": "4:10:09"}
+{"current_steps": 1005, "total_steps": 2884, "loss": 0.2102, "lr": 3.296362723692503e-05, "epoch": 2.4393203883495147, "percentage": 34.85, "elapsed_time": "2:13:26", "remaining_time": "4:09:28"}
+{"current_steps": 1010, "total_steps": 2884, "loss": 0.2115, "lr": 3.287120229361242e-05, "epoch": 2.4514563106796117, "percentage": 35.02, "elapsed_time": "2:13:55", "remaining_time": "4:08:29"}
+{"current_steps": 1015, "total_steps": 2884, "loss": 0.2005, "lr": 3.2778305740501354e-05, "epoch": 2.4635922330097086, "percentage": 35.19, "elapsed_time": "2:14:32", "remaining_time": "4:07:45"}
+{"current_steps": 1020, "total_steps": 2884, "loss": 0.2142, "lr": 3.268494098138612e-05, "epoch": 2.475728155339806, "percentage": 35.37, "elapsed_time": "2:15:09", "remaining_time": "4:06:59"}
+{"current_steps": 1025, "total_steps": 2884, "loss": 0.2013, "lr": 3.259111143721638e-05, "epoch": 2.487864077669903, "percentage": 35.54, "elapsed_time": "2:15:50", "remaining_time": "4:06:21"}
+{"current_steps": 1030, "total_steps": 2884, "loss": 0.1957, "lr": 3.2496820545971856e-05, "epoch": 2.5, "percentage": 35.71, "elapsed_time": "2:16:24", "remaining_time": "4:05:32"}
+{"current_steps": 1035, "total_steps": 2884, "loss": 0.1958, "lr": 3.2402071762536335e-05, "epoch": 2.512135922330097, "percentage": 35.89, "elapsed_time": "2:17:08", "remaining_time": "4:05:00"}
+{"current_steps": 1040, "total_steps": 2884, "loss": 0.2061, "lr": 3.23068685585711e-05, "epoch": 2.524271844660194, "percentage": 36.06, "elapsed_time": "2:17:48", "remaining_time": "4:04:21"}
+{"current_steps": 1045, "total_steps": 2884, "loss": 0.2075, "lr": 3.2211214422387723e-05, "epoch": 2.5364077669902914, "percentage": 36.23, "elapsed_time": "2:18:29", "remaining_time": "4:03:42"}
+{"current_steps": 1050, "total_steps": 2884, "loss": 0.2141, "lr": 3.211511285882024e-05, "epoch": 2.5485436893203883, "percentage": 36.41, "elapsed_time": "2:19:01", "remaining_time": "4:02:49"}
+{"current_steps": 1055, "total_steps": 2884, "loss": 0.2107, "lr": 3.201856738909673e-05, "epoch": 2.5606796116504853, "percentage": 36.58, "elapsed_time": "2:19:41", "remaining_time": "4:02:09"}
+{"current_steps": 1060, "total_steps": 2884, "loss": 0.2093, "lr": 3.192158155071032e-05, "epoch": 2.5728155339805827, "percentage": 36.75, "elapsed_time": "2:20:12", "remaining_time": "4:01:15"}
+{"current_steps": 1065, "total_steps": 2884, "loss": 0.2095, "lr": 3.182415889728953e-05, "epoch": 2.5849514563106797, "percentage": 36.93, "elapsed_time": "2:20:57", "remaining_time": "4:00:46"}
+{"current_steps": 1070, "total_steps": 2884, "loss": 0.2009, "lr": 3.172630299846811e-05, "epoch": 2.5970873786407767, "percentage": 37.1, "elapsed_time": "2:21:38", "remaining_time": "4:00:07"}
+{"current_steps": 1075, "total_steps": 2884, "loss": 0.2029, "lr": 3.162801743975419e-05, "epoch": 2.6092233009708736, "percentage": 37.27, "elapsed_time": "2:22:16", "remaining_time": "3:59:25"}
+{"current_steps": 1080, "total_steps": 2884, "loss": 0.2069, "lr": 3.1529305822398976e-05, "epoch": 2.6213592233009706, "percentage": 37.45, "elapsed_time": "2:22:58", "remaining_time": "3:58:49"}
+{"current_steps": 1085, "total_steps": 2884, "loss": 0.2088, "lr": 3.143017176326473e-05, "epoch": 2.633495145631068, "percentage": 37.62, "elapsed_time": "2:23:35", "remaining_time": "3:58:04"}
+{"current_steps": 1090, "total_steps": 2884, "loss": 0.1874, "lr": 3.133061889469229e-05, "epoch": 2.645631067961165, "percentage": 37.79, "elapsed_time": "2:24:26", "remaining_time": "3:57:43"}
+{"current_steps": 1095, "total_steps": 2884, "loss": 0.2097, "lr": 3.123065086436795e-05, "epoch": 2.657766990291262, "percentage": 37.97, "elapsed_time": "2:25:11", "remaining_time": "3:57:12"}
+{"current_steps": 1100, "total_steps": 2884, "loss": 0.2058, "lr": 3.113027133518983e-05, "epoch": 2.6699029126213594, "percentage": 38.14, "elapsed_time": "2:25:48", "remaining_time": "3:56:29"}
+{"current_steps": 1105, "total_steps": 2884, "loss": 0.2026, "lr": 3.102948398513365e-05, "epoch": 2.6820388349514563, "percentage": 38.31, "elapsed_time": "2:26:21", "remaining_time": "3:55:37"}
+{"current_steps": 1110, "total_steps": 2884, "loss": 0.2116, "lr": 3.092829250711797e-05, "epoch": 2.6941747572815533, "percentage": 38.49, "elapsed_time": "2:26:57", "remaining_time": "3:54:51"}
+{"current_steps": 1115, "total_steps": 2884, "loss": 0.2133, "lr": 3.082670060886888e-05, "epoch": 2.7063106796116507, "percentage": 38.66, "elapsed_time": "2:27:27", "remaining_time": "3:53:57"}
+{"current_steps": 1120, "total_steps": 2884, "loss": 0.2075, "lr": 3.0724712012784147e-05, "epoch": 2.7184466019417477, "percentage": 38.83, "elapsed_time": "2:28:10", "remaining_time": "3:53:22"}
+{"current_steps": 1125, "total_steps": 2884, "loss": 0.2112, "lr": 3.062233045579681e-05, "epoch": 2.7305825242718447, "percentage": 39.01, "elapsed_time": "2:28:49", "remaining_time": "3:52:41"}
+{"current_steps": 1130, "total_steps": 2884, "loss": 0.1989, "lr": 3.0519559689238305e-05, "epoch": 2.7427184466019416, "percentage": 39.18, "elapsed_time": "2:29:20", "remaining_time": "3:51:48"}
+{"current_steps": 1135, "total_steps": 2884, "loss": 0.1965, "lr": 3.041640347870092e-05, "epoch": 2.7548543689320386, "percentage": 39.36, "elapsed_time": "2:29:56", "remaining_time": "3:51:03"}
+{"current_steps": 1140, "total_steps": 2884, "loss": 0.2147, "lr": 3.0312865603899943e-05, "epoch": 2.766990291262136, "percentage": 39.53, "elapsed_time": "2:30:24", "remaining_time": "3:50:05"}
+{"current_steps": 1145, "total_steps": 2884, "loss": 0.2063, "lr": 3.020894985853504e-05, "epoch": 2.779126213592233, "percentage": 39.7, "elapsed_time": "2:31:03", "remaining_time": "3:49:25"}
+{"current_steps": 1150, "total_steps": 2884, "loss": 0.1956, "lr": 3.0104660050151375e-05, "epoch": 2.79126213592233, "percentage": 39.88, "elapsed_time": "2:31:44", "remaining_time": "3:48:47"}
+{"current_steps": 1155, "total_steps": 2884, "loss": 0.2085, "lr": 3.0000000000000004e-05, "epoch": 2.8033980582524274, "percentage": 40.05, "elapsed_time": "2:32:13", "remaining_time": "3:47:52"}
+{"current_steps": 1160, "total_steps": 2884, "loss": 0.2103, "lr": 2.989497354289791e-05, "epoch": 2.8155339805825244, "percentage": 40.22, "elapsed_time": "2:32:55", "remaining_time": "3:47:16"}
+{"current_steps": 1165, "total_steps": 2884, "loss": 0.2094, "lr": 2.9789584527087488e-05, "epoch": 2.8276699029126213, "percentage": 40.4, "elapsed_time": "2:33:43", "remaining_time": "3:46:49"}
+{"current_steps": 1170, "total_steps": 2884, "loss": 0.2054, "lr": 2.9683836814095533e-05, "epoch": 2.8398058252427183, "percentage": 40.57, "elapsed_time": "2:34:28", "remaining_time": "3:46:18"}
+{"current_steps": 1175, "total_steps": 2884, "loss": 0.2086, "lr": 2.957773427859174e-05, "epoch": 2.8519417475728153, "percentage": 40.74, "elapsed_time": "2:35:02", "remaining_time": "3:45:30"}
+{"current_steps": 1180, "total_steps": 2884, "loss": 0.2151, "lr": 2.947128080824677e-05, "epoch": 2.8640776699029127, "percentage": 40.92, "elapsed_time": "2:35:44", "remaining_time": "3:44:53"}
+{"current_steps": 1185, "total_steps": 2884, "loss": 0.2163, "lr": 2.9364480303589763e-05, "epoch": 2.8762135922330097, "percentage": 41.09, "elapsed_time": "2:36:20", "remaining_time": "3:44:10"}
+{"current_steps": 1190, "total_steps": 2884, "loss": 0.2053, "lr": 2.9257336677865442e-05, "epoch": 2.8883495145631066, "percentage": 41.26, "elapsed_time": "2:36:47", "remaining_time": "3:43:11"}
+{"current_steps": 1195, "total_steps": 2884, "loss": 0.2092, "lr": 2.9149853856890732e-05, "epoch": 2.900485436893204, "percentage": 41.44, "elapsed_time": "2:37:29", "remaining_time": "3:42:35"}
+{"current_steps": 1200, "total_steps": 2884, "loss": 0.2058, "lr": 2.9042035778910898e-05, "epoch": 2.912621359223301, "percentage": 41.61, "elapsed_time": "2:38:16", "remaining_time": "3:42:07"}
+{"current_steps": 1205, "total_steps": 2884, "loss": 0.1996, "lr": 2.893388639445526e-05, "epoch": 2.924757281553398, "percentage": 41.78, "elapsed_time": "2:39:00", "remaining_time": "3:41:33"}
+{"current_steps": 1210, "total_steps": 2884, "loss": 0.2115, "lr": 2.882540966619243e-05, "epoch": 2.9368932038834954, "percentage": 41.96, "elapsed_time": "2:39:33", "remaining_time": "3:40:44"}
+{"current_steps": 1215, "total_steps": 2884, "loss": 0.2123, "lr": 2.8716609568785138e-05, "epoch": 2.9490291262135924, "percentage": 42.13, "elapsed_time": "2:40:19", "remaining_time": "3:40:13"}
+{"current_steps": 1220, "total_steps": 2884, "loss": 0.2051, "lr": 2.8607490088744587e-05, "epoch": 2.9611650485436893, "percentage": 42.3, "elapsed_time": "2:40:58", "remaining_time": "3:39:32"}
+{"current_steps": 1225, "total_steps": 2884, "loss": 0.2103, "lr": 2.8498055224284347e-05, "epoch": 2.9733009708737863, "percentage": 42.48, "elapsed_time": "2:41:43", "remaining_time": "3:39:01"}
+{"current_steps": 1230, "total_steps": 2884, "loss": 0.1962, "lr": 2.8388308985173934e-05, "epoch": 2.9854368932038833, "percentage": 42.65, "elapsed_time": "2:42:27", "remaining_time": "3:38:28"}
+{"current_steps": 1235, "total_steps": 2884, "loss": 0.2028, "lr": 2.8278255392591826e-05, "epoch": 2.9975728155339807, "percentage": 42.82, "elapsed_time": "2:43:08", "remaining_time": "3:37:49"}
+{"current_steps": 1240, "total_steps": 2884, "loss": 0.1861, "lr": 2.8167898478978154e-05, "epoch": 3.0097087378640777, "percentage": 43.0, "elapsed_time": "2:43:39", "remaining_time": "3:36:58"}
+{"current_steps": 1245, "total_steps": 2884, "loss": 0.1798, "lr": 2.8057242287886927e-05, "epoch": 3.0218446601941746, "percentage": 43.17, "elapsed_time": "2:44:18", "remaining_time": "3:36:18"}
+{"current_steps": 1250, "total_steps": 2884, "loss": 0.1853, "lr": 2.7946290873837914e-05, "epoch": 3.033980582524272, "percentage": 43.34, "elapsed_time": "2:44:51", "remaining_time": "3:35:30"}
+{"current_steps": 1255, "total_steps": 2884, "loss": 0.1816, "lr": 2.7835048302168038e-05, "epoch": 3.046116504854369, "percentage": 43.52, "elapsed_time": "2:45:32", "remaining_time": "3:34:52"}
+{"current_steps": 1260, "total_steps": 2884, "loss": 0.1815, "lr": 2.772351864888245e-05, "epoch": 3.058252427184466, "percentage": 43.69, "elapsed_time": "2:46:22", "remaining_time": "3:34:26"}
+{"current_steps": 1265, "total_steps": 2884, "loss": 0.1796, "lr": 2.761170600050517e-05, "epoch": 3.070388349514563, "percentage": 43.86, "elapsed_time": "2:46:57", "remaining_time": "3:33:40"}
+{"current_steps": 1270, "total_steps": 2884, "loss": 0.176, "lr": 2.749961445392934e-05, "epoch": 3.0825242718446604, "percentage": 44.04, "elapsed_time": "2:47:46", "remaining_time": "3:33:13"}
+{"current_steps": 1275, "total_steps": 2884, "loss": 0.1871, "lr": 2.738724811626715e-05, "epoch": 3.0946601941747574, "percentage": 44.21, "elapsed_time": "2:48:22", "remaining_time": "3:32:28"}
+{"current_steps": 1280, "total_steps": 2884, "loss": 0.1859, "lr": 2.727461110469931e-05, "epoch": 3.1067961165048543, "percentage": 44.38, "elapsed_time": "2:49:02", "remaining_time": "3:31:49"}
+{"current_steps": 1285, "total_steps": 2884, "loss": 0.1824, "lr": 2.716170754632422e-05, "epoch": 3.1189320388349513, "percentage": 44.56, "elapsed_time": "2:49:42", "remaining_time": "3:31:10"}
+{"current_steps": 1290, "total_steps": 2884, "loss": 0.1801, "lr": 2.7048541578006724e-05, "epoch": 3.1310679611650487, "percentage": 44.73, "elapsed_time": "2:50:15", "remaining_time": "3:30:23"}
+{"current_steps": 1295, "total_steps": 2884, "loss": 0.1855, "lr": 2.6935117346226573e-05, "epoch": 3.1432038834951457, "percentage": 44.9, "elapsed_time": "2:50:50", "remaining_time": "3:29:37"}
+{"current_steps": 1300, "total_steps": 2884, "loss": 0.1799, "lr": 2.682143900692645e-05, "epoch": 3.1553398058252426, "percentage": 45.08, "elapsed_time": "2:51:32", "remaining_time": "3:29:01"}
+{"current_steps": 1305, "total_steps": 2884, "loss": 0.1655, "lr": 2.6707510725359712e-05, "epoch": 3.1674757281553396, "percentage": 45.25, "elapsed_time": "2:52:24", "remaining_time": "3:28:35"}
+{"current_steps": 1310, "total_steps": 2884, "loss": 0.1761, "lr": 2.6593336675937808e-05, "epoch": 3.179611650485437, "percentage": 45.42, "elapsed_time": "2:52:57", "remaining_time": "3:27:49"}
+{"current_steps": 1315, "total_steps": 2884, "loss": 0.1842, "lr": 2.647892104207725e-05, "epoch": 3.191747572815534, "percentage": 45.6, "elapsed_time": "2:53:42", "remaining_time": "3:27:16"}
+{"current_steps": 1320, "total_steps": 2884, "loss": 0.1811, "lr": 2.6364268016046396e-05, "epoch": 3.203883495145631, "percentage": 45.77, "elapsed_time": "2:54:18", "remaining_time": "3:26:31"}
+{"current_steps": 1325, "total_steps": 2884, "loss": 0.1741, "lr": 2.6249381798811807e-05, "epoch": 3.216019417475728, "percentage": 45.94, "elapsed_time": "2:54:58", "remaining_time": "3:25:53"}
+{"current_steps": 1330, "total_steps": 2884, "loss": 0.1913, "lr": 2.6134266599884344e-05, "epoch": 3.2281553398058254, "percentage": 46.12, "elapsed_time": "2:55:38", "remaining_time": "3:25:13"}
+{"current_steps": 1335, "total_steps": 2884, "loss": 0.1841, "lr": 2.6018926637164895e-05, "epoch": 3.2402912621359223, "percentage": 46.29, "elapsed_time": "2:56:07", "remaining_time": "3:24:21"}
+{"current_steps": 1340, "total_steps": 2884, "loss": 0.1758, "lr": 2.5903366136789882e-05, "epoch": 3.2524271844660193, "percentage": 46.46, "elapsed_time": "2:56:44", "remaining_time": "3:23:38"}
+{"current_steps": 1345, "total_steps": 2884, "loss": 0.1919, "lr": 2.578758933297635e-05, "epoch": 3.2645631067961167, "percentage": 46.64, "elapsed_time": "2:57:20", "remaining_time": "3:22:55"}
+{"current_steps": 1350, "total_steps": 2884, "loss": 0.1769, "lr": 2.567160046786686e-05, "epoch": 3.2766990291262137, "percentage": 46.81, "elapsed_time": "2:57:52", "remaining_time": "3:22:07"}
+{"current_steps": 1355, "total_steps": 2884, "loss": 0.1691, "lr": 2.5555403791374068e-05, "epoch": 3.2888349514563107, "percentage": 46.98, "elapsed_time": "2:58:26", "remaining_time": "3:21:21"}
+{"current_steps": 1360, "total_steps": 2884, "loss": 0.1833, "lr": 2.543900356102495e-05, "epoch": 3.3009708737864076, "percentage": 47.16, "elapsed_time": "2:59:11", "remaining_time": "3:20:48"}
+{"current_steps": 1365, "total_steps": 2884, "loss": 0.1904, "lr": 2.5322404041804865e-05, "epoch": 3.313106796116505, "percentage": 47.33, "elapsed_time": "2:59:45", "remaining_time": "3:20:01"}
+{"current_steps": 1370, "total_steps": 2884, "loss": 0.1761, "lr": 2.5205609506001222e-05, "epoch": 3.325242718446602, "percentage": 47.5, "elapsed_time": "3:00:28", "remaining_time": "3:19:26"}
+{"current_steps": 1375, "total_steps": 2884, "loss": 0.1981, "lr": 2.5088624233047015e-05, "epoch": 3.337378640776699, "percentage": 47.68, "elapsed_time": "3:01:01", "remaining_time": "3:18:40"}
+{"current_steps": 1380, "total_steps": 2884, "loss": 0.1797, "lr": 2.4971452509363942e-05, "epoch": 3.349514563106796, "percentage": 47.85, "elapsed_time": "3:01:30", "remaining_time": "3:17:49"}
+{"current_steps": 1385, "total_steps": 2884, "loss": 0.18, "lr": 2.4854098628205415e-05, "epoch": 3.3616504854368934, "percentage": 48.02, "elapsed_time": "3:02:12", "remaining_time": "3:17:12"}
+{"current_steps": 1390, "total_steps": 2884, "loss": 0.1888, "lr": 2.4736566889499205e-05, "epoch": 3.3737864077669903, "percentage": 48.2, "elapsed_time": "3:02:45", "remaining_time": "3:16:25"}
+{"current_steps": 1395, "total_steps": 2884, "loss": 0.1889, "lr": 2.46188615996899e-05, "epoch": 3.3859223300970873, "percentage": 48.37, "elapsed_time": "3:03:30", "remaining_time": "3:15:51"}
+{"current_steps": 1400, "total_steps": 2884, "loss": 0.1826, "lr": 2.4500987071581148e-05, "epoch": 3.3980582524271843, "percentage": 48.54, "elapsed_time": "3:04:04", "remaining_time": "3:15:06"}
+{"current_steps": 1405, "total_steps": 2884, "loss": 0.1785, "lr": 2.438294762417758e-05, "epoch": 3.4101941747572817, "percentage": 48.72, "elapsed_time": "3:04:34", "remaining_time": "3:14:18"}
+{"current_steps": 1410, "total_steps": 2884, "loss": 0.1786, "lr": 2.42647475825266e-05, "epoch": 3.4223300970873787, "percentage": 48.89, "elapsed_time": "3:05:09", "remaining_time": "3:13:33"}
+{"current_steps": 1415, "total_steps": 2884, "loss": 0.1842, "lr": 2.4146391277559888e-05, "epoch": 3.4344660194174756, "percentage": 49.06, "elapsed_time": "3:05:40", "remaining_time": "3:12:45"}
+{"current_steps": 1420, "total_steps": 2884, "loss": 0.1836, "lr": 2.402788304593473e-05, "epoch": 3.4466019417475726, "percentage": 49.24, "elapsed_time": "3:06:24", "remaining_time": "3:12:10"}
+{"current_steps": 1425, "total_steps": 2884, "loss": 0.1832, "lr": 2.3909227229875098e-05, "epoch": 3.45873786407767, "percentage": 49.41, "elapsed_time": "3:07:03", "remaining_time": "3:11:30"}
+{"current_steps": 1430, "total_steps": 2884, "loss": 0.1778, "lr": 2.3790428177012568e-05, "epoch": 3.470873786407767, "percentage": 49.58, "elapsed_time": "3:07:47", "remaining_time": "3:10:56"}
+{"current_steps": 1435, "total_steps": 2884, "loss": 0.1805, "lr": 2.367149024022702e-05, "epoch": 3.483009708737864, "percentage": 49.76, "elapsed_time": "3:08:26", "remaining_time": "3:10:16"}
+{"current_steps": 1440, "total_steps": 2884, "loss": 0.1881, "lr": 2.355241777748711e-05, "epoch": 3.4951456310679614, "percentage": 49.93, "elapsed_time": "3:09:05", "remaining_time": "3:09:36"}
+{"current_steps": 1445, "total_steps": 2884, "loss": 0.1872, "lr": 2.3433215151690654e-05, "epoch": 3.5072815533980584, "percentage": 50.1, "elapsed_time": "3:09:40", "remaining_time": "3:08:53"}
+{"current_steps": 1450, "total_steps": 2884, "loss": 0.1823, "lr": 2.3313886730504702e-05, "epoch": 3.5194174757281553, "percentage": 50.28, "elapsed_time": "3:10:28", "remaining_time": "3:08:22"}
+{"current_steps": 1455, "total_steps": 2884, "loss": 0.1798, "lr": 2.319443688620556e-05, "epoch": 3.5315533980582523, "percentage": 50.45, "elapsed_time": "3:11:05", "remaining_time": "3:07:40"}
+{"current_steps": 1460, "total_steps": 2884, "loss": 0.196, "lr": 2.307486999551854e-05, "epoch": 3.5436893203883493, "percentage": 50.62, "elapsed_time": "3:11:44", "remaining_time": "3:07:00"}
+{"current_steps": 1465, "total_steps": 2884, "loss": 0.1873, "lr": 2.2955190439457633e-05, "epoch": 3.5558252427184467, "percentage": 50.8, "elapsed_time": "3:12:28", "remaining_time": "3:06:25"}
+{"current_steps": 1470, "total_steps": 2884, "loss": 0.181, "lr": 2.2835402603164952e-05, "epoch": 3.5679611650485437, "percentage": 50.97, "elapsed_time": "3:13:06", "remaining_time": "3:05:45"}
+{"current_steps": 1475, "total_steps": 2884, "loss": 0.1829, "lr": 2.271551087575008e-05, "epoch": 3.5800970873786406, "percentage": 51.14, "elapsed_time": "3:13:52", "remaining_time": "3:05:11"}
+{"current_steps": 1480, "total_steps": 2884, "loss": 0.1803, "lr": 2.259551965012925e-05, "epoch": 3.592233009708738, "percentage": 51.32, "elapsed_time": "3:14:27", "remaining_time": "3:04:28"}
+{"current_steps": 1485, "total_steps": 2884, "loss": 0.1811, "lr": 2.247543332286436e-05, "epoch": 3.604368932038835, "percentage": 51.49, "elapsed_time": "3:15:12", "remaining_time": "3:03:54"}
+{"current_steps": 1490, "total_steps": 2884, "loss": 0.192, "lr": 2.2355256294001923e-05, "epoch": 3.616504854368932, "percentage": 51.66, "elapsed_time": "3:15:54", "remaining_time": "3:03:17"}
+{"current_steps": 1495, "total_steps": 2884, "loss": 0.1795, "lr": 2.2234992966911797e-05, "epoch": 3.6286407766990294, "percentage": 51.84, "elapsed_time": "3:16:32", "remaining_time": "3:02:36"}
+{"current_steps": 1500, "total_steps": 2884, "loss": 0.1761, "lr": 2.2114647748125884e-05, "epoch": 3.6407766990291264, "percentage": 52.01, "elapsed_time": "3:17:12", "remaining_time": "3:01:57"}
+{"current_steps": 1505, "total_steps": 2884, "loss": 0.1732, "lr": 2.1994225047176644e-05, "epoch": 3.6529126213592233, "percentage": 52.18, "elapsed_time": "3:18:35", "remaining_time": "3:01:57"}
+{"current_steps": 1510, "total_steps": 2884, "loss": 0.1801, "lr": 2.1873729276435555e-05, "epoch": 3.6650485436893203, "percentage": 52.36, "elapsed_time": "3:18:58", "remaining_time": "3:01:03"}
+{"current_steps": 1515, "total_steps": 2884, "loss": 0.1841, "lr": 2.1753164850951388e-05, "epoch": 3.6771844660194173, "percentage": 52.53, "elapsed_time": "3:19:33", "remaining_time": "3:00:19"}
+{"current_steps": 1520, "total_steps": 2884, "loss": 0.1853, "lr": 2.1632536188288514e-05, "epoch": 3.6893203883495147, "percentage": 52.7, "elapsed_time": "3:20:19", "remaining_time": "2:59:45"}
+{"current_steps": 1525, "total_steps": 2884, "loss": 0.1815, "lr": 2.1511847708364968e-05, "epoch": 3.7014563106796117, "percentage": 52.88, "elapsed_time": "3:20:58", "remaining_time": "2:59:05"}
+{"current_steps": 1530, "total_steps": 2884, "loss": 0.1843, "lr": 2.1391103833290547e-05, "epoch": 3.7135922330097086, "percentage": 53.05, "elapsed_time": "3:21:38", "remaining_time": "2:58:26"}
+{"current_steps": 1535, "total_steps": 2884, "loss": 0.1775, "lr": 2.127030898720476e-05, "epoch": 3.725728155339806, "percentage": 53.22, "elapsed_time": "3:22:18", "remaining_time": "2:57:47"}
+{"current_steps": 1540, "total_steps": 2884, "loss": 0.1866, "lr": 2.1149467596114718e-05, "epoch": 3.737864077669903, "percentage": 53.4, "elapsed_time": "3:22:57", "remaining_time": "2:57:07"}
+{"current_steps": 1545, "total_steps": 2884, "loss": 0.1851, "lr": 2.1028584087732996e-05, "epoch": 3.75, "percentage": 53.57, "elapsed_time": "3:23:31", "remaining_time": "2:56:23"}
+{"current_steps": 1550, "total_steps": 2884, "loss": 0.1787, "lr": 2.090766289131536e-05, "epoch": 3.762135922330097, "percentage": 53.74, "elapsed_time": "3:24:05", "remaining_time": "2:55:39"}
+{"current_steps": 1555, "total_steps": 2884, "loss": 0.1884, "lr": 2.0786708437498495e-05, "epoch": 3.774271844660194, "percentage": 53.92, "elapsed_time": "3:24:43", "remaining_time": "2:54:58"}
+{"current_steps": 1560, "total_steps": 2884, "loss": 0.1749, "lr": 2.066572515813766e-05, "epoch": 3.7864077669902914, "percentage": 54.09, "elapsed_time": "3:25:24", "remaining_time": "2:54:20"}
+{"current_steps": 1565, "total_steps": 2884, "loss": 0.187, "lr": 2.0544717486144304e-05, "epoch": 3.7985436893203883, "percentage": 54.26, "elapsed_time": "3:25:56", "remaining_time": "2:53:34"}
+{"current_steps": 1570, "total_steps": 2884, "loss": 0.1901, "lr": 2.042368985532364e-05, "epoch": 3.8106796116504853, "percentage": 54.44, "elapsed_time": "3:26:30", "remaining_time": "2:52:50"}
+{"current_steps": 1575, "total_steps": 2884, "loss": 0.1829, "lr": 2.0302646700212176e-05, "epoch": 3.8228155339805827, "percentage": 54.61, "elapsed_time": "3:27:00", "remaining_time": "2:52:02"}
+{"current_steps": 1580, "total_steps": 2884, "loss": 0.1859, "lr": 2.0181592455915265e-05, "epoch": 3.8349514563106797, "percentage": 54.79, "elapsed_time": "3:27:39", "remaining_time": "2:51:23"}
+{"current_steps": 1585, "total_steps": 2884, "loss": 0.1794, "lr": 2.006053155794454e-05, "epoch": 3.8470873786407767, "percentage": 54.96, "elapsed_time": "3:28:19", "remaining_time": "2:50:43"}
+{"current_steps": 1590, "total_steps": 2884, "loss": 0.186, "lr": 1.9939468442055464e-05, "epoch": 3.8592233009708736, "percentage": 55.13, "elapsed_time": "3:29:04", "remaining_time": "2:50:09"}
+{"current_steps": 1595, "total_steps": 2884, "loss": 0.1861, "lr": 1.9818407544084738e-05, "epoch": 3.8713592233009706, "percentage": 55.31, "elapsed_time": "3:29:49", "remaining_time": "2:49:34"}
+{"current_steps": 1600, "total_steps": 2884, "loss": 0.1911, "lr": 1.9697353299787823e-05, "epoch": 3.883495145631068, "percentage": 55.48, "elapsed_time": "3:30:21", "remaining_time": "2:48:49"}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e4341b780912c31ee66c00f7b534d0b65c126c6aa29b248cb2d0428d0b87b701
+size 8593