Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .ipynb_checkpoints/README-checkpoint.md +69 -0
- README.md +69 -0
- all_results.json +9 -0
- chat_template.jinja +154 -0
- config.json +113 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- processor_config.json +60 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
- train_results.json +9 -0
- trainer_log.jsonl +164 -0
- trainer_state.json +1184 -0
- training_args.bin +3 -0
- training_loss.png +0 -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
|
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen3.5-9B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: qwen35_caption_galore
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# qwen35_caption_galore
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
family_to_muon_lr = {
|
| 39 |
+
"language": _fallback(getattr(training_args, "language_muon_lr", 4e-5), language_lr),
|
| 40 |
+
"vision": _fallback(getattr(training_args, "vision_muon_lr", 1e-5), vision_lr),
|
| 41 |
+
"merger": _fallback(getattr(training_args, "merger_muon_lr", 1e-4), merger_lr),
|
| 42 |
+
}
|
| 43 |
+
|
| 44 |
+
family_to_adamw_lr = {
|
| 45 |
+
"language": _fallback(getattr(training_args, "language_adamw_lr", 1e-5), language_lr),
|
| 46 |
+
"vision": _fallback(getattr(training_args, "vision_adamw_lr", 1e-6), vision_lr),
|
| 47 |
+
"merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
|
| 48 |
+
}
|
| 49 |
+
- train_batch_size: 1
|
| 50 |
+
- eval_batch_size: 8
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- gradient_accumulation_steps: 32
|
| 54 |
+
- total_train_batch_size: 32
|
| 55 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 56 |
+
- lr_scheduler_type: cosine_with_min_lr
|
| 57 |
+
- lr_scheduler_warmup_steps: 0.05
|
| 58 |
+
- num_epochs: 1
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 5.5.0
|
| 67 |
+
- Pytorch 2.11.0+cu128
|
| 68 |
+
- Datasets 4.0.0
|
| 69 |
+
- Tokenizers 0.22.2
|
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen3.5-9B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: qwen35_caption_galore
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# qwen35_caption_galore
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
More information needed
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
family_to_muon_lr = {
|
| 39 |
+
"language": _fallback(getattr(training_args, "language_muon_lr", 4e-5), language_lr),
|
| 40 |
+
"vision": _fallback(getattr(training_args, "vision_muon_lr", 1e-5), vision_lr),
|
| 41 |
+
"merger": _fallback(getattr(training_args, "merger_muon_lr", 1e-4), merger_lr),
|
| 42 |
+
}
|
| 43 |
+
|
| 44 |
+
family_to_adamw_lr = {
|
| 45 |
+
"language": _fallback(getattr(training_args, "language_adamw_lr", 1e-5), language_lr),
|
| 46 |
+
"vision": _fallback(getattr(training_args, "vision_adamw_lr", 1e-6), vision_lr),
|
| 47 |
+
"merger": _fallback(getattr(training_args, "merger_adamw_lr", 1e-5), merger_lr),
|
| 48 |
+
}
|
| 49 |
+
- train_batch_size: 1
|
| 50 |
+
- eval_batch_size: 8
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- gradient_accumulation_steps: 32
|
| 54 |
+
- total_train_batch_size: 32
|
| 55 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 56 |
+
- lr_scheduler_type: cosine_with_min_lr
|
| 57 |
+
- lr_scheduler_warmup_steps: 0.05
|
| 58 |
+
- num_epochs: 1
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 5.5.0
|
| 67 |
+
- Pytorch 2.11.0+cu128
|
| 68 |
+
- Datasets 4.0.0
|
| 69 |
+
- Tokenizers 0.22.2
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"effective_tokens_per_sec": 4074.350224923108,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"total_flos": 8.183535699912294e+17,
|
| 5 |
+
"train_loss": 1.4031060467437138,
|
| 6 |
+
"train_runtime": 3980.916,
|
| 7 |
+
"train_samples_per_second": 2.629,
|
| 8 |
+
"train_steps_per_second": 0.082
|
| 9 |
+
}
|
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 +1,113 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3_5ForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 248046,
|
| 7 |
+
"hidden_size": 4096,
|
| 8 |
+
"image_token_id": 248056,
|
| 9 |
+
"model_type": "qwen3_5",
|
| 10 |
+
"pad_token_id": 248044,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"attn_output_gate": true,
|
| 15 |
+
"bos_token_id": null,
|
| 16 |
+
"dtype": "bfloat16",
|
| 17 |
+
"eos_token_id": 248044,
|
| 18 |
+
"full_attention_interval": 4,
|
| 19 |
+
"head_dim": 256,
|
| 20 |
+
"hidden_act": "silu",
|
| 21 |
+
"hidden_size": 4096,
|
| 22 |
+
"initializer_range": 0.02,
|
| 23 |
+
"intermediate_size": 12288,
|
| 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 |
+
],
|
| 58 |
+
"linear_conv_kernel_dim": 4,
|
| 59 |
+
"linear_key_head_dim": 128,
|
| 60 |
+
"linear_num_key_heads": 16,
|
| 61 |
+
"linear_num_value_heads": 32,
|
| 62 |
+
"linear_value_head_dim": 128,
|
| 63 |
+
"mamba_ssm_dtype": "float32",
|
| 64 |
+
"max_position_embeddings": 262144,
|
| 65 |
+
"mlp_only_layers": [],
|
| 66 |
+
"model_type": "qwen3_5_text",
|
| 67 |
+
"mtp_num_hidden_layers": 1,
|
| 68 |
+
"mtp_use_dedicated_embeddings": false,
|
| 69 |
+
"num_attention_heads": 16,
|
| 70 |
+
"num_hidden_layers": 32,
|
| 71 |
+
"num_key_value_heads": 4,
|
| 72 |
+
"pad_token_id": null,
|
| 73 |
+
"partial_rotary_factor": 0.25,
|
| 74 |
+
"rms_norm_eps": 1e-06,
|
| 75 |
+
"rope_parameters": {
|
| 76 |
+
"mrope_interleaved": true,
|
| 77 |
+
"mrope_section": [
|
| 78 |
+
11,
|
| 79 |
+
11,
|
| 80 |
+
10
|
| 81 |
+
],
|
| 82 |
+
"partial_rotary_factor": 0.25,
|
| 83 |
+
"rope_theta": 10000000,
|
| 84 |
+
"rope_type": "default"
|
| 85 |
+
},
|
| 86 |
+
"tie_word_embeddings": false,
|
| 87 |
+
"use_cache": false,
|
| 88 |
+
"vocab_size": 248320
|
| 89 |
+
},
|
| 90 |
+
"tie_word_embeddings": false,
|
| 91 |
+
"transformers_version": "5.5.0",
|
| 92 |
+
"use_cache": false,
|
| 93 |
+
"video_token_id": 248057,
|
| 94 |
+
"vision_config": {
|
| 95 |
+
"deepstack_visual_indexes": [],
|
| 96 |
+
"depth": 27,
|
| 97 |
+
"dtype": "bfloat16",
|
| 98 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 99 |
+
"hidden_size": 1152,
|
| 100 |
+
"in_channels": 3,
|
| 101 |
+
"initializer_range": 0.02,
|
| 102 |
+
"intermediate_size": 4304,
|
| 103 |
+
"model_type": "qwen3_5",
|
| 104 |
+
"num_heads": 16,
|
| 105 |
+
"num_position_embeddings": 2304,
|
| 106 |
+
"out_hidden_size": 4096,
|
| 107 |
+
"patch_size": 16,
|
| 108 |
+
"spatial_merge_size": 2,
|
| 109 |
+
"temporal_patch_size": 2
|
| 110 |
+
},
|
| 111 |
+
"vision_end_token_id": 248054,
|
| 112 |
+
"vision_start_token_id": 248053
|
| 113 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_from_model_config": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
248046,
|
| 5 |
+
248044
|
| 6 |
+
],
|
| 7 |
+
"pad_token_id": 248044,
|
| 8 |
+
"transformers_version": "5.5.0",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:632156ab8249dea449f231344353bf0a640a020392dfdac6bfed3458c8bb0963
|
| 3 |
+
size 18819740168
|
processor_config.json
ADDED
|
@@ -0,0 +1,60 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
"merge_size": 2,
|
| 48 |
+
"min_frames": 4,
|
| 49 |
+
"patch_size": 16,
|
| 50 |
+
"resample": 3,
|
| 51 |
+
"rescale_factor": 0.00392156862745098,
|
| 52 |
+
"return_metadata": false,
|
| 53 |
+
"size": {
|
| 54 |
+
"longest_edge": 25165824,
|
| 55 |
+
"shortest_edge": 4096
|
| 56 |
+
},
|
| 57 |
+
"temporal_patch_size": 2,
|
| 58 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 59 |
+
}
|
| 60 |
+
}
|
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": true,
|
| 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 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"effective_tokens_per_sec": 4074.350224923108,
|
| 3 |
+
"epoch": 1.0,
|
| 4 |
+
"total_flos": 8.183535699912294e+17,
|
| 5 |
+
"train_loss": 1.4031060467437138,
|
| 6 |
+
"train_runtime": 3980.916,
|
| 7 |
+
"train_samples_per_second": 2.629,
|
| 8 |
+
"train_steps_per_second": 0.082
|
| 9 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,164 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 2, "total_steps": 327, "loss": 1.96957528591156, "lr": 2.3529411764705885e-06, "epoch": 0.0061162079510703364, "percentage": 0.61, "elapsed_time": "0:00:46", "remaining_time": "2:05:00"}
|
| 2 |
+
{"current_steps": 4, "total_steps": 327, "loss": 2.0347838401794434, "lr": 7.058823529411766e-06, "epoch": 0.012232415902140673, "percentage": 1.22, "elapsed_time": "0:01:09", "remaining_time": "1:33:52"}
|
| 3 |
+
{"current_steps": 6, "total_steps": 327, "loss": 1.9940425157546997, "lr": 1.1764705882352942e-05, "epoch": 0.01834862385321101, "percentage": 1.83, "elapsed_time": "0:01:33", "remaining_time": "1:23:41"}
|
| 4 |
+
{"current_steps": 8, "total_steps": 327, "loss": 2.06846284866333, "lr": 1.647058823529412e-05, "epoch": 0.024464831804281346, "percentage": 2.45, "elapsed_time": "0:01:58", "remaining_time": "1:18:41"}
|
| 5 |
+
{"current_steps": 10, "total_steps": 327, "loss": 1.9072656631469727, "lr": 2.1176470588235296e-05, "epoch": 0.03058103975535168, "percentage": 3.06, "elapsed_time": "0:02:22", "remaining_time": "1:15:24"}
|
| 6 |
+
{"current_steps": 12, "total_steps": 327, "loss": 1.8469384908676147, "lr": 2.5882352941176475e-05, "epoch": 0.03669724770642202, "percentage": 3.67, "elapsed_time": "0:02:46", "remaining_time": "1:13:01"}
|
| 7 |
+
{"current_steps": 14, "total_steps": 327, "loss": 1.822761058807373, "lr": 3.0588235294117644e-05, "epoch": 0.04281345565749235, "percentage": 4.28, "elapsed_time": "0:03:10", "remaining_time": "1:11:08"}
|
| 8 |
+
{"current_steps": 16, "total_steps": 327, "loss": 1.7572168111801147, "lr": 3.529411764705883e-05, "epoch": 0.04892966360856269, "percentage": 4.89, "elapsed_time": "0:03:35", "remaining_time": "1:09:45"}
|
| 9 |
+
{"current_steps": 18, "total_steps": 327, "loss": 1.7028628587722778, "lr": 4e-05, "epoch": 0.05504587155963303, "percentage": 5.5, "elapsed_time": "0:03:58", "remaining_time": "1:08:14"}
|
| 10 |
+
{"current_steps": 20, "total_steps": 327, "loss": 1.8212647438049316, "lr": 3.999630287622123e-05, "epoch": 0.06116207951070336, "percentage": 6.12, "elapsed_time": "0:04:22", "remaining_time": "1:07:13"}
|
| 11 |
+
{"current_steps": 22, "total_steps": 327, "loss": 1.6563327312469482, "lr": 3.9985213023632064e-05, "epoch": 0.0672782874617737, "percentage": 6.73, "elapsed_time": "0:04:47", "remaining_time": "1:06:21"}
|
| 12 |
+
{"current_steps": 24, "total_steps": 327, "loss": 1.6510090827941895, "lr": 3.996673499785002e-05, "epoch": 0.07339449541284404, "percentage": 7.34, "elapsed_time": "0:05:10", "remaining_time": "1:05:21"}
|
| 13 |
+
{"current_steps": 26, "total_steps": 327, "loss": 1.5338315963745117, "lr": 3.99408763894916e-05, "epoch": 0.07951070336391437, "percentage": 7.95, "elapsed_time": "0:05:35", "remaining_time": "1:04:38"}
|
| 14 |
+
{"current_steps": 28, "total_steps": 327, "loss": 1.451381802558899, "lr": 3.9907647821054114e-05, "epoch": 0.0856269113149847, "percentage": 8.56, "elapsed_time": "0:05:59", "remaining_time": "1:04:03"}
|
| 15 |
+
{"current_steps": 30, "total_steps": 327, "loss": 1.5903527736663818, "lr": 3.986706294255207e-05, "epoch": 0.09174311926605505, "percentage": 9.17, "elapsed_time": "0:06:24", "remaining_time": "1:03:25"}
|
| 16 |
+
{"current_steps": 32, "total_steps": 327, "loss": 1.5307936668395996, "lr": 3.981913842590985e-05, "epoch": 0.09785932721712538, "percentage": 9.79, "elapsed_time": "0:06:48", "remaining_time": "1:02:42"}
|
| 17 |
+
{"current_steps": 34, "total_steps": 327, "loss": 1.413094401359558, "lr": 3.9763893958113005e-05, "epoch": 0.10397553516819572, "percentage": 10.4, "elapsed_time": "0:07:12", "remaining_time": "1:02:03"}
|
| 18 |
+
{"current_steps": 36, "total_steps": 327, "loss": 1.4268063306808472, "lr": 3.970135223312103e-05, "epoch": 0.11009174311926606, "percentage": 11.01, "elapsed_time": "0:07:36", "remaining_time": "1:01:26"}
|
| 19 |
+
{"current_steps": 38, "total_steps": 327, "loss": 1.4923566579818726, "lr": 3.96315389425449e-05, "epoch": 0.1162079510703364, "percentage": 11.62, "elapsed_time": "0:08:00", "remaining_time": "1:00:55"}
|
| 20 |
+
{"current_steps": 40, "total_steps": 327, "loss": 1.574055790901184, "lr": 3.9554482765093134e-05, "epoch": 0.12232415902140673, "percentage": 12.23, "elapsed_time": "0:08:23", "remaining_time": "1:00:11"}
|
| 21 |
+
{"current_steps": 42, "total_steps": 327, "loss": 1.415814995765686, "lr": 3.947021535479083e-05, "epoch": 0.12844036697247707, "percentage": 12.84, "elapsed_time": "0:08:47", "remaining_time": "0:59:39"}
|
| 22 |
+
{"current_steps": 44, "total_steps": 327, "loss": 1.4422385692596436, "lr": 3.937877132797649e-05, "epoch": 0.1345565749235474, "percentage": 13.46, "elapsed_time": "0:09:12", "remaining_time": "0:59:12"}
|
| 23 |
+
{"current_steps": 46, "total_steps": 327, "loss": 1.4337655305862427, "lr": 3.928018824908187e-05, "epoch": 0.14067278287461774, "percentage": 14.07, "elapsed_time": "0:09:36", "remaining_time": "0:58:41"}
|
| 24 |
+
{"current_steps": 48, "total_steps": 327, "loss": 1.5849357843399048, "lr": 3.917450661520088e-05, "epoch": 0.14678899082568808, "percentage": 14.68, "elapsed_time": "0:10:00", "remaining_time": "0:58:09"}
|
| 25 |
+
{"current_steps": 50, "total_steps": 327, "loss": 1.5441187620162964, "lr": 3.906176983945371e-05, "epoch": 0.1529051987767584, "percentage": 15.29, "elapsed_time": "0:10:23", "remaining_time": "0:57:36"}
|
| 26 |
+
{"current_steps": 52, "total_steps": 327, "loss": 1.4055734872817993, "lr": 3.894202423315306e-05, "epoch": 0.15902140672782875, "percentage": 15.9, "elapsed_time": "0:10:47", "remaining_time": "0:57:04"}
|
| 27 |
+
{"current_steps": 54, "total_steps": 327, "loss": 1.543579339981079, "lr": 3.8815318986779875e-05, "epoch": 0.1651376146788991, "percentage": 16.51, "elapsed_time": "0:11:11", "remaining_time": "0:56:33"}
|
| 28 |
+
{"current_steps": 56, "total_steps": 327, "loss": 1.4346128702163696, "lr": 3.868170614977628e-05, "epoch": 0.1712538226299694, "percentage": 17.13, "elapsed_time": "0:11:35", "remaining_time": "0:56:04"}
|
| 29 |
+
{"current_steps": 58, "total_steps": 327, "loss": 1.5318936109542847, "lr": 3.854124060916415e-05, "epoch": 0.17737003058103976, "percentage": 17.74, "elapsed_time": "0:11:59", "remaining_time": "0:55:36"}
|
| 30 |
+
{"current_steps": 60, "total_steps": 327, "loss": 1.3749366998672485, "lr": 3.839398006699797e-05, "epoch": 0.1834862385321101, "percentage": 18.35, "elapsed_time": "0:12:22", "remaining_time": "0:55:03"}
|
| 31 |
+
{"current_steps": 62, "total_steps": 327, "loss": 1.436793565750122, "lr": 3.823998501666131e-05, "epoch": 0.18960244648318042, "percentage": 18.96, "elapsed_time": "0:12:46", "remaining_time": "0:54:34"}
|
| 32 |
+
{"current_steps": 64, "total_steps": 327, "loss": 1.3264566659927368, "lr": 3.8079318718016666e-05, "epoch": 0.19571865443425077, "percentage": 19.57, "elapsed_time": "0:13:09", "remaining_time": "0:54:03"}
|
| 33 |
+
{"current_steps": 66, "total_steps": 327, "loss": 1.4578938484191895, "lr": 3.7912047171418815e-05, "epoch": 0.2018348623853211, "percentage": 20.18, "elapsed_time": "0:13:33", "remaining_time": "0:53:36"}
|
| 34 |
+
{"current_steps": 68, "total_steps": 327, "loss": 1.3888816833496094, "lr": 3.773823909060248e-05, "epoch": 0.20795107033639143, "percentage": 20.8, "elapsed_time": "0:13:57", "remaining_time": "0:53:08"}
|
| 35 |
+
{"current_steps": 70, "total_steps": 327, "loss": 1.4028871059417725, "lr": 3.755796587445528e-05, "epoch": 0.21406727828746178, "percentage": 21.41, "elapsed_time": "0:14:20", "remaining_time": "0:52:39"}
|
| 36 |
+
{"current_steps": 72, "total_steps": 327, "loss": 1.3480572700500488, "lr": 3.7371301577687666e-05, "epoch": 0.22018348623853212, "percentage": 22.02, "elapsed_time": "0:14:44", "remaining_time": "0:52:12"}
|
| 37 |
+
{"current_steps": 74, "total_steps": 327, "loss": 1.4603177309036255, "lr": 3.717832288041188e-05, "epoch": 0.22629969418960244, "percentage": 22.63, "elapsed_time": "0:15:07", "remaining_time": "0:51:43"}
|
| 38 |
+
{"current_steps": 76, "total_steps": 327, "loss": 1.4285566806793213, "lr": 3.697910905664243e-05, "epoch": 0.2324159021406728, "percentage": 23.24, "elapsed_time": "0:15:31", "remaining_time": "0:51:16"}
|
| 39 |
+
{"current_steps": 78, "total_steps": 327, "loss": 1.462870478630066, "lr": 3.6773741941730975e-05, "epoch": 0.23853211009174313, "percentage": 23.85, "elapsed_time": "0:15:55", "remaining_time": "0:50:48"}
|
| 40 |
+
{"current_steps": 80, "total_steps": 327, "loss": 1.3728106021881104, "lr": 3.656230589874905e-05, "epoch": 0.24464831804281345, "percentage": 24.46, "elapsed_time": "0:16:19", "remaining_time": "0:50:22"}
|
| 41 |
+
{"current_steps": 82, "total_steps": 327, "loss": 1.3789210319519043, "lr": 3.6344887783832474e-05, "epoch": 0.25076452599388377, "percentage": 25.08, "elapsed_time": "0:16:42", "remaining_time": "0:49:54"}
|
| 42 |
+
{"current_steps": 84, "total_steps": 327, "loss": 1.438659429550171, "lr": 3.6121576910501517e-05, "epoch": 0.25688073394495414, "percentage": 25.69, "elapsed_time": "0:17:06", "remaining_time": "0:49:30"}
|
| 43 |
+
{"current_steps": 86, "total_steps": 327, "loss": 1.4267497062683105, "lr": 3.589246501297172e-05, "epoch": 0.26299694189602446, "percentage": 26.3, "elapsed_time": "0:17:30", "remaining_time": "0:49:04"}
|
| 44 |
+
{"current_steps": 88, "total_steps": 327, "loss": 1.297946572303772, "lr": 3.565764620847024e-05, "epoch": 0.2691131498470948, "percentage": 26.91, "elapsed_time": "0:17:54", "remaining_time": "0:48:38"}
|
| 45 |
+
{"current_steps": 90, "total_steps": 327, "loss": 1.3422534465789795, "lr": 3.541721695857328e-05, "epoch": 0.27522935779816515, "percentage": 27.52, "elapsed_time": "0:18:18", "remaining_time": "0:48:11"}
|
| 46 |
+
{"current_steps": 92, "total_steps": 327, "loss": 1.3573137521743774, "lr": 3.5171276029580485e-05, "epoch": 0.28134556574923547, "percentage": 28.13, "elapsed_time": "0:18:41", "remaining_time": "0:47:43"}
|
| 47 |
+
{"current_steps": 94, "total_steps": 327, "loss": 1.4575246572494507, "lr": 3.4919924451942625e-05, "epoch": 0.2874617737003058, "percentage": 28.75, "elapsed_time": "0:19:05", "remaining_time": "0:47:18"}
|
| 48 |
+
{"current_steps": 96, "total_steps": 327, "loss": 1.3683665990829468, "lr": 3.466326547875907e-05, "epoch": 0.29357798165137616, "percentage": 29.36, "elapsed_time": "0:19:27", "remaining_time": "0:46:50"}
|
| 49 |
+
{"current_steps": 98, "total_steps": 327, "loss": 1.2624497413635254, "lr": 3.440140454336236e-05, "epoch": 0.2996941896024465, "percentage": 29.97, "elapsed_time": "0:19:51", "remaining_time": "0:46:24"}
|
| 50 |
+
{"current_steps": 100, "total_steps": 327, "loss": 1.4250640869140625, "lr": 3.413444921600705e-05, "epoch": 0.3058103975535168, "percentage": 30.58, "elapsed_time": "0:20:16", "remaining_time": "0:46:00"}
|
| 51 |
+
{"current_steps": 102, "total_steps": 327, "loss": 1.4060899019241333, "lr": 3.3862509159680775e-05, "epoch": 0.3119266055045872, "percentage": 31.19, "elapsed_time": "0:20:39", "remaining_time": "0:45:35"}
|
| 52 |
+
{"current_steps": 104, "total_steps": 327, "loss": 1.44656503200531, "lr": 3.3585696085055594e-05, "epoch": 0.3180428134556575, "percentage": 31.8, "elapsed_time": "0:21:03", "remaining_time": "0:45:10"}
|
| 53 |
+
{"current_steps": 106, "total_steps": 327, "loss": 1.5084904432296753, "lr": 3.330412370459823e-05, "epoch": 0.3241590214067278, "percentage": 32.42, "elapsed_time": "0:21:27", "remaining_time": "0:44:44"}
|
| 54 |
+
{"current_steps": 108, "total_steps": 327, "loss": 1.4001638889312744, "lr": 3.301790768585793e-05, "epoch": 0.3302752293577982, "percentage": 33.03, "elapsed_time": "0:21:51", "remaining_time": "0:44:18"}
|
| 55 |
+
{"current_steps": 110, "total_steps": 327, "loss": 1.4370101690292358, "lr": 3.272716560395123e-05, "epoch": 0.3363914373088685, "percentage": 33.64, "elapsed_time": "0:22:14", "remaining_time": "0:43:52"}
|
| 56 |
+
{"current_steps": 112, "total_steps": 327, "loss": 1.4086581468582153, "lr": 3.243201689326306e-05, "epoch": 0.3425076452599388, "percentage": 34.25, "elapsed_time": "0:22:37", "remaining_time": "0:43:26"}
|
| 57 |
+
{"current_steps": 114, "total_steps": 327, "loss": 1.389402151107788, "lr": 3.213258279838416e-05, "epoch": 0.3486238532110092, "percentage": 34.86, "elapsed_time": "0:23:01", "remaining_time": "0:43:01"}
|
| 58 |
+
{"current_steps": 116, "total_steps": 327, "loss": 1.371553897857666, "lr": 3.182898632430479e-05, "epoch": 0.3547400611620795, "percentage": 35.47, "elapsed_time": "0:23:25", "remaining_time": "0:42:37"}
|
| 59 |
+
{"current_steps": 118, "total_steps": 327, "loss": 1.4507074356079102, "lr": 3.1521352185885326e-05, "epoch": 0.36085626911314983, "percentage": 36.09, "elapsed_time": "0:23:49", "remaining_time": "0:42:12"}
|
| 60 |
+
{"current_steps": 120, "total_steps": 327, "loss": 1.3349779844284058, "lr": 3.120980675662449e-05, "epoch": 0.3669724770642202, "percentage": 36.7, "elapsed_time": "0:24:13", "remaining_time": "0:41:47"}
|
| 61 |
+
{"current_steps": 122, "total_steps": 327, "loss": 1.3503204584121704, "lr": 3.0894478016746106e-05, "epoch": 0.3730886850152905, "percentage": 37.31, "elapsed_time": "0:24:37", "remaining_time": "0:41:22"}
|
| 62 |
+
{"current_steps": 124, "total_steps": 327, "loss": 1.4363230466842651, "lr": 3.0575495500626015e-05, "epoch": 0.37920489296636084, "percentage": 37.92, "elapsed_time": "0:25:01", "remaining_time": "0:40:58"}
|
| 63 |
+
{"current_steps": 126, "total_steps": 327, "loss": 1.3254035711288452, "lr": 3.025299024358036e-05, "epoch": 0.3853211009174312, "percentage": 38.53, "elapsed_time": "0:25:25", "remaining_time": "0:40:33"}
|
| 64 |
+
{"current_steps": 128, "total_steps": 327, "loss": 1.410750389099121, "lr": 2.9927094728037422e-05, "epoch": 0.39143730886850153, "percentage": 39.14, "elapsed_time": "0:25:49", "remaining_time": "0:40:08"}
|
| 65 |
+
{"current_steps": 130, "total_steps": 327, "loss": 1.397456169128418, "lr": 2.9597942829114976e-05, "epoch": 0.39755351681957185, "percentage": 39.76, "elapsed_time": "0:26:14", "remaining_time": "0:39:45"}
|
| 66 |
+
{"current_steps": 132, "total_steps": 327, "loss": 1.3679834604263306, "lr": 2.926566975962551e-05, "epoch": 0.4036697247706422, "percentage": 40.37, "elapsed_time": "0:26:37", "remaining_time": "0:39:19"}
|
| 67 |
+
{"current_steps": 134, "total_steps": 327, "loss": 1.4191218614578247, "lr": 2.8930412014531924e-05, "epoch": 0.40978593272171254, "percentage": 40.98, "elapsed_time": "0:27:00", "remaining_time": "0:38:54"}
|
| 68 |
+
{"current_steps": 136, "total_steps": 327, "loss": 1.2690709829330444, "lr": 2.859230731487661e-05, "epoch": 0.41590214067278286, "percentage": 41.59, "elapsed_time": "0:27:24", "remaining_time": "0:38:28"}
|
| 69 |
+
{"current_steps": 138, "total_steps": 327, "loss": 1.3012070655822754, "lr": 2.8251494551206767e-05, "epoch": 0.42201834862385323, "percentage": 42.2, "elapsed_time": "0:27:48", "remaining_time": "0:38:04"}
|
| 70 |
+
{"current_steps": 140, "total_steps": 327, "loss": 1.2863593101501465, "lr": 2.7908113726519356e-05, "epoch": 0.42813455657492355, "percentage": 42.81, "elapsed_time": "0:28:12", "remaining_time": "0:37:40"}
|
| 71 |
+
{"current_steps": 142, "total_steps": 327, "loss": 1.442170262336731, "lr": 2.7562305898749054e-05, "epoch": 0.43425076452599387, "percentage": 43.43, "elapsed_time": "0:28:36", "remaining_time": "0:37:16"}
|
| 72 |
+
{"current_steps": 144, "total_steps": 327, "loss": 1.3614513874053955, "lr": 2.7214213122822864e-05, "epoch": 0.44036697247706424, "percentage": 44.04, "elapsed_time": "0:29:00", "remaining_time": "0:36:52"}
|
| 73 |
+
{"current_steps": 146, "total_steps": 327, "loss": 1.2583218812942505, "lr": 2.6863978392305118e-05, "epoch": 0.44648318042813456, "percentage": 44.65, "elapsed_time": "0:29:24", "remaining_time": "0:36:27"}
|
| 74 |
+
{"current_steps": 148, "total_steps": 327, "loss": 1.4321554899215698, "lr": 2.651174558065697e-05, "epoch": 0.4525993883792049, "percentage": 45.26, "elapsed_time": "0:29:48", "remaining_time": "0:36:02"}
|
| 75 |
+
{"current_steps": 150, "total_steps": 327, "loss": 1.414106845855713, "lr": 2.6157659382134384e-05, "epoch": 0.45871559633027525, "percentage": 45.87, "elapsed_time": "0:30:13", "remaining_time": "0:35:39"}
|
| 76 |
+
{"current_steps": 152, "total_steps": 327, "loss": 1.4366655349731445, "lr": 2.5801865252348935e-05, "epoch": 0.4648318042813456, "percentage": 46.48, "elapsed_time": "0:30:36", "remaining_time": "0:35:14"}
|
| 77 |
+
{"current_steps": 154, "total_steps": 327, "loss": 1.3970258235931396, "lr": 2.5444509348515912e-05, "epoch": 0.4709480122324159, "percentage": 47.09, "elapsed_time": "0:31:00", "remaining_time": "0:34:50"}
|
| 78 |
+
{"current_steps": 156, "total_steps": 327, "loss": 1.4000701904296875, "lr": 2.508573846941417e-05, "epoch": 0.47706422018348627, "percentage": 47.71, "elapsed_time": "0:31:24", "remaining_time": "0:34:25"}
|
| 79 |
+
{"current_steps": 158, "total_steps": 327, "loss": 1.4267001152038574, "lr": 2.472569999508238e-05, "epoch": 0.4831804281345566, "percentage": 48.32, "elapsed_time": "0:31:48", "remaining_time": "0:34:01"}
|
| 80 |
+
{"current_steps": 160, "total_steps": 327, "loss": 1.4192265272140503, "lr": 2.4364541826276638e-05, "epoch": 0.4892966360856269, "percentage": 48.93, "elapsed_time": "0:32:12", "remaining_time": "0:33:37"}
|
| 81 |
+
{"current_steps": 162, "total_steps": 327, "loss": 1.314334511756897, "lr": 2.4002412323714026e-05, "epoch": 0.4954128440366973, "percentage": 49.54, "elapsed_time": "0:32:37", "remaining_time": "0:33:13"}
|
| 82 |
+
{"current_steps": 164, "total_steps": 327, "loss": 1.355038046836853, "lr": 2.363946024712732e-05, "epoch": 0.5015290519877675, "percentage": 50.15, "elapsed_time": "0:33:01", "remaining_time": "0:32:48"}
|
| 83 |
+
{"current_steps": 166, "total_steps": 327, "loss": 1.2806464433670044, "lr": 2.3275834694155716e-05, "epoch": 0.5076452599388379, "percentage": 50.76, "elapsed_time": "0:33:25", "remaining_time": "0:32:24"}
|
| 84 |
+
{"current_steps": 168, "total_steps": 327, "loss": 1.3307536840438843, "lr": 2.2911685039096834e-05, "epoch": 0.5137614678899083, "percentage": 51.38, "elapsed_time": "0:33:48", "remaining_time": "0:32:00"}
|
| 85 |
+
{"current_steps": 170, "total_steps": 327, "loss": 1.3525010347366333, "lr": 2.2547160871544973e-05, "epoch": 0.5198776758409785, "percentage": 51.99, "elapsed_time": "0:34:12", "remaining_time": "0:31:35"}
|
| 86 |
+
{"current_steps": 172, "total_steps": 327, "loss": 1.3771812915802002, "lr": 2.2182411934941004e-05, "epoch": 0.5259938837920489, "percentage": 52.6, "elapsed_time": "0:34:35", "remaining_time": "0:31:10"}
|
| 87 |
+
{"current_steps": 174, "total_steps": 327, "loss": 1.342699408531189, "lr": 2.1817588065059008e-05, "epoch": 0.5321100917431193, "percentage": 53.21, "elapsed_time": "0:34:59", "remaining_time": "0:30:46"}
|
| 88 |
+
{"current_steps": 176, "total_steps": 327, "loss": 1.3631731271743774, "lr": 2.145283912845504e-05, "epoch": 0.5382262996941896, "percentage": 53.82, "elapsed_time": "0:35:23", "remaining_time": "0:30:22"}
|
| 89 |
+
{"current_steps": 178, "total_steps": 327, "loss": 1.3468397855758667, "lr": 2.1088314960903172e-05, "epoch": 0.5443425076452599, "percentage": 54.43, "elapsed_time": "0:35:47", "remaining_time": "0:29:57"}
|
| 90 |
+
{"current_steps": 180, "total_steps": 327, "loss": 1.3079278469085693, "lr": 2.072416530584429e-05, "epoch": 0.5504587155963303, "percentage": 55.05, "elapsed_time": "0:36:12", "remaining_time": "0:29:34"}
|
| 91 |
+
{"current_steps": 182, "total_steps": 327, "loss": 1.3927726745605469, "lr": 2.0360539752872688e-05, "epoch": 0.5565749235474006, "percentage": 55.66, "elapsed_time": "0:36:35", "remaining_time": "0:29:09"}
|
| 92 |
+
{"current_steps": 184, "total_steps": 327, "loss": 1.3745498657226562, "lr": 1.9997587676285976e-05, "epoch": 0.5626911314984709, "percentage": 56.27, "elapsed_time": "0:36:58", "remaining_time": "0:28:44"}
|
| 93 |
+
{"current_steps": 186, "total_steps": 327, "loss": 1.3934822082519531, "lr": 1.9635458173723365e-05, "epoch": 0.5688073394495413, "percentage": 56.88, "elapsed_time": "0:37:23", "remaining_time": "0:28:20"}
|
| 94 |
+
{"current_steps": 188, "total_steps": 327, "loss": 1.4668513536453247, "lr": 1.9274300004917625e-05, "epoch": 0.5749235474006116, "percentage": 57.49, "elapsed_time": "0:37:46", "remaining_time": "0:27:56"}
|
| 95 |
+
{"current_steps": 190, "total_steps": 327, "loss": 1.2894922494888306, "lr": 1.8914261530585842e-05, "epoch": 0.581039755351682, "percentage": 58.1, "elapsed_time": "0:38:10", "remaining_time": "0:27:31"}
|
| 96 |
+
{"current_steps": 192, "total_steps": 327, "loss": 1.3256540298461914, "lr": 1.855549065148409e-05, "epoch": 0.5871559633027523, "percentage": 58.72, "elapsed_time": "0:38:33", "remaining_time": "0:27:06"}
|
| 97 |
+
{"current_steps": 194, "total_steps": 327, "loss": 1.3802309036254883, "lr": 1.8198134747651067e-05, "epoch": 0.5932721712538226, "percentage": 59.33, "elapsed_time": "0:38:57", "remaining_time": "0:26:42"}
|
| 98 |
+
{"current_steps": 196, "total_steps": 327, "loss": 1.3032485246658325, "lr": 1.7842340617865625e-05, "epoch": 0.599388379204893, "percentage": 59.94, "elapsed_time": "0:39:22", "remaining_time": "0:26:18"}
|
| 99 |
+
{"current_steps": 198, "total_steps": 327, "loss": 1.236058235168457, "lr": 1.748825441934303e-05, "epoch": 0.6055045871559633, "percentage": 60.55, "elapsed_time": "0:39:45", "remaining_time": "0:25:54"}
|
| 100 |
+
{"current_steps": 200, "total_steps": 327, "loss": 1.4403380155563354, "lr": 1.713602160769489e-05, "epoch": 0.6116207951070336, "percentage": 61.16, "elapsed_time": "0:40:09", "remaining_time": "0:25:30"}
|
| 101 |
+
{"current_steps": 202, "total_steps": 327, "loss": 1.3596861362457275, "lr": 1.6785786877177145e-05, "epoch": 0.617737003058104, "percentage": 61.77, "elapsed_time": "0:40:33", "remaining_time": "0:25:05"}
|
| 102 |
+
{"current_steps": 204, "total_steps": 327, "loss": 1.3777844905853271, "lr": 1.643769410125095e-05, "epoch": 0.6238532110091743, "percentage": 62.39, "elapsed_time": "0:40:57", "remaining_time": "0:24:41"}
|
| 103 |
+
{"current_steps": 206, "total_steps": 327, "loss": 1.3549814224243164, "lr": 1.609188627348065e-05, "epoch": 0.6299694189602446, "percentage": 63.0, "elapsed_time": "0:41:21", "remaining_time": "0:24:17"}
|
| 104 |
+
{"current_steps": 208, "total_steps": 327, "loss": 1.2403396368026733, "lr": 1.574850544879324e-05, "epoch": 0.636085626911315, "percentage": 63.61, "elapsed_time": "0:41:45", "remaining_time": "0:23:53"}
|
| 105 |
+
{"current_steps": 210, "total_steps": 327, "loss": 1.3685152530670166, "lr": 1.5407692685123392e-05, "epoch": 0.6422018348623854, "percentage": 64.22, "elapsed_time": "0:42:09", "remaining_time": "0:23:29"}
|
| 106 |
+
{"current_steps": 212, "total_steps": 327, "loss": 1.3501070737838745, "lr": 1.5069587985468078e-05, "epoch": 0.6483180428134556, "percentage": 64.83, "elapsed_time": "0:42:33", "remaining_time": "0:23:05"}
|
| 107 |
+
{"current_steps": 214, "total_steps": 327, "loss": 1.292812466621399, "lr": 1.4734330240374504e-05, "epoch": 0.654434250764526, "percentage": 65.44, "elapsed_time": "0:42:57", "remaining_time": "0:22:40"}
|
| 108 |
+
{"current_steps": 216, "total_steps": 327, "loss": 1.287298560142517, "lr": 1.4402057170885026e-05, "epoch": 0.6605504587155964, "percentage": 66.06, "elapsed_time": "0:43:21", "remaining_time": "0:22:16"}
|
| 109 |
+
{"current_steps": 218, "total_steps": 327, "loss": 1.3475459814071655, "lr": 1.4072905271962585e-05, "epoch": 0.6666666666666666, "percentage": 66.67, "elapsed_time": "0:43:44", "remaining_time": "0:21:52"}
|
| 110 |
+
{"current_steps": 220, "total_steps": 327, "loss": 1.2376188039779663, "lr": 1.3747009756419657e-05, "epoch": 0.672782874617737, "percentage": 67.28, "elapsed_time": "0:44:08", "remaining_time": "0:21:28"}
|
| 111 |
+
{"current_steps": 222, "total_steps": 327, "loss": 1.315477728843689, "lr": 1.3424504499373994e-05, "epoch": 0.6788990825688074, "percentage": 67.89, "elapsed_time": "0:44:32", "remaining_time": "0:21:04"}
|
| 112 |
+
{"current_steps": 224, "total_steps": 327, "loss": 1.364182949066162, "lr": 1.31055219832539e-05, "epoch": 0.6850152905198776, "percentage": 68.5, "elapsed_time": "0:44:55", "remaining_time": "0:20:39"}
|
| 113 |
+
{"current_steps": 226, "total_steps": 327, "loss": 1.3197802305221558, "lr": 1.2790193243375521e-05, "epoch": 0.691131498470948, "percentage": 69.11, "elapsed_time": "0:45:20", "remaining_time": "0:20:15"}
|
| 114 |
+
{"current_steps": 228, "total_steps": 327, "loss": 1.2909021377563477, "lr": 1.2478647814114683e-05, "epoch": 0.6972477064220184, "percentage": 69.72, "elapsed_time": "0:45:44", "remaining_time": "0:19:51"}
|
| 115 |
+
{"current_steps": 230, "total_steps": 327, "loss": 1.2902398109436035, "lr": 1.2171013675695222e-05, "epoch": 0.7033639143730887, "percentage": 70.34, "elapsed_time": "0:46:07", "remaining_time": "0:19:27"}
|
| 116 |
+
{"current_steps": 232, "total_steps": 327, "loss": 1.3986810445785522, "lr": 1.1867417201615848e-05, "epoch": 0.709480122324159, "percentage": 70.95, "elapsed_time": "0:46:31", "remaining_time": "0:19:03"}
|
| 117 |
+
{"current_steps": 234, "total_steps": 327, "loss": 1.2758734226226807, "lr": 1.1567983106736946e-05, "epoch": 0.7155963302752294, "percentage": 71.56, "elapsed_time": "0:46:55", "remaining_time": "0:18:38"}
|
| 118 |
+
{"current_steps": 236, "total_steps": 327, "loss": 1.317265272140503, "lr": 1.1272834396048777e-05, "epoch": 0.7217125382262997, "percentage": 72.17, "elapsed_time": "0:47:19", "remaining_time": "0:18:14"}
|
| 119 |
+
{"current_steps": 238, "total_steps": 327, "loss": 1.4039820432662964, "lr": 1.0982092314142068e-05, "epoch": 0.72782874617737, "percentage": 72.78, "elapsed_time": "0:47:43", "remaining_time": "0:17:50"}
|
| 120 |
+
{"current_steps": 240, "total_steps": 327, "loss": 1.330233097076416, "lr": 1.0695876295401771e-05, "epoch": 0.7339449541284404, "percentage": 73.39, "elapsed_time": "0:48:06", "remaining_time": "0:17:26"}
|
| 121 |
+
{"current_steps": 242, "total_steps": 327, "loss": 1.3207037448883057, "lr": 1.041430391494441e-05, "epoch": 0.7400611620795107, "percentage": 74.01, "elapsed_time": "0:48:30", "remaining_time": "0:17:02"}
|
| 122 |
+
{"current_steps": 244, "total_steps": 327, "loss": 1.3986611366271973, "lr": 1.013749084031923e-05, "epoch": 0.746177370030581, "percentage": 74.62, "elapsed_time": "0:48:56", "remaining_time": "0:16:38"}
|
| 123 |
+
{"current_steps": 246, "total_steps": 327, "loss": 1.3146181106567383, "lr": 9.86555078399295e-06, "epoch": 0.7522935779816514, "percentage": 75.23, "elapsed_time": "0:49:20", "remaining_time": "0:16:14"}
|
| 124 |
+
{"current_steps": 248, "total_steps": 327, "loss": 1.3460875749588013, "lr": 9.598595456637642e-06, "epoch": 0.7584097859327217, "percentage": 75.84, "elapsed_time": "0:49:45", "remaining_time": "0:15:51"}
|
| 125 |
+
{"current_steps": 250, "total_steps": 327, "loss": 1.2672019004821777, "lr": 9.336734521240934e-06, "epoch": 0.764525993883792, "percentage": 76.45, "elapsed_time": "0:50:09", "remaining_time": "0:15:26"}
|
| 126 |
+
{"current_steps": 252, "total_steps": 327, "loss": 1.3179923295974731, "lr": 9.080075548057383e-06, "epoch": 0.7706422018348624, "percentage": 77.06, "elapsed_time": "0:50:32", "remaining_time": "0:15:02"}
|
| 127 |
+
{"current_steps": 254, "total_steps": 327, "loss": 1.4186333417892456, "lr": 8.828723970419519e-06, "epoch": 0.7767584097859327, "percentage": 77.68, "elapsed_time": "0:50:57", "remaining_time": "0:14:38"}
|
| 128 |
+
{"current_steps": 256, "total_steps": 327, "loss": 1.2970129251480103, "lr": 8.582783041426728e-06, "epoch": 0.7828746177370031, "percentage": 78.29, "elapsed_time": "0:51:21", "remaining_time": "0:14:14"}
|
| 129 |
+
{"current_steps": 258, "total_steps": 327, "loss": 1.3273588418960571, "lr": 8.342353791529765e-06, "epoch": 0.7889908256880734, "percentage": 78.9, "elapsed_time": "0:51:44", "remaining_time": "0:13:50"}
|
| 130 |
+
{"current_steps": 260, "total_steps": 327, "loss": 1.3187005519866943, "lr": 8.107534987028286e-06, "epoch": 0.7951070336391437, "percentage": 79.51, "elapsed_time": "0:52:08", "remaining_time": "0:13:26"}
|
| 131 |
+
{"current_steps": 262, "total_steps": 327, "loss": 1.288523554801941, "lr": 7.878423089498492e-06, "epoch": 0.8012232415902141, "percentage": 80.12, "elapsed_time": "0:52:33", "remaining_time": "0:13:02"}
|
| 132 |
+
{"current_steps": 264, "total_steps": 327, "loss": 1.3323516845703125, "lr": 7.655112216167533e-06, "epoch": 0.8073394495412844, "percentage": 80.73, "elapsed_time": "0:52:57", "remaining_time": "0:12:38"}
|
| 133 |
+
{"current_steps": 266, "total_steps": 327, "loss": 1.3667104244232178, "lr": 7.437694101250949e-06, "epoch": 0.8134556574923547, "percentage": 81.35, "elapsed_time": "0:53:21", "remaining_time": "0:12:14"}
|
| 134 |
+
{"current_steps": 268, "total_steps": 327, "loss": 1.354952096939087, "lr": 7.226258058269031e-06, "epoch": 0.8195718654434251, "percentage": 81.96, "elapsed_time": "0:53:45", "remaining_time": "0:11:50"}
|
| 135 |
+
{"current_steps": 270, "total_steps": 327, "loss": 1.2679226398468018, "lr": 7.020890943357573e-06, "epoch": 0.8256880733944955, "percentage": 82.57, "elapsed_time": "0:54:09", "remaining_time": "0:11:26"}
|
| 136 |
+
{"current_steps": 272, "total_steps": 327, "loss": 1.3207221031188965, "lr": 6.821677119588124e-06, "epoch": 0.8318042813455657, "percentage": 83.18, "elapsed_time": "0:54:33", "remaining_time": "0:11:01"}
|
| 137 |
+
{"current_steps": 274, "total_steps": 327, "loss": 1.4085071086883545, "lr": 6.628698422312341e-06, "epoch": 0.8379204892966361, "percentage": 83.79, "elapsed_time": "0:54:57", "remaining_time": "0:10:37"}
|
| 138 |
+
{"current_steps": 276, "total_steps": 327, "loss": 1.3547308444976807, "lr": 6.442034125544726e-06, "epoch": 0.8440366972477065, "percentage": 84.4, "elapsed_time": "0:55:22", "remaining_time": "0:10:13"}
|
| 139 |
+
{"current_steps": 278, "total_steps": 327, "loss": 1.346556305885315, "lr": 6.261760909397523e-06, "epoch": 0.8501529051987767, "percentage": 85.02, "elapsed_time": "0:55:46", "remaining_time": "0:09:49"}
|
| 140 |
+
{"current_steps": 280, "total_steps": 327, "loss": 1.3009809255599976, "lr": 6.087952828581187e-06, "epoch": 0.8562691131498471, "percentage": 85.63, "elapsed_time": "0:56:10", "remaining_time": "0:09:25"}
|
| 141 |
+
{"current_steps": 282, "total_steps": 327, "loss": 1.3994947671890259, "lr": 5.920681281983339e-06, "epoch": 0.8623853211009175, "percentage": 86.24, "elapsed_time": "0:56:34", "remaining_time": "0:09:01"}
|
| 142 |
+
{"current_steps": 284, "total_steps": 327, "loss": 1.291093111038208, "lr": 5.760014983338687e-06, "epoch": 0.8685015290519877, "percentage": 86.85, "elapsed_time": "0:56:58", "remaining_time": "0:08:37"}
|
| 143 |
+
{"current_steps": 286, "total_steps": 327, "loss": 1.2565807104110718, "lr": 5.606019933002025e-06, "epoch": 0.8746177370030581, "percentage": 87.46, "elapsed_time": "0:57:22", "remaining_time": "0:08:13"}
|
| 144 |
+
{"current_steps": 288, "total_steps": 327, "loss": 1.2513775825500488, "lr": 5.458759390835851e-06, "epoch": 0.8807339449541285, "percentage": 88.07, "elapsed_time": "0:57:46", "remaining_time": "0:07:49"}
|
| 145 |
+
{"current_steps": 290, "total_steps": 327, "loss": 1.3214612007141113, "lr": 5.318293850223726e-06, "epoch": 0.8868501529051988, "percentage": 88.69, "elapsed_time": "0:58:09", "remaining_time": "0:07:25"}
|
| 146 |
+
{"current_steps": 292, "total_steps": 327, "loss": 1.4418059587478638, "lr": 5.184681013220134e-06, "epoch": 0.8929663608562691, "percentage": 89.3, "elapsed_time": "0:58:33", "remaining_time": "0:07:01"}
|
| 147 |
+
{"current_steps": 294, "total_steps": 327, "loss": 1.3208688497543335, "lr": 5.057975766846941e-06, "epoch": 0.8990825688073395, "percentage": 89.91, "elapsed_time": "0:58:57", "remaining_time": "0:06:37"}
|
| 148 |
+
{"current_steps": 296, "total_steps": 327, "loss": 1.4112577438354492, "lr": 4.938230160546292e-06, "epoch": 0.9051987767584098, "percentage": 90.52, "elapsed_time": "0:59:20", "remaining_time": "0:06:12"}
|
| 149 |
+
{"current_steps": 298, "total_steps": 327, "loss": 1.356927514076233, "lr": 4.825493384799122e-06, "epoch": 0.9113149847094801, "percentage": 91.13, "elapsed_time": "0:59:44", "remaining_time": "0:05:48"}
|
| 150 |
+
{"current_steps": 300, "total_steps": 327, "loss": 1.3079042434692383, "lr": 4.719811750918136e-06, "epoch": 0.9174311926605505, "percentage": 91.74, "elapsed_time": "1:00:07", "remaining_time": "0:05:24"}
|
| 151 |
+
{"current_steps": 302, "total_steps": 327, "loss": 1.2854888439178467, "lr": 4.621228672023517e-06, "epoch": 0.9235474006116208, "percentage": 92.35, "elapsed_time": "1:00:31", "remaining_time": "0:05:00"}
|
| 152 |
+
{"current_steps": 304, "total_steps": 327, "loss": 1.2977776527404785, "lr": 4.529784645209172e-06, "epoch": 0.9296636085626911, "percentage": 92.97, "elapsed_time": "1:00:54", "remaining_time": "0:04:36"}
|
| 153 |
+
{"current_steps": 306, "total_steps": 327, "loss": 1.2907675504684448, "lr": 4.4455172349068696e-06, "epoch": 0.9357798165137615, "percentage": 93.58, "elapsed_time": "1:01:19", "remaining_time": "0:04:12"}
|
| 154 |
+
{"current_steps": 308, "total_steps": 327, "loss": 1.2298390865325928, "lr": 4.3684610574551e-06, "epoch": 0.9418960244648318, "percentage": 94.19, "elapsed_time": "1:01:43", "remaining_time": "0:03:48"}
|
| 155 |
+
{"current_steps": 310, "total_steps": 327, "loss": 1.3057259321212769, "lr": 4.298647766878974e-06, "epoch": 0.9480122324159022, "percentage": 94.8, "elapsed_time": "1:02:08", "remaining_time": "0:03:24"}
|
| 156 |
+
{"current_steps": 312, "total_steps": 327, "loss": 1.3313639163970947, "lr": 4.236106041887007e-06, "epoch": 0.9541284403669725, "percentage": 95.41, "elapsed_time": "1:02:31", "remaining_time": "0:03:00"}
|
| 157 |
+
{"current_steps": 314, "total_steps": 327, "loss": 1.3252257108688354, "lr": 4.180861574090156e-06, "epoch": 0.9602446483180428, "percentage": 96.02, "elapsed_time": "1:02:55", "remaining_time": "0:02:36"}
|
| 158 |
+
{"current_steps": 316, "total_steps": 327, "loss": 1.258653163909912, "lr": 4.1329370574479296e-06, "epoch": 0.9663608562691132, "percentage": 96.64, "elapsed_time": "1:03:20", "remaining_time": "0:02:12"}
|
| 159 |
+
{"current_steps": 318, "total_steps": 327, "loss": 1.3827545642852783, "lr": 4.0923521789458876e-06, "epoch": 0.9724770642201835, "percentage": 97.25, "elapsed_time": "1:03:44", "remaining_time": "0:01:48"}
|
| 160 |
+
{"current_steps": 320, "total_steps": 327, "loss": 1.2586948871612549, "lr": 4.059123610508407e-06, "epoch": 0.9785932721712538, "percentage": 97.86, "elapsed_time": "1:04:07", "remaining_time": "0:01:24"}
|
| 161 |
+
{"current_steps": 322, "total_steps": 327, "loss": 1.1728885173797607, "lr": 4.033265002149985e-06, "epoch": 0.9847094801223242, "percentage": 98.47, "elapsed_time": "1:04:31", "remaining_time": "0:01:00"}
|
| 162 |
+
{"current_steps": 324, "total_steps": 327, "loss": 1.230262041091919, "lr": 4.014786976367939e-06, "epoch": 0.9908256880733946, "percentage": 99.08, "elapsed_time": "1:04:55", "remaining_time": "0:00:36"}
|
| 163 |
+
{"current_steps": 326, "total_steps": 327, "loss": 1.3188743591308594, "lr": 4.00369712377877e-06, "epoch": 0.9969418960244648, "percentage": 99.69, "elapsed_time": "1:05:18", "remaining_time": "0:00:12"}
|
| 164 |
+
{"current_steps": 327, "total_steps": 327, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "1:06:20", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1184 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 327,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0061162079510703364,
|
| 14 |
+
"grad_norm": 0.8125,
|
| 15 |
+
"learning_rate": 2.3529411764705885e-06,
|
| 16 |
+
"loss": 1.96957528591156,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.012232415902140673,
|
| 21 |
+
"grad_norm": 0.65234375,
|
| 22 |
+
"learning_rate": 7.058823529411766e-06,
|
| 23 |
+
"loss": 2.0347838401794434,
|
| 24 |
+
"step": 4
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.01834862385321101,
|
| 28 |
+
"grad_norm": 0.578125,
|
| 29 |
+
"learning_rate": 1.1764705882352942e-05,
|
| 30 |
+
"loss": 1.9940425157546997,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.024464831804281346,
|
| 35 |
+
"grad_norm": 0.640625,
|
| 36 |
+
"learning_rate": 1.647058823529412e-05,
|
| 37 |
+
"loss": 2.06846284866333,
|
| 38 |
+
"step": 8
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.03058103975535168,
|
| 42 |
+
"grad_norm": 0.80859375,
|
| 43 |
+
"learning_rate": 2.1176470588235296e-05,
|
| 44 |
+
"loss": 1.9072656631469727,
|
| 45 |
+
"step": 10
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.03669724770642202,
|
| 49 |
+
"grad_norm": 0.62109375,
|
| 50 |
+
"learning_rate": 2.5882352941176475e-05,
|
| 51 |
+
"loss": 1.8469384908676147,
|
| 52 |
+
"step": 12
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.04281345565749235,
|
| 56 |
+
"grad_norm": 0.67578125,
|
| 57 |
+
"learning_rate": 3.0588235294117644e-05,
|
| 58 |
+
"loss": 1.822761058807373,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.04892966360856269,
|
| 63 |
+
"grad_norm": 0.59765625,
|
| 64 |
+
"learning_rate": 3.529411764705883e-05,
|
| 65 |
+
"loss": 1.7572168111801147,
|
| 66 |
+
"step": 16
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.05504587155963303,
|
| 70 |
+
"grad_norm": 0.45703125,
|
| 71 |
+
"learning_rate": 4e-05,
|
| 72 |
+
"loss": 1.7028628587722778,
|
| 73 |
+
"step": 18
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.06116207951070336,
|
| 77 |
+
"grad_norm": 0.6796875,
|
| 78 |
+
"learning_rate": 3.999630287622123e-05,
|
| 79 |
+
"loss": 1.8212647438049316,
|
| 80 |
+
"step": 20
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.0672782874617737,
|
| 84 |
+
"grad_norm": 0.40234375,
|
| 85 |
+
"learning_rate": 3.9985213023632064e-05,
|
| 86 |
+
"loss": 1.6563327312469482,
|
| 87 |
+
"step": 22
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.07339449541284404,
|
| 91 |
+
"grad_norm": 0.4921875,
|
| 92 |
+
"learning_rate": 3.996673499785002e-05,
|
| 93 |
+
"loss": 1.6510090827941895,
|
| 94 |
+
"step": 24
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.07951070336391437,
|
| 98 |
+
"grad_norm": 0.7109375,
|
| 99 |
+
"learning_rate": 3.99408763894916e-05,
|
| 100 |
+
"loss": 1.5338315963745117,
|
| 101 |
+
"step": 26
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.0856269113149847,
|
| 105 |
+
"grad_norm": 0.404296875,
|
| 106 |
+
"learning_rate": 3.9907647821054114e-05,
|
| 107 |
+
"loss": 1.451381802558899,
|
| 108 |
+
"step": 28
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.09174311926605505,
|
| 112 |
+
"grad_norm": 0.30859375,
|
| 113 |
+
"learning_rate": 3.986706294255207e-05,
|
| 114 |
+
"loss": 1.5903527736663818,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.09785932721712538,
|
| 119 |
+
"grad_norm": 0.5078125,
|
| 120 |
+
"learning_rate": 3.981913842590985e-05,
|
| 121 |
+
"loss": 1.5307936668395996,
|
| 122 |
+
"step": 32
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.10397553516819572,
|
| 126 |
+
"grad_norm": 0.314453125,
|
| 127 |
+
"learning_rate": 3.9763893958113005e-05,
|
| 128 |
+
"loss": 1.413094401359558,
|
| 129 |
+
"step": 34
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.11009174311926606,
|
| 133 |
+
"grad_norm": 0.625,
|
| 134 |
+
"learning_rate": 3.970135223312103e-05,
|
| 135 |
+
"loss": 1.4268063306808472,
|
| 136 |
+
"step": 36
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.1162079510703364,
|
| 140 |
+
"grad_norm": 0.291015625,
|
| 141 |
+
"learning_rate": 3.96315389425449e-05,
|
| 142 |
+
"loss": 1.4923566579818726,
|
| 143 |
+
"step": 38
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.12232415902140673,
|
| 147 |
+
"grad_norm": 0.298828125,
|
| 148 |
+
"learning_rate": 3.9554482765093134e-05,
|
| 149 |
+
"loss": 1.574055790901184,
|
| 150 |
+
"step": 40
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.12844036697247707,
|
| 154 |
+
"grad_norm": 0.474609375,
|
| 155 |
+
"learning_rate": 3.947021535479083e-05,
|
| 156 |
+
"loss": 1.415814995765686,
|
| 157 |
+
"step": 42
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.1345565749235474,
|
| 161 |
+
"grad_norm": 0.37109375,
|
| 162 |
+
"learning_rate": 3.937877132797649e-05,
|
| 163 |
+
"loss": 1.4422385692596436,
|
| 164 |
+
"step": 44
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.14067278287461774,
|
| 168 |
+
"grad_norm": 0.375,
|
| 169 |
+
"learning_rate": 3.928018824908187e-05,
|
| 170 |
+
"loss": 1.4337655305862427,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.14678899082568808,
|
| 175 |
+
"grad_norm": 0.478515625,
|
| 176 |
+
"learning_rate": 3.917450661520088e-05,
|
| 177 |
+
"loss": 1.5849357843399048,
|
| 178 |
+
"step": 48
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.1529051987767584,
|
| 182 |
+
"grad_norm": 0.578125,
|
| 183 |
+
"learning_rate": 3.906176983945371e-05,
|
| 184 |
+
"loss": 1.5441187620162964,
|
| 185 |
+
"step": 50
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.15902140672782875,
|
| 189 |
+
"grad_norm": 0.310546875,
|
| 190 |
+
"learning_rate": 3.894202423315306e-05,
|
| 191 |
+
"loss": 1.4055734872817993,
|
| 192 |
+
"step": 52
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.1651376146788991,
|
| 196 |
+
"grad_norm": 0.36328125,
|
| 197 |
+
"learning_rate": 3.8815318986779875e-05,
|
| 198 |
+
"loss": 1.543579339981079,
|
| 199 |
+
"step": 54
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.1712538226299694,
|
| 203 |
+
"grad_norm": 0.328125,
|
| 204 |
+
"learning_rate": 3.868170614977628e-05,
|
| 205 |
+
"loss": 1.4346128702163696,
|
| 206 |
+
"step": 56
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.17737003058103976,
|
| 210 |
+
"grad_norm": 0.310546875,
|
| 211 |
+
"learning_rate": 3.854124060916415e-05,
|
| 212 |
+
"loss": 1.5318936109542847,
|
| 213 |
+
"step": 58
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.1834862385321101,
|
| 217 |
+
"grad_norm": 0.4140625,
|
| 218 |
+
"learning_rate": 3.839398006699797e-05,
|
| 219 |
+
"loss": 1.3749366998672485,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.18960244648318042,
|
| 224 |
+
"grad_norm": 0.47265625,
|
| 225 |
+
"learning_rate": 3.823998501666131e-05,
|
| 226 |
+
"loss": 1.436793565750122,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.19571865443425077,
|
| 231 |
+
"grad_norm": 0.40625,
|
| 232 |
+
"learning_rate": 3.8079318718016666e-05,
|
| 233 |
+
"loss": 1.3264566659927368,
|
| 234 |
+
"step": 64
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.2018348623853211,
|
| 238 |
+
"grad_norm": 1.34375,
|
| 239 |
+
"learning_rate": 3.7912047171418815e-05,
|
| 240 |
+
"loss": 1.4578938484191895,
|
| 241 |
+
"step": 66
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.20795107033639143,
|
| 245 |
+
"grad_norm": 0.490234375,
|
| 246 |
+
"learning_rate": 3.773823909060248e-05,
|
| 247 |
+
"loss": 1.3888816833496094,
|
| 248 |
+
"step": 68
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.21406727828746178,
|
| 252 |
+
"grad_norm": 0.33984375,
|
| 253 |
+
"learning_rate": 3.755796587445528e-05,
|
| 254 |
+
"loss": 1.4028871059417725,
|
| 255 |
+
"step": 70
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.22018348623853212,
|
| 259 |
+
"grad_norm": 0.287109375,
|
| 260 |
+
"learning_rate": 3.7371301577687666e-05,
|
| 261 |
+
"loss": 1.3480572700500488,
|
| 262 |
+
"step": 72
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.22629969418960244,
|
| 266 |
+
"grad_norm": 1.4453125,
|
| 267 |
+
"learning_rate": 3.717832288041188e-05,
|
| 268 |
+
"loss": 1.4603177309036255,
|
| 269 |
+
"step": 74
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.2324159021406728,
|
| 273 |
+
"grad_norm": 0.3984375,
|
| 274 |
+
"learning_rate": 3.697910905664243e-05,
|
| 275 |
+
"loss": 1.4285566806793213,
|
| 276 |
+
"step": 76
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.23853211009174313,
|
| 280 |
+
"grad_norm": 0.353515625,
|
| 281 |
+
"learning_rate": 3.6773741941730975e-05,
|
| 282 |
+
"loss": 1.462870478630066,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.24464831804281345,
|
| 287 |
+
"grad_norm": 0.578125,
|
| 288 |
+
"learning_rate": 3.656230589874905e-05,
|
| 289 |
+
"loss": 1.3728106021881104,
|
| 290 |
+
"step": 80
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.25076452599388377,
|
| 294 |
+
"grad_norm": 0.35546875,
|
| 295 |
+
"learning_rate": 3.6344887783832474e-05,
|
| 296 |
+
"loss": 1.3789210319519043,
|
| 297 |
+
"step": 82
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.25688073394495414,
|
| 301 |
+
"grad_norm": 0.318359375,
|
| 302 |
+
"learning_rate": 3.6121576910501517e-05,
|
| 303 |
+
"loss": 1.438659429550171,
|
| 304 |
+
"step": 84
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.26299694189602446,
|
| 308 |
+
"grad_norm": 0.6796875,
|
| 309 |
+
"learning_rate": 3.589246501297172e-05,
|
| 310 |
+
"loss": 1.4267497062683105,
|
| 311 |
+
"step": 86
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.2691131498470948,
|
| 315 |
+
"grad_norm": 0.265625,
|
| 316 |
+
"learning_rate": 3.565764620847024e-05,
|
| 317 |
+
"loss": 1.297946572303772,
|
| 318 |
+
"step": 88
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.27522935779816515,
|
| 322 |
+
"grad_norm": 0.50390625,
|
| 323 |
+
"learning_rate": 3.541721695857328e-05,
|
| 324 |
+
"loss": 1.3422534465789795,
|
| 325 |
+
"step": 90
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.28134556574923547,
|
| 329 |
+
"grad_norm": 0.302734375,
|
| 330 |
+
"learning_rate": 3.5171276029580485e-05,
|
| 331 |
+
"loss": 1.3573137521743774,
|
| 332 |
+
"step": 92
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2874617737003058,
|
| 336 |
+
"grad_norm": 0.58203125,
|
| 337 |
+
"learning_rate": 3.4919924451942625e-05,
|
| 338 |
+
"loss": 1.4575246572494507,
|
| 339 |
+
"step": 94
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.29357798165137616,
|
| 343 |
+
"grad_norm": 0.376953125,
|
| 344 |
+
"learning_rate": 3.466326547875907e-05,
|
| 345 |
+
"loss": 1.3683665990829468,
|
| 346 |
+
"step": 96
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.2996941896024465,
|
| 350 |
+
"grad_norm": 0.244140625,
|
| 351 |
+
"learning_rate": 3.440140454336236e-05,
|
| 352 |
+
"loss": 1.2624497413635254,
|
| 353 |
+
"step": 98
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.3058103975535168,
|
| 357 |
+
"grad_norm": 0.369140625,
|
| 358 |
+
"learning_rate": 3.413444921600705e-05,
|
| 359 |
+
"loss": 1.4250640869140625,
|
| 360 |
+
"step": 100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.3119266055045872,
|
| 364 |
+
"grad_norm": 0.69921875,
|
| 365 |
+
"learning_rate": 3.3862509159680775e-05,
|
| 366 |
+
"loss": 1.4060899019241333,
|
| 367 |
+
"step": 102
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.3180428134556575,
|
| 371 |
+
"grad_norm": 0.416015625,
|
| 372 |
+
"learning_rate": 3.3585696085055594e-05,
|
| 373 |
+
"loss": 1.44656503200531,
|
| 374 |
+
"step": 104
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.3241590214067278,
|
| 378 |
+
"grad_norm": 0.63671875,
|
| 379 |
+
"learning_rate": 3.330412370459823e-05,
|
| 380 |
+
"loss": 1.5084904432296753,
|
| 381 |
+
"step": 106
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.3302752293577982,
|
| 385 |
+
"grad_norm": 0.408203125,
|
| 386 |
+
"learning_rate": 3.301790768585793e-05,
|
| 387 |
+
"loss": 1.4001638889312744,
|
| 388 |
+
"step": 108
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.3363914373088685,
|
| 392 |
+
"grad_norm": 0.337890625,
|
| 393 |
+
"learning_rate": 3.272716560395123e-05,
|
| 394 |
+
"loss": 1.4370101690292358,
|
| 395 |
+
"step": 110
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.3425076452599388,
|
| 399 |
+
"grad_norm": 0.61328125,
|
| 400 |
+
"learning_rate": 3.243201689326306e-05,
|
| 401 |
+
"loss": 1.4086581468582153,
|
| 402 |
+
"step": 112
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.3486238532110092,
|
| 406 |
+
"grad_norm": 0.48828125,
|
| 407 |
+
"learning_rate": 3.213258279838416e-05,
|
| 408 |
+
"loss": 1.389402151107788,
|
| 409 |
+
"step": 114
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.3547400611620795,
|
| 413 |
+
"grad_norm": 0.3515625,
|
| 414 |
+
"learning_rate": 3.182898632430479e-05,
|
| 415 |
+
"loss": 1.371553897857666,
|
| 416 |
+
"step": 116
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.36085626911314983,
|
| 420 |
+
"grad_norm": 0.392578125,
|
| 421 |
+
"learning_rate": 3.1521352185885326e-05,
|
| 422 |
+
"loss": 1.4507074356079102,
|
| 423 |
+
"step": 118
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.3669724770642202,
|
| 427 |
+
"grad_norm": 0.703125,
|
| 428 |
+
"learning_rate": 3.120980675662449e-05,
|
| 429 |
+
"loss": 1.3349779844284058,
|
| 430 |
+
"step": 120
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.3730886850152905,
|
| 434 |
+
"grad_norm": 0.357421875,
|
| 435 |
+
"learning_rate": 3.0894478016746106e-05,
|
| 436 |
+
"loss": 1.3503204584121704,
|
| 437 |
+
"step": 122
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.37920489296636084,
|
| 441 |
+
"grad_norm": 0.435546875,
|
| 442 |
+
"learning_rate": 3.0575495500626015e-05,
|
| 443 |
+
"loss": 1.4363230466842651,
|
| 444 |
+
"step": 124
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.3853211009174312,
|
| 448 |
+
"grad_norm": 0.25390625,
|
| 449 |
+
"learning_rate": 3.025299024358036e-05,
|
| 450 |
+
"loss": 1.3254035711288452,
|
| 451 |
+
"step": 126
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.39143730886850153,
|
| 455 |
+
"grad_norm": 0.357421875,
|
| 456 |
+
"learning_rate": 2.9927094728037422e-05,
|
| 457 |
+
"loss": 1.410750389099121,
|
| 458 |
+
"step": 128
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.39755351681957185,
|
| 462 |
+
"grad_norm": 0.4609375,
|
| 463 |
+
"learning_rate": 2.9597942829114976e-05,
|
| 464 |
+
"loss": 1.397456169128418,
|
| 465 |
+
"step": 130
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.4036697247706422,
|
| 469 |
+
"grad_norm": 0.5,
|
| 470 |
+
"learning_rate": 2.926566975962551e-05,
|
| 471 |
+
"loss": 1.3679834604263306,
|
| 472 |
+
"step": 132
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.40978593272171254,
|
| 476 |
+
"grad_norm": 0.380859375,
|
| 477 |
+
"learning_rate": 2.8930412014531924e-05,
|
| 478 |
+
"loss": 1.4191218614578247,
|
| 479 |
+
"step": 134
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.41590214067278286,
|
| 483 |
+
"grad_norm": 0.41796875,
|
| 484 |
+
"learning_rate": 2.859230731487661e-05,
|
| 485 |
+
"loss": 1.2690709829330444,
|
| 486 |
+
"step": 136
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.42201834862385323,
|
| 490 |
+
"grad_norm": 0.439453125,
|
| 491 |
+
"learning_rate": 2.8251494551206767e-05,
|
| 492 |
+
"loss": 1.3012070655822754,
|
| 493 |
+
"step": 138
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.42813455657492355,
|
| 497 |
+
"grad_norm": 0.3515625,
|
| 498 |
+
"learning_rate": 2.7908113726519356e-05,
|
| 499 |
+
"loss": 1.2863593101501465,
|
| 500 |
+
"step": 140
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.43425076452599387,
|
| 504 |
+
"grad_norm": 0.498046875,
|
| 505 |
+
"learning_rate": 2.7562305898749054e-05,
|
| 506 |
+
"loss": 1.442170262336731,
|
| 507 |
+
"step": 142
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.44036697247706424,
|
| 511 |
+
"grad_norm": 0.3984375,
|
| 512 |
+
"learning_rate": 2.7214213122822864e-05,
|
| 513 |
+
"loss": 1.3614513874053955,
|
| 514 |
+
"step": 144
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.44648318042813456,
|
| 518 |
+
"grad_norm": 0.28125,
|
| 519 |
+
"learning_rate": 2.6863978392305118e-05,
|
| 520 |
+
"loss": 1.2583218812942505,
|
| 521 |
+
"step": 146
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.4525993883792049,
|
| 525 |
+
"grad_norm": 0.349609375,
|
| 526 |
+
"learning_rate": 2.651174558065697e-05,
|
| 527 |
+
"loss": 1.4321554899215698,
|
| 528 |
+
"step": 148
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.45871559633027525,
|
| 532 |
+
"grad_norm": 0.341796875,
|
| 533 |
+
"learning_rate": 2.6157659382134384e-05,
|
| 534 |
+
"loss": 1.414106845855713,
|
| 535 |
+
"step": 150
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.4648318042813456,
|
| 539 |
+
"grad_norm": 0.57421875,
|
| 540 |
+
"learning_rate": 2.5801865252348935e-05,
|
| 541 |
+
"loss": 1.4366655349731445,
|
| 542 |
+
"step": 152
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.4709480122324159,
|
| 546 |
+
"grad_norm": 0.392578125,
|
| 547 |
+
"learning_rate": 2.5444509348515912e-05,
|
| 548 |
+
"loss": 1.3970258235931396,
|
| 549 |
+
"step": 154
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.47706422018348627,
|
| 553 |
+
"grad_norm": 3.078125,
|
| 554 |
+
"learning_rate": 2.508573846941417e-05,
|
| 555 |
+
"loss": 1.4000701904296875,
|
| 556 |
+
"step": 156
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.4831804281345566,
|
| 560 |
+
"grad_norm": 0.431640625,
|
| 561 |
+
"learning_rate": 2.472569999508238e-05,
|
| 562 |
+
"loss": 1.4267001152038574,
|
| 563 |
+
"step": 158
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.4892966360856269,
|
| 567 |
+
"grad_norm": 0.33203125,
|
| 568 |
+
"learning_rate": 2.4364541826276638e-05,
|
| 569 |
+
"loss": 1.4192265272140503,
|
| 570 |
+
"step": 160
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.4954128440366973,
|
| 574 |
+
"grad_norm": 0.283203125,
|
| 575 |
+
"learning_rate": 2.4002412323714026e-05,
|
| 576 |
+
"loss": 1.314334511756897,
|
| 577 |
+
"step": 162
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.5015290519877675,
|
| 581 |
+
"grad_norm": 0.56640625,
|
| 582 |
+
"learning_rate": 2.363946024712732e-05,
|
| 583 |
+
"loss": 1.355038046836853,
|
| 584 |
+
"step": 164
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.5076452599388379,
|
| 588 |
+
"grad_norm": 0.6484375,
|
| 589 |
+
"learning_rate": 2.3275834694155716e-05,
|
| 590 |
+
"loss": 1.2806464433670044,
|
| 591 |
+
"step": 166
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.5137614678899083,
|
| 595 |
+
"grad_norm": 0.6015625,
|
| 596 |
+
"learning_rate": 2.2911685039096834e-05,
|
| 597 |
+
"loss": 1.3307536840438843,
|
| 598 |
+
"step": 168
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.5198776758409785,
|
| 602 |
+
"grad_norm": 0.333984375,
|
| 603 |
+
"learning_rate": 2.2547160871544973e-05,
|
| 604 |
+
"loss": 1.3525010347366333,
|
| 605 |
+
"step": 170
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.5259938837920489,
|
| 609 |
+
"grad_norm": 0.404296875,
|
| 610 |
+
"learning_rate": 2.2182411934941004e-05,
|
| 611 |
+
"loss": 1.3771812915802002,
|
| 612 |
+
"step": 172
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.5321100917431193,
|
| 616 |
+
"grad_norm": 0.337890625,
|
| 617 |
+
"learning_rate": 2.1817588065059008e-05,
|
| 618 |
+
"loss": 1.342699408531189,
|
| 619 |
+
"step": 174
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.5382262996941896,
|
| 623 |
+
"grad_norm": 0.52734375,
|
| 624 |
+
"learning_rate": 2.145283912845504e-05,
|
| 625 |
+
"loss": 1.3631731271743774,
|
| 626 |
+
"step": 176
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.5443425076452599,
|
| 630 |
+
"grad_norm": 0.4375,
|
| 631 |
+
"learning_rate": 2.1088314960903172e-05,
|
| 632 |
+
"loss": 1.3468397855758667,
|
| 633 |
+
"step": 178
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.5504587155963303,
|
| 637 |
+
"grad_norm": 0.341796875,
|
| 638 |
+
"learning_rate": 2.072416530584429e-05,
|
| 639 |
+
"loss": 1.3079278469085693,
|
| 640 |
+
"step": 180
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.5565749235474006,
|
| 644 |
+
"grad_norm": 0.478515625,
|
| 645 |
+
"learning_rate": 2.0360539752872688e-05,
|
| 646 |
+
"loss": 1.3927726745605469,
|
| 647 |
+
"step": 182
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.5626911314984709,
|
| 651 |
+
"grad_norm": 0.71875,
|
| 652 |
+
"learning_rate": 1.9997587676285976e-05,
|
| 653 |
+
"loss": 1.3745498657226562,
|
| 654 |
+
"step": 184
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.5688073394495413,
|
| 658 |
+
"grad_norm": 0.259765625,
|
| 659 |
+
"learning_rate": 1.9635458173723365e-05,
|
| 660 |
+
"loss": 1.3934822082519531,
|
| 661 |
+
"step": 186
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.5749235474006116,
|
| 665 |
+
"grad_norm": 0.3203125,
|
| 666 |
+
"learning_rate": 1.9274300004917625e-05,
|
| 667 |
+
"loss": 1.4668513536453247,
|
| 668 |
+
"step": 188
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.581039755351682,
|
| 672 |
+
"grad_norm": 0.375,
|
| 673 |
+
"learning_rate": 1.8914261530585842e-05,
|
| 674 |
+
"loss": 1.2894922494888306,
|
| 675 |
+
"step": 190
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.5871559633027523,
|
| 679 |
+
"grad_norm": 0.322265625,
|
| 680 |
+
"learning_rate": 1.855549065148409e-05,
|
| 681 |
+
"loss": 1.3256540298461914,
|
| 682 |
+
"step": 192
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.5932721712538226,
|
| 686 |
+
"grad_norm": 0.92578125,
|
| 687 |
+
"learning_rate": 1.8198134747651067e-05,
|
| 688 |
+
"loss": 1.3802309036254883,
|
| 689 |
+
"step": 194
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.599388379204893,
|
| 693 |
+
"grad_norm": 0.33203125,
|
| 694 |
+
"learning_rate": 1.7842340617865625e-05,
|
| 695 |
+
"loss": 1.3032485246658325,
|
| 696 |
+
"step": 196
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.6055045871559633,
|
| 700 |
+
"grad_norm": 0.54296875,
|
| 701 |
+
"learning_rate": 1.748825441934303e-05,
|
| 702 |
+
"loss": 1.236058235168457,
|
| 703 |
+
"step": 198
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.6116207951070336,
|
| 707 |
+
"grad_norm": 0.376953125,
|
| 708 |
+
"learning_rate": 1.713602160769489e-05,
|
| 709 |
+
"loss": 1.4403380155563354,
|
| 710 |
+
"step": 200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.617737003058104,
|
| 714 |
+
"grad_norm": 0.359375,
|
| 715 |
+
"learning_rate": 1.6785786877177145e-05,
|
| 716 |
+
"loss": 1.3596861362457275,
|
| 717 |
+
"step": 202
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.6238532110091743,
|
| 721 |
+
"grad_norm": 0.408203125,
|
| 722 |
+
"learning_rate": 1.643769410125095e-05,
|
| 723 |
+
"loss": 1.3777844905853271,
|
| 724 |
+
"step": 204
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.6299694189602446,
|
| 728 |
+
"grad_norm": 0.4609375,
|
| 729 |
+
"learning_rate": 1.609188627348065e-05,
|
| 730 |
+
"loss": 1.3549814224243164,
|
| 731 |
+
"step": 206
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.636085626911315,
|
| 735 |
+
"grad_norm": 0.60546875,
|
| 736 |
+
"learning_rate": 1.574850544879324e-05,
|
| 737 |
+
"loss": 1.2403396368026733,
|
| 738 |
+
"step": 208
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.6422018348623854,
|
| 742 |
+
"grad_norm": 0.421875,
|
| 743 |
+
"learning_rate": 1.5407692685123392e-05,
|
| 744 |
+
"loss": 1.3685152530670166,
|
| 745 |
+
"step": 210
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.6483180428134556,
|
| 749 |
+
"grad_norm": 0.298828125,
|
| 750 |
+
"learning_rate": 1.5069587985468078e-05,
|
| 751 |
+
"loss": 1.3501070737838745,
|
| 752 |
+
"step": 212
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.654434250764526,
|
| 756 |
+
"grad_norm": 0.625,
|
| 757 |
+
"learning_rate": 1.4734330240374504e-05,
|
| 758 |
+
"loss": 1.292812466621399,
|
| 759 |
+
"step": 214
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.6605504587155964,
|
| 763 |
+
"grad_norm": 0.3125,
|
| 764 |
+
"learning_rate": 1.4402057170885026e-05,
|
| 765 |
+
"loss": 1.287298560142517,
|
| 766 |
+
"step": 216
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.6666666666666666,
|
| 770 |
+
"grad_norm": 0.27734375,
|
| 771 |
+
"learning_rate": 1.4072905271962585e-05,
|
| 772 |
+
"loss": 1.3475459814071655,
|
| 773 |
+
"step": 218
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.672782874617737,
|
| 777 |
+
"grad_norm": 0.376953125,
|
| 778 |
+
"learning_rate": 1.3747009756419657e-05,
|
| 779 |
+
"loss": 1.2376188039779663,
|
| 780 |
+
"step": 220
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.6788990825688074,
|
| 784 |
+
"grad_norm": 0.47265625,
|
| 785 |
+
"learning_rate": 1.3424504499373994e-05,
|
| 786 |
+
"loss": 1.315477728843689,
|
| 787 |
+
"step": 222
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.6850152905198776,
|
| 791 |
+
"grad_norm": 0.365234375,
|
| 792 |
+
"learning_rate": 1.31055219832539e-05,
|
| 793 |
+
"loss": 1.364182949066162,
|
| 794 |
+
"step": 224
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.691131498470948,
|
| 798 |
+
"grad_norm": 0.326171875,
|
| 799 |
+
"learning_rate": 1.2790193243375521e-05,
|
| 800 |
+
"loss": 1.3197802305221558,
|
| 801 |
+
"step": 226
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.6972477064220184,
|
| 805 |
+
"grad_norm": 0.26171875,
|
| 806 |
+
"learning_rate": 1.2478647814114683e-05,
|
| 807 |
+
"loss": 1.2909021377563477,
|
| 808 |
+
"step": 228
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.7033639143730887,
|
| 812 |
+
"grad_norm": 0.3984375,
|
| 813 |
+
"learning_rate": 1.2171013675695222e-05,
|
| 814 |
+
"loss": 1.2902398109436035,
|
| 815 |
+
"step": 230
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.709480122324159,
|
| 819 |
+
"grad_norm": 0.8515625,
|
| 820 |
+
"learning_rate": 1.1867417201615848e-05,
|
| 821 |
+
"loss": 1.3986810445785522,
|
| 822 |
+
"step": 232
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.7155963302752294,
|
| 826 |
+
"grad_norm": 0.29296875,
|
| 827 |
+
"learning_rate": 1.1567983106736946e-05,
|
| 828 |
+
"loss": 1.2758734226226807,
|
| 829 |
+
"step": 234
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 0.7217125382262997,
|
| 833 |
+
"grad_norm": 0.37109375,
|
| 834 |
+
"learning_rate": 1.1272834396048777e-05,
|
| 835 |
+
"loss": 1.317265272140503,
|
| 836 |
+
"step": 236
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 0.72782874617737,
|
| 840 |
+
"grad_norm": 3.296875,
|
| 841 |
+
"learning_rate": 1.0982092314142068e-05,
|
| 842 |
+
"loss": 1.4039820432662964,
|
| 843 |
+
"step": 238
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 0.7339449541284404,
|
| 847 |
+
"grad_norm": 0.40234375,
|
| 848 |
+
"learning_rate": 1.0695876295401771e-05,
|
| 849 |
+
"loss": 1.330233097076416,
|
| 850 |
+
"step": 240
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 0.7400611620795107,
|
| 854 |
+
"grad_norm": 1.7890625,
|
| 855 |
+
"learning_rate": 1.041430391494441e-05,
|
| 856 |
+
"loss": 1.3207037448883057,
|
| 857 |
+
"step": 242
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 0.746177370030581,
|
| 861 |
+
"grad_norm": 0.2451171875,
|
| 862 |
+
"learning_rate": 1.013749084031923e-05,
|
| 863 |
+
"loss": 1.3986611366271973,
|
| 864 |
+
"step": 244
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 0.7522935779816514,
|
| 868 |
+
"grad_norm": 0.42578125,
|
| 869 |
+
"learning_rate": 9.86555078399295e-06,
|
| 870 |
+
"loss": 1.3146181106567383,
|
| 871 |
+
"step": 246
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 0.7584097859327217,
|
| 875 |
+
"grad_norm": 0.310546875,
|
| 876 |
+
"learning_rate": 9.598595456637642e-06,
|
| 877 |
+
"loss": 1.3460875749588013,
|
| 878 |
+
"step": 248
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 0.764525993883792,
|
| 882 |
+
"grad_norm": 0.267578125,
|
| 883 |
+
"learning_rate": 9.336734521240934e-06,
|
| 884 |
+
"loss": 1.2672019004821777,
|
| 885 |
+
"step": 250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 0.7706422018348624,
|
| 889 |
+
"grad_norm": 0.291015625,
|
| 890 |
+
"learning_rate": 9.080075548057383e-06,
|
| 891 |
+
"loss": 1.3179923295974731,
|
| 892 |
+
"step": 252
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 0.7767584097859327,
|
| 896 |
+
"grad_norm": 0.703125,
|
| 897 |
+
"learning_rate": 8.828723970419519e-06,
|
| 898 |
+
"loss": 1.4186333417892456,
|
| 899 |
+
"step": 254
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 0.7828746177370031,
|
| 903 |
+
"grad_norm": 0.390625,
|
| 904 |
+
"learning_rate": 8.582783041426728e-06,
|
| 905 |
+
"loss": 1.2970129251480103,
|
| 906 |
+
"step": 256
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 0.7889908256880734,
|
| 910 |
+
"grad_norm": 0.21875,
|
| 911 |
+
"learning_rate": 8.342353791529765e-06,
|
| 912 |
+
"loss": 1.3273588418960571,
|
| 913 |
+
"step": 258
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 0.7951070336391437,
|
| 917 |
+
"grad_norm": 0.37109375,
|
| 918 |
+
"learning_rate": 8.107534987028286e-06,
|
| 919 |
+
"loss": 1.3187005519866943,
|
| 920 |
+
"step": 260
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 0.8012232415902141,
|
| 924 |
+
"grad_norm": 0.345703125,
|
| 925 |
+
"learning_rate": 7.878423089498492e-06,
|
| 926 |
+
"loss": 1.288523554801941,
|
| 927 |
+
"step": 262
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 0.8073394495412844,
|
| 931 |
+
"grad_norm": 0.6484375,
|
| 932 |
+
"learning_rate": 7.655112216167533e-06,
|
| 933 |
+
"loss": 1.3323516845703125,
|
| 934 |
+
"step": 264
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 0.8134556574923547,
|
| 938 |
+
"grad_norm": 0.345703125,
|
| 939 |
+
"learning_rate": 7.437694101250949e-06,
|
| 940 |
+
"loss": 1.3667104244232178,
|
| 941 |
+
"step": 266
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 0.8195718654434251,
|
| 945 |
+
"grad_norm": 0.294921875,
|
| 946 |
+
"learning_rate": 7.226258058269031e-06,
|
| 947 |
+
"loss": 1.354952096939087,
|
| 948 |
+
"step": 268
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 0.8256880733944955,
|
| 952 |
+
"grad_norm": 0.42578125,
|
| 953 |
+
"learning_rate": 7.020890943357573e-06,
|
| 954 |
+
"loss": 1.2679226398468018,
|
| 955 |
+
"step": 270
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 0.8318042813455657,
|
| 959 |
+
"grad_norm": 0.447265625,
|
| 960 |
+
"learning_rate": 6.821677119588124e-06,
|
| 961 |
+
"loss": 1.3207221031188965,
|
| 962 |
+
"step": 272
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 0.8379204892966361,
|
| 966 |
+
"grad_norm": 0.62109375,
|
| 967 |
+
"learning_rate": 6.628698422312341e-06,
|
| 968 |
+
"loss": 1.4085071086883545,
|
| 969 |
+
"step": 274
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 0.8440366972477065,
|
| 973 |
+
"grad_norm": 0.474609375,
|
| 974 |
+
"learning_rate": 6.442034125544726e-06,
|
| 975 |
+
"loss": 1.3547308444976807,
|
| 976 |
+
"step": 276
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 0.8501529051987767,
|
| 980 |
+
"grad_norm": 0.31640625,
|
| 981 |
+
"learning_rate": 6.261760909397523e-06,
|
| 982 |
+
"loss": 1.346556305885315,
|
| 983 |
+
"step": 278
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 0.8562691131498471,
|
| 987 |
+
"grad_norm": 0.46875,
|
| 988 |
+
"learning_rate": 6.087952828581187e-06,
|
| 989 |
+
"loss": 1.3009809255599976,
|
| 990 |
+
"step": 280
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 0.8623853211009175,
|
| 994 |
+
"grad_norm": 0.8671875,
|
| 995 |
+
"learning_rate": 5.920681281983339e-06,
|
| 996 |
+
"loss": 1.3994947671890259,
|
| 997 |
+
"step": 282
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 0.8685015290519877,
|
| 1001 |
+
"grad_norm": 0.23046875,
|
| 1002 |
+
"learning_rate": 5.760014983338687e-06,
|
| 1003 |
+
"loss": 1.291093111038208,
|
| 1004 |
+
"step": 284
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 0.8746177370030581,
|
| 1008 |
+
"grad_norm": 0.83984375,
|
| 1009 |
+
"learning_rate": 5.606019933002025e-06,
|
| 1010 |
+
"loss": 1.2565807104110718,
|
| 1011 |
+
"step": 286
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 0.8807339449541285,
|
| 1015 |
+
"grad_norm": 0.326171875,
|
| 1016 |
+
"learning_rate": 5.458759390835851e-06,
|
| 1017 |
+
"loss": 1.2513775825500488,
|
| 1018 |
+
"step": 288
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 0.8868501529051988,
|
| 1022 |
+
"grad_norm": 0.49609375,
|
| 1023 |
+
"learning_rate": 5.318293850223726e-06,
|
| 1024 |
+
"loss": 1.3214612007141113,
|
| 1025 |
+
"step": 290
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 0.8929663608562691,
|
| 1029 |
+
"grad_norm": 0.5859375,
|
| 1030 |
+
"learning_rate": 5.184681013220134e-06,
|
| 1031 |
+
"loss": 1.4418059587478638,
|
| 1032 |
+
"step": 292
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 0.8990825688073395,
|
| 1036 |
+
"grad_norm": 0.29296875,
|
| 1037 |
+
"learning_rate": 5.057975766846941e-06,
|
| 1038 |
+
"loss": 1.3208688497543335,
|
| 1039 |
+
"step": 294
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 0.9051987767584098,
|
| 1043 |
+
"grad_norm": 0.66796875,
|
| 1044 |
+
"learning_rate": 4.938230160546292e-06,
|
| 1045 |
+
"loss": 1.4112577438354492,
|
| 1046 |
+
"step": 296
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 0.9113149847094801,
|
| 1050 |
+
"grad_norm": 0.322265625,
|
| 1051 |
+
"learning_rate": 4.825493384799122e-06,
|
| 1052 |
+
"loss": 1.356927514076233,
|
| 1053 |
+
"step": 298
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 0.9174311926605505,
|
| 1057 |
+
"grad_norm": 0.357421875,
|
| 1058 |
+
"learning_rate": 4.719811750918136e-06,
|
| 1059 |
+
"loss": 1.3079042434692383,
|
| 1060 |
+
"step": 300
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 0.9235474006116208,
|
| 1064 |
+
"grad_norm": 0.40234375,
|
| 1065 |
+
"learning_rate": 4.621228672023517e-06,
|
| 1066 |
+
"loss": 1.2854888439178467,
|
| 1067 |
+
"step": 302
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 0.9296636085626911,
|
| 1071 |
+
"grad_norm": 0.2890625,
|
| 1072 |
+
"learning_rate": 4.529784645209172e-06,
|
| 1073 |
+
"loss": 1.2977776527404785,
|
| 1074 |
+
"step": 304
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 0.9357798165137615,
|
| 1078 |
+
"grad_norm": 0.30859375,
|
| 1079 |
+
"learning_rate": 4.4455172349068696e-06,
|
| 1080 |
+
"loss": 1.2907675504684448,
|
| 1081 |
+
"step": 306
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 0.9418960244648318,
|
| 1085 |
+
"grad_norm": 0.53515625,
|
| 1086 |
+
"learning_rate": 4.3684610574551e-06,
|
| 1087 |
+
"loss": 1.2298390865325928,
|
| 1088 |
+
"step": 308
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 0.9480122324159022,
|
| 1092 |
+
"grad_norm": 0.33984375,
|
| 1093 |
+
"learning_rate": 4.298647766878974e-06,
|
| 1094 |
+
"loss": 1.3057259321212769,
|
| 1095 |
+
"step": 310
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 0.9541284403669725,
|
| 1099 |
+
"grad_norm": 0.3125,
|
| 1100 |
+
"learning_rate": 4.236106041887007e-06,
|
| 1101 |
+
"loss": 1.3313639163970947,
|
| 1102 |
+
"step": 312
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 0.9602446483180428,
|
| 1106 |
+
"grad_norm": 0.66015625,
|
| 1107 |
+
"learning_rate": 4.180861574090156e-06,
|
| 1108 |
+
"loss": 1.3252257108688354,
|
| 1109 |
+
"step": 314
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 0.9663608562691132,
|
| 1113 |
+
"grad_norm": 0.6171875,
|
| 1114 |
+
"learning_rate": 4.1329370574479296e-06,
|
| 1115 |
+
"loss": 1.258653163909912,
|
| 1116 |
+
"step": 316
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 0.9724770642201835,
|
| 1120 |
+
"grad_norm": 0.6328125,
|
| 1121 |
+
"learning_rate": 4.0923521789458876e-06,
|
| 1122 |
+
"loss": 1.3827545642852783,
|
| 1123 |
+
"step": 318
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 0.9785932721712538,
|
| 1127 |
+
"grad_norm": 1.2578125,
|
| 1128 |
+
"learning_rate": 4.059123610508407e-06,
|
| 1129 |
+
"loss": 1.2586948871612549,
|
| 1130 |
+
"step": 320
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 0.9847094801223242,
|
| 1134 |
+
"grad_norm": 0.333984375,
|
| 1135 |
+
"learning_rate": 4.033265002149985e-06,
|
| 1136 |
+
"loss": 1.1728885173797607,
|
| 1137 |
+
"step": 322
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 0.9908256880733946,
|
| 1141 |
+
"grad_norm": 0.37109375,
|
| 1142 |
+
"learning_rate": 4.014786976367939e-06,
|
| 1143 |
+
"loss": 1.230262041091919,
|
| 1144 |
+
"step": 324
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 0.9969418960244648,
|
| 1148 |
+
"grad_norm": 0.78125,
|
| 1149 |
+
"learning_rate": 4.00369712377877e-06,
|
| 1150 |
+
"loss": 1.3188743591308594,
|
| 1151 |
+
"step": 326
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.0,
|
| 1155 |
+
"step": 327,
|
| 1156 |
+
"total_flos": 8.183535699912294e+17,
|
| 1157 |
+
"train_loss": 1.4031060467437138,
|
| 1158 |
+
"train_runtime": 3980.916,
|
| 1159 |
+
"train_samples_per_second": 2.629,
|
| 1160 |
+
"train_steps_per_second": 0.082
|
| 1161 |
+
}
|
| 1162 |
+
],
|
| 1163 |
+
"logging_steps": 2,
|
| 1164 |
+
"max_steps": 327,
|
| 1165 |
+
"num_input_tokens_seen": 0,
|
| 1166 |
+
"num_train_epochs": 1,
|
| 1167 |
+
"save_steps": 9999999,
|
| 1168 |
+
"stateful_callbacks": {
|
| 1169 |
+
"TrainerControl": {
|
| 1170 |
+
"args": {
|
| 1171 |
+
"should_epoch_stop": false,
|
| 1172 |
+
"should_evaluate": false,
|
| 1173 |
+
"should_log": false,
|
| 1174 |
+
"should_save": true,
|
| 1175 |
+
"should_training_stop": true
|
| 1176 |
+
},
|
| 1177 |
+
"attributes": {}
|
| 1178 |
+
}
|
| 1179 |
+
},
|
| 1180 |
+
"total_flos": 8.183535699912294e+17,
|
| 1181 |
+
"train_batch_size": 1,
|
| 1182 |
+
"trial_name": null,
|
| 1183 |
+
"trial_params": null
|
| 1184 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8d45cb18d4c3ea7e48a7f69a78dad21eedda21c711e498e7099de63e208f811c
|
| 3 |
+
size 5649
|
training_loss.png
ADDED
|