Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- chat_template.jinja +170 -0
- config.json +288 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- processor_config.json +61 -0
- tokenizer.json +3 -0
- tokenizer_config.json +49 -0
- trainer_state.json +2056 -0
- training_args.bin +3 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,170 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- set image_count = namespace(value=0) %}
|
| 2 |
+
{%- set video_count = namespace(value=0) %}
|
| 3 |
+
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
|
| 4 |
+
{%- if content is string %}
|
| 5 |
+
{{- content }}
|
| 6 |
+
{%- elif content is iterable and content is not mapping %}
|
| 7 |
+
{%- for item in content %}
|
| 8 |
+
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
|
| 9 |
+
{%- if is_system_content %}
|
| 10 |
+
{{- raise_exception('System message cannot contain images.') }}
|
| 11 |
+
{%- endif %}
|
| 12 |
+
{%- if do_vision_count %}
|
| 13 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{%- if add_vision_id %}
|
| 16 |
+
{{- 'Picture ' ~ image_count.value ~ ': ' }}
|
| 17 |
+
{%- endif %}
|
| 18 |
+
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
|
| 19 |
+
{%- elif 'video' in item or item.type == 'video' %}
|
| 20 |
+
{%- if is_system_content %}
|
| 21 |
+
{{- raise_exception('System message cannot contain videos.') }}
|
| 22 |
+
{%- endif %}
|
| 23 |
+
{%- if do_vision_count %}
|
| 24 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 25 |
+
{%- endif %}
|
| 26 |
+
{%- if add_vision_id %}
|
| 27 |
+
{{- 'Video ' ~ video_count.value ~ ': ' }}
|
| 28 |
+
{%- endif %}
|
| 29 |
+
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
|
| 30 |
+
{%- elif 'text' in item %}
|
| 31 |
+
{{- item.text }}
|
| 32 |
+
{%- else %}
|
| 33 |
+
{{- raise_exception('Unexpected item type in content.') }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endfor %}
|
| 36 |
+
{%- elif content is none or content is undefined %}
|
| 37 |
+
{{- '' }}
|
| 38 |
+
{%- else %}
|
| 39 |
+
{{- raise_exception('Unexpected content type.') }}
|
| 40 |
+
{%- endif %}
|
| 41 |
+
{%- endmacro %}
|
| 42 |
+
{%- if not messages %}
|
| 43 |
+
{{- raise_exception('No messages provided.') }}
|
| 44 |
+
{%- endif %}
|
| 45 |
+
{%- set reasoning_instructions = '' %}
|
| 46 |
+
{%- if enable_thinking is undefined or enable_thinking is true %}
|
| 47 |
+
{%- set resolved_reasoning_effort = reasoning_effort|default('xhigh') %}
|
| 48 |
+
{%- if resolved_reasoning_effort not in ('xhigh', 'medium', 'low') %}
|
| 49 |
+
{{- raise_exception('Unexpected reasoning effort ' ~ reasoning_effort ~ '. Supported types are xhigh (default), medium, and low.') }}
|
| 50 |
+
{%- endif %}
|
| 51 |
+
{%- if resolved_reasoning_effort == 'xhigh' %}
|
| 52 |
+
{%- set reasoning_instructions = 'Reasoning effort is set to xhigh. Please think carefully through the task, validate key assumptions, consider plausible alternatives, and prioritize correctness, consistency, and clarity in the final answer.' %}
|
| 53 |
+
{%- elif resolved_reasoning_effort == 'low' %}
|
| 54 |
+
{%- set reasoning_instructions = 'Reasoning effort is set to low. Keep your thinking brief and focused, moving directly to the conclusion without unnecessary elaboration.' %}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endif %}
|
| 57 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 58 |
+
{{- '<|im_start|>system\n' }}
|
| 59 |
+
{%- if reasoning_instructions %}
|
| 60 |
+
{{- reasoning_instructions + '\n\n' }}
|
| 61 |
+
{%- endif %}
|
| 62 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 63 |
+
{%- for tool in tools %}
|
| 64 |
+
{{- "\n" }}
|
| 65 |
+
{{- tool | tojson }}
|
| 66 |
+
{%- endfor %}
|
| 67 |
+
{{- "\n</tools>" }}
|
| 68 |
+
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
|
| 69 |
+
{%- if messages[0].role == 'system' %}
|
| 70 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 71 |
+
{%- if content %}
|
| 72 |
+
{{- '\n\n' + content }}
|
| 73 |
+
{%- endif %}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{{- '<|im_end|>\n' }}
|
| 76 |
+
{%- else %}
|
| 77 |
+
{%- if messages[0].role == 'system' %}
|
| 78 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 79 |
+
{%- if content %}
|
| 80 |
+
{{- '<|im_start|>system\n' + (reasoning_instructions + '\n\n' if reasoning_instructions else '') + content + '<|im_end|>\n' }}
|
| 81 |
+
{%- elif reasoning_instructions %}
|
| 82 |
+
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
|
| 83 |
+
{%- endif %}
|
| 84 |
+
{%- elif reasoning_instructions %}
|
| 85 |
+
{{- '<|im_start|>system\n' + reasoning_instructions + '<|im_end|>\n' }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- endif %}
|
| 88 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 89 |
+
{%- for message in messages[::-1] %}
|
| 90 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 91 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 92 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 93 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 94 |
+
{%- set ns.multi_step_tool = false %}
|
| 95 |
+
{%- set ns.last_query_index = index %}
|
| 96 |
+
{%- endif %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endfor %}
|
| 99 |
+
{%- if ns.multi_step_tool %}
|
| 100 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 101 |
+
{%- endif %}
|
| 102 |
+
{%- for message in messages %}
|
| 103 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 104 |
+
{%- if message.role == "system" %}
|
| 105 |
+
{%- if not loop.first %}
|
| 106 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 107 |
+
{%- endif %}
|
| 108 |
+
{%- elif message.role == "user" %}
|
| 109 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 110 |
+
{%- elif message.role == "assistant" %}
|
| 111 |
+
{%- set reasoning_content = '' %}
|
| 112 |
+
{%- if message.reasoning_content is string %}
|
| 113 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 114 |
+
{%- endif %}
|
| 115 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 116 |
+
{%- if preserve_thinking is undefined or preserve_thinking is true or loop.index0 > ns.last_query_index %}
|
| 117 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 118 |
+
{%- else %}
|
| 119 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 120 |
+
{%- endif %}
|
| 121 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 122 |
+
{%- for tool_call in message.tool_calls %}
|
| 123 |
+
{%- if tool_call.function is defined %}
|
| 124 |
+
{%- set tool_call = tool_call.function %}
|
| 125 |
+
{%- endif %}
|
| 126 |
+
{%- if loop.first %}
|
| 127 |
+
{%- if content|trim %}
|
| 128 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 129 |
+
{%- else %}
|
| 130 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 131 |
+
{%- endif %}
|
| 132 |
+
{%- else %}
|
| 133 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{%- if tool_call.arguments is defined and tool_call.arguments != '' %}
|
| 136 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 137 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 138 |
+
{%- set args_value = args_value | string if args_value is string else args_value | tojson | safe %}
|
| 139 |
+
{{- args_value }}
|
| 140 |
+
{{- '\n</parameter>\n' }}
|
| 141 |
+
{%- endfor %}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{{- '</function>\n</tool_call>' }}
|
| 144 |
+
{%- endfor %}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{{- '<|im_end|>\n' }}
|
| 147 |
+
{%- elif message.role == "tool" %}
|
| 148 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 149 |
+
{{- '<|im_start|>user' }}
|
| 150 |
+
{%- endif %}
|
| 151 |
+
{{- '\n<tool_response>\n' }}
|
| 152 |
+
{{- content }}
|
| 153 |
+
{{- '\n</tool_response>' }}
|
| 154 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 155 |
+
{{- '<|im_end|>\n' }}
|
| 156 |
+
{%- elif loop.last %}
|
| 157 |
+
{{- '<|im_end|>\n' }}
|
| 158 |
+
{%- endif %}
|
| 159 |
+
{%- else %}
|
| 160 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 161 |
+
{%- endif %}
|
| 162 |
+
{%- endfor %}
|
| 163 |
+
{%- if add_generation_prompt %}
|
| 164 |
+
{{- '<|im_start|>assistant\n' }}
|
| 165 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 166 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 167 |
+
{%- else %}
|
| 168 |
+
{{- '<think>\n' }}
|
| 169 |
+
{%- endif %}
|
| 170 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,288 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architecture_type": "decoder-kv",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"GLiClassModel"
|
| 5 |
+
],
|
| 6 |
+
"calibrator_beta_max": 3.0,
|
| 7 |
+
"calibrator_dropout": 0.1,
|
| 8 |
+
"calibrator_hidden_size": 256,
|
| 9 |
+
"calibrator_use_bias": false,
|
| 10 |
+
"class_token_index": 248077,
|
| 11 |
+
"class_token_pooling": "first",
|
| 12 |
+
"contrastive_loss_coef": 0.0,
|
| 13 |
+
"dropout": 0.3,
|
| 14 |
+
"dtype": "float32",
|
| 15 |
+
"embed_class_token": true,
|
| 16 |
+
"encoder_config": {
|
| 17 |
+
"_name_or_path": "Qwen/Qwen3.8-27B",
|
| 18 |
+
"architectures": [
|
| 19 |
+
"Qwen3_5ForConditionalGeneration"
|
| 20 |
+
],
|
| 21 |
+
"image_token_id": 248056,
|
| 22 |
+
"language_model_only": false,
|
| 23 |
+
"model_type": "qwen3_5",
|
| 24 |
+
"text_config": {
|
| 25 |
+
"_name_or_path": "",
|
| 26 |
+
"architectures": null,
|
| 27 |
+
"attention_bias": false,
|
| 28 |
+
"attention_dropout": 0.0,
|
| 29 |
+
"attn_output_gate": true,
|
| 30 |
+
"bos_token_id": 248044,
|
| 31 |
+
"chunk_size_feed_forward": 0,
|
| 32 |
+
"dtype": "bfloat16",
|
| 33 |
+
"eos_token_id": 248044,
|
| 34 |
+
"full_attention_interval": 4,
|
| 35 |
+
"head_dim": 256,
|
| 36 |
+
"hidden_act": "silu",
|
| 37 |
+
"hidden_size": 5120,
|
| 38 |
+
"id2label": {
|
| 39 |
+
"0": "LABEL_0",
|
| 40 |
+
"1": "LABEL_1"
|
| 41 |
+
},
|
| 42 |
+
"initializer_range": 0.02,
|
| 43 |
+
"intermediate_size": 17408,
|
| 44 |
+
"is_encoder_decoder": false,
|
| 45 |
+
"label2id": {
|
| 46 |
+
"LABEL_0": 0,
|
| 47 |
+
"LABEL_1": 1
|
| 48 |
+
},
|
| 49 |
+
"layer_types": [
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"linear_attention",
|
| 53 |
+
"full_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"linear_attention",
|
| 57 |
+
"full_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"linear_attention",
|
| 61 |
+
"full_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"linear_attention",
|
| 65 |
+
"full_attention",
|
| 66 |
+
"linear_attention",
|
| 67 |
+
"linear_attention",
|
| 68 |
+
"linear_attention",
|
| 69 |
+
"full_attention",
|
| 70 |
+
"linear_attention",
|
| 71 |
+
"linear_attention",
|
| 72 |
+
"linear_attention",
|
| 73 |
+
"full_attention",
|
| 74 |
+
"linear_attention",
|
| 75 |
+
"linear_attention",
|
| 76 |
+
"linear_attention",
|
| 77 |
+
"full_attention",
|
| 78 |
+
"linear_attention",
|
| 79 |
+
"linear_attention",
|
| 80 |
+
"linear_attention",
|
| 81 |
+
"full_attention",
|
| 82 |
+
"linear_attention",
|
| 83 |
+
"linear_attention",
|
| 84 |
+
"linear_attention",
|
| 85 |
+
"full_attention",
|
| 86 |
+
"linear_attention",
|
| 87 |
+
"linear_attention",
|
| 88 |
+
"linear_attention",
|
| 89 |
+
"full_attention",
|
| 90 |
+
"linear_attention",
|
| 91 |
+
"linear_attention",
|
| 92 |
+
"linear_attention",
|
| 93 |
+
"full_attention",
|
| 94 |
+
"linear_attention",
|
| 95 |
+
"linear_attention",
|
| 96 |
+
"linear_attention",
|
| 97 |
+
"full_attention",
|
| 98 |
+
"linear_attention",
|
| 99 |
+
"linear_attention",
|
| 100 |
+
"linear_attention",
|
| 101 |
+
"full_attention",
|
| 102 |
+
"linear_attention",
|
| 103 |
+
"linear_attention",
|
| 104 |
+
"linear_attention",
|
| 105 |
+
"full_attention",
|
| 106 |
+
"linear_attention",
|
| 107 |
+
"linear_attention",
|
| 108 |
+
"linear_attention",
|
| 109 |
+
"full_attention",
|
| 110 |
+
"linear_attention",
|
| 111 |
+
"linear_attention",
|
| 112 |
+
"linear_attention",
|
| 113 |
+
"full_attention"
|
| 114 |
+
],
|
| 115 |
+
"linear_conv_kernel_dim": 4,
|
| 116 |
+
"linear_key_head_dim": 128,
|
| 117 |
+
"linear_num_key_heads": 16,
|
| 118 |
+
"linear_num_value_heads": 48,
|
| 119 |
+
"linear_value_head_dim": 128,
|
| 120 |
+
"mamba_ssm_dtype": "float32",
|
| 121 |
+
"max_position_embeddings": 262144,
|
| 122 |
+
"model_type": "qwen3_5_text",
|
| 123 |
+
"mtp_num_hidden_layers": 1,
|
| 124 |
+
"mtp_use_dedicated_embeddings": false,
|
| 125 |
+
"num_attention_heads": 24,
|
| 126 |
+
"num_hidden_layers": 64,
|
| 127 |
+
"num_key_value_heads": 4,
|
| 128 |
+
"output_attentions": false,
|
| 129 |
+
"output_gate_type": "swish",
|
| 130 |
+
"output_hidden_states": false,
|
| 131 |
+
"pad_token_id": null,
|
| 132 |
+
"partial_rotary_factor": 0.25,
|
| 133 |
+
"problem_type": null,
|
| 134 |
+
"return_dict": true,
|
| 135 |
+
"rms_norm_eps": 1e-06,
|
| 136 |
+
"rope_parameters": {
|
| 137 |
+
"mrope_interleaved": true,
|
| 138 |
+
"mrope_section": [
|
| 139 |
+
11,
|
| 140 |
+
11,
|
| 141 |
+
10
|
| 142 |
+
],
|
| 143 |
+
"partial_rotary_factor": 0.25,
|
| 144 |
+
"rope_theta": 10000000,
|
| 145 |
+
"rope_type": "default"
|
| 146 |
+
},
|
| 147 |
+
"tie_word_embeddings": false,
|
| 148 |
+
"use_cache": true,
|
| 149 |
+
"vocab_size": 248080
|
| 150 |
+
},
|
| 151 |
+
"tie_word_embeddings": false,
|
| 152 |
+
"video_token_id": 248057,
|
| 153 |
+
"vision_config": {
|
| 154 |
+
"_name_or_path": "",
|
| 155 |
+
"architectures": null,
|
| 156 |
+
"chunk_size_feed_forward": 0,
|
| 157 |
+
"deepstack_visual_indexes": [],
|
| 158 |
+
"depth": 27,
|
| 159 |
+
"dtype": null,
|
| 160 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 161 |
+
"hidden_size": 1152,
|
| 162 |
+
"id2label": {
|
| 163 |
+
"0": "LABEL_0",
|
| 164 |
+
"1": "LABEL_1"
|
| 165 |
+
},
|
| 166 |
+
"in_channels": 3,
|
| 167 |
+
"initializer_range": 0.02,
|
| 168 |
+
"intermediate_size": 4304,
|
| 169 |
+
"is_encoder_decoder": false,
|
| 170 |
+
"label2id": {
|
| 171 |
+
"LABEL_0": 0,
|
| 172 |
+
"LABEL_1": 1
|
| 173 |
+
},
|
| 174 |
+
"model_type": "qwen3_5_vision",
|
| 175 |
+
"num_heads": 16,
|
| 176 |
+
"num_position_embeddings": 2304,
|
| 177 |
+
"out_hidden_size": 5120,
|
| 178 |
+
"output_attentions": false,
|
| 179 |
+
"output_hidden_states": false,
|
| 180 |
+
"patch_size": 16,
|
| 181 |
+
"problem_type": null,
|
| 182 |
+
"return_dict": true,
|
| 183 |
+
"rope_parameters": {
|
| 184 |
+
"rope_theta": 10000.0,
|
| 185 |
+
"rope_type": "axial"
|
| 186 |
+
},
|
| 187 |
+
"spatial_merge_size": 2,
|
| 188 |
+
"temporal_patch_size": 2
|
| 189 |
+
},
|
| 190 |
+
"vision_end_token_id": 248054,
|
| 191 |
+
"vision_start_token_id": 248053
|
| 192 |
+
},
|
| 193 |
+
"encoder_layer_id": -1,
|
| 194 |
+
"encoder_model_name": "Qwen/Qwen3.8-27B",
|
| 195 |
+
"eos_token_id": 248046,
|
| 196 |
+
"example_token_index": 248079,
|
| 197 |
+
"extract_text_features": false,
|
| 198 |
+
"focal_loss_alpha": 0.75,
|
| 199 |
+
"focal_loss_gamma": -1,
|
| 200 |
+
"focal_loss_reduction": "none",
|
| 201 |
+
"freeze_media_encoders": true,
|
| 202 |
+
"hidden_size": 5120,
|
| 203 |
+
"ignore_index": -100,
|
| 204 |
+
"initializer_range": 0.03,
|
| 205 |
+
"label_model_config": {
|
| 206 |
+
"_name_or_path": "BAAI/bge-small-en-v1.5",
|
| 207 |
+
"add_cross_attention": false,
|
| 208 |
+
"architectures": [
|
| 209 |
+
"BertModel"
|
| 210 |
+
],
|
| 211 |
+
"attention_probs_dropout_prob": 0.1,
|
| 212 |
+
"bos_token_id": null,
|
| 213 |
+
"chunk_size_feed_forward": 0,
|
| 214 |
+
"classifier_dropout": null,
|
| 215 |
+
"dtype": "float32",
|
| 216 |
+
"eos_token_id": null,
|
| 217 |
+
"hidden_act": "gelu",
|
| 218 |
+
"hidden_dropout_prob": 0.1,
|
| 219 |
+
"hidden_size": 384,
|
| 220 |
+
"id2label": {
|
| 221 |
+
"0": "LABEL_0"
|
| 222 |
+
},
|
| 223 |
+
"initializer_range": 0.02,
|
| 224 |
+
"intermediate_size": 1536,
|
| 225 |
+
"is_decoder": false,
|
| 226 |
+
"is_encoder_decoder": false,
|
| 227 |
+
"label2id": {
|
| 228 |
+
"LABEL_0": 0
|
| 229 |
+
},
|
| 230 |
+
"layer_norm_eps": 1e-12,
|
| 231 |
+
"max_position_embeddings": 512,
|
| 232 |
+
"model_type": "bert",
|
| 233 |
+
"num_attention_heads": 12,
|
| 234 |
+
"num_hidden_layers": 12,
|
| 235 |
+
"output_attentions": false,
|
| 236 |
+
"output_hidden_states": false,
|
| 237 |
+
"pad_token_id": 0,
|
| 238 |
+
"position_embedding_type": "absolute",
|
| 239 |
+
"problem_type": null,
|
| 240 |
+
"return_dict": true,
|
| 241 |
+
"tie_word_embeddings": true,
|
| 242 |
+
"type_vocab_size": 2,
|
| 243 |
+
"use_cache": true,
|
| 244 |
+
"vocab_size": 30522
|
| 245 |
+
},
|
| 246 |
+
"label_model_name": "BAAI/bge-small-en-v1.5",
|
| 247 |
+
"layer_wise": false,
|
| 248 |
+
"logit_scale_init_value": 2.6592,
|
| 249 |
+
"max_labels_alloc": "dynamic",
|
| 250 |
+
"max_num_classes": 25,
|
| 251 |
+
"model_type": "GLiClass",
|
| 252 |
+
"multimodal": true,
|
| 253 |
+
"normalize_features": false,
|
| 254 |
+
"pad_token_id": 248044,
|
| 255 |
+
"pooling_strategy": "avg",
|
| 256 |
+
"problem_type": "multi_label_classification",
|
| 257 |
+
"projector_hidden_act": "gelu",
|
| 258 |
+
"prompt_first": true,
|
| 259 |
+
"recurrent_bptt_steps": null,
|
| 260 |
+
"recurrent_confidence_coef": 0.0,
|
| 261 |
+
"recurrent_confidence_margin": 0.0,
|
| 262 |
+
"recurrent_confidence_mode": "relative",
|
| 263 |
+
"recurrent_halt_threshold": 0.01,
|
| 264 |
+
"recurrent_improvement_coef": 0.1,
|
| 265 |
+
"recurrent_improvement_margin": 0.05,
|
| 266 |
+
"recurrent_inference": true,
|
| 267 |
+
"recurrent_inference_max_steps": null,
|
| 268 |
+
"recurrent_min_steps": 1,
|
| 269 |
+
"recurrent_read_text": false,
|
| 270 |
+
"recurrent_steps": 3,
|
| 271 |
+
"scorer_attn_dropout": 0.1,
|
| 272 |
+
"scorer_encoder_num_layers": 2,
|
| 273 |
+
"scorer_full_sequence": false,
|
| 274 |
+
"scorer_mlp_hidden_size": 1024,
|
| 275 |
+
"scorer_num_heads": 16,
|
| 276 |
+
"scorer_type": "simple",
|
| 277 |
+
"sep_token_index": 248078,
|
| 278 |
+
"shuffle_labels": true,
|
| 279 |
+
"squeeze_layers": false,
|
| 280 |
+
"text_token_index": 248078,
|
| 281 |
+
"transformers_version": "5.19.0",
|
| 282 |
+
"use_cache": false,
|
| 283 |
+
"use_calibrator": false,
|
| 284 |
+
"use_embedding_projection": false,
|
| 285 |
+
"use_lstm": false,
|
| 286 |
+
"use_segment_embeddings": false,
|
| 287 |
+
"vocab_size": 248080
|
| 288 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6846bbbfca512047421f603a246963ecd003b707e5b06d7fce23338e8ea1958c
|
| 3 |
+
size 49951172240
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1cbe6231a900d8e15e3b178e659cc04d458bfa875c3ddd083c05ded6ae2a99d6
|
| 3 |
+
size 25631013660
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor_config.json
ADDED
|
@@ -0,0 +1,61 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"do_convert_rgb": true,
|
| 4 |
+
"do_normalize": true,
|
| 5 |
+
"do_rescale": true,
|
| 6 |
+
"do_resize": true,
|
| 7 |
+
"image_mean": [
|
| 8 |
+
0.5,
|
| 9 |
+
0.5,
|
| 10 |
+
0.5
|
| 11 |
+
],
|
| 12 |
+
"image_processor_type": "Qwen2VLImageProcessor",
|
| 13 |
+
"image_std": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"patch_size": 16,
|
| 20 |
+
"resample": 3,
|
| 21 |
+
"rescale_factor": 0.00392156862745098,
|
| 22 |
+
"size": {
|
| 23 |
+
"longest_edge": 16777216,
|
| 24 |
+
"shortest_edge": 65536
|
| 25 |
+
},
|
| 26 |
+
"temporal_patch_size": 2
|
| 27 |
+
},
|
| 28 |
+
"processor_class": "Qwen3VLProcessor",
|
| 29 |
+
"video_processor": {
|
| 30 |
+
"do_convert_rgb": true,
|
| 31 |
+
"do_normalize": true,
|
| 32 |
+
"do_rescale": true,
|
| 33 |
+
"do_resize": true,
|
| 34 |
+
"do_sample_frames": true,
|
| 35 |
+
"fps": 2,
|
| 36 |
+
"image_mean": [
|
| 37 |
+
0.5,
|
| 38 |
+
0.5,
|
| 39 |
+
0.5
|
| 40 |
+
],
|
| 41 |
+
"image_std": [
|
| 42 |
+
0.5,
|
| 43 |
+
0.5,
|
| 44 |
+
0.5
|
| 45 |
+
],
|
| 46 |
+
"max_frames": 768,
|
| 47 |
+
"max_video_tokens": 768,
|
| 48 |
+
"merge_size": 2,
|
| 49 |
+
"min_frames": 4,
|
| 50 |
+
"patch_size": 16,
|
| 51 |
+
"resample": 3,
|
| 52 |
+
"rescale_factor": 0.00392156862745098,
|
| 53 |
+
"return_metadata": false,
|
| 54 |
+
"size": {
|
| 55 |
+
"longest_edge": 25165824,
|
| 56 |
+
"shortest_edge": 4096
|
| 57 |
+
},
|
| 58 |
+
"temporal_patch_size": 2,
|
| 59 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 60 |
+
}
|
| 61 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:04472e9fcd4aea467a49025c27c0469a428bda2f812268fc9b26fea77c016f71
|
| 3 |
+
size 19989897
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"audio_bos_token": "<|audio_start|>",
|
| 4 |
+
"audio_eos_token": "<|audio_end|>",
|
| 5 |
+
"audio_token": "<|audio_pad|>",
|
| 6 |
+
"backend": "tokenizers",
|
| 7 |
+
"bos_token": null,
|
| 8 |
+
"clean_up_tokenization_spaces": false,
|
| 9 |
+
"eos_token": "<|im_end|>",
|
| 10 |
+
"errors": "replace",
|
| 11 |
+
"extra_special_tokens": [
|
| 12 |
+
"<|im_start|>",
|
| 13 |
+
"<|im_end|>",
|
| 14 |
+
"<|object_ref_start|>",
|
| 15 |
+
"<|object_ref_end|>",
|
| 16 |
+
"<|box_start|>",
|
| 17 |
+
"<|box_end|>",
|
| 18 |
+
"<|quad_start|>",
|
| 19 |
+
"<|quad_end|>",
|
| 20 |
+
"<|vision_start|>",
|
| 21 |
+
"<|vision_end|>",
|
| 22 |
+
"<|vision_pad|>",
|
| 23 |
+
"<|image_pad|>",
|
| 24 |
+
"<|video_pad|>"
|
| 25 |
+
],
|
| 26 |
+
"image_token": "<|image_pad|>",
|
| 27 |
+
"is_local": false,
|
| 28 |
+
"local_files_only": false,
|
| 29 |
+
"merges_file": null,
|
| 30 |
+
"model_max_length": 262144,
|
| 31 |
+
"model_specific_special_tokens": {
|
| 32 |
+
"audio_bos_token": "<|audio_start|>",
|
| 33 |
+
"audio_eos_token": "<|audio_end|>",
|
| 34 |
+
"audio_token": "<|audio_pad|>",
|
| 35 |
+
"image_token": "<|image_pad|>",
|
| 36 |
+
"video_token": "<|video_pad|>",
|
| 37 |
+
"vision_bos_token": "<|vision_start|>",
|
| 38 |
+
"vision_eos_token": "<|vision_end|>"
|
| 39 |
+
},
|
| 40 |
+
"pad_token": "<|endoftext|>",
|
| 41 |
+
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
|
| 42 |
+
"processor_class": "Qwen3VLProcessor",
|
| 43 |
+
"split_special_tokens": false,
|
| 44 |
+
"tokenizer_class": "Qwen3_5Tokenizer",
|
| 45 |
+
"unk_token": null,
|
| 46 |
+
"video_token": "<|video_pad|>",
|
| 47 |
+
"vision_bos_token": "<|vision_start|>",
|
| 48 |
+
"vision_eos_token": "<|vision_end|>"
|
| 49 |
+
}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2056 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 0.3377617653681603,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3000,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"entropy_step_1": 0.5071,
|
| 14 |
+
"entropy_step_2": 0.5119,
|
| 15 |
+
"entropy_step_3": 0.5334,
|
| 16 |
+
"epoch": 0.002251745102454402,
|
| 17 |
+
"grad_norm": 152.6436767578125,
|
| 18 |
+
"learning_rate": 2.1348314606741574e-06,
|
| 19 |
+
"loss": 0.3228358507156372,
|
| 20 |
+
"loss_step_1": 0.3397,
|
| 21 |
+
"loss_step_2": 0.323,
|
| 22 |
+
"loss_step_3": 0.3292,
|
| 23 |
+
"step": 20
|
| 24 |
+
},
|
| 25 |
+
{
|
| 26 |
+
"entropy_step_1": 0.4986,
|
| 27 |
+
"entropy_step_2": 0.5136,
|
| 28 |
+
"entropy_step_3": 0.5174,
|
| 29 |
+
"epoch": 0.004503490204908804,
|
| 30 |
+
"grad_norm": 82.56465911865234,
|
| 31 |
+
"learning_rate": 4.382022471910113e-06,
|
| 32 |
+
"loss": 0.29514193534851074,
|
| 33 |
+
"loss_step_1": 0.2969,
|
| 34 |
+
"loss_step_2": 0.2954,
|
| 35 |
+
"loss_step_3": 0.3208,
|
| 36 |
+
"step": 40
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"entropy_step_1": 0.4912,
|
| 40 |
+
"entropy_step_2": 0.4888,
|
| 41 |
+
"entropy_step_3": 0.4925,
|
| 42 |
+
"epoch": 0.006755235307363206,
|
| 43 |
+
"grad_norm": 96.96111297607422,
|
| 44 |
+
"learning_rate": 6.629213483146068e-06,
|
| 45 |
+
"loss": 0.27988529205322266,
|
| 46 |
+
"loss_step_1": 0.2897,
|
| 47 |
+
"loss_step_2": 0.2827,
|
| 48 |
+
"loss_step_3": 0.2716,
|
| 49 |
+
"step": 60
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"entropy_step_1": 0.5095,
|
| 53 |
+
"entropy_step_2": 0.5193,
|
| 54 |
+
"entropy_step_3": 0.5371,
|
| 55 |
+
"epoch": 0.009006980409817608,
|
| 56 |
+
"grad_norm": 69.78874206542969,
|
| 57 |
+
"learning_rate": 8.876404494382023e-06,
|
| 58 |
+
"loss": 0.2626279354095459,
|
| 59 |
+
"loss_step_1": 0.2705,
|
| 60 |
+
"loss_step_2": 0.2666,
|
| 61 |
+
"loss_step_3": 0.2681,
|
| 62 |
+
"step": 80
|
| 63 |
+
},
|
| 64 |
+
{
|
| 65 |
+
"entropy_step_1": 0.5451,
|
| 66 |
+
"entropy_step_2": 0.5455,
|
| 67 |
+
"entropy_step_3": 0.5558,
|
| 68 |
+
"epoch": 0.01125872551227201,
|
| 69 |
+
"grad_norm": 55.91513442993164,
|
| 70 |
+
"learning_rate": 1.1123595505617979e-05,
|
| 71 |
+
"loss": 0.27101755142211914,
|
| 72 |
+
"loss_step_1": 0.2703,
|
| 73 |
+
"loss_step_2": 0.271,
|
| 74 |
+
"loss_step_3": 0.2681,
|
| 75 |
+
"step": 100
|
| 76 |
+
},
|
| 77 |
+
{
|
| 78 |
+
"entropy_step_1": 0.5382,
|
| 79 |
+
"entropy_step_2": 0.5378,
|
| 80 |
+
"entropy_step_3": 0.5583,
|
| 81 |
+
"epoch": 0.013510470614726412,
|
| 82 |
+
"grad_norm": 41.265892028808594,
|
| 83 |
+
"learning_rate": 1.3370786516853933e-05,
|
| 84 |
+
"loss": 0.2572871923446655,
|
| 85 |
+
"loss_step_1": 0.2591,
|
| 86 |
+
"loss_step_2": 0.2582,
|
| 87 |
+
"loss_step_3": 0.2676,
|
| 88 |
+
"step": 120
|
| 89 |
+
},
|
| 90 |
+
{
|
| 91 |
+
"entropy_step_1": 0.569,
|
| 92 |
+
"entropy_step_2": 0.5649,
|
| 93 |
+
"entropy_step_3": 0.5679,
|
| 94 |
+
"epoch": 0.015762215717180814,
|
| 95 |
+
"grad_norm": 36.103328704833984,
|
| 96 |
+
"learning_rate": 1.561797752808989e-05,
|
| 97 |
+
"loss": 0.2525103807449341,
|
| 98 |
+
"loss_step_1": 0.2513,
|
| 99 |
+
"loss_step_2": 0.2497,
|
| 100 |
+
"loss_step_3": 0.2568,
|
| 101 |
+
"step": 140
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"entropy_step_1": 0.5107,
|
| 105 |
+
"entropy_step_2": 0.5314,
|
| 106 |
+
"entropy_step_3": 0.553,
|
| 107 |
+
"epoch": 0.018013960819635216,
|
| 108 |
+
"grad_norm": 82.27144622802734,
|
| 109 |
+
"learning_rate": 1.7865168539325843e-05,
|
| 110 |
+
"loss": 0.24409973621368408,
|
| 111 |
+
"loss_step_1": 0.2396,
|
| 112 |
+
"loss_step_2": 0.2354,
|
| 113 |
+
"loss_step_3": 0.2597,
|
| 114 |
+
"step": 160
|
| 115 |
+
},
|
| 116 |
+
{
|
| 117 |
+
"entropy_step_1": 0.5096,
|
| 118 |
+
"entropy_step_2": 0.5089,
|
| 119 |
+
"entropy_step_3": 0.5026,
|
| 120 |
+
"epoch": 0.02026570592208962,
|
| 121 |
+
"grad_norm": 56.205013275146484,
|
| 122 |
+
"learning_rate": 2.01123595505618e-05,
|
| 123 |
+
"loss": 0.24852406978607178,
|
| 124 |
+
"loss_step_1": 0.2405,
|
| 125 |
+
"loss_step_2": 0.2359,
|
| 126 |
+
"loss_step_3": 0.2298,
|
| 127 |
+
"step": 180
|
| 128 |
+
},
|
| 129 |
+
{
|
| 130 |
+
"entropy_step_1": 0.5096,
|
| 131 |
+
"entropy_step_2": 0.5212,
|
| 132 |
+
"entropy_step_3": 0.505,
|
| 133 |
+
"epoch": 0.02251745102454402,
|
| 134 |
+
"grad_norm": 90.33285522460938,
|
| 135 |
+
"learning_rate": 2.2359550561797755e-05,
|
| 136 |
+
"loss": 0.26528267860412597,
|
| 137 |
+
"loss_step_1": 0.2671,
|
| 138 |
+
"loss_step_2": 0.268,
|
| 139 |
+
"loss_step_3": 0.2574,
|
| 140 |
+
"step": 200
|
| 141 |
+
},
|
| 142 |
+
{
|
| 143 |
+
"entropy_step_1": 0.5181,
|
| 144 |
+
"entropy_step_2": 0.5089,
|
| 145 |
+
"entropy_step_3": 0.5073,
|
| 146 |
+
"epoch": 0.024769196126998422,
|
| 147 |
+
"grad_norm": 37.29897689819336,
|
| 148 |
+
"learning_rate": 2.4606741573033708e-05,
|
| 149 |
+
"loss": 0.25939555168151857,
|
| 150 |
+
"loss_step_1": 0.259,
|
| 151 |
+
"loss_step_2": 0.2639,
|
| 152 |
+
"loss_step_3": 0.2608,
|
| 153 |
+
"step": 220
|
| 154 |
+
},
|
| 155 |
+
{
|
| 156 |
+
"entropy_step_1": 0.5119,
|
| 157 |
+
"entropy_step_2": 0.5074,
|
| 158 |
+
"entropy_step_3": 0.5096,
|
| 159 |
+
"epoch": 0.027020941229452825,
|
| 160 |
+
"grad_norm": 32.72456359863281,
|
| 161 |
+
"learning_rate": 2.6853932584269664e-05,
|
| 162 |
+
"loss": 0.23640341758728028,
|
| 163 |
+
"loss_step_1": 0.2316,
|
| 164 |
+
"loss_step_2": 0.2363,
|
| 165 |
+
"loss_step_3": 0.231,
|
| 166 |
+
"step": 240
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"entropy_step_1": 0.5365,
|
| 170 |
+
"entropy_step_2": 0.5413,
|
| 171 |
+
"entropy_step_3": 0.5348,
|
| 172 |
+
"epoch": 0.029272686331907227,
|
| 173 |
+
"grad_norm": 64.05130767822266,
|
| 174 |
+
"learning_rate": 2.910112359550562e-05,
|
| 175 |
+
"loss": 0.25620646476745607,
|
| 176 |
+
"loss_step_1": 0.2572,
|
| 177 |
+
"loss_step_2": 0.2605,
|
| 178 |
+
"loss_step_3": 0.2559,
|
| 179 |
+
"step": 260
|
| 180 |
+
},
|
| 181 |
+
{
|
| 182 |
+
"entropy_step_1": 0.511,
|
| 183 |
+
"entropy_step_2": 0.5137,
|
| 184 |
+
"entropy_step_3": 0.5369,
|
| 185 |
+
"epoch": 0.03152443143436163,
|
| 186 |
+
"grad_norm": 11.283477783203125,
|
| 187 |
+
"learning_rate": 3.1348314606741577e-05,
|
| 188 |
+
"loss": 0.2500739812850952,
|
| 189 |
+
"loss_step_1": 0.2508,
|
| 190 |
+
"loss_step_2": 0.255,
|
| 191 |
+
"loss_step_3": 0.2577,
|
| 192 |
+
"step": 280
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"entropy_step_1": 0.4744,
|
| 196 |
+
"entropy_step_2": 0.4708,
|
| 197 |
+
"entropy_step_3": 0.4854,
|
| 198 |
+
"epoch": 0.033776176536816034,
|
| 199 |
+
"grad_norm": 30.046085357666016,
|
| 200 |
+
"learning_rate": 3.359550561797753e-05,
|
| 201 |
+
"loss": 0.2620354652404785,
|
| 202 |
+
"loss_step_1": 0.2531,
|
| 203 |
+
"loss_step_2": 0.2562,
|
| 204 |
+
"loss_step_3": 0.2592,
|
| 205 |
+
"step": 300
|
| 206 |
+
},
|
| 207 |
+
{
|
| 208 |
+
"entropy_step_1": 0.5122,
|
| 209 |
+
"entropy_step_2": 0.5082,
|
| 210 |
+
"entropy_step_3": 0.528,
|
| 211 |
+
"epoch": 0.03602792163927043,
|
| 212 |
+
"grad_norm": 115.32505798339844,
|
| 213 |
+
"learning_rate": 3.584269662921348e-05,
|
| 214 |
+
"loss": 0.23967413902282714,
|
| 215 |
+
"loss_step_1": 0.2444,
|
| 216 |
+
"loss_step_2": 0.2471,
|
| 217 |
+
"loss_step_3": 0.2476,
|
| 218 |
+
"step": 320
|
| 219 |
+
},
|
| 220 |
+
{
|
| 221 |
+
"entropy_step_1": 0.5323,
|
| 222 |
+
"entropy_step_2": 0.5317,
|
| 223 |
+
"entropy_step_3": 0.5358,
|
| 224 |
+
"epoch": 0.03827966674172484,
|
| 225 |
+
"grad_norm": 21.213909149169922,
|
| 226 |
+
"learning_rate": 3.808988764044944e-05,
|
| 227 |
+
"loss": 0.2502254247665405,
|
| 228 |
+
"loss_step_1": 0.2447,
|
| 229 |
+
"loss_step_2": 0.2447,
|
| 230 |
+
"loss_step_3": 0.2492,
|
| 231 |
+
"step": 340
|
| 232 |
+
},
|
| 233 |
+
{
|
| 234 |
+
"entropy_step_1": 0.5409,
|
| 235 |
+
"entropy_step_2": 0.5452,
|
| 236 |
+
"entropy_step_3": 0.5462,
|
| 237 |
+
"epoch": 0.04053141184417924,
|
| 238 |
+
"grad_norm": 61.29066467285156,
|
| 239 |
+
"learning_rate": 4.0337078651685395e-05,
|
| 240 |
+
"loss": 0.24284050464630128,
|
| 241 |
+
"loss_step_1": 0.2415,
|
| 242 |
+
"loss_step_2": 0.2416,
|
| 243 |
+
"loss_step_3": 0.2389,
|
| 244 |
+
"step": 360
|
| 245 |
+
},
|
| 246 |
+
{
|
| 247 |
+
"entropy_step_1": 0.5259,
|
| 248 |
+
"entropy_step_2": 0.5241,
|
| 249 |
+
"entropy_step_3": 0.5625,
|
| 250 |
+
"epoch": 0.04278315694663364,
|
| 251 |
+
"grad_norm": 12.363038063049316,
|
| 252 |
+
"learning_rate": 4.258426966292135e-05,
|
| 253 |
+
"loss": 0.24444761276245117,
|
| 254 |
+
"loss_step_1": 0.244,
|
| 255 |
+
"loss_step_2": 0.2446,
|
| 256 |
+
"loss_step_3": 0.2574,
|
| 257 |
+
"step": 380
|
| 258 |
+
},
|
| 259 |
+
{
|
| 260 |
+
"entropy_step_1": 0.5149,
|
| 261 |
+
"entropy_step_2": 0.5206,
|
| 262 |
+
"entropy_step_3": 0.5308,
|
| 263 |
+
"epoch": 0.04503490204908804,
|
| 264 |
+
"grad_norm": 128.7165985107422,
|
| 265 |
+
"learning_rate": 4.483146067415731e-05,
|
| 266 |
+
"loss": 0.24292342662811278,
|
| 267 |
+
"loss_step_1": 0.2446,
|
| 268 |
+
"loss_step_2": 0.2447,
|
| 269 |
+
"loss_step_3": 0.2457,
|
| 270 |
+
"step": 400
|
| 271 |
+
},
|
| 272 |
+
{
|
| 273 |
+
"entropy_step_1": 0.4971,
|
| 274 |
+
"entropy_step_2": 0.5056,
|
| 275 |
+
"entropy_step_3": 0.507,
|
| 276 |
+
"epoch": 0.047286647151542446,
|
| 277 |
+
"grad_norm": 23.033126831054688,
|
| 278 |
+
"learning_rate": 4.707865168539326e-05,
|
| 279 |
+
"loss": 0.24463484287261963,
|
| 280 |
+
"loss_step_1": 0.2467,
|
| 281 |
+
"loss_step_2": 0.2435,
|
| 282 |
+
"loss_step_3": 0.2437,
|
| 283 |
+
"step": 420
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"entropy_step_1": 0.4698,
|
| 287 |
+
"entropy_step_2": 0.4834,
|
| 288 |
+
"entropy_step_3": 0.4777,
|
| 289 |
+
"epoch": 0.049538392253996845,
|
| 290 |
+
"grad_norm": 310.9460754394531,
|
| 291 |
+
"learning_rate": 4.932584269662921e-05,
|
| 292 |
+
"loss": 0.2659726142883301,
|
| 293 |
+
"loss_step_1": 0.2726,
|
| 294 |
+
"loss_step_2": 0.274,
|
| 295 |
+
"loss_step_3": 0.2631,
|
| 296 |
+
"step": 440
|
| 297 |
+
},
|
| 298 |
+
{
|
| 299 |
+
"entropy_step_1": 0.4355,
|
| 300 |
+
"entropy_step_2": 0.4385,
|
| 301 |
+
"entropy_step_3": 0.454,
|
| 302 |
+
"epoch": 0.05179013735645125,
|
| 303 |
+
"grad_norm": 42.6382942199707,
|
| 304 |
+
"learning_rate": 4.991703212042195e-05,
|
| 305 |
+
"loss": 0.26493167877197266,
|
| 306 |
+
"loss_step_1": 0.2585,
|
| 307 |
+
"loss_step_2": 0.2619,
|
| 308 |
+
"loss_step_3": 0.2874,
|
| 309 |
+
"step": 460
|
| 310 |
+
},
|
| 311 |
+
{
|
| 312 |
+
"entropy_step_1": 0.5178,
|
| 313 |
+
"entropy_step_2": 0.5251,
|
| 314 |
+
"entropy_step_3": 0.5181,
|
| 315 |
+
"epoch": 0.05404188245890565,
|
| 316 |
+
"grad_norm": 26.805788040161133,
|
| 317 |
+
"learning_rate": 4.97985065781676e-05,
|
| 318 |
+
"loss": 0.23524324893951415,
|
| 319 |
+
"loss_step_1": 0.2401,
|
| 320 |
+
"loss_step_2": 0.2446,
|
| 321 |
+
"loss_step_3": 0.2447,
|
| 322 |
+
"step": 480
|
| 323 |
+
},
|
| 324 |
+
{
|
| 325 |
+
"entropy_step_1": 0.4867,
|
| 326 |
+
"entropy_step_2": 0.4941,
|
| 327 |
+
"entropy_step_3": 0.5018,
|
| 328 |
+
"epoch": 0.056293627561360055,
|
| 329 |
+
"grad_norm": 76.55230712890625,
|
| 330 |
+
"learning_rate": 4.967998103591324e-05,
|
| 331 |
+
"loss": 0.23355183601379395,
|
| 332 |
+
"loss_step_1": 0.2355,
|
| 333 |
+
"loss_step_2": 0.2352,
|
| 334 |
+
"loss_step_3": 0.2434,
|
| 335 |
+
"step": 500
|
| 336 |
+
},
|
| 337 |
+
{
|
| 338 |
+
"epoch": 0.056293627561360055,
|
| 339 |
+
"eval_accuracy": 0.9625,
|
| 340 |
+
"eval_f1": 0.9515068493150685,
|
| 341 |
+
"eval_loss": 0.14244329929351807,
|
| 342 |
+
"eval_precision": 0.9472972972972973,
|
| 343 |
+
"eval_recall": 0.9625,
|
| 344 |
+
"eval_runtime": 9.7208,
|
| 345 |
+
"eval_samples_per_second": 10.287,
|
| 346 |
+
"eval_steps_per_second": 1.337,
|
| 347 |
+
"step": 500
|
| 348 |
+
},
|
| 349 |
+
{
|
| 350 |
+
"entropy_step_1": 0.4976,
|
| 351 |
+
"entropy_step_2": 0.5087,
|
| 352 |
+
"entropy_step_3": 0.497,
|
| 353 |
+
"epoch": 0.05854537266381445,
|
| 354 |
+
"grad_norm": 69.90751647949219,
|
| 355 |
+
"learning_rate": 4.9561455493658886e-05,
|
| 356 |
+
"loss": 0.2311638593673706,
|
| 357 |
+
"loss_step_1": 0.2166,
|
| 358 |
+
"loss_step_2": 0.2179,
|
| 359 |
+
"loss_step_3": 0.2117,
|
| 360 |
+
"step": 520
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"entropy_step_1": 0.5476,
|
| 364 |
+
"entropy_step_2": 0.5545,
|
| 365 |
+
"entropy_step_3": 0.5697,
|
| 366 |
+
"epoch": 0.06079711776626886,
|
| 367 |
+
"grad_norm": 14.77850341796875,
|
| 368 |
+
"learning_rate": 4.944292995140453e-05,
|
| 369 |
+
"loss": 0.2462395668029785,
|
| 370 |
+
"loss_step_1": 0.2399,
|
| 371 |
+
"loss_step_2": 0.2391,
|
| 372 |
+
"loss_step_3": 0.242,
|
| 373 |
+
"step": 540
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"entropy_step_1": 0.4636,
|
| 377 |
+
"entropy_step_2": 0.4637,
|
| 378 |
+
"entropy_step_3": 0.4628,
|
| 379 |
+
"epoch": 0.06304886286872326,
|
| 380 |
+
"grad_norm": 189.9615936279297,
|
| 381 |
+
"learning_rate": 4.9324404409150174e-05,
|
| 382 |
+
"loss": 0.29347028732299807,
|
| 383 |
+
"loss_step_1": 0.2986,
|
| 384 |
+
"loss_step_2": 0.3006,
|
| 385 |
+
"loss_step_3": 0.2919,
|
| 386 |
+
"step": 560
|
| 387 |
+
},
|
| 388 |
+
{
|
| 389 |
+
"entropy_step_1": 0.5222,
|
| 390 |
+
"entropy_step_2": 0.5247,
|
| 391 |
+
"entropy_step_3": 0.5243,
|
| 392 |
+
"epoch": 0.06530060797117766,
|
| 393 |
+
"grad_norm": 31.364818572998047,
|
| 394 |
+
"learning_rate": 4.920587886689582e-05,
|
| 395 |
+
"loss": 0.26621253490448,
|
| 396 |
+
"loss_step_1": 0.2646,
|
| 397 |
+
"loss_step_2": 0.2668,
|
| 398 |
+
"loss_step_3": 0.2686,
|
| 399 |
+
"step": 580
|
| 400 |
+
},
|
| 401 |
+
{
|
| 402 |
+
"entropy_step_1": 0.5319,
|
| 403 |
+
"entropy_step_2": 0.5297,
|
| 404 |
+
"entropy_step_3": 0.5233,
|
| 405 |
+
"epoch": 0.06755235307363207,
|
| 406 |
+
"grad_norm": 14.925419807434082,
|
| 407 |
+
"learning_rate": 4.908735332464146e-05,
|
| 408 |
+
"loss": 0.22840323448181152,
|
| 409 |
+
"loss_step_1": 0.2335,
|
| 410 |
+
"loss_step_2": 0.233,
|
| 411 |
+
"loss_step_3": 0.226,
|
| 412 |
+
"step": 600
|
| 413 |
+
},
|
| 414 |
+
{
|
| 415 |
+
"entropy_step_1": 0.522,
|
| 416 |
+
"entropy_step_2": 0.5204,
|
| 417 |
+
"entropy_step_3": 0.5244,
|
| 418 |
+
"epoch": 0.06980409817608647,
|
| 419 |
+
"grad_norm": 3.6739323139190674,
|
| 420 |
+
"learning_rate": 4.8968827782387106e-05,
|
| 421 |
+
"loss": 0.22206854820251465,
|
| 422 |
+
"loss_step_1": 0.2259,
|
| 423 |
+
"loss_step_2": 0.2259,
|
| 424 |
+
"loss_step_3": 0.2294,
|
| 425 |
+
"step": 620
|
| 426 |
+
},
|
| 427 |
+
{
|
| 428 |
+
"entropy_step_1": 0.5309,
|
| 429 |
+
"entropy_step_2": 0.5362,
|
| 430 |
+
"entropy_step_3": 0.5306,
|
| 431 |
+
"epoch": 0.07205584327854087,
|
| 432 |
+
"grad_norm": 21.777225494384766,
|
| 433 |
+
"learning_rate": 4.885030224013275e-05,
|
| 434 |
+
"loss": 0.2330942392349243,
|
| 435 |
+
"loss_step_1": 0.2338,
|
| 436 |
+
"loss_step_2": 0.2335,
|
| 437 |
+
"loss_step_3": 0.2299,
|
| 438 |
+
"step": 640
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"entropy_step_1": 0.4562,
|
| 442 |
+
"entropy_step_2": 0.4599,
|
| 443 |
+
"entropy_step_3": 0.4735,
|
| 444 |
+
"epoch": 0.07430758838099527,
|
| 445 |
+
"grad_norm": 120.43797302246094,
|
| 446 |
+
"learning_rate": 4.8731776697878395e-05,
|
| 447 |
+
"loss": 0.2406167984008789,
|
| 448 |
+
"loss_step_1": 0.2349,
|
| 449 |
+
"loss_step_2": 0.2387,
|
| 450 |
+
"loss_step_3": 0.2598,
|
| 451 |
+
"step": 660
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"entropy_step_1": 0.4436,
|
| 455 |
+
"entropy_step_2": 0.465,
|
| 456 |
+
"entropy_step_3": 0.4566,
|
| 457 |
+
"epoch": 0.07655933348344968,
|
| 458 |
+
"grad_norm": 36.90608215332031,
|
| 459 |
+
"learning_rate": 4.861325115562404e-05,
|
| 460 |
+
"loss": 0.19849456548690797,
|
| 461 |
+
"loss_step_1": 0.1943,
|
| 462 |
+
"loss_step_2": 0.1956,
|
| 463 |
+
"loss_step_3": 0.19,
|
| 464 |
+
"step": 680
|
| 465 |
+
},
|
| 466 |
+
{
|
| 467 |
+
"entropy_step_1": 0.4146,
|
| 468 |
+
"entropy_step_2": 0.4284,
|
| 469 |
+
"entropy_step_3": 0.4569,
|
| 470 |
+
"epoch": 0.07881107858590408,
|
| 471 |
+
"grad_norm": 20.899234771728516,
|
| 472 |
+
"learning_rate": 4.849472561336968e-05,
|
| 473 |
+
"loss": 0.17954031229019166,
|
| 474 |
+
"loss_step_1": 0.1814,
|
| 475 |
+
"loss_step_2": 0.1826,
|
| 476 |
+
"loss_step_3": 0.1989,
|
| 477 |
+
"step": 700
|
| 478 |
+
},
|
| 479 |
+
{
|
| 480 |
+
"entropy_step_1": 0.3553,
|
| 481 |
+
"entropy_step_2": 0.3702,
|
| 482 |
+
"entropy_step_3": 0.3773,
|
| 483 |
+
"epoch": 0.08106282368835847,
|
| 484 |
+
"grad_norm": 23.099576950073242,
|
| 485 |
+
"learning_rate": 4.837620007111533e-05,
|
| 486 |
+
"loss": 0.14584234952926636,
|
| 487 |
+
"loss_step_1": 0.1415,
|
| 488 |
+
"loss_step_2": 0.1424,
|
| 489 |
+
"loss_step_3": 0.1487,
|
| 490 |
+
"step": 720
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"entropy_step_1": 0.3945,
|
| 494 |
+
"entropy_step_2": 0.3976,
|
| 495 |
+
"entropy_step_3": 0.393,
|
| 496 |
+
"epoch": 0.08331456879081288,
|
| 497 |
+
"grad_norm": 35.8271484375,
|
| 498 |
+
"learning_rate": 4.825767452886097e-05,
|
| 499 |
+
"loss": 0.19350186586380005,
|
| 500 |
+
"loss_step_1": 0.1948,
|
| 501 |
+
"loss_step_2": 0.1955,
|
| 502 |
+
"loss_step_3": 0.155,
|
| 503 |
+
"step": 740
|
| 504 |
+
},
|
| 505 |
+
{
|
| 506 |
+
"entropy_step_1": 0.3417,
|
| 507 |
+
"entropy_step_2": 0.3498,
|
| 508 |
+
"entropy_step_3": 0.3445,
|
| 509 |
+
"epoch": 0.08556631389326728,
|
| 510 |
+
"grad_norm": 25.94721031188965,
|
| 511 |
+
"learning_rate": 4.8139148986606615e-05,
|
| 512 |
+
"loss": 0.15360891819000244,
|
| 513 |
+
"loss_step_1": 0.153,
|
| 514 |
+
"loss_step_2": 0.1513,
|
| 515 |
+
"loss_step_3": 0.143,
|
| 516 |
+
"step": 760
|
| 517 |
+
},
|
| 518 |
+
{
|
| 519 |
+
"entropy_step_1": 0.2974,
|
| 520 |
+
"entropy_step_2": 0.2995,
|
| 521 |
+
"entropy_step_3": 0.2892,
|
| 522 |
+
"epoch": 0.08781805899572169,
|
| 523 |
+
"grad_norm": 36.524986267089844,
|
| 524 |
+
"learning_rate": 4.802062344435226e-05,
|
| 525 |
+
"loss": 0.12694748640060424,
|
| 526 |
+
"loss_step_1": 0.1222,
|
| 527 |
+
"loss_step_2": 0.1223,
|
| 528 |
+
"loss_step_3": 0.1054,
|
| 529 |
+
"step": 780
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"entropy_step_1": 0.3502,
|
| 533 |
+
"entropy_step_2": 0.3493,
|
| 534 |
+
"entropy_step_3": 0.3637,
|
| 535 |
+
"epoch": 0.09006980409817608,
|
| 536 |
+
"grad_norm": 19.627296447753906,
|
| 537 |
+
"learning_rate": 4.7902097902097904e-05,
|
| 538 |
+
"loss": 0.14579046964645387,
|
| 539 |
+
"loss_step_1": 0.1417,
|
| 540 |
+
"loss_step_2": 0.1424,
|
| 541 |
+
"loss_step_3": 0.1332,
|
| 542 |
+
"step": 800
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"entropy_step_1": 0.2712,
|
| 546 |
+
"entropy_step_2": 0.2813,
|
| 547 |
+
"entropy_step_3": 0.2782,
|
| 548 |
+
"epoch": 0.09232154920063049,
|
| 549 |
+
"grad_norm": 10.341985702514648,
|
| 550 |
+
"learning_rate": 4.778357235984355e-05,
|
| 551 |
+
"loss": 0.11724411249160767,
|
| 552 |
+
"loss_step_1": 0.1098,
|
| 553 |
+
"loss_step_2": 0.1094,
|
| 554 |
+
"loss_step_3": 0.1039,
|
| 555 |
+
"step": 820
|
| 556 |
+
},
|
| 557 |
+
{
|
| 558 |
+
"entropy_step_1": 0.279,
|
| 559 |
+
"entropy_step_2": 0.284,
|
| 560 |
+
"entropy_step_3": 0.2586,
|
| 561 |
+
"epoch": 0.09457329430308489,
|
| 562 |
+
"grad_norm": 45.71856689453125,
|
| 563 |
+
"learning_rate": 4.766504681758919e-05,
|
| 564 |
+
"loss": 0.14866987466812134,
|
| 565 |
+
"loss_step_1": 0.1415,
|
| 566 |
+
"loss_step_2": 0.1408,
|
| 567 |
+
"loss_step_3": 0.131,
|
| 568 |
+
"step": 840
|
| 569 |
+
},
|
| 570 |
+
{
|
| 571 |
+
"entropy_step_1": 0.3152,
|
| 572 |
+
"entropy_step_2": 0.3161,
|
| 573 |
+
"entropy_step_3": 0.3284,
|
| 574 |
+
"epoch": 0.0968250394055393,
|
| 575 |
+
"grad_norm": 85.21240234375,
|
| 576 |
+
"learning_rate": 4.7546521275334836e-05,
|
| 577 |
+
"loss": 0.14316539764404296,
|
| 578 |
+
"loss_step_1": 0.1553,
|
| 579 |
+
"loss_step_2": 0.1554,
|
| 580 |
+
"loss_step_3": 0.161,
|
| 581 |
+
"step": 860
|
| 582 |
+
},
|
| 583 |
+
{
|
| 584 |
+
"entropy_step_1": 0.3032,
|
| 585 |
+
"entropy_step_2": 0.3137,
|
| 586 |
+
"entropy_step_3": 0.2967,
|
| 587 |
+
"epoch": 0.09907678450799369,
|
| 588 |
+
"grad_norm": 45.822105407714844,
|
| 589 |
+
"learning_rate": 4.742799573308048e-05,
|
| 590 |
+
"loss": 0.12941205501556396,
|
| 591 |
+
"loss_step_1": 0.1371,
|
| 592 |
+
"loss_step_2": 0.1368,
|
| 593 |
+
"loss_step_3": 0.133,
|
| 594 |
+
"step": 880
|
| 595 |
+
},
|
| 596 |
+
{
|
| 597 |
+
"entropy_step_1": 0.2648,
|
| 598 |
+
"entropy_step_2": 0.2713,
|
| 599 |
+
"entropy_step_3": 0.2632,
|
| 600 |
+
"epoch": 0.1013285296104481,
|
| 601 |
+
"grad_norm": 52.29207229614258,
|
| 602 |
+
"learning_rate": 4.7309470190826124e-05,
|
| 603 |
+
"loss": 0.12652232646942138,
|
| 604 |
+
"loss_step_1": 0.125,
|
| 605 |
+
"loss_step_2": 0.1247,
|
| 606 |
+
"loss_step_3": 0.1238,
|
| 607 |
+
"step": 900
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"entropy_step_1": 0.2569,
|
| 611 |
+
"entropy_step_2": 0.2674,
|
| 612 |
+
"entropy_step_3": 0.2845,
|
| 613 |
+
"epoch": 0.1035802747129025,
|
| 614 |
+
"grad_norm": 42.026790618896484,
|
| 615 |
+
"learning_rate": 4.7190944648571775e-05,
|
| 616 |
+
"loss": 0.10588388442993164,
|
| 617 |
+
"loss_step_1": 0.1127,
|
| 618 |
+
"loss_step_2": 0.1114,
|
| 619 |
+
"loss_step_3": 0.1156,
|
| 620 |
+
"step": 920
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"entropy_step_1": 0.2346,
|
| 624 |
+
"entropy_step_2": 0.2488,
|
| 625 |
+
"entropy_step_3": 0.2508,
|
| 626 |
+
"epoch": 0.1058320198153569,
|
| 627 |
+
"grad_norm": 5.713146686553955,
|
| 628 |
+
"learning_rate": 4.707241910631741e-05,
|
| 629 |
+
"loss": 0.10807274580001831,
|
| 630 |
+
"loss_step_1": 0.1075,
|
| 631 |
+
"loss_step_2": 0.1075,
|
| 632 |
+
"loss_step_3": 0.1072,
|
| 633 |
+
"step": 940
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"entropy_step_1": 0.2735,
|
| 637 |
+
"entropy_step_2": 0.2775,
|
| 638 |
+
"entropy_step_3": 0.2909,
|
| 639 |
+
"epoch": 0.1080837649178113,
|
| 640 |
+
"grad_norm": 19.495990753173828,
|
| 641 |
+
"learning_rate": 4.695389356406306e-05,
|
| 642 |
+
"loss": 0.11960618495941162,
|
| 643 |
+
"loss_step_1": 0.1136,
|
| 644 |
+
"loss_step_2": 0.114,
|
| 645 |
+
"loss_step_3": 0.1204,
|
| 646 |
+
"step": 960
|
| 647 |
+
},
|
| 648 |
+
{
|
| 649 |
+
"entropy_step_1": 0.2581,
|
| 650 |
+
"entropy_step_2": 0.2582,
|
| 651 |
+
"entropy_step_3": 0.2768,
|
| 652 |
+
"epoch": 0.1103355100202657,
|
| 653 |
+
"grad_norm": 26.731643676757812,
|
| 654 |
+
"learning_rate": 4.68353680218087e-05,
|
| 655 |
+
"loss": 0.10982362031936646,
|
| 656 |
+
"loss_step_1": 0.111,
|
| 657 |
+
"loss_step_2": 0.1104,
|
| 658 |
+
"loss_step_3": 0.1287,
|
| 659 |
+
"step": 980
|
| 660 |
+
},
|
| 661 |
+
{
|
| 662 |
+
"entropy_step_1": 0.2307,
|
| 663 |
+
"entropy_step_2": 0.2353,
|
| 664 |
+
"entropy_step_3": 0.2437,
|
| 665 |
+
"epoch": 0.11258725512272011,
|
| 666 |
+
"grad_norm": 38.24470901489258,
|
| 667 |
+
"learning_rate": 4.6716842479554345e-05,
|
| 668 |
+
"loss": 0.10078544616699218,
|
| 669 |
+
"loss_step_1": 0.0943,
|
| 670 |
+
"loss_step_2": 0.0939,
|
| 671 |
+
"loss_step_3": 0.0934,
|
| 672 |
+
"step": 1000
|
| 673 |
+
},
|
| 674 |
+
{
|
| 675 |
+
"epoch": 0.11258725512272011,
|
| 676 |
+
"eval_accuracy": 0.9821428571428571,
|
| 677 |
+
"eval_f1": 0.9829213537391978,
|
| 678 |
+
"eval_loss": 0.049600545316934586,
|
| 679 |
+
"eval_precision": 0.9841862117981522,
|
| 680 |
+
"eval_recall": 0.9821428571428571,
|
| 681 |
+
"eval_runtime": 9.7838,
|
| 682 |
+
"eval_samples_per_second": 10.221,
|
| 683 |
+
"eval_steps_per_second": 1.329,
|
| 684 |
+
"step": 1000
|
| 685 |
+
},
|
| 686 |
+
{
|
| 687 |
+
"entropy_step_1": 0.2705,
|
| 688 |
+
"entropy_step_2": 0.2724,
|
| 689 |
+
"entropy_step_3": 0.2658,
|
| 690 |
+
"epoch": 0.11483900022517451,
|
| 691 |
+
"grad_norm": 30.772653579711914,
|
| 692 |
+
"learning_rate": 4.659831693729999e-05,
|
| 693 |
+
"loss": 0.13021235466003417,
|
| 694 |
+
"loss_step_1": 0.1523,
|
| 695 |
+
"loss_step_2": 0.1516,
|
| 696 |
+
"loss_step_3": 0.1032,
|
| 697 |
+
"step": 1020
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"entropy_step_1": 0.2125,
|
| 701 |
+
"entropy_step_2": 0.2221,
|
| 702 |
+
"entropy_step_3": 0.2112,
|
| 703 |
+
"epoch": 0.1170907453276289,
|
| 704 |
+
"grad_norm": 36.184364318847656,
|
| 705 |
+
"learning_rate": 4.647979139504563e-05,
|
| 706 |
+
"loss": 0.11268470287322999,
|
| 707 |
+
"loss_step_1": 0.1217,
|
| 708 |
+
"loss_step_2": 0.119,
|
| 709 |
+
"loss_step_3": 0.1171,
|
| 710 |
+
"step": 1040
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"entropy_step_1": 0.2495,
|
| 714 |
+
"entropy_step_2": 0.2624,
|
| 715 |
+
"entropy_step_3": 0.2576,
|
| 716 |
+
"epoch": 0.11934249043008331,
|
| 717 |
+
"grad_norm": 12.86143970489502,
|
| 718 |
+
"learning_rate": 4.636126585279128e-05,
|
| 719 |
+
"loss": 0.09750348925590516,
|
| 720 |
+
"loss_step_1": 0.0982,
|
| 721 |
+
"loss_step_2": 0.0976,
|
| 722 |
+
"loss_step_3": 0.0901,
|
| 723 |
+
"step": 1060
|
| 724 |
+
},
|
| 725 |
+
{
|
| 726 |
+
"entropy_step_1": 0.2096,
|
| 727 |
+
"entropy_step_2": 0.2292,
|
| 728 |
+
"entropy_step_3": 0.2352,
|
| 729 |
+
"epoch": 0.12159423553253772,
|
| 730 |
+
"grad_norm": 11.619362831115723,
|
| 731 |
+
"learning_rate": 4.624274031053692e-05,
|
| 732 |
+
"loss": 0.09676148295402527,
|
| 733 |
+
"loss_step_1": 0.0934,
|
| 734 |
+
"loss_step_2": 0.0934,
|
| 735 |
+
"loss_step_3": 0.1014,
|
| 736 |
+
"step": 1080
|
| 737 |
+
},
|
| 738 |
+
{
|
| 739 |
+
"entropy_step_1": 0.2377,
|
| 740 |
+
"entropy_step_2": 0.2554,
|
| 741 |
+
"entropy_step_3": 0.2914,
|
| 742 |
+
"epoch": 0.12384598063499212,
|
| 743 |
+
"grad_norm": 15.9982271194458,
|
| 744 |
+
"learning_rate": 4.612421476828257e-05,
|
| 745 |
+
"loss": 0.11465377807617187,
|
| 746 |
+
"loss_step_1": 0.1209,
|
| 747 |
+
"loss_step_2": 0.1187,
|
| 748 |
+
"loss_step_3": 0.1461,
|
| 749 |
+
"step": 1100
|
| 750 |
+
},
|
| 751 |
+
{
|
| 752 |
+
"entropy_step_1": 0.2254,
|
| 753 |
+
"entropy_step_2": 0.2429,
|
| 754 |
+
"entropy_step_3": 0.2172,
|
| 755 |
+
"epoch": 0.12609772573744651,
|
| 756 |
+
"grad_norm": 13.497550010681152,
|
| 757 |
+
"learning_rate": 4.600568922602821e-05,
|
| 758 |
+
"loss": 0.09773769974708557,
|
| 759 |
+
"loss_step_1": 0.1001,
|
| 760 |
+
"loss_step_2": 0.0993,
|
| 761 |
+
"loss_step_3": 0.0953,
|
| 762 |
+
"step": 1120
|
| 763 |
+
},
|
| 764 |
+
{
|
| 765 |
+
"entropy_step_1": 0.1969,
|
| 766 |
+
"entropy_step_2": 0.2068,
|
| 767 |
+
"entropy_step_3": 0.1969,
|
| 768 |
+
"epoch": 0.12834947083990092,
|
| 769 |
+
"grad_norm": 15.986771583557129,
|
| 770 |
+
"learning_rate": 4.5887163683773854e-05,
|
| 771 |
+
"loss": 0.11234849691390991,
|
| 772 |
+
"loss_step_1": 0.0848,
|
| 773 |
+
"loss_step_2": 0.0833,
|
| 774 |
+
"loss_step_3": 0.0883,
|
| 775 |
+
"step": 1140
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"entropy_step_1": 0.1976,
|
| 779 |
+
"entropy_step_2": 0.1972,
|
| 780 |
+
"entropy_step_3": 0.1826,
|
| 781 |
+
"epoch": 0.13060121594235533,
|
| 782 |
+
"grad_norm": 54.908870697021484,
|
| 783 |
+
"learning_rate": 4.57686381415195e-05,
|
| 784 |
+
"loss": 0.09917433857917786,
|
| 785 |
+
"loss_step_1": 0.0924,
|
| 786 |
+
"loss_step_2": 0.0914,
|
| 787 |
+
"loss_step_3": 0.0656,
|
| 788 |
+
"step": 1160
|
| 789 |
+
},
|
| 790 |
+
{
|
| 791 |
+
"entropy_step_1": 0.226,
|
| 792 |
+
"entropy_step_2": 0.2217,
|
| 793 |
+
"entropy_step_3": 0.2363,
|
| 794 |
+
"epoch": 0.13285296104480973,
|
| 795 |
+
"grad_norm": 120.96832275390625,
|
| 796 |
+
"learning_rate": 4.565011259926514e-05,
|
| 797 |
+
"loss": 0.09798040986061096,
|
| 798 |
+
"loss_step_1": 0.0855,
|
| 799 |
+
"loss_step_2": 0.0855,
|
| 800 |
+
"loss_step_3": 0.076,
|
| 801 |
+
"step": 1180
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"entropy_step_1": 0.1968,
|
| 805 |
+
"entropy_step_2": 0.1982,
|
| 806 |
+
"entropy_step_3": 0.2086,
|
| 807 |
+
"epoch": 0.13510470614726414,
|
| 808 |
+
"grad_norm": 10.197748184204102,
|
| 809 |
+
"learning_rate": 4.5531587057010786e-05,
|
| 810 |
+
"loss": 0.09928179383277894,
|
| 811 |
+
"loss_step_1": 0.0902,
|
| 812 |
+
"loss_step_2": 0.0905,
|
| 813 |
+
"loss_step_3": 0.0942,
|
| 814 |
+
"step": 1200
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"entropy_step_1": 0.2044,
|
| 818 |
+
"entropy_step_2": 0.2121,
|
| 819 |
+
"entropy_step_3": 0.2027,
|
| 820 |
+
"epoch": 0.13735645124971854,
|
| 821 |
+
"grad_norm": 15.765093803405762,
|
| 822 |
+
"learning_rate": 4.541306151475643e-05,
|
| 823 |
+
"loss": 0.09436439275741577,
|
| 824 |
+
"loss_step_1": 0.097,
|
| 825 |
+
"loss_step_2": 0.0955,
|
| 826 |
+
"loss_step_3": 0.0756,
|
| 827 |
+
"step": 1220
|
| 828 |
+
},
|
| 829 |
+
{
|
| 830 |
+
"entropy_step_1": 0.2002,
|
| 831 |
+
"entropy_step_2": 0.2076,
|
| 832 |
+
"entropy_step_3": 0.1945,
|
| 833 |
+
"epoch": 0.13960819635217295,
|
| 834 |
+
"grad_norm": 21.087186813354492,
|
| 835 |
+
"learning_rate": 4.5294535972502075e-05,
|
| 836 |
+
"loss": 0.08575084209442138,
|
| 837 |
+
"loss_step_1": 0.0889,
|
| 838 |
+
"loss_step_2": 0.0885,
|
| 839 |
+
"loss_step_3": 0.0962,
|
| 840 |
+
"step": 1240
|
| 841 |
+
},
|
| 842 |
+
{
|
| 843 |
+
"entropy_step_1": 0.2292,
|
| 844 |
+
"entropy_step_2": 0.2271,
|
| 845 |
+
"entropy_step_3": 0.2221,
|
| 846 |
+
"epoch": 0.14185994145462733,
|
| 847 |
+
"grad_norm": 20.05746841430664,
|
| 848 |
+
"learning_rate": 4.5176010430247726e-05,
|
| 849 |
+
"loss": 0.09527861475944518,
|
| 850 |
+
"loss_step_1": 0.0926,
|
| 851 |
+
"loss_step_2": 0.0928,
|
| 852 |
+
"loss_step_3": 0.0733,
|
| 853 |
+
"step": 1260
|
| 854 |
+
},
|
| 855 |
+
{
|
| 856 |
+
"entropy_step_1": 0.2401,
|
| 857 |
+
"entropy_step_2": 0.2335,
|
| 858 |
+
"entropy_step_3": 0.25,
|
| 859 |
+
"epoch": 0.14411168655708173,
|
| 860 |
+
"grad_norm": 50.57461166381836,
|
| 861 |
+
"learning_rate": 4.505748488799336e-05,
|
| 862 |
+
"loss": 0.09648898243904114,
|
| 863 |
+
"loss_step_1": 0.0988,
|
| 864 |
+
"loss_step_2": 0.0986,
|
| 865 |
+
"loss_step_3": 0.0976,
|
| 866 |
+
"step": 1280
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"entropy_step_1": 0.1809,
|
| 870 |
+
"entropy_step_2": 0.1837,
|
| 871 |
+
"entropy_step_3": 0.185,
|
| 872 |
+
"epoch": 0.14636343165953614,
|
| 873 |
+
"grad_norm": 22.53580093383789,
|
| 874 |
+
"learning_rate": 4.493895934573901e-05,
|
| 875 |
+
"loss": 0.07595239281654358,
|
| 876 |
+
"loss_step_1": 0.0738,
|
| 877 |
+
"loss_step_2": 0.0736,
|
| 878 |
+
"loss_step_3": 0.0717,
|
| 879 |
+
"step": 1300
|
| 880 |
+
},
|
| 881 |
+
{
|
| 882 |
+
"entropy_step_1": 0.1965,
|
| 883 |
+
"entropy_step_2": 0.2035,
|
| 884 |
+
"entropy_step_3": 0.2156,
|
| 885 |
+
"epoch": 0.14861517676199054,
|
| 886 |
+
"grad_norm": 426.2031555175781,
|
| 887 |
+
"learning_rate": 4.482043380348465e-05,
|
| 888 |
+
"loss": 0.08849629759788513,
|
| 889 |
+
"loss_step_1": 0.0931,
|
| 890 |
+
"loss_step_2": 0.0919,
|
| 891 |
+
"loss_step_3": 0.0906,
|
| 892 |
+
"step": 1320
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"entropy_step_1": 0.2199,
|
| 896 |
+
"entropy_step_2": 0.2205,
|
| 897 |
+
"entropy_step_3": 0.2208,
|
| 898 |
+
"epoch": 0.15086692186444495,
|
| 899 |
+
"grad_norm": 26.94179344177246,
|
| 900 |
+
"learning_rate": 4.4701908261230295e-05,
|
| 901 |
+
"loss": 0.1093055009841919,
|
| 902 |
+
"loss_step_1": 0.1041,
|
| 903 |
+
"loss_step_2": 0.1037,
|
| 904 |
+
"loss_step_3": 0.1117,
|
| 905 |
+
"step": 1340
|
| 906 |
+
},
|
| 907 |
+
{
|
| 908 |
+
"entropy_step_1": 0.2253,
|
| 909 |
+
"entropy_step_2": 0.2234,
|
| 910 |
+
"entropy_step_3": 0.2268,
|
| 911 |
+
"epoch": 0.15311866696689935,
|
| 912 |
+
"grad_norm": 53.97324752807617,
|
| 913 |
+
"learning_rate": 4.458338271897594e-05,
|
| 914 |
+
"loss": 0.1041757583618164,
|
| 915 |
+
"loss_step_1": 0.097,
|
| 916 |
+
"loss_step_2": 0.0963,
|
| 917 |
+
"loss_step_3": 0.0807,
|
| 918 |
+
"step": 1360
|
| 919 |
+
},
|
| 920 |
+
{
|
| 921 |
+
"entropy_step_1": 0.2075,
|
| 922 |
+
"entropy_step_2": 0.2106,
|
| 923 |
+
"entropy_step_3": 0.2047,
|
| 924 |
+
"epoch": 0.15537041206935376,
|
| 925 |
+
"grad_norm": 26.236223220825195,
|
| 926 |
+
"learning_rate": 4.4464857176721584e-05,
|
| 927 |
+
"loss": 0.1046905279159546,
|
| 928 |
+
"loss_step_1": 0.1173,
|
| 929 |
+
"loss_step_2": 0.1191,
|
| 930 |
+
"loss_step_3": 0.1436,
|
| 931 |
+
"step": 1380
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"entropy_step_1": 0.1848,
|
| 935 |
+
"entropy_step_2": 0.1924,
|
| 936 |
+
"entropy_step_3": 0.1819,
|
| 937 |
+
"epoch": 0.15762215717180816,
|
| 938 |
+
"grad_norm": 54.22330093383789,
|
| 939 |
+
"learning_rate": 4.434633163446723e-05,
|
| 940 |
+
"loss": 0.10279273986816406,
|
| 941 |
+
"loss_step_1": 0.1172,
|
| 942 |
+
"loss_step_2": 0.1151,
|
| 943 |
+
"loss_step_3": 0.0833,
|
| 944 |
+
"step": 1400
|
| 945 |
+
},
|
| 946 |
+
{
|
| 947 |
+
"entropy_step_1": 0.2149,
|
| 948 |
+
"entropy_step_2": 0.2245,
|
| 949 |
+
"entropy_step_3": 0.2241,
|
| 950 |
+
"epoch": 0.15987390227426254,
|
| 951 |
+
"grad_norm": 21.585975646972656,
|
| 952 |
+
"learning_rate": 4.422780609221288e-05,
|
| 953 |
+
"loss": 0.09293524026870728,
|
| 954 |
+
"loss_step_1": 0.0896,
|
| 955 |
+
"loss_step_2": 0.0903,
|
| 956 |
+
"loss_step_3": 0.0849,
|
| 957 |
+
"step": 1420
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"entropy_step_1": 0.1844,
|
| 961 |
+
"entropy_step_2": 0.1885,
|
| 962 |
+
"entropy_step_3": 0.1815,
|
| 963 |
+
"epoch": 0.16212564737671695,
|
| 964 |
+
"grad_norm": 13.520930290222168,
|
| 965 |
+
"learning_rate": 4.410928054995852e-05,
|
| 966 |
+
"loss": 0.10251129865646362,
|
| 967 |
+
"loss_step_1": 0.0852,
|
| 968 |
+
"loss_step_2": 0.0852,
|
| 969 |
+
"loss_step_3": 0.0749,
|
| 970 |
+
"step": 1440
|
| 971 |
+
},
|
| 972 |
+
{
|
| 973 |
+
"entropy_step_1": 0.1905,
|
| 974 |
+
"entropy_step_2": 0.1905,
|
| 975 |
+
"entropy_step_3": 0.1807,
|
| 976 |
+
"epoch": 0.16437739247917135,
|
| 977 |
+
"grad_norm": 8.29106616973877,
|
| 978 |
+
"learning_rate": 4.399075500770416e-05,
|
| 979 |
+
"loss": 0.08954123258590699,
|
| 980 |
+
"loss_step_1": 0.0831,
|
| 981 |
+
"loss_step_2": 0.0828,
|
| 982 |
+
"loss_step_3": 0.074,
|
| 983 |
+
"step": 1460
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"entropy_step_1": 0.1977,
|
| 987 |
+
"entropy_step_2": 0.1943,
|
| 988 |
+
"entropy_step_3": 0.1847,
|
| 989 |
+
"epoch": 0.16662913758162576,
|
| 990 |
+
"grad_norm": 32.59114456176758,
|
| 991 |
+
"learning_rate": 4.3872229465449804e-05,
|
| 992 |
+
"loss": 0.08137682676315308,
|
| 993 |
+
"loss_step_1": 0.0807,
|
| 994 |
+
"loss_step_2": 0.0811,
|
| 995 |
+
"loss_step_3": 0.0765,
|
| 996 |
+
"step": 1480
|
| 997 |
+
},
|
| 998 |
+
{
|
| 999 |
+
"entropy_step_1": 0.1979,
|
| 1000 |
+
"entropy_step_2": 0.1906,
|
| 1001 |
+
"entropy_step_3": 0.196,
|
| 1002 |
+
"epoch": 0.16888088268408016,
|
| 1003 |
+
"grad_norm": 28.63804817199707,
|
| 1004 |
+
"learning_rate": 4.375370392319545e-05,
|
| 1005 |
+
"loss": 0.08560625910758972,
|
| 1006 |
+
"loss_step_1": 0.0875,
|
| 1007 |
+
"loss_step_2": 0.0891,
|
| 1008 |
+
"loss_step_3": 0.0898,
|
| 1009 |
+
"step": 1500
|
| 1010 |
+
},
|
| 1011 |
+
{
|
| 1012 |
+
"epoch": 0.16888088268408016,
|
| 1013 |
+
"eval_accuracy": 0.9832142857142857,
|
| 1014 |
+
"eval_f1": 0.9842921404664746,
|
| 1015 |
+
"eval_loss": 0.03931603580713272,
|
| 1016 |
+
"eval_precision": 0.9864771746205165,
|
| 1017 |
+
"eval_recall": 0.9832142857142857,
|
| 1018 |
+
"eval_runtime": 9.5173,
|
| 1019 |
+
"eval_samples_per_second": 10.507,
|
| 1020 |
+
"eval_steps_per_second": 1.366,
|
| 1021 |
+
"step": 1500
|
| 1022 |
+
},
|
| 1023 |
+
{
|
| 1024 |
+
"entropy_step_1": 0.2113,
|
| 1025 |
+
"entropy_step_2": 0.2108,
|
| 1026 |
+
"entropy_step_3": 0.2074,
|
| 1027 |
+
"epoch": 0.17113262778653457,
|
| 1028 |
+
"grad_norm": 5.3955769538879395,
|
| 1029 |
+
"learning_rate": 4.363517838094109e-05,
|
| 1030 |
+
"loss": 0.08812484741210938,
|
| 1031 |
+
"loss_step_1": 0.08,
|
| 1032 |
+
"loss_step_2": 0.0796,
|
| 1033 |
+
"loss_step_3": 0.0844,
|
| 1034 |
+
"step": 1520
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"entropy_step_1": 0.1906,
|
| 1038 |
+
"entropy_step_2": 0.1932,
|
| 1039 |
+
"entropy_step_3": 0.1852,
|
| 1040 |
+
"epoch": 0.17338437288898897,
|
| 1041 |
+
"grad_norm": 22.33837127685547,
|
| 1042 |
+
"learning_rate": 4.351665283868674e-05,
|
| 1043 |
+
"loss": 0.11392149925231934,
|
| 1044 |
+
"loss_step_1": 0.1163,
|
| 1045 |
+
"loss_step_2": 0.1169,
|
| 1046 |
+
"loss_step_3": 0.1491,
|
| 1047 |
+
"step": 1540
|
| 1048 |
+
},
|
| 1049 |
+
{
|
| 1050 |
+
"entropy_step_1": 0.1491,
|
| 1051 |
+
"entropy_step_2": 0.1536,
|
| 1052 |
+
"entropy_step_3": 0.1487,
|
| 1053 |
+
"epoch": 0.17563611799144338,
|
| 1054 |
+
"grad_norm": 93.93433380126953,
|
| 1055 |
+
"learning_rate": 4.339812729643238e-05,
|
| 1056 |
+
"loss": 0.09162638187408448,
|
| 1057 |
+
"loss_step_1": 0.0948,
|
| 1058 |
+
"loss_step_2": 0.0956,
|
| 1059 |
+
"loss_step_3": 0.0818,
|
| 1060 |
+
"step": 1560
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"entropy_step_1": 0.1939,
|
| 1064 |
+
"entropy_step_2": 0.2001,
|
| 1065 |
+
"entropy_step_3": 0.1961,
|
| 1066 |
+
"epoch": 0.17788786309389776,
|
| 1067 |
+
"grad_norm": 4.740994453430176,
|
| 1068 |
+
"learning_rate": 4.3279601754178025e-05,
|
| 1069 |
+
"loss": 0.08496600389480591,
|
| 1070 |
+
"loss_step_1": 0.0817,
|
| 1071 |
+
"loss_step_2": 0.082,
|
| 1072 |
+
"loss_step_3": 0.0878,
|
| 1073 |
+
"step": 1580
|
| 1074 |
+
},
|
| 1075 |
+
{
|
| 1076 |
+
"entropy_step_1": 0.1944,
|
| 1077 |
+
"entropy_step_2": 0.1983,
|
| 1078 |
+
"entropy_step_3": 0.2016,
|
| 1079 |
+
"epoch": 0.18013960819635216,
|
| 1080 |
+
"grad_norm": 18.27373504638672,
|
| 1081 |
+
"learning_rate": 4.3161076211923676e-05,
|
| 1082 |
+
"loss": 0.08413347005844116,
|
| 1083 |
+
"loss_step_1": 0.0836,
|
| 1084 |
+
"loss_step_2": 0.0835,
|
| 1085 |
+
"loss_step_3": 0.0904,
|
| 1086 |
+
"step": 1600
|
| 1087 |
+
},
|
| 1088 |
+
{
|
| 1089 |
+
"entropy_step_1": 0.1708,
|
| 1090 |
+
"entropy_step_2": 0.1757,
|
| 1091 |
+
"entropy_step_3": 0.1726,
|
| 1092 |
+
"epoch": 0.18239135329880657,
|
| 1093 |
+
"grad_norm": 27.723474502563477,
|
| 1094 |
+
"learning_rate": 4.304255066966932e-05,
|
| 1095 |
+
"loss": 0.09160991311073304,
|
| 1096 |
+
"loss_step_1": 0.0823,
|
| 1097 |
+
"loss_step_2": 0.0811,
|
| 1098 |
+
"loss_step_3": 0.081,
|
| 1099 |
+
"step": 1620
|
| 1100 |
+
},
|
| 1101 |
+
{
|
| 1102 |
+
"entropy_step_1": 0.209,
|
| 1103 |
+
"entropy_step_2": 0.2139,
|
| 1104 |
+
"entropy_step_3": 0.2214,
|
| 1105 |
+
"epoch": 0.18464309840126097,
|
| 1106 |
+
"grad_norm": 10.07846736907959,
|
| 1107 |
+
"learning_rate": 4.292402512741496e-05,
|
| 1108 |
+
"loss": 0.09279954433441162,
|
| 1109 |
+
"loss_step_1": 0.1007,
|
| 1110 |
+
"loss_step_2": 0.1001,
|
| 1111 |
+
"loss_step_3": 0.0757,
|
| 1112 |
+
"step": 1640
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"entropy_step_1": 0.2006,
|
| 1116 |
+
"entropy_step_2": 0.2091,
|
| 1117 |
+
"entropy_step_3": 0.2053,
|
| 1118 |
+
"epoch": 0.18689484350371538,
|
| 1119 |
+
"grad_norm": 14.717902183532715,
|
| 1120 |
+
"learning_rate": 4.28054995851606e-05,
|
| 1121 |
+
"loss": 0.08274680376052856,
|
| 1122 |
+
"loss_step_1": 0.0832,
|
| 1123 |
+
"loss_step_2": 0.0824,
|
| 1124 |
+
"loss_step_3": 0.0746,
|
| 1125 |
+
"step": 1660
|
| 1126 |
+
},
|
| 1127 |
+
{
|
| 1128 |
+
"entropy_step_1": 0.1724,
|
| 1129 |
+
"entropy_step_2": 0.1763,
|
| 1130 |
+
"entropy_step_3": 0.1644,
|
| 1131 |
+
"epoch": 0.18914658860616979,
|
| 1132 |
+
"grad_norm": 50.370201110839844,
|
| 1133 |
+
"learning_rate": 4.2686974042906246e-05,
|
| 1134 |
+
"loss": 0.08542762994766236,
|
| 1135 |
+
"loss_step_1": 0.0839,
|
| 1136 |
+
"loss_step_2": 0.0834,
|
| 1137 |
+
"loss_step_3": 0.0696,
|
| 1138 |
+
"step": 1680
|
| 1139 |
+
},
|
| 1140 |
+
{
|
| 1141 |
+
"entropy_step_1": 0.2037,
|
| 1142 |
+
"entropy_step_2": 0.204,
|
| 1143 |
+
"entropy_step_3": 0.2156,
|
| 1144 |
+
"epoch": 0.1913983337086242,
|
| 1145 |
+
"grad_norm": 18.906110763549805,
|
| 1146 |
+
"learning_rate": 4.256844850065189e-05,
|
| 1147 |
+
"loss": 0.08353109955787659,
|
| 1148 |
+
"loss_step_1": 0.0916,
|
| 1149 |
+
"loss_step_2": 0.0915,
|
| 1150 |
+
"loss_step_3": 0.1006,
|
| 1151 |
+
"step": 1700
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"entropy_step_1": 0.1579,
|
| 1155 |
+
"entropy_step_2": 0.1602,
|
| 1156 |
+
"entropy_step_3": 0.1639,
|
| 1157 |
+
"epoch": 0.1936500788110786,
|
| 1158 |
+
"grad_norm": 14.388580322265625,
|
| 1159 |
+
"learning_rate": 4.2449922958397534e-05,
|
| 1160 |
+
"loss": 0.07970066666603089,
|
| 1161 |
+
"loss_step_1": 0.0791,
|
| 1162 |
+
"loss_step_2": 0.079,
|
| 1163 |
+
"loss_step_3": 0.0885,
|
| 1164 |
+
"step": 1720
|
| 1165 |
+
},
|
| 1166 |
+
{
|
| 1167 |
+
"entropy_step_1": 0.1957,
|
| 1168 |
+
"entropy_step_2": 0.1995,
|
| 1169 |
+
"entropy_step_3": 0.1828,
|
| 1170 |
+
"epoch": 0.19590182391353297,
|
| 1171 |
+
"grad_norm": 48.5572395324707,
|
| 1172 |
+
"learning_rate": 4.233139741614318e-05,
|
| 1173 |
+
"loss": 0.08778284192085266,
|
| 1174 |
+
"loss_step_1": 0.0989,
|
| 1175 |
+
"loss_step_2": 0.098,
|
| 1176 |
+
"loss_step_3": 0.0675,
|
| 1177 |
+
"step": 1740
|
| 1178 |
+
},
|
| 1179 |
+
{
|
| 1180 |
+
"entropy_step_1": 0.1851,
|
| 1181 |
+
"entropy_step_2": 0.1894,
|
| 1182 |
+
"entropy_step_3": 0.1887,
|
| 1183 |
+
"epoch": 0.19815356901598738,
|
| 1184 |
+
"grad_norm": 25.075510025024414,
|
| 1185 |
+
"learning_rate": 4.221287187388883e-05,
|
| 1186 |
+
"loss": 0.1105013370513916,
|
| 1187 |
+
"loss_step_1": 0.114,
|
| 1188 |
+
"loss_step_2": 0.1179,
|
| 1189 |
+
"loss_step_3": 0.0817,
|
| 1190 |
+
"step": 1760
|
| 1191 |
+
},
|
| 1192 |
+
{
|
| 1193 |
+
"entropy_step_1": 0.2045,
|
| 1194 |
+
"entropy_step_2": 0.2072,
|
| 1195 |
+
"entropy_step_3": 0.1969,
|
| 1196 |
+
"epoch": 0.20040531411844179,
|
| 1197 |
+
"grad_norm": 45.432674407958984,
|
| 1198 |
+
"learning_rate": 4.209434633163447e-05,
|
| 1199 |
+
"loss": 0.09110472202301026,
|
| 1200 |
+
"loss_step_1": 0.0891,
|
| 1201 |
+
"loss_step_2": 0.0896,
|
| 1202 |
+
"loss_step_3": 0.0891,
|
| 1203 |
+
"step": 1780
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"entropy_step_1": 0.1837,
|
| 1207 |
+
"entropy_step_2": 0.1864,
|
| 1208 |
+
"entropy_step_3": 0.1752,
|
| 1209 |
+
"epoch": 0.2026570592208962,
|
| 1210 |
+
"grad_norm": 36.06223678588867,
|
| 1211 |
+
"learning_rate": 4.197582078938012e-05,
|
| 1212 |
+
"loss": 0.09789063334465027,
|
| 1213 |
+
"loss_step_1": 0.0917,
|
| 1214 |
+
"loss_step_2": 0.0909,
|
| 1215 |
+
"loss_step_3": 0.0774,
|
| 1216 |
+
"step": 1800
|
| 1217 |
+
},
|
| 1218 |
+
{
|
| 1219 |
+
"entropy_step_1": 0.1678,
|
| 1220 |
+
"entropy_step_2": 0.1703,
|
| 1221 |
+
"entropy_step_3": 0.1818,
|
| 1222 |
+
"epoch": 0.2049088043233506,
|
| 1223 |
+
"grad_norm": 10.547739028930664,
|
| 1224 |
+
"learning_rate": 4.1857295247125755e-05,
|
| 1225 |
+
"loss": 0.08343779444694518,
|
| 1226 |
+
"loss_step_1": 0.0849,
|
| 1227 |
+
"loss_step_2": 0.0843,
|
| 1228 |
+
"loss_step_3": 0.0822,
|
| 1229 |
+
"step": 1820
|
| 1230 |
+
},
|
| 1231 |
+
{
|
| 1232 |
+
"entropy_step_1": 0.1455,
|
| 1233 |
+
"entropy_step_2": 0.1514,
|
| 1234 |
+
"entropy_step_3": 0.1602,
|
| 1235 |
+
"epoch": 0.207160549425805,
|
| 1236 |
+
"grad_norm": 19.243698120117188,
|
| 1237 |
+
"learning_rate": 4.17387697048714e-05,
|
| 1238 |
+
"loss": 0.064711594581604,
|
| 1239 |
+
"loss_step_1": 0.0692,
|
| 1240 |
+
"loss_step_2": 0.0691,
|
| 1241 |
+
"loss_step_3": 0.0734,
|
| 1242 |
+
"step": 1840
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"entropy_step_1": 0.1451,
|
| 1246 |
+
"entropy_step_2": 0.1453,
|
| 1247 |
+
"entropy_step_3": 0.1384,
|
| 1248 |
+
"epoch": 0.2094122945282594,
|
| 1249 |
+
"grad_norm": 7.763682842254639,
|
| 1250 |
+
"learning_rate": 4.162024416261704e-05,
|
| 1251 |
+
"loss": 0.06751511693000793,
|
| 1252 |
+
"loss_step_1": 0.064,
|
| 1253 |
+
"loss_step_2": 0.0637,
|
| 1254 |
+
"loss_step_3": 0.0712,
|
| 1255 |
+
"step": 1860
|
| 1256 |
+
},
|
| 1257 |
+
{
|
| 1258 |
+
"entropy_step_1": 0.1772,
|
| 1259 |
+
"entropy_step_2": 0.1779,
|
| 1260 |
+
"entropy_step_3": 0.1817,
|
| 1261 |
+
"epoch": 0.2116640396307138,
|
| 1262 |
+
"grad_norm": 13.758148193359375,
|
| 1263 |
+
"learning_rate": 4.150171862036269e-05,
|
| 1264 |
+
"loss": 0.07371515631675721,
|
| 1265 |
+
"loss_step_1": 0.0704,
|
| 1266 |
+
"loss_step_2": 0.0711,
|
| 1267 |
+
"loss_step_3": 0.0805,
|
| 1268 |
+
"step": 1880
|
| 1269 |
+
},
|
| 1270 |
+
{
|
| 1271 |
+
"entropy_step_1": 0.1872,
|
| 1272 |
+
"entropy_step_2": 0.1877,
|
| 1273 |
+
"entropy_step_3": 0.1918,
|
| 1274 |
+
"epoch": 0.21391578473316822,
|
| 1275 |
+
"grad_norm": 12.492297172546387,
|
| 1276 |
+
"learning_rate": 4.138319307810833e-05,
|
| 1277 |
+
"loss": 0.07589672803878784,
|
| 1278 |
+
"loss_step_1": 0.0793,
|
| 1279 |
+
"loss_step_2": 0.0797,
|
| 1280 |
+
"loss_step_3": 0.0712,
|
| 1281 |
+
"step": 1900
|
| 1282 |
+
},
|
| 1283 |
+
{
|
| 1284 |
+
"entropy_step_1": 0.1755,
|
| 1285 |
+
"entropy_step_2": 0.18,
|
| 1286 |
+
"entropy_step_3": 0.1707,
|
| 1287 |
+
"epoch": 0.2161675298356226,
|
| 1288 |
+
"grad_norm": 20.3720703125,
|
| 1289 |
+
"learning_rate": 4.126466753585398e-05,
|
| 1290 |
+
"loss": 0.0737459897994995,
|
| 1291 |
+
"loss_step_1": 0.0724,
|
| 1292 |
+
"loss_step_2": 0.0717,
|
| 1293 |
+
"loss_step_3": 0.0643,
|
| 1294 |
+
"step": 1920
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"entropy_step_1": 0.1572,
|
| 1298 |
+
"entropy_step_2": 0.1603,
|
| 1299 |
+
"entropy_step_3": 0.1756,
|
| 1300 |
+
"epoch": 0.218419274938077,
|
| 1301 |
+
"grad_norm": 14.254826545715332,
|
| 1302 |
+
"learning_rate": 4.1146141993599626e-05,
|
| 1303 |
+
"loss": 0.0933718740940094,
|
| 1304 |
+
"loss_step_1": 0.1067,
|
| 1305 |
+
"loss_step_2": 0.1067,
|
| 1306 |
+
"loss_step_3": 0.1246,
|
| 1307 |
+
"step": 1940
|
| 1308 |
+
},
|
| 1309 |
+
{
|
| 1310 |
+
"entropy_step_1": 0.1778,
|
| 1311 |
+
"entropy_step_2": 0.1832,
|
| 1312 |
+
"entropy_step_3": 0.1838,
|
| 1313 |
+
"epoch": 0.2206710200405314,
|
| 1314 |
+
"grad_norm": 15.021376609802246,
|
| 1315 |
+
"learning_rate": 4.102761645134527e-05,
|
| 1316 |
+
"loss": 0.10391606092453003,
|
| 1317 |
+
"loss_step_1": 0.0878,
|
| 1318 |
+
"loss_step_2": 0.0868,
|
| 1319 |
+
"loss_step_3": 0.1037,
|
| 1320 |
+
"step": 1960
|
| 1321 |
+
},
|
| 1322 |
+
{
|
| 1323 |
+
"entropy_step_1": 0.1957,
|
| 1324 |
+
"entropy_step_2": 0.2026,
|
| 1325 |
+
"entropy_step_3": 0.1986,
|
| 1326 |
+
"epoch": 0.2229227651429858,
|
| 1327 |
+
"grad_norm": 21.728527069091797,
|
| 1328 |
+
"learning_rate": 4.0909090909090915e-05,
|
| 1329 |
+
"loss": 0.07559056878089905,
|
| 1330 |
+
"loss_step_1": 0.0832,
|
| 1331 |
+
"loss_step_2": 0.0828,
|
| 1332 |
+
"loss_step_3": 0.0745,
|
| 1333 |
+
"step": 1980
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"entropy_step_1": 0.1804,
|
| 1337 |
+
"entropy_step_2": 0.1847,
|
| 1338 |
+
"entropy_step_3": 0.1768,
|
| 1339 |
+
"epoch": 0.22517451024544022,
|
| 1340 |
+
"grad_norm": 36.36247253417969,
|
| 1341 |
+
"learning_rate": 4.079056536683655e-05,
|
| 1342 |
+
"loss": 0.08275629878044129,
|
| 1343 |
+
"loss_step_1": 0.0803,
|
| 1344 |
+
"loss_step_2": 0.0801,
|
| 1345 |
+
"loss_step_3": 0.0851,
|
| 1346 |
+
"step": 2000
|
| 1347 |
+
},
|
| 1348 |
+
{
|
| 1349 |
+
"epoch": 0.22517451024544022,
|
| 1350 |
+
"eval_accuracy": 0.9860714285714286,
|
| 1351 |
+
"eval_f1": 0.9869157659494572,
|
| 1352 |
+
"eval_loss": 0.01845250092446804,
|
| 1353 |
+
"eval_precision": 0.9887818300245491,
|
| 1354 |
+
"eval_recall": 0.9860714285714286,
|
| 1355 |
+
"eval_runtime": 9.5335,
|
| 1356 |
+
"eval_samples_per_second": 10.489,
|
| 1357 |
+
"eval_steps_per_second": 1.364,
|
| 1358 |
+
"step": 2000
|
| 1359 |
+
},
|
| 1360 |
+
{
|
| 1361 |
+
"entropy_step_1": 0.1696,
|
| 1362 |
+
"entropy_step_2": 0.1687,
|
| 1363 |
+
"entropy_step_3": 0.1623,
|
| 1364 |
+
"epoch": 0.22742625534789462,
|
| 1365 |
+
"grad_norm": 11.531885147094727,
|
| 1366 |
+
"learning_rate": 4.0672039824582196e-05,
|
| 1367 |
+
"loss": 0.0685614824295044,
|
| 1368 |
+
"loss_step_1": 0.0716,
|
| 1369 |
+
"loss_step_2": 0.0719,
|
| 1370 |
+
"loss_step_3": 0.0716,
|
| 1371 |
+
"step": 2020
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"entropy_step_1": 0.1677,
|
| 1375 |
+
"entropy_step_2": 0.1682,
|
| 1376 |
+
"entropy_step_3": 0.1779,
|
| 1377 |
+
"epoch": 0.22967800045034903,
|
| 1378 |
+
"grad_norm": 10.91732120513916,
|
| 1379 |
+
"learning_rate": 4.055351428232784e-05,
|
| 1380 |
+
"loss": 0.09348326921463013,
|
| 1381 |
+
"loss_step_1": 0.0993,
|
| 1382 |
+
"loss_step_2": 0.1002,
|
| 1383 |
+
"loss_step_3": 0.1143,
|
| 1384 |
+
"step": 2040
|
| 1385 |
+
},
|
| 1386 |
+
{
|
| 1387 |
+
"entropy_step_1": 0.1656,
|
| 1388 |
+
"entropy_step_2": 0.1689,
|
| 1389 |
+
"entropy_step_3": 0.1667,
|
| 1390 |
+
"epoch": 0.23192974555280343,
|
| 1391 |
+
"grad_norm": 11.45389461517334,
|
| 1392 |
+
"learning_rate": 4.0434988740073485e-05,
|
| 1393 |
+
"loss": 0.08703227043151855,
|
| 1394 |
+
"loss_step_1": 0.089,
|
| 1395 |
+
"loss_step_2": 0.0897,
|
| 1396 |
+
"loss_step_3": 0.0984,
|
| 1397 |
+
"step": 2060
|
| 1398 |
+
},
|
| 1399 |
+
{
|
| 1400 |
+
"entropy_step_1": 0.1785,
|
| 1401 |
+
"entropy_step_2": 0.1841,
|
| 1402 |
+
"entropy_step_3": 0.1879,
|
| 1403 |
+
"epoch": 0.2341814906552578,
|
| 1404 |
+
"grad_norm": 12.561020851135254,
|
| 1405 |
+
"learning_rate": 4.031646319781913e-05,
|
| 1406 |
+
"loss": 0.07899390459060669,
|
| 1407 |
+
"loss_step_1": 0.0909,
|
| 1408 |
+
"loss_step_2": 0.0903,
|
| 1409 |
+
"loss_step_3": 0.0887,
|
| 1410 |
+
"step": 2080
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"entropy_step_1": 0.2004,
|
| 1414 |
+
"entropy_step_2": 0.2118,
|
| 1415 |
+
"entropy_step_3": 0.2125,
|
| 1416 |
+
"epoch": 0.23643323575771222,
|
| 1417 |
+
"grad_norm": 9.441752433776855,
|
| 1418 |
+
"learning_rate": 4.019793765556478e-05,
|
| 1419 |
+
"loss": 0.07696235775947571,
|
| 1420 |
+
"loss_step_1": 0.0789,
|
| 1421 |
+
"loss_step_2": 0.0792,
|
| 1422 |
+
"loss_step_3": 0.0834,
|
| 1423 |
+
"step": 2100
|
| 1424 |
+
},
|
| 1425 |
+
{
|
| 1426 |
+
"entropy_step_1": 0.1602,
|
| 1427 |
+
"entropy_step_2": 0.1654,
|
| 1428 |
+
"entropy_step_3": 0.1796,
|
| 1429 |
+
"epoch": 0.23868498086016662,
|
| 1430 |
+
"grad_norm": 18.588212966918945,
|
| 1431 |
+
"learning_rate": 4.0079412113310424e-05,
|
| 1432 |
+
"loss": 0.08245367407798768,
|
| 1433 |
+
"loss_step_1": 0.0835,
|
| 1434 |
+
"loss_step_2": 0.0826,
|
| 1435 |
+
"loss_step_3": 0.0851,
|
| 1436 |
+
"step": 2120
|
| 1437 |
+
},
|
| 1438 |
+
{
|
| 1439 |
+
"entropy_step_1": 0.1618,
|
| 1440 |
+
"entropy_step_2": 0.1654,
|
| 1441 |
+
"entropy_step_3": 0.1581,
|
| 1442 |
+
"epoch": 0.24093672596262103,
|
| 1443 |
+
"grad_norm": 32.4371223449707,
|
| 1444 |
+
"learning_rate": 3.996088657105607e-05,
|
| 1445 |
+
"loss": 0.07823102474212647,
|
| 1446 |
+
"loss_step_1": 0.0732,
|
| 1447 |
+
"loss_step_2": 0.0723,
|
| 1448 |
+
"loss_step_3": 0.0711,
|
| 1449 |
+
"step": 2140
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"entropy_step_1": 0.1576,
|
| 1453 |
+
"entropy_step_2": 0.1635,
|
| 1454 |
+
"entropy_step_3": 0.1588,
|
| 1455 |
+
"epoch": 0.24318847106507543,
|
| 1456 |
+
"grad_norm": 13.143197059631348,
|
| 1457 |
+
"learning_rate": 3.984236102880171e-05,
|
| 1458 |
+
"loss": 0.08596002459526061,
|
| 1459 |
+
"loss_step_1": 0.0822,
|
| 1460 |
+
"loss_step_2": 0.0834,
|
| 1461 |
+
"loss_step_3": 0.0608,
|
| 1462 |
+
"step": 2160
|
| 1463 |
+
},
|
| 1464 |
+
{
|
| 1465 |
+
"entropy_step_1": 0.1772,
|
| 1466 |
+
"entropy_step_2": 0.185,
|
| 1467 |
+
"entropy_step_3": 0.1685,
|
| 1468 |
+
"epoch": 0.24544021616752984,
|
| 1469 |
+
"grad_norm": 20.744983673095703,
|
| 1470 |
+
"learning_rate": 3.972383548654735e-05,
|
| 1471 |
+
"loss": 0.0802798330783844,
|
| 1472 |
+
"loss_step_1": 0.0849,
|
| 1473 |
+
"loss_step_2": 0.0847,
|
| 1474 |
+
"loss_step_3": 0.0794,
|
| 1475 |
+
"step": 2180
|
| 1476 |
+
},
|
| 1477 |
+
{
|
| 1478 |
+
"entropy_step_1": 0.2089,
|
| 1479 |
+
"entropy_step_2": 0.2152,
|
| 1480 |
+
"entropy_step_3": 0.2091,
|
| 1481 |
+
"epoch": 0.24769196126998425,
|
| 1482 |
+
"grad_norm": 59.57087707519531,
|
| 1483 |
+
"learning_rate": 3.9605309944292994e-05,
|
| 1484 |
+
"loss": 0.10311335325241089,
|
| 1485 |
+
"loss_step_1": 0.092,
|
| 1486 |
+
"loss_step_2": 0.0929,
|
| 1487 |
+
"loss_step_3": 0.0886,
|
| 1488 |
+
"step": 2200
|
| 1489 |
+
},
|
| 1490 |
+
{
|
| 1491 |
+
"entropy_step_1": 0.2667,
|
| 1492 |
+
"entropy_step_2": 0.267,
|
| 1493 |
+
"entropy_step_3": 0.272,
|
| 1494 |
+
"epoch": 0.24994370637243865,
|
| 1495 |
+
"grad_norm": 11.140969276428223,
|
| 1496 |
+
"learning_rate": 3.948678440203864e-05,
|
| 1497 |
+
"loss": 0.10753285884857178,
|
| 1498 |
+
"loss_step_1": 0.0864,
|
| 1499 |
+
"loss_step_2": 0.0859,
|
| 1500 |
+
"loss_step_3": 0.073,
|
| 1501 |
+
"step": 2220
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"entropy_step_1": 0.2058,
|
| 1505 |
+
"entropy_step_2": 0.2066,
|
| 1506 |
+
"entropy_step_3": 0.2021,
|
| 1507 |
+
"epoch": 0.25219545147489303,
|
| 1508 |
+
"grad_norm": 52.50346374511719,
|
| 1509 |
+
"learning_rate": 3.936825885978428e-05,
|
| 1510 |
+
"loss": 0.09625864624977112,
|
| 1511 |
+
"loss_step_1": 0.0999,
|
| 1512 |
+
"loss_step_2": 0.1002,
|
| 1513 |
+
"loss_step_3": 0.0903,
|
| 1514 |
+
"step": 2240
|
| 1515 |
+
},
|
| 1516 |
+
{
|
| 1517 |
+
"entropy_step_1": 0.1788,
|
| 1518 |
+
"entropy_step_2": 0.1783,
|
| 1519 |
+
"entropy_step_3": 0.2086,
|
| 1520 |
+
"epoch": 0.25444719657734743,
|
| 1521 |
+
"grad_norm": 26.116437911987305,
|
| 1522 |
+
"learning_rate": 3.924973331752993e-05,
|
| 1523 |
+
"loss": 0.09085633754730224,
|
| 1524 |
+
"loss_step_1": 0.1006,
|
| 1525 |
+
"loss_step_2": 0.1,
|
| 1526 |
+
"loss_step_3": 0.1182,
|
| 1527 |
+
"step": 2260
|
| 1528 |
+
},
|
| 1529 |
+
{
|
| 1530 |
+
"entropy_step_1": 0.1745,
|
| 1531 |
+
"entropy_step_2": 0.1763,
|
| 1532 |
+
"entropy_step_3": 0.1643,
|
| 1533 |
+
"epoch": 0.25669894167980184,
|
| 1534 |
+
"grad_norm": 58.48428726196289,
|
| 1535 |
+
"learning_rate": 3.913120777527558e-05,
|
| 1536 |
+
"loss": 0.07470017671585083,
|
| 1537 |
+
"loss_step_1": 0.0729,
|
| 1538 |
+
"loss_step_2": 0.0728,
|
| 1539 |
+
"loss_step_3": 0.0678,
|
| 1540 |
+
"step": 2280
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"entropy_step_1": 0.1703,
|
| 1544 |
+
"entropy_step_2": 0.1687,
|
| 1545 |
+
"entropy_step_3": 0.1681,
|
| 1546 |
+
"epoch": 0.25895068678225625,
|
| 1547 |
+
"grad_norm": 35.77830505371094,
|
| 1548 |
+
"learning_rate": 3.901268223302122e-05,
|
| 1549 |
+
"loss": 0.08094346523284912,
|
| 1550 |
+
"loss_step_1": 0.0715,
|
| 1551 |
+
"loss_step_2": 0.0716,
|
| 1552 |
+
"loss_step_3": 0.0753,
|
| 1553 |
+
"step": 2300
|
| 1554 |
+
},
|
| 1555 |
+
{
|
| 1556 |
+
"entropy_step_1": 0.2099,
|
| 1557 |
+
"entropy_step_2": 0.2092,
|
| 1558 |
+
"entropy_step_3": 0.197,
|
| 1559 |
+
"epoch": 0.26120243188471065,
|
| 1560 |
+
"grad_norm": 9.37353801727295,
|
| 1561 |
+
"learning_rate": 3.8894156690766865e-05,
|
| 1562 |
+
"loss": 0.09115276336669922,
|
| 1563 |
+
"loss_step_1": 0.0992,
|
| 1564 |
+
"loss_step_2": 0.1,
|
| 1565 |
+
"loss_step_3": 0.1128,
|
| 1566 |
+
"step": 2320
|
| 1567 |
+
},
|
| 1568 |
+
{
|
| 1569 |
+
"entropy_step_1": 0.1591,
|
| 1570 |
+
"entropy_step_2": 0.1616,
|
| 1571 |
+
"entropy_step_3": 0.1684,
|
| 1572 |
+
"epoch": 0.26345417698716506,
|
| 1573 |
+
"grad_norm": 7.601145267486572,
|
| 1574 |
+
"learning_rate": 3.877563114851251e-05,
|
| 1575 |
+
"loss": 0.08132302165031433,
|
| 1576 |
+
"loss_step_1": 0.0828,
|
| 1577 |
+
"loss_step_2": 0.0823,
|
| 1578 |
+
"loss_step_3": 0.1034,
|
| 1579 |
+
"step": 2340
|
| 1580 |
+
},
|
| 1581 |
+
{
|
| 1582 |
+
"entropy_step_1": 0.1998,
|
| 1583 |
+
"entropy_step_2": 0.2061,
|
| 1584 |
+
"entropy_step_3": 0.1994,
|
| 1585 |
+
"epoch": 0.26570592208961946,
|
| 1586 |
+
"grad_norm": 20.68280601501465,
|
| 1587 |
+
"learning_rate": 3.865710560625815e-05,
|
| 1588 |
+
"loss": 0.07925176620483398,
|
| 1589 |
+
"loss_step_1": 0.0822,
|
| 1590 |
+
"loss_step_2": 0.0816,
|
| 1591 |
+
"loss_step_3": 0.083,
|
| 1592 |
+
"step": 2360
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"entropy_step_1": 0.1546,
|
| 1596 |
+
"entropy_step_2": 0.1583,
|
| 1597 |
+
"entropy_step_3": 0.1878,
|
| 1598 |
+
"epoch": 0.26795766719207387,
|
| 1599 |
+
"grad_norm": 28.0628604888916,
|
| 1600 |
+
"learning_rate": 3.853858006400379e-05,
|
| 1601 |
+
"loss": 0.07469387054443359,
|
| 1602 |
+
"loss_step_1": 0.0666,
|
| 1603 |
+
"loss_step_2": 0.0659,
|
| 1604 |
+
"loss_step_3": 0.0836,
|
| 1605 |
+
"step": 2380
|
| 1606 |
+
},
|
| 1607 |
+
{
|
| 1608 |
+
"entropy_step_1": 0.1429,
|
| 1609 |
+
"entropy_step_2": 0.1453,
|
| 1610 |
+
"entropy_step_3": 0.1502,
|
| 1611 |
+
"epoch": 0.2702094122945283,
|
| 1612 |
+
"grad_norm": 51.92823791503906,
|
| 1613 |
+
"learning_rate": 3.8420054521749435e-05,
|
| 1614 |
+
"loss": 0.07140672206878662,
|
| 1615 |
+
"loss_step_1": 0.059,
|
| 1616 |
+
"loss_step_2": 0.0585,
|
| 1617 |
+
"loss_step_3": 0.0607,
|
| 1618 |
+
"step": 2400
|
| 1619 |
+
},
|
| 1620 |
+
{
|
| 1621 |
+
"entropy_step_1": 0.1731,
|
| 1622 |
+
"entropy_step_2": 0.1767,
|
| 1623 |
+
"entropy_step_3": 0.1841,
|
| 1624 |
+
"epoch": 0.2724611573969827,
|
| 1625 |
+
"grad_norm": 14.429466247558594,
|
| 1626 |
+
"learning_rate": 3.8301528979495086e-05,
|
| 1627 |
+
"loss": 0.07514737248420715,
|
| 1628 |
+
"loss_step_1": 0.0851,
|
| 1629 |
+
"loss_step_2": 0.0841,
|
| 1630 |
+
"loss_step_3": 0.0902,
|
| 1631 |
+
"step": 2420
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"entropy_step_1": 0.1956,
|
| 1635 |
+
"entropy_step_2": 0.2044,
|
| 1636 |
+
"entropy_step_3": 0.2047,
|
| 1637 |
+
"epoch": 0.2747129024994371,
|
| 1638 |
+
"grad_norm": 8.800642013549805,
|
| 1639 |
+
"learning_rate": 3.818300343724073e-05,
|
| 1640 |
+
"loss": 0.08749198913574219,
|
| 1641 |
+
"loss_step_1": 0.0939,
|
| 1642 |
+
"loss_step_2": 0.0949,
|
| 1643 |
+
"loss_step_3": 0.1007,
|
| 1644 |
+
"step": 2440
|
| 1645 |
+
},
|
| 1646 |
+
{
|
| 1647 |
+
"entropy_step_1": 0.1507,
|
| 1648 |
+
"entropy_step_2": 0.158,
|
| 1649 |
+
"entropy_step_3": 0.1601,
|
| 1650 |
+
"epoch": 0.2769646476018915,
|
| 1651 |
+
"grad_norm": 14.694356918334961,
|
| 1652 |
+
"learning_rate": 3.8064477894986374e-05,
|
| 1653 |
+
"loss": 0.07953562140464783,
|
| 1654 |
+
"loss_step_1": 0.083,
|
| 1655 |
+
"loss_step_2": 0.0822,
|
| 1656 |
+
"loss_step_3": 0.0712,
|
| 1657 |
+
"step": 2460
|
| 1658 |
+
},
|
| 1659 |
+
{
|
| 1660 |
+
"entropy_step_1": 0.1765,
|
| 1661 |
+
"entropy_step_2": 0.1813,
|
| 1662 |
+
"entropy_step_3": 0.1857,
|
| 1663 |
+
"epoch": 0.2792163927043459,
|
| 1664 |
+
"grad_norm": 51.66787338256836,
|
| 1665 |
+
"learning_rate": 3.794595235273202e-05,
|
| 1666 |
+
"loss": 0.0781484842300415,
|
| 1667 |
+
"loss_step_1": 0.0855,
|
| 1668 |
+
"loss_step_2": 0.085,
|
| 1669 |
+
"loss_step_3": 0.0851,
|
| 1670 |
+
"step": 2480
|
| 1671 |
+
},
|
| 1672 |
+
{
|
| 1673 |
+
"entropy_step_1": 0.196,
|
| 1674 |
+
"entropy_step_2": 0.2025,
|
| 1675 |
+
"entropy_step_3": 0.1875,
|
| 1676 |
+
"epoch": 0.28146813780680024,
|
| 1677 |
+
"grad_norm": 15.549168586730957,
|
| 1678 |
+
"learning_rate": 3.782742681047766e-05,
|
| 1679 |
+
"loss": 0.07543327808380126,
|
| 1680 |
+
"loss_step_1": 0.0762,
|
| 1681 |
+
"loss_step_2": 0.0759,
|
| 1682 |
+
"loss_step_3": 0.0713,
|
| 1683 |
+
"step": 2500
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 0.28146813780680024,
|
| 1687 |
+
"eval_accuracy": 0.9839285714285714,
|
| 1688 |
+
"eval_f1": 0.9850729568264418,
|
| 1689 |
+
"eval_loss": 0.02278345823287964,
|
| 1690 |
+
"eval_precision": 0.9876088229746766,
|
| 1691 |
+
"eval_recall": 0.9839285714285714,
|
| 1692 |
+
"eval_runtime": 9.5591,
|
| 1693 |
+
"eval_samples_per_second": 10.461,
|
| 1694 |
+
"eval_steps_per_second": 1.36,
|
| 1695 |
+
"step": 2500
|
| 1696 |
+
},
|
| 1697 |
+
{
|
| 1698 |
+
"entropy_step_1": 0.1714,
|
| 1699 |
+
"entropy_step_2": 0.1731,
|
| 1700 |
+
"entropy_step_3": 0.1621,
|
| 1701 |
+
"epoch": 0.28371988290925465,
|
| 1702 |
+
"grad_norm": 17.55965805053711,
|
| 1703 |
+
"learning_rate": 3.77089012682233e-05,
|
| 1704 |
+
"loss": 0.08143405914306641,
|
| 1705 |
+
"loss_step_1": 0.0722,
|
| 1706 |
+
"loss_step_2": 0.0719,
|
| 1707 |
+
"loss_step_3": 0.061,
|
| 1708 |
+
"step": 2520
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"entropy_step_1": 0.1695,
|
| 1712 |
+
"entropy_step_2": 0.1672,
|
| 1713 |
+
"entropy_step_3": 0.1385,
|
| 1714 |
+
"epoch": 0.28597162801170906,
|
| 1715 |
+
"grad_norm": 74.84268951416016,
|
| 1716 |
+
"learning_rate": 3.7590375725968944e-05,
|
| 1717 |
+
"loss": 0.08690762519836426,
|
| 1718 |
+
"loss_step_1": 0.0961,
|
| 1719 |
+
"loss_step_2": 0.0961,
|
| 1720 |
+
"loss_step_3": 0.1111,
|
| 1721 |
+
"step": 2540
|
| 1722 |
+
},
|
| 1723 |
+
{
|
| 1724 |
+
"entropy_step_1": 0.1978,
|
| 1725 |
+
"entropy_step_2": 0.1984,
|
| 1726 |
+
"entropy_step_3": 0.1842,
|
| 1727 |
+
"epoch": 0.28822337311416346,
|
| 1728 |
+
"grad_norm": 23.08629035949707,
|
| 1729 |
+
"learning_rate": 3.747185018371459e-05,
|
| 1730 |
+
"loss": 0.08158662319183349,
|
| 1731 |
+
"loss_step_1": 0.0777,
|
| 1732 |
+
"loss_step_2": 0.0773,
|
| 1733 |
+
"loss_step_3": 0.0706,
|
| 1734 |
+
"step": 2560
|
| 1735 |
+
},
|
| 1736 |
+
{
|
| 1737 |
+
"entropy_step_1": 0.1518,
|
| 1738 |
+
"entropy_step_2": 0.1513,
|
| 1739 |
+
"entropy_step_3": 0.1688,
|
| 1740 |
+
"epoch": 0.29047511821661787,
|
| 1741 |
+
"grad_norm": 16.573776245117188,
|
| 1742 |
+
"learning_rate": 3.735332464146024e-05,
|
| 1743 |
+
"loss": 0.06529904007911683,
|
| 1744 |
+
"loss_step_1": 0.0695,
|
| 1745 |
+
"loss_step_2": 0.0687,
|
| 1746 |
+
"loss_step_3": 0.0718,
|
| 1747 |
+
"step": 2580
|
| 1748 |
+
},
|
| 1749 |
+
{
|
| 1750 |
+
"entropy_step_1": 0.1529,
|
| 1751 |
+
"entropy_step_2": 0.15,
|
| 1752 |
+
"entropy_step_3": 0.1459,
|
| 1753 |
+
"epoch": 0.2927268633190723,
|
| 1754 |
+
"grad_norm": 13.409026145935059,
|
| 1755 |
+
"learning_rate": 3.723479909920588e-05,
|
| 1756 |
+
"loss": 0.07439209222793579,
|
| 1757 |
+
"loss_step_1": 0.0801,
|
| 1758 |
+
"loss_step_2": 0.0807,
|
| 1759 |
+
"loss_step_3": 0.0522,
|
| 1760 |
+
"step": 2600
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"entropy_step_1": 0.1301,
|
| 1764 |
+
"entropy_step_2": 0.1263,
|
| 1765 |
+
"entropy_step_3": 0.1326,
|
| 1766 |
+
"epoch": 0.2949786084215267,
|
| 1767 |
+
"grad_norm": 4.898118019104004,
|
| 1768 |
+
"learning_rate": 3.711627355695153e-05,
|
| 1769 |
+
"loss": 0.060008573532104495,
|
| 1770 |
+
"loss_step_1": 0.0523,
|
| 1771 |
+
"loss_step_2": 0.0549,
|
| 1772 |
+
"loss_step_3": 0.0552,
|
| 1773 |
+
"step": 2620
|
| 1774 |
+
},
|
| 1775 |
+
{
|
| 1776 |
+
"entropy_step_1": 0.1539,
|
| 1777 |
+
"entropy_step_2": 0.148,
|
| 1778 |
+
"entropy_step_3": 0.1407,
|
| 1779 |
+
"epoch": 0.2972303535239811,
|
| 1780 |
+
"grad_norm": 10.824843406677246,
|
| 1781 |
+
"learning_rate": 3.699774801469717e-05,
|
| 1782 |
+
"loss": 0.07593064904212951,
|
| 1783 |
+
"loss_step_1": 0.0693,
|
| 1784 |
+
"loss_step_2": 0.0685,
|
| 1785 |
+
"loss_step_3": 0.0536,
|
| 1786 |
+
"step": 2640
|
| 1787 |
+
},
|
| 1788 |
+
{
|
| 1789 |
+
"entropy_step_1": 0.1405,
|
| 1790 |
+
"entropy_step_2": 0.1371,
|
| 1791 |
+
"entropy_step_3": 0.1304,
|
| 1792 |
+
"epoch": 0.2994820986264355,
|
| 1793 |
+
"grad_norm": 11.237263679504395,
|
| 1794 |
+
"learning_rate": 3.6879222472442816e-05,
|
| 1795 |
+
"loss": 0.06541634798049926,
|
| 1796 |
+
"loss_step_1": 0.0594,
|
| 1797 |
+
"loss_step_2": 0.0598,
|
| 1798 |
+
"loss_step_3": 0.0621,
|
| 1799 |
+
"step": 2660
|
| 1800 |
+
},
|
| 1801 |
+
{
|
| 1802 |
+
"entropy_step_1": 0.1568,
|
| 1803 |
+
"entropy_step_2": 0.1577,
|
| 1804 |
+
"entropy_step_3": 0.1671,
|
| 1805 |
+
"epoch": 0.3017338437288899,
|
| 1806 |
+
"grad_norm": 33.05281066894531,
|
| 1807 |
+
"learning_rate": 3.676069693018846e-05,
|
| 1808 |
+
"loss": 0.06452785730361939,
|
| 1809 |
+
"loss_step_1": 0.0681,
|
| 1810 |
+
"loss_step_2": 0.0681,
|
| 1811 |
+
"loss_step_3": 0.0655,
|
| 1812 |
+
"step": 2680
|
| 1813 |
+
},
|
| 1814 |
+
{
|
| 1815 |
+
"entropy_step_1": 0.1712,
|
| 1816 |
+
"entropy_step_2": 0.1701,
|
| 1817 |
+
"entropy_step_3": 0.1749,
|
| 1818 |
+
"epoch": 0.3039855888313443,
|
| 1819 |
+
"grad_norm": 21.46320915222168,
|
| 1820 |
+
"learning_rate": 3.66421713879341e-05,
|
| 1821 |
+
"loss": 0.09549169540405274,
|
| 1822 |
+
"loss_step_1": 0.1028,
|
| 1823 |
+
"loss_step_2": 0.1009,
|
| 1824 |
+
"loss_step_3": 0.1295,
|
| 1825 |
+
"step": 2700
|
| 1826 |
+
},
|
| 1827 |
+
{
|
| 1828 |
+
"entropy_step_1": 0.1425,
|
| 1829 |
+
"entropy_step_2": 0.1418,
|
| 1830 |
+
"entropy_step_3": 0.1646,
|
| 1831 |
+
"epoch": 0.3062373339337987,
|
| 1832 |
+
"grad_norm": 13.858271598815918,
|
| 1833 |
+
"learning_rate": 3.652364584567974e-05,
|
| 1834 |
+
"loss": 0.08211459517478943,
|
| 1835 |
+
"loss_step_1": 0.0865,
|
| 1836 |
+
"loss_step_2": 0.086,
|
| 1837 |
+
"loss_step_3": 0.0836,
|
| 1838 |
+
"step": 2720
|
| 1839 |
+
},
|
| 1840 |
+
{
|
| 1841 |
+
"entropy_step_1": 0.1651,
|
| 1842 |
+
"entropy_step_2": 0.1606,
|
| 1843 |
+
"entropy_step_3": 0.1582,
|
| 1844 |
+
"epoch": 0.3084890790362531,
|
| 1845 |
+
"grad_norm": 33.63695526123047,
|
| 1846 |
+
"learning_rate": 3.6405120303425385e-05,
|
| 1847 |
+
"loss": 0.07108281254768371,
|
| 1848 |
+
"loss_step_1": 0.066,
|
| 1849 |
+
"loss_step_2": 0.0662,
|
| 1850 |
+
"loss_step_3": 0.0702,
|
| 1851 |
+
"step": 2740
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"entropy_step_1": 0.1535,
|
| 1855 |
+
"entropy_step_2": 0.1546,
|
| 1856 |
+
"entropy_step_3": 0.1573,
|
| 1857 |
+
"epoch": 0.3107408241387075,
|
| 1858 |
+
"grad_norm": 13.39726448059082,
|
| 1859 |
+
"learning_rate": 3.6286594761171036e-05,
|
| 1860 |
+
"loss": 0.06529198288917541,
|
| 1861 |
+
"loss_step_1": 0.0674,
|
| 1862 |
+
"loss_step_2": 0.0666,
|
| 1863 |
+
"loss_step_3": 0.074,
|
| 1864 |
+
"step": 2760
|
| 1865 |
+
},
|
| 1866 |
+
{
|
| 1867 |
+
"entropy_step_1": 0.1432,
|
| 1868 |
+
"entropy_step_2": 0.148,
|
| 1869 |
+
"entropy_step_3": 0.152,
|
| 1870 |
+
"epoch": 0.3129925692411619,
|
| 1871 |
+
"grad_norm": 41.96938705444336,
|
| 1872 |
+
"learning_rate": 3.616806921891668e-05,
|
| 1873 |
+
"loss": 0.07317432165145873,
|
| 1874 |
+
"loss_step_1": 0.0644,
|
| 1875 |
+
"loss_step_2": 0.0649,
|
| 1876 |
+
"loss_step_3": 0.0739,
|
| 1877 |
+
"step": 2780
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"entropy_step_1": 0.1556,
|
| 1881 |
+
"entropy_step_2": 0.1585,
|
| 1882 |
+
"entropy_step_3": 0.1766,
|
| 1883 |
+
"epoch": 0.3152443143436163,
|
| 1884 |
+
"grad_norm": 34.93521499633789,
|
| 1885 |
+
"learning_rate": 3.6049543676662325e-05,
|
| 1886 |
+
"loss": 0.07776182889938354,
|
| 1887 |
+
"loss_step_1": 0.0881,
|
| 1888 |
+
"loss_step_2": 0.0874,
|
| 1889 |
+
"loss_step_3": 0.0946,
|
| 1890 |
+
"step": 2800
|
| 1891 |
+
},
|
| 1892 |
+
{
|
| 1893 |
+
"entropy_step_1": 0.1567,
|
| 1894 |
+
"entropy_step_2": 0.1581,
|
| 1895 |
+
"entropy_step_3": 0.1372,
|
| 1896 |
+
"epoch": 0.3174960594460707,
|
| 1897 |
+
"grad_norm": 17.880144119262695,
|
| 1898 |
+
"learning_rate": 3.593101813440797e-05,
|
| 1899 |
+
"loss": 0.07650998830795289,
|
| 1900 |
+
"loss_step_1": 0.081,
|
| 1901 |
+
"loss_step_2": 0.0803,
|
| 1902 |
+
"loss_step_3": 0.0801,
|
| 1903 |
+
"step": 2820
|
| 1904 |
+
},
|
| 1905 |
+
{
|
| 1906 |
+
"entropy_step_1": 0.1783,
|
| 1907 |
+
"entropy_step_2": 0.1811,
|
| 1908 |
+
"entropy_step_3": 0.1972,
|
| 1909 |
+
"epoch": 0.3197478045485251,
|
| 1910 |
+
"grad_norm": 10.349809646606445,
|
| 1911 |
+
"learning_rate": 3.581249259215361e-05,
|
| 1912 |
+
"loss": 0.08447476029396057,
|
| 1913 |
+
"loss_step_1": 0.0827,
|
| 1914 |
+
"loss_step_2": 0.0823,
|
| 1915 |
+
"loss_step_3": 0.0779,
|
| 1916 |
+
"step": 2840
|
| 1917 |
+
},
|
| 1918 |
+
{
|
| 1919 |
+
"entropy_step_1": 0.1191,
|
| 1920 |
+
"entropy_step_2": 0.1223,
|
| 1921 |
+
"entropy_step_3": 0.1286,
|
| 1922 |
+
"epoch": 0.3219995496509795,
|
| 1923 |
+
"grad_norm": 13.57351303100586,
|
| 1924 |
+
"learning_rate": 3.569396704989926e-05,
|
| 1925 |
+
"loss": 0.06497950553894043,
|
| 1926 |
+
"loss_step_1": 0.0642,
|
| 1927 |
+
"loss_step_2": 0.0631,
|
| 1928 |
+
"loss_step_3": 0.0561,
|
| 1929 |
+
"step": 2860
|
| 1930 |
+
},
|
| 1931 |
+
{
|
| 1932 |
+
"entropy_step_1": 0.1663,
|
| 1933 |
+
"entropy_step_2": 0.168,
|
| 1934 |
+
"entropy_step_3": 0.1607,
|
| 1935 |
+
"epoch": 0.3242512947534339,
|
| 1936 |
+
"grad_norm": 43.37236785888672,
|
| 1937 |
+
"learning_rate": 3.5575441507644894e-05,
|
| 1938 |
+
"loss": 0.07337754368782043,
|
| 1939 |
+
"loss_step_1": 0.0744,
|
| 1940 |
+
"loss_step_2": 0.074,
|
| 1941 |
+
"loss_step_3": 0.0708,
|
| 1942 |
+
"step": 2880
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"entropy_step_1": 0.1494,
|
| 1946 |
+
"entropy_step_2": 0.1494,
|
| 1947 |
+
"entropy_step_3": 0.1409,
|
| 1948 |
+
"epoch": 0.3265030398558883,
|
| 1949 |
+
"grad_norm": 7.599946975708008,
|
| 1950 |
+
"learning_rate": 3.545691596539054e-05,
|
| 1951 |
+
"loss": 0.06760333180427551,
|
| 1952 |
+
"loss_step_1": 0.065,
|
| 1953 |
+
"loss_step_2": 0.0657,
|
| 1954 |
+
"loss_step_3": 0.0641,
|
| 1955 |
+
"step": 2900
|
| 1956 |
+
},
|
| 1957 |
+
{
|
| 1958 |
+
"entropy_step_1": 0.1691,
|
| 1959 |
+
"entropy_step_2": 0.1723,
|
| 1960 |
+
"entropy_step_3": 0.1686,
|
| 1961 |
+
"epoch": 0.3287547849583427,
|
| 1962 |
+
"grad_norm": 41.83497619628906,
|
| 1963 |
+
"learning_rate": 3.533839042313619e-05,
|
| 1964 |
+
"loss": 0.09451901912689209,
|
| 1965 |
+
"loss_step_1": 0.1203,
|
| 1966 |
+
"loss_step_2": 0.1204,
|
| 1967 |
+
"loss_step_3": 0.0777,
|
| 1968 |
+
"step": 2920
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"entropy_step_1": 0.1538,
|
| 1972 |
+
"entropy_step_2": 0.1616,
|
| 1973 |
+
"entropy_step_3": 0.1667,
|
| 1974 |
+
"epoch": 0.3310065300607971,
|
| 1975 |
+
"grad_norm": 14.508233070373535,
|
| 1976 |
+
"learning_rate": 3.5219864880881833e-05,
|
| 1977 |
+
"loss": 0.06872593760490417,
|
| 1978 |
+
"loss_step_1": 0.0694,
|
| 1979 |
+
"loss_step_2": 0.0689,
|
| 1980 |
+
"loss_step_3": 0.0684,
|
| 1981 |
+
"step": 2940
|
| 1982 |
+
},
|
| 1983 |
+
{
|
| 1984 |
+
"entropy_step_1": 0.1628,
|
| 1985 |
+
"entropy_step_2": 0.1705,
|
| 1986 |
+
"entropy_step_3": 0.1672,
|
| 1987 |
+
"epoch": 0.3332582751632515,
|
| 1988 |
+
"grad_norm": 14.131729125976562,
|
| 1989 |
+
"learning_rate": 3.510133933862748e-05,
|
| 1990 |
+
"loss": 0.07098121643066406,
|
| 1991 |
+
"loss_step_1": 0.0711,
|
| 1992 |
+
"loss_step_2": 0.0709,
|
| 1993 |
+
"loss_step_3": 0.0617,
|
| 1994 |
+
"step": 2960
|
| 1995 |
+
},
|
| 1996 |
+
{
|
| 1997 |
+
"entropy_step_1": 0.1623,
|
| 1998 |
+
"entropy_step_2": 0.1672,
|
| 1999 |
+
"entropy_step_3": 0.1701,
|
| 2000 |
+
"epoch": 0.3355100202657059,
|
| 2001 |
+
"grad_norm": 9.615864753723145,
|
| 2002 |
+
"learning_rate": 3.498281379637312e-05,
|
| 2003 |
+
"loss": 0.08790453672409057,
|
| 2004 |
+
"loss_step_1": 0.1031,
|
| 2005 |
+
"loss_step_2": 0.1019,
|
| 2006 |
+
"loss_step_3": 0.0712,
|
| 2007 |
+
"step": 2980
|
| 2008 |
+
},
|
| 2009 |
+
{
|
| 2010 |
+
"entropy_step_1": 0.1713,
|
| 2011 |
+
"entropy_step_2": 0.177,
|
| 2012 |
+
"entropy_step_3": 0.154,
|
| 2013 |
+
"epoch": 0.3377617653681603,
|
| 2014 |
+
"grad_norm": 19.8389892578125,
|
| 2015 |
+
"learning_rate": 3.4864288254118766e-05,
|
| 2016 |
+
"loss": 0.08365345001220703,
|
| 2017 |
+
"loss_step_1": 0.0865,
|
| 2018 |
+
"loss_step_2": 0.0855,
|
| 2019 |
+
"loss_step_3": 0.0739,
|
| 2020 |
+
"step": 3000
|
| 2021 |
+
},
|
| 2022 |
+
{
|
| 2023 |
+
"epoch": 0.3377617653681603,
|
| 2024 |
+
"eval_accuracy": 0.9660714285714286,
|
| 2025 |
+
"eval_f1": 0.9702899255355045,
|
| 2026 |
+
"eval_loss": 0.021565444767475128,
|
| 2027 |
+
"eval_precision": 0.9782635395385892,
|
| 2028 |
+
"eval_recall": 0.9660714285714286,
|
| 2029 |
+
"eval_runtime": 9.7415,
|
| 2030 |
+
"eval_samples_per_second": 10.265,
|
| 2031 |
+
"eval_steps_per_second": 1.334,
|
| 2032 |
+
"step": 3000
|
| 2033 |
+
}
|
| 2034 |
+
],
|
| 2035 |
+
"logging_steps": 20,
|
| 2036 |
+
"max_steps": 8882,
|
| 2037 |
+
"num_input_tokens_seen": 0,
|
| 2038 |
+
"num_train_epochs": 1,
|
| 2039 |
+
"save_steps": 500,
|
| 2040 |
+
"stateful_callbacks": {
|
| 2041 |
+
"TrainerControl": {
|
| 2042 |
+
"args": {
|
| 2043 |
+
"should_epoch_stop": false,
|
| 2044 |
+
"should_evaluate": false,
|
| 2045 |
+
"should_log": false,
|
| 2046 |
+
"should_save": true,
|
| 2047 |
+
"should_training_stop": false
|
| 2048 |
+
},
|
| 2049 |
+
"attributes": {}
|
| 2050 |
+
}
|
| 2051 |
+
},
|
| 2052 |
+
"total_flos": 1.7267639829990998e+19,
|
| 2053 |
+
"train_batch_size": 8,
|
| 2054 |
+
"trial_name": null,
|
| 2055 |
+
"trial_params": null
|
| 2056 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59b675d9f4f8acfae1450597ae646dd7e80b502f78ff5e1843d992ba3b7da375
|
| 3 |
+
size 5457
|