Yichen Feng commited on
Model save
Browse files- .gitattributes +1 -0
- README.md +59 -0
- chat_template.jinja +154 -0
- config.json +127 -0
- generation_config.json +13 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +0 -0
- processor_config.json +63 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
- trainer_log.jsonl +160 -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
|
README.md
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: apache-2.0
|
| 4 |
+
base_model: Qwen/Qwen3.5-35B-A3B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- generated_from_trainer
|
| 8 |
+
model-index:
|
| 9 |
+
- name: Qwen3.5-35B-A3B-SFT-artarena_sft-LR1.0e-6-EPOCHS3-LF
|
| 10 |
+
results: []
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 14 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 15 |
+
|
| 16 |
+
# Qwen3.5-35B-A3B-SFT-artarena_sft-LR1.0e-6-EPOCHS3-LF
|
| 17 |
+
|
| 18 |
+
This model is a fine-tuned version of [Qwen/Qwen3.5-35B-A3B](https://huggingface.co/Qwen/Qwen3.5-35B-A3B) on an unknown dataset.
|
| 19 |
+
|
| 20 |
+
## Model description
|
| 21 |
+
|
| 22 |
+
More information needed
|
| 23 |
+
|
| 24 |
+
## Intended uses & limitations
|
| 25 |
+
|
| 26 |
+
More information needed
|
| 27 |
+
|
| 28 |
+
## Training and evaluation data
|
| 29 |
+
|
| 30 |
+
More information needed
|
| 31 |
+
|
| 32 |
+
## Training procedure
|
| 33 |
+
|
| 34 |
+
### Training hyperparameters
|
| 35 |
+
|
| 36 |
+
The following hyperparameters were used during training:
|
| 37 |
+
- learning_rate: 1e-06
|
| 38 |
+
- train_batch_size: 4
|
| 39 |
+
- eval_batch_size: 8
|
| 40 |
+
- seed: 42
|
| 41 |
+
- distributed_type: multi-GPU
|
| 42 |
+
- num_devices: 8
|
| 43 |
+
- total_train_batch_size: 32
|
| 44 |
+
- total_eval_batch_size: 64
|
| 45 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 46 |
+
- lr_scheduler_type: cosine
|
| 47 |
+
- lr_scheduler_warmup_steps: 10.0
|
| 48 |
+
- num_epochs: 3.0
|
| 49 |
+
|
| 50 |
+
### Training results
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
### Framework versions
|
| 55 |
+
|
| 56 |
+
- Transformers 5.2.0
|
| 57 |
+
- Pytorch 2.10.0+cu128
|
| 58 |
+
- Datasets 4.0.0
|
| 59 |
+
- Tokenizers 0.22.2
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,154 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
{%- if tools and tools is iterable and tools is not mapping %}
|
| 46 |
+
{{- '<|im_start|>system\n' }}
|
| 47 |
+
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
|
| 48 |
+
{%- for tool in tools %}
|
| 49 |
+
{{- "\n" }}
|
| 50 |
+
{{- tool | tojson }}
|
| 51 |
+
{%- endfor %}
|
| 52 |
+
{{- "\n</tools>" }}
|
| 53 |
+
{{- '\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>' }}
|
| 54 |
+
{%- if messages[0].role == 'system' %}
|
| 55 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 56 |
+
{%- if content %}
|
| 57 |
+
{{- '\n\n' + content }}
|
| 58 |
+
{%- endif %}
|
| 59 |
+
{%- endif %}
|
| 60 |
+
{{- '<|im_end|>\n' }}
|
| 61 |
+
{%- else %}
|
| 62 |
+
{%- if messages[0].role == 'system' %}
|
| 63 |
+
{%- set content = render_content(messages[0].content, false, true)|trim %}
|
| 64 |
+
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
|
| 65 |
+
{%- endif %}
|
| 66 |
+
{%- endif %}
|
| 67 |
+
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
|
| 68 |
+
{%- for message in messages[::-1] %}
|
| 69 |
+
{%- set index = (messages|length - 1) - loop.index0 %}
|
| 70 |
+
{%- if ns.multi_step_tool and message.role == "user" %}
|
| 71 |
+
{%- set content = render_content(message.content, false)|trim %}
|
| 72 |
+
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
|
| 73 |
+
{%- set ns.multi_step_tool = false %}
|
| 74 |
+
{%- set ns.last_query_index = index %}
|
| 75 |
+
{%- endif %}
|
| 76 |
+
{%- endif %}
|
| 77 |
+
{%- endfor %}
|
| 78 |
+
{%- if ns.multi_step_tool %}
|
| 79 |
+
{{- raise_exception('No user query found in messages.') }}
|
| 80 |
+
{%- endif %}
|
| 81 |
+
{%- for message in messages %}
|
| 82 |
+
{%- set content = render_content(message.content, true)|trim %}
|
| 83 |
+
{%- if message.role == "system" %}
|
| 84 |
+
{%- if not loop.first %}
|
| 85 |
+
{{- raise_exception('System message must be at the beginning.') }}
|
| 86 |
+
{%- endif %}
|
| 87 |
+
{%- elif message.role == "user" %}
|
| 88 |
+
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
|
| 89 |
+
{%- elif message.role == "assistant" %}
|
| 90 |
+
{%- set reasoning_content = '' %}
|
| 91 |
+
{%- if message.reasoning_content is string %}
|
| 92 |
+
{%- set reasoning_content = message.reasoning_content %}
|
| 93 |
+
{%- else %}
|
| 94 |
+
{%- if '</think>' in content %}
|
| 95 |
+
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
|
| 96 |
+
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
|
| 97 |
+
{%- endif %}
|
| 98 |
+
{%- endif %}
|
| 99 |
+
{%- set reasoning_content = reasoning_content|trim %}
|
| 100 |
+
{%- if loop.index0 > ns.last_query_index %}
|
| 101 |
+
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
|
| 102 |
+
{%- else %}
|
| 103 |
+
{{- '<|im_start|>' + message.role + '\n' + content }}
|
| 104 |
+
{%- endif %}
|
| 105 |
+
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
|
| 106 |
+
{%- for tool_call in message.tool_calls %}
|
| 107 |
+
{%- if tool_call.function is defined %}
|
| 108 |
+
{%- set tool_call = tool_call.function %}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- if loop.first %}
|
| 111 |
+
{%- if content|trim %}
|
| 112 |
+
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 113 |
+
{%- else %}
|
| 114 |
+
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- else %}
|
| 117 |
+
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
|
| 118 |
+
{%- endif %}
|
| 119 |
+
{%- if tool_call.arguments is defined %}
|
| 120 |
+
{%- for args_name, args_value in tool_call.arguments|items %}
|
| 121 |
+
{{- '<parameter=' + args_name + '>\n' }}
|
| 122 |
+
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
|
| 123 |
+
{{- args_value }}
|
| 124 |
+
{{- '\n</parameter>\n' }}
|
| 125 |
+
{%- endfor %}
|
| 126 |
+
{%- endif %}
|
| 127 |
+
{{- '</function>\n</tool_call>' }}
|
| 128 |
+
{%- endfor %}
|
| 129 |
+
{%- endif %}
|
| 130 |
+
{{- '<|im_end|>\n' }}
|
| 131 |
+
{%- elif message.role == "tool" %}
|
| 132 |
+
{%- if loop.previtem and loop.previtem.role != "tool" %}
|
| 133 |
+
{{- '<|im_start|>user' }}
|
| 134 |
+
{%- endif %}
|
| 135 |
+
{{- '\n<tool_response>\n' }}
|
| 136 |
+
{{- content }}
|
| 137 |
+
{{- '\n</tool_response>' }}
|
| 138 |
+
{%- if not loop.last and loop.nextitem.role != "tool" %}
|
| 139 |
+
{{- '<|im_end|>\n' }}
|
| 140 |
+
{%- elif loop.last %}
|
| 141 |
+
{{- '<|im_end|>\n' }}
|
| 142 |
+
{%- endif %}
|
| 143 |
+
{%- else %}
|
| 144 |
+
{{- raise_exception('Unexpected message role.') }}
|
| 145 |
+
{%- endif %}
|
| 146 |
+
{%- endfor %}
|
| 147 |
+
{%- if add_generation_prompt %}
|
| 148 |
+
{{- '<|im_start|>assistant\n' }}
|
| 149 |
+
{%- if enable_thinking is defined and enable_thinking is false %}
|
| 150 |
+
{{- '<think>\n\n</think>\n\n' }}
|
| 151 |
+
{%- else %}
|
| 152 |
+
{{- '<think>\n' }}
|
| 153 |
+
{%- endif %}
|
| 154 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,127 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5MoeForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"bos_token_id": null,
|
| 6 |
+
"dtype": "bfloat16",
|
| 7 |
+
"eos_token_id": 248046,
|
| 8 |
+
"hidden_size": 2048,
|
| 9 |
+
"image_token_id": 248056,
|
| 10 |
+
"model_type": "qwen3_5_moe",
|
| 11 |
+
"pad_token_id": 248044,
|
| 12 |
+
"text_config": {
|
| 13 |
+
"attention_bias": false,
|
| 14 |
+
"attention_dropout": 0.0,
|
| 15 |
+
"attn_output_gate": true,
|
| 16 |
+
"bos_token_id": null,
|
| 17 |
+
"dtype": "bfloat16",
|
| 18 |
+
"eos_token_id": 248044,
|
| 19 |
+
"full_attention_interval": 4,
|
| 20 |
+
"head_dim": 256,
|
| 21 |
+
"hidden_act": "silu",
|
| 22 |
+
"hidden_size": 2048,
|
| 23 |
+
"initializer_range": 0.02,
|
| 24 |
+
"layer_types": [
|
| 25 |
+
"linear_attention",
|
| 26 |
+
"linear_attention",
|
| 27 |
+
"linear_attention",
|
| 28 |
+
"full_attention",
|
| 29 |
+
"linear_attention",
|
| 30 |
+
"linear_attention",
|
| 31 |
+
"linear_attention",
|
| 32 |
+
"full_attention",
|
| 33 |
+
"linear_attention",
|
| 34 |
+
"linear_attention",
|
| 35 |
+
"linear_attention",
|
| 36 |
+
"full_attention",
|
| 37 |
+
"linear_attention",
|
| 38 |
+
"linear_attention",
|
| 39 |
+
"linear_attention",
|
| 40 |
+
"full_attention",
|
| 41 |
+
"linear_attention",
|
| 42 |
+
"linear_attention",
|
| 43 |
+
"linear_attention",
|
| 44 |
+
"full_attention",
|
| 45 |
+
"linear_attention",
|
| 46 |
+
"linear_attention",
|
| 47 |
+
"linear_attention",
|
| 48 |
+
"full_attention",
|
| 49 |
+
"linear_attention",
|
| 50 |
+
"linear_attention",
|
| 51 |
+
"linear_attention",
|
| 52 |
+
"full_attention",
|
| 53 |
+
"linear_attention",
|
| 54 |
+
"linear_attention",
|
| 55 |
+
"linear_attention",
|
| 56 |
+
"full_attention",
|
| 57 |
+
"linear_attention",
|
| 58 |
+
"linear_attention",
|
| 59 |
+
"linear_attention",
|
| 60 |
+
"full_attention",
|
| 61 |
+
"linear_attention",
|
| 62 |
+
"linear_attention",
|
| 63 |
+
"linear_attention",
|
| 64 |
+
"full_attention"
|
| 65 |
+
],
|
| 66 |
+
"linear_conv_kernel_dim": 4,
|
| 67 |
+
"linear_key_head_dim": 128,
|
| 68 |
+
"linear_num_key_heads": 16,
|
| 69 |
+
"linear_num_value_heads": 32,
|
| 70 |
+
"linear_value_head_dim": 128,
|
| 71 |
+
"mamba_ssm_dtype": "float32",
|
| 72 |
+
"max_position_embeddings": 262144,
|
| 73 |
+
"mlp_only_layers": [],
|
| 74 |
+
"model_type": "qwen3_5_moe_text",
|
| 75 |
+
"moe_intermediate_size": 512,
|
| 76 |
+
"mtp_num_hidden_layers": 1,
|
| 77 |
+
"mtp_use_dedicated_embeddings": false,
|
| 78 |
+
"num_attention_heads": 16,
|
| 79 |
+
"num_experts": 256,
|
| 80 |
+
"num_experts_per_tok": 8,
|
| 81 |
+
"num_hidden_layers": 40,
|
| 82 |
+
"num_key_value_heads": 2,
|
| 83 |
+
"output_router_logits": false,
|
| 84 |
+
"pad_token_id": null,
|
| 85 |
+
"partial_rotary_factor": 0.25,
|
| 86 |
+
"rms_norm_eps": 1e-06,
|
| 87 |
+
"rope_parameters": {
|
| 88 |
+
"mrope_interleaved": true,
|
| 89 |
+
"mrope_section": [
|
| 90 |
+
11,
|
| 91 |
+
11,
|
| 92 |
+
10
|
| 93 |
+
],
|
| 94 |
+
"partial_rotary_factor": 0.25,
|
| 95 |
+
"rope_theta": 10000000,
|
| 96 |
+
"rope_type": "default"
|
| 97 |
+
},
|
| 98 |
+
"router_aux_loss_coef": 0.001,
|
| 99 |
+
"shared_expert_intermediate_size": 512,
|
| 100 |
+
"tie_word_embeddings": false,
|
| 101 |
+
"use_cache": false,
|
| 102 |
+
"vocab_size": 248320
|
| 103 |
+
},
|
| 104 |
+
"tie_word_embeddings": false,
|
| 105 |
+
"transformers_version": "5.2.0",
|
| 106 |
+
"use_cache": false,
|
| 107 |
+
"video_token_id": 248057,
|
| 108 |
+
"vision_config": {
|
| 109 |
+
"deepstack_visual_indexes": [],
|
| 110 |
+
"depth": 27,
|
| 111 |
+
"dtype": "bfloat16",
|
| 112 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 113 |
+
"hidden_size": 1152,
|
| 114 |
+
"in_channels": 3,
|
| 115 |
+
"initializer_range": 0.02,
|
| 116 |
+
"intermediate_size": 4304,
|
| 117 |
+
"model_type": "qwen3_5_moe",
|
| 118 |
+
"num_heads": 16,
|
| 119 |
+
"num_position_embeddings": 2304,
|
| 120 |
+
"out_hidden_size": 2048,
|
| 121 |
+
"patch_size": 16,
|
| 122 |
+
"spatial_merge_size": 2,
|
| 123 |
+
"temporal_patch_size": 2
|
| 124 |
+
},
|
| 125 |
+
"vision_end_token_id": 248054,
|
| 126 |
+
"vision_start_token_id": 248053
|
| 127 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248046,
|
| 5 |
+
248046,
|
| 6 |
+
248044
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 248044,
|
| 9 |
+
"temperature": 1.0,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.95,
|
| 12 |
+
"transformers_version": "5.2.0"
|
| 13 |
+
}
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9e20e63866142c1e869a650a2380a86bb9157c50c102db912ac09a53936b534b
|
| 3 |
+
size 49742567544
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7d9d46149fcfd5b7b772bc51b1b4ff48581f9c04613784604b3f2a4789e7e7a3
|
| 3 |
+
size 20476251592
|
model.safetensors.index.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
processor_config.json
ADDED
|
@@ -0,0 +1,63 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"image_processor": {
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"do_convert_rgb": true,
|
| 5 |
+
"do_normalize": true,
|
| 6 |
+
"do_rescale": true,
|
| 7 |
+
"do_resize": true,
|
| 8 |
+
"image_mean": [
|
| 9 |
+
0.5,
|
| 10 |
+
0.5,
|
| 11 |
+
0.5
|
| 12 |
+
],
|
| 13 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 14 |
+
"image_std": [
|
| 15 |
+
0.5,
|
| 16 |
+
0.5,
|
| 17 |
+
0.5
|
| 18 |
+
],
|
| 19 |
+
"merge_size": 2,
|
| 20 |
+
"patch_size": 16,
|
| 21 |
+
"resample": 3,
|
| 22 |
+
"rescale_factor": 0.00392156862745098,
|
| 23 |
+
"size": {
|
| 24 |
+
"longest_edge": 16777216,
|
| 25 |
+
"shortest_edge": 65536
|
| 26 |
+
},
|
| 27 |
+
"temporal_patch_size": 2
|
| 28 |
+
},
|
| 29 |
+
"processor_class": "Qwen3VLProcessor",
|
| 30 |
+
"video_processor": {
|
| 31 |
+
"data_format": "channels_first",
|
| 32 |
+
"default_to_square": true,
|
| 33 |
+
"do_convert_rgb": true,
|
| 34 |
+
"do_normalize": true,
|
| 35 |
+
"do_rescale": true,
|
| 36 |
+
"do_resize": true,
|
| 37 |
+
"do_sample_frames": true,
|
| 38 |
+
"fps": 2,
|
| 39 |
+
"image_mean": [
|
| 40 |
+
0.5,
|
| 41 |
+
0.5,
|
| 42 |
+
0.5
|
| 43 |
+
],
|
| 44 |
+
"image_std": [
|
| 45 |
+
0.5,
|
| 46 |
+
0.5,
|
| 47 |
+
0.5
|
| 48 |
+
],
|
| 49 |
+
"max_frames": 768,
|
| 50 |
+
"merge_size": 2,
|
| 51 |
+
"min_frames": 4,
|
| 52 |
+
"patch_size": 16,
|
| 53 |
+
"resample": 3,
|
| 54 |
+
"rescale_factor": 0.00392156862745098,
|
| 55 |
+
"return_metadata": false,
|
| 56 |
+
"size": {
|
| 57 |
+
"longest_edge": 25165824,
|
| 58 |
+
"shortest_edge": 4096
|
| 59 |
+
},
|
| 60 |
+
"temporal_patch_size": 2,
|
| 61 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 62 |
+
}
|
| 63 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87a7830d63fcf43bf241c3c5242e96e62dd3fdc29224ca26fed8ea333db72de4
|
| 3 |
+
size 19989343
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,33 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"image_token": "<|image_pad|>",
|
| 12 |
+
"is_local": false,
|
| 13 |
+
"model_max_length": 262144,
|
| 14 |
+
"model_specific_special_tokens": {
|
| 15 |
+
"audio_bos_token": "<|audio_start|>",
|
| 16 |
+
"audio_eos_token": "<|audio_end|>",
|
| 17 |
+
"audio_token": "<|audio_pad|>",
|
| 18 |
+
"image_token": "<|image_pad|>",
|
| 19 |
+
"video_token": "<|video_pad|>",
|
| 20 |
+
"vision_bos_token": "<|vision_start|>",
|
| 21 |
+
"vision_eos_token": "<|vision_end|>"
|
| 22 |
+
},
|
| 23 |
+
"pad_token": "<|endoftext|>",
|
| 24 |
+
"padding_side": "right",
|
| 25 |
+
"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+",
|
| 26 |
+
"processor_class": "Qwen3VLProcessor",
|
| 27 |
+
"split_special_tokens": false,
|
| 28 |
+
"tokenizer_class": "TokenizersBackend",
|
| 29 |
+
"unk_token": null,
|
| 30 |
+
"video_token": "<|video_pad|>",
|
| 31 |
+
"vision_bos_token": "<|vision_start|>",
|
| 32 |
+
"vision_eos_token": "<|vision_end|>"
|
| 33 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,160 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 1, "total_steps": 159, "loss": 1.3308970928192139, "lr": 0.0, "epoch": 0.018867924528301886, "percentage": 0.63, "elapsed_time": "0:00:17", "remaining_time": "0:46:35"}
|
| 2 |
+
{"current_steps": 2, "total_steps": 159, "loss": 1.285962700843811, "lr": 1e-07, "epoch": 0.03773584905660377, "percentage": 1.26, "elapsed_time": "0:00:27", "remaining_time": "0:36:07"}
|
| 3 |
+
{"current_steps": 3, "total_steps": 159, "loss": 1.3014495372772217, "lr": 2e-07, "epoch": 0.05660377358490566, "percentage": 1.89, "elapsed_time": "0:00:36", "remaining_time": "0:31:36"}
|
| 4 |
+
{"current_steps": 4, "total_steps": 159, "loss": 1.306698203086853, "lr": 3e-07, "epoch": 0.07547169811320754, "percentage": 2.52, "elapsed_time": "0:00:46", "remaining_time": "0:30:02"}
|
| 5 |
+
{"current_steps": 5, "total_steps": 159, "loss": 1.316192388534546, "lr": 4e-07, "epoch": 0.09433962264150944, "percentage": 3.14, "elapsed_time": "0:00:55", "remaining_time": "0:28:20"}
|
| 6 |
+
{"current_steps": 6, "total_steps": 159, "loss": 1.3045374155044556, "lr": 5e-07, "epoch": 0.11320754716981132, "percentage": 3.77, "elapsed_time": "0:01:04", "remaining_time": "0:27:21"}
|
| 7 |
+
{"current_steps": 7, "total_steps": 159, "loss": 1.3311705589294434, "lr": 6e-07, "epoch": 0.1320754716981132, "percentage": 4.4, "elapsed_time": "0:01:14", "remaining_time": "0:26:51"}
|
| 8 |
+
{"current_steps": 8, "total_steps": 159, "loss": 1.2908077239990234, "lr": 7e-07, "epoch": 0.1509433962264151, "percentage": 5.03, "elapsed_time": "0:01:22", "remaining_time": "0:25:59"}
|
| 9 |
+
{"current_steps": 9, "total_steps": 159, "loss": 1.3058435916900635, "lr": 8e-07, "epoch": 0.16981132075471697, "percentage": 5.66, "elapsed_time": "0:01:30", "remaining_time": "0:25:14"}
|
| 10 |
+
{"current_steps": 10, "total_steps": 159, "loss": 1.2856130599975586, "lr": 9e-07, "epoch": 0.18867924528301888, "percentage": 6.29, "elapsed_time": "0:01:38", "remaining_time": "0:24:28"}
|
| 11 |
+
{"current_steps": 11, "total_steps": 159, "loss": 1.2199636697769165, "lr": 1e-06, "epoch": 0.20754716981132076, "percentage": 6.92, "elapsed_time": "0:01:46", "remaining_time": "0:23:56"}
|
| 12 |
+
{"current_steps": 12, "total_steps": 159, "loss": 1.1673463582992554, "lr": 9.99888864929809e-07, "epoch": 0.22641509433962265, "percentage": 7.55, "elapsed_time": "0:01:54", "remaining_time": "0:23:26"}
|
| 13 |
+
{"current_steps": 13, "total_steps": 159, "loss": 1.1699671745300293, "lr": 9.995555091232516e-07, "epoch": 0.24528301886792453, "percentage": 8.18, "elapsed_time": "0:02:02", "remaining_time": "0:22:59"}
|
| 14 |
+
{"current_steps": 14, "total_steps": 159, "loss": 1.1814613342285156, "lr": 9.990000807704114e-07, "epoch": 0.2641509433962264, "percentage": 8.81, "elapsed_time": "0:02:11", "remaining_time": "0:22:42"}
|
| 15 |
+
{"current_steps": 15, "total_steps": 159, "loss": 1.0652694702148438, "lr": 9.982228267815643e-07, "epoch": 0.2830188679245283, "percentage": 9.43, "elapsed_time": "0:02:19", "remaining_time": "0:22:21"}
|
| 16 |
+
{"current_steps": 16, "total_steps": 159, "loss": 1.0635337829589844, "lr": 9.972240926774166e-07, "epoch": 0.3018867924528302, "percentage": 10.06, "elapsed_time": "0:02:28", "remaining_time": "0:22:03"}
|
| 17 |
+
{"current_steps": 17, "total_steps": 159, "loss": 1.0902111530303955, "lr": 9.96004322435508e-07, "epoch": 0.32075471698113206, "percentage": 10.69, "elapsed_time": "0:02:36", "remaining_time": "0:21:47"}
|
| 18 |
+
{"current_steps": 18, "total_steps": 159, "loss": 1.06702721118927, "lr": 9.945640582928437e-07, "epoch": 0.33962264150943394, "percentage": 11.32, "elapsed_time": "0:02:44", "remaining_time": "0:21:28"}
|
| 19 |
+
{"current_steps": 19, "total_steps": 159, "loss": 1.0476477146148682, "lr": 9.9290394050485e-07, "epoch": 0.3584905660377358, "percentage": 11.95, "elapsed_time": "0:02:52", "remaining_time": "0:21:14"}
|
| 20 |
+
{"current_steps": 20, "total_steps": 159, "loss": 1.0617330074310303, "lr": 9.91024707060755e-07, "epoch": 0.37735849056603776, "percentage": 12.58, "elapsed_time": "0:03:01", "remaining_time": "0:20:58"}
|
| 21 |
+
{"current_steps": 21, "total_steps": 159, "loss": 1.07832932472229, "lr": 9.889271933555212e-07, "epoch": 0.39622641509433965, "percentage": 13.21, "elapsed_time": "0:03:09", "remaining_time": "0:20:42"}
|
| 22 |
+
{"current_steps": 22, "total_steps": 159, "loss": 1.0324124097824097, "lr": 9.8661233181848e-07, "epoch": 0.41509433962264153, "percentage": 13.84, "elapsed_time": "0:03:17", "remaining_time": "0:20:30"}
|
| 23 |
+
{"current_steps": 23, "total_steps": 159, "loss": 0.9815853834152222, "lr": 9.840811514988293e-07, "epoch": 0.4339622641509434, "percentage": 14.47, "elapsed_time": "0:03:25", "remaining_time": "0:20:17"}
|
| 24 |
+
{"current_steps": 24, "total_steps": 159, "loss": 1.0266845226287842, "lr": 9.813347776081788e-07, "epoch": 0.4528301886792453, "percentage": 15.09, "elapsed_time": "0:03:33", "remaining_time": "0:20:02"}
|
| 25 |
+
{"current_steps": 25, "total_steps": 159, "loss": 1.0085935592651367, "lr": 9.78374431020349e-07, "epoch": 0.4716981132075472, "percentage": 15.72, "elapsed_time": "0:03:41", "remaining_time": "0:19:48"}
|
| 26 |
+
{"current_steps": 26, "total_steps": 159, "loss": 0.9968965649604797, "lr": 9.752014277286431e-07, "epoch": 0.49056603773584906, "percentage": 16.35, "elapsed_time": "0:03:49", "remaining_time": "0:19:35"}
|
| 27 |
+
{"current_steps": 27, "total_steps": 159, "loss": 0.9803509712219238, "lr": 9.718171782608353e-07, "epoch": 0.5094339622641509, "percentage": 16.98, "elapsed_time": "0:03:57", "remaining_time": "0:19:23"}
|
| 28 |
+
{"current_steps": 28, "total_steps": 159, "loss": 0.9759021997451782, "lr": 9.682231870521345e-07, "epoch": 0.5283018867924528, "percentage": 17.61, "elapsed_time": "0:04:06", "remaining_time": "0:19:11"}
|
| 29 |
+
{"current_steps": 29, "total_steps": 159, "loss": 0.9812103509902954, "lr": 9.644210517764013e-07, "epoch": 0.5471698113207547, "percentage": 18.24, "elapsed_time": "0:04:14", "remaining_time": "0:18:59"}
|
| 30 |
+
{"current_steps": 30, "total_steps": 159, "loss": 0.9091012477874756, "lr": 9.60412462635919e-07, "epoch": 0.5660377358490566, "percentage": 18.87, "elapsed_time": "0:04:22", "remaining_time": "0:18:47"}
|
| 31 |
+
{"current_steps": 31, "total_steps": 159, "loss": 0.9503388404846191, "lr": 9.561992016100291e-07, "epoch": 0.5849056603773585, "percentage": 19.5, "elapsed_time": "0:04:30", "remaining_time": "0:18:35"}
|
| 32 |
+
{"current_steps": 32, "total_steps": 159, "loss": 0.9247981309890747, "lr": 9.517831416629716e-07, "epoch": 0.6037735849056604, "percentage": 20.13, "elapsed_time": "0:04:37", "remaining_time": "0:18:22"}
|
| 33 |
+
{"current_steps": 33, "total_steps": 159, "loss": 0.9473499655723572, "lr": 9.471662459112745e-07, "epoch": 0.6226415094339622, "percentage": 20.75, "elapsed_time": "0:04:45", "remaining_time": "0:18:11"}
|
| 34 |
+
{"current_steps": 34, "total_steps": 159, "loss": 0.9340516328811646, "lr": 9.423505667510723e-07, "epoch": 0.6415094339622641, "percentage": 21.38, "elapsed_time": "0:04:54", "remaining_time": "0:18:01"}
|
| 35 |
+
{"current_steps": 35, "total_steps": 159, "loss": 0.9248940348625183, "lr": 9.373382449457303e-07, "epoch": 0.660377358490566, "percentage": 22.01, "elapsed_time": "0:05:02", "remaining_time": "0:17:50"}
|
| 36 |
+
{"current_steps": 36, "total_steps": 159, "loss": 0.9420664310455322, "lr": 9.321315086741915e-07, "epoch": 0.6792452830188679, "percentage": 22.64, "elapsed_time": "0:05:10", "remaining_time": "0:17:39"}
|
| 37 |
+
{"current_steps": 37, "total_steps": 159, "loss": 0.9231287240982056, "lr": 9.267326725404598e-07, "epoch": 0.6981132075471698, "percentage": 23.27, "elapsed_time": "0:05:19", "remaining_time": "0:17:32"}
|
| 38 |
+
{"current_steps": 38, "total_steps": 159, "loss": 0.9293084740638733, "lr": 9.21144136544666e-07, "epoch": 0.7169811320754716, "percentage": 23.9, "elapsed_time": "0:05:27", "remaining_time": "0:17:22"}
|
| 39 |
+
{"current_steps": 39, "total_steps": 159, "loss": 0.9372609853744507, "lr": 9.153683850161705e-07, "epoch": 0.7358490566037735, "percentage": 24.53, "elapsed_time": "0:05:35", "remaining_time": "0:17:12"}
|
| 40 |
+
{"current_steps": 40, "total_steps": 159, "loss": 0.9204014539718628, "lr": 9.094079855091797e-07, "epoch": 0.7547169811320755, "percentage": 25.16, "elapsed_time": "0:05:43", "remaining_time": "0:17:03"}
|
| 41 |
+
{"current_steps": 41, "total_steps": 159, "loss": 0.9143469333648682, "lr": 9.032655876613635e-07, "epoch": 0.7735849056603774, "percentage": 25.79, "elapsed_time": "0:05:52", "remaining_time": "0:16:54"}
|
| 42 |
+
{"current_steps": 42, "total_steps": 159, "loss": 0.901626467704773, "lr": 8.96943922015986e-07, "epoch": 0.7924528301886793, "percentage": 26.42, "elapsed_time": "0:06:00", "remaining_time": "0:16:44"}
|
| 43 |
+
{"current_steps": 43, "total_steps": 159, "loss": 0.9193109273910522, "lr": 8.90445798808068e-07, "epoch": 0.8113207547169812, "percentage": 27.04, "elapsed_time": "0:06:08", "remaining_time": "0:16:34"}
|
| 44 |
+
{"current_steps": 44, "total_steps": 159, "loss": 0.9078618288040161, "lr": 8.837741067151249e-07, "epoch": 0.8301886792452831, "percentage": 27.67, "elapsed_time": "0:06:17", "remaining_time": "0:16:25"}
|
| 45 |
+
{"current_steps": 45, "total_steps": 159, "loss": 0.9032235145568848, "lr": 8.769318115730328e-07, "epoch": 0.8490566037735849, "percentage": 28.3, "elapsed_time": "0:06:25", "remaining_time": "0:16:16"}
|
| 46 |
+
{"current_steps": 46, "total_steps": 159, "loss": 0.8799638152122498, "lr": 8.699219550575952e-07, "epoch": 0.8679245283018868, "percentage": 28.93, "elapsed_time": "0:06:33", "remaining_time": "0:16:07"}
|
| 47 |
+
{"current_steps": 47, "total_steps": 159, "loss": 0.9072629809379578, "lr": 8.627476533323956e-07, "epoch": 0.8867924528301887, "percentage": 29.56, "elapsed_time": "0:06:42", "remaining_time": "0:15:58"}
|
| 48 |
+
{"current_steps": 48, "total_steps": 159, "loss": 0.879642128944397, "lr": 8.554120956635374e-07, "epoch": 0.9056603773584906, "percentage": 30.19, "elapsed_time": "0:06:50", "remaining_time": "0:15:48"}
|
| 49 |
+
{"current_steps": 49, "total_steps": 159, "loss": 0.9129672050476074, "lr": 8.479185430018858e-07, "epoch": 0.9245283018867925, "percentage": 30.82, "elapsed_time": "0:06:58", "remaining_time": "0:15:39"}
|
| 50 |
+
{"current_steps": 50, "total_steps": 159, "loss": 0.9072036147117615, "lr": 8.402703265334454e-07, "epoch": 0.9433962264150944, "percentage": 31.45, "elapsed_time": "0:07:07", "remaining_time": "0:15:31"}
|
| 51 |
+
{"current_steps": 51, "total_steps": 159, "loss": 0.8936312198638916, "lr": 8.324708461985124e-07, "epoch": 0.9622641509433962, "percentage": 32.08, "elapsed_time": "0:07:16", "remaining_time": "0:15:23"}
|
| 52 |
+
{"current_steps": 52, "total_steps": 159, "loss": 0.886029839515686, "lr": 8.245235691802643e-07, "epoch": 0.9811320754716981, "percentage": 32.7, "elapsed_time": "0:07:25", "remaining_time": "0:15:17"}
|
| 53 |
+
{"current_steps": 53, "total_steps": 159, "loss": 0.886949360370636, "lr": 8.164320283634585e-07, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "0:07:34", "remaining_time": "0:15:09"}
|
| 54 |
+
{"current_steps": 54, "total_steps": 159, "loss": 0.8734487891197205, "lr": 8.081998207639212e-07, "epoch": 1.0188679245283019, "percentage": 33.96, "elapsed_time": "0:07:45", "remaining_time": "0:15:04"}
|
| 55 |
+
{"current_steps": 55, "total_steps": 159, "loss": 0.8541756868362427, "lr": 7.998306059295302e-07, "epoch": 1.0377358490566038, "percentage": 34.59, "elapsed_time": "0:07:54", "remaining_time": "0:14:56"}
|
| 56 |
+
{"current_steps": 56, "total_steps": 159, "loss": 0.855162501335144, "lr": 7.913281043133977e-07, "epoch": 1.0566037735849056, "percentage": 35.22, "elapsed_time": "0:08:02", "remaining_time": "0:14:47"}
|
| 57 |
+
{"current_steps": 57, "total_steps": 159, "loss": 0.8469276428222656, "lr": 7.826960956199794e-07, "epoch": 1.0754716981132075, "percentage": 35.85, "elapsed_time": "0:08:10", "remaining_time": "0:14:38"}
|
| 58 |
+
{"current_steps": 58, "total_steps": 159, "loss": 0.8612252473831177, "lr": 7.739384171248434e-07, "epoch": 1.0943396226415094, "percentage": 36.48, "elapsed_time": "0:08:19", "remaining_time": "0:14:29"}
|
| 59 |
+
{"current_steps": 59, "total_steps": 159, "loss": 0.8504967093467712, "lr": 7.650589619688468e-07, "epoch": 1.1132075471698113, "percentage": 37.11, "elapsed_time": "0:08:28", "remaining_time": "0:14:21"}
|
| 60 |
+
{"current_steps": 60, "total_steps": 159, "loss": 0.8487892150878906, "lr": 7.560616774274774e-07, "epoch": 1.1320754716981132, "percentage": 37.74, "elapsed_time": "0:08:36", "remaining_time": "0:14:11"}
|
| 61 |
+
{"current_steps": 61, "total_steps": 159, "loss": 0.8430064916610718, "lr": 7.469505631561317e-07, "epoch": 1.150943396226415, "percentage": 38.36, "elapsed_time": "0:08:44", "remaining_time": "0:14:02"}
|
| 62 |
+
{"current_steps": 62, "total_steps": 159, "loss": 0.834577202796936, "lr": 7.377296694121058e-07, "epoch": 1.169811320754717, "percentage": 38.99, "elapsed_time": "0:08:52", "remaining_time": "0:13:53"}
|
| 63 |
+
{"current_steps": 63, "total_steps": 159, "loss": 0.8389214277267456, "lr": 7.284030952540936e-07, "epoch": 1.1886792452830188, "percentage": 39.62, "elapsed_time": "0:09:00", "remaining_time": "0:13:44"}
|
| 64 |
+
{"current_steps": 64, "total_steps": 159, "loss": 0.8442764282226562, "lr": 7.189749867199898e-07, "epoch": 1.2075471698113207, "percentage": 40.25, "elapsed_time": "0:09:09", "remaining_time": "0:13:36"}
|
| 65 |
+
{"current_steps": 65, "total_steps": 159, "loss": 0.802047848701477, "lr": 7.094495349838092e-07, "epoch": 1.2264150943396226, "percentage": 40.88, "elapsed_time": "0:09:17", "remaining_time": "0:13:26"}
|
| 66 |
+
{"current_steps": 66, "total_steps": 159, "loss": 0.8562427163124084, "lr": 6.998309744925411e-07, "epoch": 1.2452830188679245, "percentage": 41.51, "elapsed_time": "0:09:25", "remaining_time": "0:13:16"}
|
| 67 |
+
{"current_steps": 67, "total_steps": 159, "loss": 0.8214827179908752, "lr": 6.901235810837667e-07, "epoch": 1.2641509433962264, "percentage": 42.14, "elapsed_time": "0:09:33", "remaining_time": "0:13:07"}
|
| 68 |
+
{"current_steps": 68, "total_steps": 159, "loss": 0.7995479702949524, "lr": 6.803316700848778e-07, "epoch": 1.2830188679245282, "percentage": 42.77, "elapsed_time": "0:09:41", "remaining_time": "0:12:58"}
|
| 69 |
+
{"current_steps": 69, "total_steps": 159, "loss": 0.8077808022499084, "lr": 6.704595943947385e-07, "epoch": 1.3018867924528301, "percentage": 43.4, "elapsed_time": "0:09:49", "remaining_time": "0:12:49"}
|
| 70 |
+
{"current_steps": 70, "total_steps": 159, "loss": 0.8417398929595947, "lr": 6.605117425486481e-07, "epoch": 1.320754716981132, "percentage": 44.03, "elapsed_time": "0:09:57", "remaining_time": "0:12:39"}
|
| 71 |
+
{"current_steps": 71, "total_steps": 159, "loss": 0.8494030833244324, "lr": 6.504925367674594e-07, "epoch": 1.3396226415094339, "percentage": 44.65, "elapsed_time": "0:10:05", "remaining_time": "0:12:30"}
|
| 72 |
+
{"current_steps": 72, "total_steps": 159, "loss": 0.8620424866676331, "lr": 6.40406430991723e-07, "epoch": 1.3584905660377358, "percentage": 45.28, "elapsed_time": "0:10:13", "remaining_time": "0:12:20"}
|
| 73 |
+
{"current_steps": 73, "total_steps": 159, "loss": 0.8398749232292175, "lr": 6.302579089017327e-07, "epoch": 1.3773584905660377, "percentage": 45.91, "elapsed_time": "0:10:22", "remaining_time": "0:12:12"}
|
| 74 |
+
{"current_steps": 74, "total_steps": 159, "loss": 0.8420323133468628, "lr": 6.200514819243475e-07, "epoch": 1.3962264150943398, "percentage": 46.54, "elapsed_time": "0:10:30", "remaining_time": "0:12:04"}
|
| 75 |
+
{"current_steps": 75, "total_steps": 159, "loss": 0.8359158635139465, "lr": 6.097916872274814e-07, "epoch": 1.4150943396226414, "percentage": 47.17, "elapsed_time": "0:10:39", "remaining_time": "0:11:55"}
|
| 76 |
+
{"current_steps": 76, "total_steps": 159, "loss": 0.8336814641952515, "lr": 5.994830857031499e-07, "epoch": 1.4339622641509435, "percentage": 47.8, "elapsed_time": "0:10:47", "remaining_time": "0:11:47"}
|
| 77 |
+
{"current_steps": 77, "total_steps": 159, "loss": 0.7930982112884521, "lr": 5.891302599399684e-07, "epoch": 1.4528301886792452, "percentage": 48.43, "elapsed_time": "0:10:55", "remaining_time": "0:11:37"}
|
| 78 |
+
{"current_steps": 78, "total_steps": 159, "loss": 0.8192281723022461, "lr": 5.78737812186009e-07, "epoch": 1.4716981132075473, "percentage": 49.06, "elapsed_time": "0:11:03", "remaining_time": "0:11:29"}
|
| 79 |
+
{"current_steps": 79, "total_steps": 159, "loss": 0.8389377593994141, "lr": 5.683103623029134e-07, "epoch": 1.490566037735849, "percentage": 49.69, "elapsed_time": "0:11:12", "remaining_time": "0:11:20"}
|
| 80 |
+
{"current_steps": 80, "total_steps": 159, "loss": 0.8256187438964844, "lr": 5.578525457121806e-07, "epoch": 1.509433962264151, "percentage": 50.31, "elapsed_time": "0:11:20", "remaining_time": "0:11:12"}
|
| 81 |
+
{"current_steps": 81, "total_steps": 159, "loss": 0.8473238945007324, "lr": 5.473690113345342e-07, "epoch": 1.5283018867924527, "percentage": 50.94, "elapsed_time": "0:11:28", "remaining_time": "0:11:02"}
|
| 82 |
+
{"current_steps": 82, "total_steps": 159, "loss": 0.8165145516395569, "lr": 5.368644195232895e-07, "epoch": 1.5471698113207548, "percentage": 51.57, "elapsed_time": "0:11:36", "remaining_time": "0:10:53"}
|
| 83 |
+
{"current_steps": 83, "total_steps": 159, "loss": 0.8529609441757202, "lr": 5.263434399926398e-07, "epoch": 1.5660377358490565, "percentage": 52.2, "elapsed_time": "0:11:44", "remaining_time": "0:10:45"}
|
| 84 |
+
{"current_steps": 84, "total_steps": 159, "loss": 0.8249980211257935, "lr": 5.158107497417794e-07, "epoch": 1.5849056603773586, "percentage": 52.83, "elapsed_time": "0:11:52", "remaining_time": "0:10:36"}
|
| 85 |
+
{"current_steps": 85, "total_steps": 159, "loss": 0.7900608777999878, "lr": 5.052710309757898e-07, "epoch": 1.6037735849056602, "percentage": 53.46, "elapsed_time": "0:12:00", "remaining_time": "0:10:27"}
|
| 86 |
+
{"current_steps": 86, "total_steps": 159, "loss": 0.7917711734771729, "lr": 4.947289690242102e-07, "epoch": 1.6226415094339623, "percentage": 54.09, "elapsed_time": "0:12:08", "remaining_time": "0:10:18"}
|
| 87 |
+
{"current_steps": 87, "total_steps": 159, "loss": 0.8228881359100342, "lr": 4.841892502582205e-07, "epoch": 1.641509433962264, "percentage": 54.72, "elapsed_time": "0:12:17", "remaining_time": "0:10:09"}
|
| 88 |
+
{"current_steps": 88, "total_steps": 159, "loss": 0.8176588416099548, "lr": 4.736565600073602e-07, "epoch": 1.6603773584905661, "percentage": 55.35, "elapsed_time": "0:12:25", "remaining_time": "0:10:01"}
|
| 89 |
+
{"current_steps": 89, "total_steps": 159, "loss": 0.8315557837486267, "lr": 4.6313558047671047e-07, "epoch": 1.6792452830188678, "percentage": 55.97, "elapsed_time": "0:12:33", "remaining_time": "0:09:52"}
|
| 90 |
+
{"current_steps": 90, "total_steps": 159, "loss": 0.8079712390899658, "lr": 4.5263098866546586e-07, "epoch": 1.6981132075471699, "percentage": 56.6, "elapsed_time": "0:12:41", "remaining_time": "0:09:44"}
|
| 91 |
+
{"current_steps": 91, "total_steps": 159, "loss": 0.7854694128036499, "lr": 4.421474542878194e-07, "epoch": 1.7169811320754715, "percentage": 57.23, "elapsed_time": "0:12:49", "remaining_time": "0:09:35"}
|
| 92 |
+
{"current_steps": 92, "total_steps": 159, "loss": 0.8382487297058105, "lr": 4.316896376970866e-07, "epoch": 1.7358490566037736, "percentage": 57.86, "elapsed_time": "0:12:57", "remaining_time": "0:09:26"}
|
| 93 |
+
{"current_steps": 93, "total_steps": 159, "loss": 0.8337287902832031, "lr": 4.2126218781399114e-07, "epoch": 1.7547169811320755, "percentage": 58.49, "elapsed_time": "0:13:05", "remaining_time": "0:09:17"}
|
| 94 |
+
{"current_steps": 94, "total_steps": 159, "loss": 0.8450314402580261, "lr": 4.1086974006003154e-07, "epoch": 1.7735849056603774, "percentage": 59.12, "elapsed_time": "0:13:13", "remaining_time": "0:09:08"}
|
| 95 |
+
{"current_steps": 95, "total_steps": 159, "loss": 0.7846765518188477, "lr": 4.0051691429685023e-07, "epoch": 1.7924528301886793, "percentage": 59.75, "elapsed_time": "0:13:22", "remaining_time": "0:09:00"}
|
| 96 |
+
{"current_steps": 96, "total_steps": 159, "loss": 0.814504861831665, "lr": 3.902083127725186e-07, "epoch": 1.8113207547169812, "percentage": 60.38, "elapsed_time": "0:13:30", "remaining_time": "0:08:52"}
|
| 97 |
+
{"current_steps": 97, "total_steps": 159, "loss": 0.8011671304702759, "lr": 3.799485180756525e-07, "epoch": 1.830188679245283, "percentage": 61.01, "elapsed_time": "0:13:38", "remaining_time": "0:08:43"}
|
| 98 |
+
{"current_steps": 98, "total_steps": 159, "loss": 0.8165295124053955, "lr": 3.697420910982672e-07, "epoch": 1.849056603773585, "percentage": 61.64, "elapsed_time": "0:13:47", "remaining_time": "0:08:34"}
|
| 99 |
+
{"current_steps": 99, "total_steps": 159, "loss": 0.8199301958084106, "lr": 3.5959356900827687e-07, "epoch": 1.8679245283018868, "percentage": 62.26, "elapsed_time": "0:13:55", "remaining_time": "0:08:26"}
|
| 100 |
+
{"current_steps": 100, "total_steps": 159, "loss": 0.8019869327545166, "lr": 3.4950746323254063e-07, "epoch": 1.8867924528301887, "percentage": 62.89, "elapsed_time": "0:14:03", "remaining_time": "0:08:17"}
|
| 101 |
+
{"current_steps": 101, "total_steps": 159, "loss": 0.8060827255249023, "lr": 3.394882574513519e-07, "epoch": 1.9056603773584906, "percentage": 63.52, "elapsed_time": "0:14:11", "remaining_time": "0:08:09"}
|
| 102 |
+
{"current_steps": 102, "total_steps": 159, "loss": 0.8078351020812988, "lr": 3.295404056052616e-07, "epoch": 1.9245283018867925, "percentage": 64.15, "elapsed_time": "0:14:20", "remaining_time": "0:08:00"}
|
| 103 |
+
{"current_steps": 103, "total_steps": 159, "loss": 0.8068495988845825, "lr": 3.1966832991512225e-07, "epoch": 1.9433962264150944, "percentage": 64.78, "elapsed_time": "0:14:28", "remaining_time": "0:07:52"}
|
| 104 |
+
{"current_steps": 104, "total_steps": 159, "loss": 0.8184278011322021, "lr": 3.0987641891623315e-07, "epoch": 1.9622641509433962, "percentage": 65.41, "elapsed_time": "0:14:36", "remaining_time": "0:07:43"}
|
| 105 |
+
{"current_steps": 105, "total_steps": 159, "loss": 0.8299746513366699, "lr": 3.0016902550745895e-07, "epoch": 1.9811320754716981, "percentage": 66.04, "elapsed_time": "0:14:45", "remaining_time": "0:07:35"}
|
| 106 |
+
{"current_steps": 106, "total_steps": 159, "loss": 0.785747766494751, "lr": 2.9055046501619083e-07, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "0:14:53", "remaining_time": "0:07:26"}
|
| 107 |
+
{"current_steps": 107, "total_steps": 159, "loss": 0.7670397758483887, "lr": 2.810250132800103e-07, "epoch": 2.018867924528302, "percentage": 67.3, "elapsed_time": "0:15:03", "remaining_time": "0:07:18"}
|
| 108 |
+
{"current_steps": 108, "total_steps": 159, "loss": 0.7878092527389526, "lr": 2.715969047459066e-07, "epoch": 2.0377358490566038, "percentage": 67.92, "elapsed_time": "0:15:11", "remaining_time": "0:07:10"}
|
| 109 |
+
{"current_steps": 109, "total_steps": 159, "loss": 0.7904379367828369, "lr": 2.6227033058789403e-07, "epoch": 2.056603773584906, "percentage": 68.55, "elapsed_time": "0:15:19", "remaining_time": "0:07:01"}
|
| 110 |
+
{"current_steps": 110, "total_steps": 159, "loss": 0.8011707067489624, "lr": 2.5304943684386825e-07, "epoch": 2.0754716981132075, "percentage": 69.18, "elapsed_time": "0:15:28", "remaining_time": "0:06:53"}
|
| 111 |
+
{"current_steps": 111, "total_steps": 159, "loss": 0.7658779621124268, "lr": 2.439383225725225e-07, "epoch": 2.0943396226415096, "percentage": 69.81, "elapsed_time": "0:15:37", "remaining_time": "0:06:45"}
|
| 112 |
+
{"current_steps": 112, "total_steps": 159, "loss": 0.7720337510108948, "lr": 2.3494103803115318e-07, "epoch": 2.1132075471698113, "percentage": 70.44, "elapsed_time": "0:15:45", "remaining_time": "0:06:36"}
|
| 113 |
+
{"current_steps": 113, "total_steps": 159, "loss": 0.7842212915420532, "lr": 2.2606158287515658e-07, "epoch": 2.1320754716981134, "percentage": 71.07, "elapsed_time": "0:15:54", "remaining_time": "0:06:28"}
|
| 114 |
+
{"current_steps": 114, "total_steps": 159, "loss": 0.7690730094909668, "lr": 2.1730390438002056e-07, "epoch": 2.150943396226415, "percentage": 71.7, "elapsed_time": "0:16:03", "remaining_time": "0:06:20"}
|
| 115 |
+
{"current_steps": 115, "total_steps": 159, "loss": 0.7737655639648438, "lr": 2.0867189568660236e-07, "epoch": 2.169811320754717, "percentage": 72.33, "elapsed_time": "0:16:12", "remaining_time": "0:06:12"}
|
| 116 |
+
{"current_steps": 116, "total_steps": 159, "loss": 0.7852470278739929, "lr": 2.0016939407046986e-07, "epoch": 2.188679245283019, "percentage": 72.96, "elapsed_time": "0:16:20", "remaining_time": "0:06:03"}
|
| 117 |
+
{"current_steps": 117, "total_steps": 159, "loss": 0.7893455624580383, "lr": 1.9180017923607883e-07, "epoch": 2.207547169811321, "percentage": 73.58, "elapsed_time": "0:16:28", "remaining_time": "0:05:54"}
|
| 118 |
+
{"current_steps": 118, "total_steps": 159, "loss": 0.7634609937667847, "lr": 1.835679716365417e-07, "epoch": 2.2264150943396226, "percentage": 74.21, "elapsed_time": "0:16:36", "remaining_time": "0:05:46"}
|
| 119 |
+
{"current_steps": 119, "total_steps": 159, "loss": 0.7859703898429871, "lr": 1.7547643081973578e-07, "epoch": 2.2452830188679247, "percentage": 74.84, "elapsed_time": "0:16:45", "remaining_time": "0:05:37"}
|
| 120 |
+
{"current_steps": 120, "total_steps": 159, "loss": 0.7709099650382996, "lr": 1.6752915380148768e-07, "epoch": 2.2641509433962264, "percentage": 75.47, "elapsed_time": "0:16:53", "remaining_time": "0:05:29"}
|
| 121 |
+
{"current_steps": 121, "total_steps": 159, "loss": 0.7789061069488525, "lr": 1.5972967346655448e-07, "epoch": 2.2830188679245285, "percentage": 76.1, "elapsed_time": "0:17:01", "remaining_time": "0:05:20"}
|
| 122 |
+
{"current_steps": 122, "total_steps": 159, "loss": 0.7862054705619812, "lr": 1.5208145699811415e-07, "epoch": 2.30188679245283, "percentage": 76.73, "elapsed_time": "0:17:09", "remaining_time": "0:05:12"}
|
| 123 |
+
{"current_steps": 123, "total_steps": 159, "loss": 0.7816888689994812, "lr": 1.4458790433646263e-07, "epoch": 2.3207547169811322, "percentage": 77.36, "elapsed_time": "0:17:17", "remaining_time": "0:05:03"}
|
| 124 |
+
{"current_steps": 124, "total_steps": 159, "loss": 0.7391059398651123, "lr": 1.3725234666760427e-07, "epoch": 2.339622641509434, "percentage": 77.99, "elapsed_time": "0:17:25", "remaining_time": "0:04:55"}
|
| 125 |
+
{"current_steps": 125, "total_steps": 159, "loss": 0.7627633810043335, "lr": 1.3007804494240476e-07, "epoch": 2.358490566037736, "percentage": 78.62, "elapsed_time": "0:17:33", "remaining_time": "0:04:46"}
|
| 126 |
+
{"current_steps": 126, "total_steps": 159, "loss": 0.7769066095352173, "lr": 1.2306818842696715e-07, "epoch": 2.3773584905660377, "percentage": 79.25, "elapsed_time": "0:17:42", "remaining_time": "0:04:38"}
|
| 127 |
+
{"current_steps": 127, "total_steps": 159, "loss": 0.7934216856956482, "lr": 1.1622589328487503e-07, "epoch": 2.3962264150943398, "percentage": 79.87, "elapsed_time": "0:17:51", "remaining_time": "0:04:29"}
|
| 128 |
+
{"current_steps": 128, "total_steps": 159, "loss": 0.7673547863960266, "lr": 1.0955420119193198e-07, "epoch": 2.4150943396226414, "percentage": 80.5, "elapsed_time": "0:17:59", "remaining_time": "0:04:21"}
|
| 129 |
+
{"current_steps": 129, "total_steps": 159, "loss": 0.7849991917610168, "lr": 1.03056077984014e-07, "epoch": 2.4339622641509435, "percentage": 81.13, "elapsed_time": "0:18:08", "remaining_time": "0:04:13"}
|
| 130 |
+
{"current_steps": 130, "total_steps": 159, "loss": 0.7473263740539551, "lr": 9.673441233863661e-08, "epoch": 2.452830188679245, "percentage": 81.76, "elapsed_time": "0:18:16", "remaining_time": "0:04:04"}
|
| 131 |
+
{"current_steps": 131, "total_steps": 159, "loss": 0.784021258354187, "lr": 9.059201449082043e-08, "epoch": 2.4716981132075473, "percentage": 82.39, "elapsed_time": "0:18:24", "remaining_time": "0:03:56"}
|
| 132 |
+
{"current_steps": 132, "total_steps": 159, "loss": 0.7882828712463379, "lr": 8.463161498382949e-08, "epoch": 2.490566037735849, "percentage": 83.02, "elapsed_time": "0:18:32", "remaining_time": "0:03:47"}
|
| 133 |
+
{"current_steps": 133, "total_steps": 159, "loss": 0.7572199702262878, "lr": 7.885586345533396e-08, "epoch": 2.509433962264151, "percentage": 83.65, "elapsed_time": "0:18:40", "remaining_time": "0:03:39"}
|
| 134 |
+
{"current_steps": 134, "total_steps": 159, "loss": 0.7826784253120422, "lr": 7.326732745954e-08, "epoch": 2.5283018867924527, "percentage": 84.28, "elapsed_time": "0:18:49", "remaining_time": "0:03:30"}
|
| 135 |
+
{"current_steps": 135, "total_steps": 159, "loss": 0.7726486325263977, "lr": 6.786849132580841e-08, "epoch": 2.547169811320755, "percentage": 84.91, "elapsed_time": "0:18:57", "remaining_time": "0:03:22"}
|
| 136 |
+
{"current_steps": 136, "total_steps": 159, "loss": 0.7736940383911133, "lr": 6.266175505426957e-08, "epoch": 2.5660377358490565, "percentage": 85.53, "elapsed_time": "0:19:06", "remaining_time": "0:03:13"}
|
| 137 |
+
{"current_steps": 137, "total_steps": 159, "loss": 0.7888213396072388, "lr": 5.7649433248927794e-08, "epoch": 2.5849056603773586, "percentage": 86.16, "elapsed_time": "0:19:15", "remaining_time": "0:03:05"}
|
| 138 |
+
{"current_steps": 138, "total_steps": 159, "loss": 0.7611340284347534, "lr": 5.283375408872537e-08, "epoch": 2.6037735849056602, "percentage": 86.79, "elapsed_time": "0:19:23", "remaining_time": "0:02:57"}
|
| 139 |
+
{"current_steps": 139, "total_steps": 159, "loss": 0.779454231262207, "lr": 4.821685833702849e-08, "epoch": 2.6226415094339623, "percentage": 87.42, "elapsed_time": "0:19:32", "remaining_time": "0:02:48"}
|
| 140 |
+
{"current_steps": 140, "total_steps": 159, "loss": 0.769560694694519, "lr": 4.3800798389970863e-08, "epoch": 2.641509433962264, "percentage": 88.05, "elapsed_time": "0:19:40", "remaining_time": "0:02:40"}
|
| 141 |
+
{"current_steps": 141, "total_steps": 159, "loss": 0.7890896797180176, "lr": 3.958753736408105e-08, "epoch": 2.660377358490566, "percentage": 88.68, "elapsed_time": "0:19:48", "remaining_time": "0:02:31"}
|
| 142 |
+
{"current_steps": 142, "total_steps": 159, "loss": 0.7476776838302612, "lr": 3.557894822359864e-08, "epoch": 2.6792452830188678, "percentage": 89.31, "elapsed_time": "0:19:56", "remaining_time": "0:02:23"}
|
| 143 |
+
{"current_steps": 143, "total_steps": 159, "loss": 0.7551087737083435, "lr": 3.1776812947865384e-08, "epoch": 2.69811320754717, "percentage": 89.94, "elapsed_time": "0:20:04", "remaining_time": "0:02:14"}
|
| 144 |
+
{"current_steps": 144, "total_steps": 159, "loss": 0.7675119638442993, "lr": 2.818282173916453e-08, "epoch": 2.7169811320754715, "percentage": 90.57, "elapsed_time": "0:20:12", "remaining_time": "0:02:06"}
|
| 145 |
+
{"current_steps": 145, "total_steps": 159, "loss": 0.7670686841011047, "lr": 2.4798572271356843e-08, "epoch": 2.7358490566037736, "percentage": 91.19, "elapsed_time": "0:20:20", "remaining_time": "0:01:57"}
|
| 146 |
+
{"current_steps": 146, "total_steps": 159, "loss": 0.7993500828742981, "lr": 2.162556897965101e-08, "epoch": 2.7547169811320753, "percentage": 91.82, "elapsed_time": "0:20:28", "remaining_time": "0:01:49"}
|
| 147 |
+
{"current_steps": 147, "total_steps": 159, "loss": 0.7754116654396057, "lr": 1.8665222391821166e-08, "epoch": 2.7735849056603774, "percentage": 92.45, "elapsed_time": "0:20:37", "remaining_time": "0:01:40"}
|
| 148 |
+
{"current_steps": 148, "total_steps": 159, "loss": 0.7710179090499878, "lr": 1.5918848501170644e-08, "epoch": 2.7924528301886795, "percentage": 93.08, "elapsed_time": "0:20:45", "remaining_time": "0:01:32"}
|
| 149 |
+
{"current_steps": 149, "total_steps": 159, "loss": 0.7384580969810486, "lr": 1.3387668181519818e-08, "epoch": 2.811320754716981, "percentage": 93.71, "elapsed_time": "0:20:53", "remaining_time": "0:01:24"}
|
| 150 |
+
{"current_steps": 150, "total_steps": 159, "loss": 0.7740883827209473, "lr": 1.1072806644478738e-08, "epoch": 2.830188679245283, "percentage": 94.34, "elapsed_time": "0:21:01", "remaining_time": "0:01:15"}
|
| 151 |
+
{"current_steps": 151, "total_steps": 159, "loss": 0.7919697165489197, "lr": 8.975292939244927e-09, "epoch": 2.849056603773585, "percentage": 94.97, "elapsed_time": "0:21:10", "remaining_time": "0:01:07"}
|
| 152 |
+
{"current_steps": 152, "total_steps": 159, "loss": 0.781722903251648, "lr": 7.096059495149853e-09, "epoch": 2.867924528301887, "percentage": 95.6, "elapsed_time": "0:21:18", "remaining_time": "0:00:58"}
|
| 153 |
+
{"current_steps": 153, "total_steps": 159, "loss": 0.7471998929977417, "lr": 5.435941707156388e-09, "epoch": 2.8867924528301887, "percentage": 96.23, "elapsed_time": "0:21:26", "remaining_time": "0:00:50"}
|
| 154 |
+
{"current_steps": 154, "total_steps": 159, "loss": 0.7751771807670593, "lr": 3.995677564492039e-09, "epoch": 2.9056603773584904, "percentage": 96.86, "elapsed_time": "0:21:34", "remaining_time": "0:00:42"}
|
| 155 |
+
{"current_steps": 155, "total_steps": 159, "loss": 0.7668254375457764, "lr": 2.7759073225832597e-09, "epoch": 2.9245283018867925, "percentage": 97.48, "elapsed_time": "0:21:42", "remaining_time": "0:00:33"}
|
| 156 |
+
{"current_steps": 156, "total_steps": 159, "loss": 0.7961957454681396, "lr": 1.7771732184357901e-09, "epoch": 2.9433962264150946, "percentage": 98.11, "elapsed_time": "0:21:51", "remaining_time": "0:00:25"}
|
| 157 |
+
{"current_steps": 157, "total_steps": 159, "loss": 0.7848834991455078, "lr": 9.999192295886971e-10, "epoch": 2.9622641509433962, "percentage": 98.74, "elapsed_time": "0:22:00", "remaining_time": "0:00:16"}
|
| 158 |
+
{"current_steps": 158, "total_steps": 159, "loss": 0.777495801448822, "lr": 4.4449087674847117e-10, "epoch": 2.981132075471698, "percentage": 99.37, "elapsed_time": "0:22:08", "remaining_time": "0:00:08"}
|
| 159 |
+
{"current_steps": 159, "total_steps": 159, "loss": 0.7618961334228516, "lr": 1.1113507019094858e-10, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:22:16", "remaining_time": "0:00:00"}
|
| 160 |
+
{"current_steps": 159, "total_steps": 159, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "0:23:58", "remaining_time": "0:00:00"}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3cfe8e2eba96acad28d240c66abc8b2f184174e223eeb1e85b5997b07bbed767
|
| 3 |
+
size 7505
|