Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .ipynb_checkpoints/README-checkpoint.md +70 -0
- README.md +70 -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 +346 -0
- trainer_state.json +2458 -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 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- half LR from step 1 to 120
|
| 39 |
+
- family_to_muon_lr = {
|
| 40 |
+
"language": _fallback(getattr(training_args, "language_muon_lr", 3e-5), language_lr),
|
| 41 |
+
"vision": _fallback(getattr(training_args, "vision_muon_lr", 3e-5), vision_lr),
|
| 42 |
+
"merger": _fallback(getattr(training_args, "merger_muon_lr", 3e-5), merger_lr),
|
| 43 |
+
}
|
| 44 |
+
|
| 45 |
+
family_to_adamw_lr = {
|
| 46 |
+
"language": _fallback(getattr(training_args, "language_adamw_lr", 3e-5), language_lr),
|
| 47 |
+
"vision": _fallback(getattr(training_args, "vision_adamw_lr", 3e-6), vision_lr),
|
| 48 |
+
"merger": _fallback(getattr(training_args, "merger_adamw_lr", 3e-5), merger_lr),
|
| 49 |
+
}
|
| 50 |
+
- train_batch_size: 1
|
| 51 |
+
- eval_batch_size: 8
|
| 52 |
+
- seed: 42
|
| 53 |
+
- distributed_type: multi-GPU
|
| 54 |
+
- gradient_accumulation_steps: 64
|
| 55 |
+
- total_train_batch_size: 64
|
| 56 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 57 |
+
- lr_scheduler_type: cosine_with_min_lr
|
| 58 |
+
- lr_scheduler_warmup_steps: 0.05
|
| 59 |
+
- num_epochs: 3
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 5.5.3
|
| 68 |
+
- Pytorch 2.11.0+cu130
|
| 69 |
+
- Datasets 4.0.0
|
| 70 |
+
- Tokenizers 0.22.2
|
README.md
ADDED
|
@@ -0,0 +1,70 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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 |
+
- half LR from step 1 to 120
|
| 39 |
+
- family_to_muon_lr = {
|
| 40 |
+
"language": _fallback(getattr(training_args, "language_muon_lr", 3e-5), language_lr),
|
| 41 |
+
"vision": _fallback(getattr(training_args, "vision_muon_lr", 3e-5), vision_lr),
|
| 42 |
+
"merger": _fallback(getattr(training_args, "merger_muon_lr", 3e-5), merger_lr),
|
| 43 |
+
}
|
| 44 |
+
|
| 45 |
+
family_to_adamw_lr = {
|
| 46 |
+
"language": _fallback(getattr(training_args, "language_adamw_lr", 3e-5), language_lr),
|
| 47 |
+
"vision": _fallback(getattr(training_args, "vision_adamw_lr", 3e-6), vision_lr),
|
| 48 |
+
"merger": _fallback(getattr(training_args, "merger_adamw_lr", 3e-5), merger_lr),
|
| 49 |
+
}
|
| 50 |
+
- train_batch_size: 1
|
| 51 |
+
- eval_batch_size: 8
|
| 52 |
+
- seed: 42
|
| 53 |
+
- distributed_type: multi-GPU
|
| 54 |
+
- gradient_accumulation_steps: 64
|
| 55 |
+
- total_train_batch_size: 64
|
| 56 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 57 |
+
- lr_scheduler_type: cosine_with_min_lr
|
| 58 |
+
- lr_scheduler_warmup_steps: 0.05
|
| 59 |
+
- num_epochs: 3
|
| 60 |
+
|
| 61 |
+
### Training results
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
|
| 65 |
+
### Framework versions
|
| 66 |
+
|
| 67 |
+
- Transformers 5.5.3
|
| 68 |
+
- Pytorch 2.11.0+cu130
|
| 69 |
+
- Datasets 4.0.0
|
| 70 |
+
- Tokenizers 0.22.2
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"effective_tokens_per_sec": 2759.3348239749225,
|
| 3 |
+
"epoch": 3.0,
|
| 4 |
+
"total_flos": 2.5683697677065257e+18,
|
| 5 |
+
"train_loss": 1.0660493817018426,
|
| 6 |
+
"train_runtime": 18433.9416,
|
| 7 |
+
"train_samples_per_second": 2.396,
|
| 8 |
+
"train_steps_per_second": 0.037
|
| 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": "5.5.3",
|
| 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": "5.5.3",
|
| 9 |
+
"use_cache": true
|
| 10 |
+
}
|
model.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:302a02846f403e5774973185e00e1b474cc3420d54a4b141a5acbee63e71fbc9
|
| 3 |
+
size 20859273368
|
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": 2759.3348239749225,
|
| 3 |
+
"epoch": 3.0,
|
| 4 |
+
"total_flos": 2.5683697677065257e+18,
|
| 5 |
+
"train_loss": 1.0660493817018426,
|
| 6 |
+
"train_runtime": 18433.9416,
|
| 7 |
+
"train_samples_per_second": 2.396,
|
| 8 |
+
"train_steps_per_second": 0.037
|
| 9 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,346 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 2, "total_steps": 690, "loss": 2.46012020111084, "lr": 8.571428571428571e-07, "epoch": 0.008695652173913044, "percentage": 0.29, "elapsed_time": "0:01:12", "remaining_time": "6:54:27"}
|
| 2 |
+
{"current_steps": 4, "total_steps": 690, "loss": 2.301504135131836, "lr": 2.5714285714285716e-06, "epoch": 0.017391304347826087, "percentage": 0.58, "elapsed_time": "0:02:01", "remaining_time": "5:47:04"}
|
| 3 |
+
{"current_steps": 6, "total_steps": 690, "loss": 2.9570844173431396, "lr": 4.2857142857142855e-06, "epoch": 0.02608695652173913, "percentage": 0.87, "elapsed_time": "0:02:50", "remaining_time": "5:23:24"}
|
| 4 |
+
{"current_steps": 8, "total_steps": 690, "loss": 1.8961513042449951, "lr": 6e-06, "epoch": 0.034782608695652174, "percentage": 1.16, "elapsed_time": "0:03:47", "remaining_time": "5:22:50"}
|
| 5 |
+
{"current_steps": 10, "total_steps": 690, "loss": 3.0871455669403076, "lr": 7.714285714285714e-06, "epoch": 0.043478260869565216, "percentage": 1.45, "elapsed_time": "0:04:45", "remaining_time": "5:23:15"}
|
| 6 |
+
{"current_steps": 12, "total_steps": 690, "loss": 2.292584180831909, "lr": 9.428571428571428e-06, "epoch": 0.05217391304347826, "percentage": 1.74, "elapsed_time": "0:05:35", "remaining_time": "5:15:29"}
|
| 7 |
+
{"current_steps": 14, "total_steps": 690, "loss": 2.5501410961151123, "lr": 1.1142857142857143e-05, "epoch": 0.06086956521739131, "percentage": 2.03, "elapsed_time": "0:06:22", "remaining_time": "5:07:58"}
|
| 8 |
+
{"current_steps": 16, "total_steps": 690, "loss": 1.931159257888794, "lr": 1.2857142857142857e-05, "epoch": 0.06956521739130435, "percentage": 2.32, "elapsed_time": "0:07:36", "remaining_time": "5:20:15"}
|
| 9 |
+
{"current_steps": 18, "total_steps": 690, "loss": 2.571274518966675, "lr": 1.4571428571428571e-05, "epoch": 0.0782608695652174, "percentage": 2.61, "elapsed_time": "0:08:15", "remaining_time": "5:08:34"}
|
| 10 |
+
{"current_steps": 20, "total_steps": 690, "loss": 1.9101747274398804, "lr": 1.6285714285714283e-05, "epoch": 0.08695652173913043, "percentage": 2.9, "elapsed_time": "0:09:08", "remaining_time": "5:06:02"}
|
| 11 |
+
{"current_steps": 22, "total_steps": 690, "loss": 1.8424170017242432, "lr": 1.8e-05, "epoch": 0.09565217391304348, "percentage": 3.19, "elapsed_time": "0:10:22", "remaining_time": "5:14:55"}
|
| 12 |
+
{"current_steps": 24, "total_steps": 690, "loss": 5.551755905151367, "lr": 1.9714285714285714e-05, "epoch": 0.10434782608695652, "percentage": 3.48, "elapsed_time": "0:11:00", "remaining_time": "5:05:39"}
|
| 13 |
+
{"current_steps": 26, "total_steps": 690, "loss": 1.828694224357605, "lr": 2.1428571428571428e-05, "epoch": 0.11304347826086956, "percentage": 3.77, "elapsed_time": "0:12:14", "remaining_time": "5:12:26"}
|
| 14 |
+
{"current_steps": 28, "total_steps": 690, "loss": 2.4214303493499756, "lr": 2.3142857142857145e-05, "epoch": 0.12173913043478261, "percentage": 4.06, "elapsed_time": "0:13:03", "remaining_time": "5:08:39"}
|
| 15 |
+
{"current_steps": 30, "total_steps": 690, "loss": 3.56320858001709, "lr": 2.485714285714286e-05, "epoch": 0.13043478260869565, "percentage": 4.35, "elapsed_time": "0:13:51", "remaining_time": "5:04:49"}
|
| 16 |
+
{"current_steps": 32, "total_steps": 690, "loss": 1.7686303853988647, "lr": 2.657142857142857e-05, "epoch": 0.1391304347826087, "percentage": 4.64, "elapsed_time": "0:14:41", "remaining_time": "5:02:13"}
|
| 17 |
+
{"current_steps": 34, "total_steps": 690, "loss": 1.9711768627166748, "lr": 2.8285714285714287e-05, "epoch": 0.14782608695652175, "percentage": 4.93, "elapsed_time": "0:15:22", "remaining_time": "4:56:32"}
|
| 18 |
+
{"current_steps": 36, "total_steps": 690, "loss": 1.890865683555603, "lr": 3e-05, "epoch": 0.1565217391304348, "percentage": 5.22, "elapsed_time": "0:16:11", "remaining_time": "4:54:15"}
|
| 19 |
+
{"current_steps": 38, "total_steps": 690, "loss": 1.682741641998291, "lr": 2.9994720778760907e-05, "epoch": 0.16521739130434782, "percentage": 5.51, "elapsed_time": "0:17:26", "remaining_time": "4:59:20"}
|
| 20 |
+
{"current_steps": 40, "total_steps": 690, "loss": 1.8588255643844604, "lr": 2.9978887486836082e-05, "epoch": 0.17391304347826086, "percentage": 5.8, "elapsed_time": "0:18:39", "remaining_time": "5:03:18"}
|
| 21 |
+
{"current_steps": 42, "total_steps": 690, "loss": 1.7579265832901, "lr": 2.9952513235982553e-05, "epoch": 0.1826086956521739, "percentage": 6.09, "elapsed_time": "0:19:37", "remaining_time": "5:02:52"}
|
| 22 |
+
{"current_steps": 44, "total_steps": 690, "loss": 3.504922389984131, "lr": 2.991561986706388e-05, "epoch": 0.19130434782608696, "percentage": 6.38, "elapsed_time": "0:20:27", "remaining_time": "5:00:18"}
|
| 23 |
+
{"current_steps": 46, "total_steps": 690, "loss": 1.5656976699829102, "lr": 2.9868237931963492e-05, "epoch": 0.2, "percentage": 6.67, "elapsed_time": "0:21:15", "remaining_time": "4:57:37"}
|
| 24 |
+
{"current_steps": 48, "total_steps": 690, "loss": 1.2987524271011353, "lr": 2.9810406668284216e-05, "epoch": 0.20869565217391303, "percentage": 6.96, "elapsed_time": "0:21:55", "remaining_time": "4:53:20"}
|
| 25 |
+
{"current_steps": 50, "total_steps": 690, "loss": 1.316739797592163, "lr": 2.9742173966855167e-05, "epoch": 0.21739130434782608, "percentage": 7.25, "elapsed_time": "0:22:35", "remaining_time": "4:49:13"}
|
| 26 |
+
{"current_steps": 52, "total_steps": 690, "loss": 1.020365595817566, "lr": 2.9663596332072664e-05, "epoch": 0.22608695652173913, "percentage": 7.54, "elapsed_time": "0:23:01", "remaining_time": "4:42:23"}
|
| 27 |
+
{"current_steps": 54, "total_steps": 690, "loss": 0.9612956047058105, "lr": 2.9574738835108235e-05, "epoch": 0.23478260869565218, "percentage": 7.83, "elapsed_time": "0:23:28", "remaining_time": "4:36:28"}
|
| 28 |
+
{"current_steps": 56, "total_steps": 690, "loss": 1.4254815578460693, "lr": 2.94756750600223e-05, "epoch": 0.24347826086956523, "percentage": 8.12, "elapsed_time": "0:24:15", "remaining_time": "4:34:42"}
|
| 29 |
+
{"current_steps": 58, "total_steps": 690, "loss": 1.4714879989624023, "lr": 2.9366487042828275e-05, "epoch": 0.25217391304347825, "percentage": 8.41, "elapsed_time": "0:25:21", "remaining_time": "4:36:24"}
|
| 30 |
+
{"current_steps": 60, "total_steps": 690, "loss": 1.8500466346740723, "lr": 2.9247265203557428e-05, "epoch": 0.2608695652173913, "percentage": 8.7, "elapsed_time": "0:26:24", "remaining_time": "4:37:21"}
|
| 31 |
+
{"current_steps": 62, "total_steps": 690, "loss": 1.0420849323272705, "lr": 2.9118108271380923e-05, "epoch": 0.26956521739130435, "percentage": 8.99, "elapsed_time": "0:27:04", "remaining_time": "4:34:17"}
|
| 32 |
+
{"current_steps": 64, "total_steps": 690, "loss": 1.2155001163482666, "lr": 2.8979123202850823e-05, "epoch": 0.2782608695652174, "percentage": 9.28, "elapsed_time": "0:27:53", "remaining_time": "4:32:47"}
|
| 33 |
+
{"current_steps": 66, "total_steps": 690, "loss": 0.5274585485458374, "lr": 2.8830425093328024e-05, "epoch": 0.28695652173913044, "percentage": 9.57, "elapsed_time": "0:28:19", "remaining_time": "4:27:44"}
|
| 34 |
+
{"current_steps": 68, "total_steps": 690, "loss": 0.9751191735267639, "lr": 2.8672137081670264e-05, "epoch": 0.2956521739130435, "percentage": 9.86, "elapsed_time": "0:29:07", "remaining_time": "4:26:28"}
|
| 35 |
+
{"current_steps": 70, "total_steps": 690, "loss": 0.45779138803482056, "lr": 2.850439024825919e-05, "epoch": 0.30434782608695654, "percentage": 10.14, "elapsed_time": "0:29:32", "remaining_time": "4:21:36"}
|
| 36 |
+
{"current_steps": 72, "total_steps": 690, "loss": 1.0098928213119507, "lr": 2.8327323506450993e-05, "epoch": 0.3130434782608696, "percentage": 10.43, "elapsed_time": "0:29:58", "remaining_time": "4:17:17"}
|
| 37 |
+
{"current_steps": 74, "total_steps": 690, "loss": 1.4895820617675781, "lr": 2.8141083487540432e-05, "epoch": 0.3217391304347826, "percentage": 10.72, "elapsed_time": "0:31:08", "remaining_time": "4:19:15"}
|
| 38 |
+
{"current_steps": 76, "total_steps": 690, "loss": 0.339144766330719, "lr": 2.794582441933354e-05, "epoch": 0.33043478260869563, "percentage": 11.01, "elapsed_time": "0:31:37", "remaining_time": "4:15:28"}
|
| 39 |
+
{"current_steps": 78, "total_steps": 690, "loss": 1.4342169761657715, "lr": 2.7741707998429524e-05, "epoch": 0.3391304347826087, "percentage": 11.3, "elapsed_time": "0:32:51", "remaining_time": "4:17:44"}
|
| 40 |
+
{"current_steps": 80, "total_steps": 690, "loss": 1.676353931427002, "lr": 2.7528903256317714e-05, "epoch": 0.34782608695652173, "percentage": 11.59, "elapsed_time": "0:34:04", "remaining_time": "4:19:49"}
|
| 41 |
+
{"current_steps": 82, "total_steps": 690, "loss": 1.4120248556137085, "lr": 2.7307586419400365e-05, "epoch": 0.3565217391304348, "percentage": 11.88, "elapsed_time": "0:35:19", "remaining_time": "4:21:54"}
|
| 42 |
+
{"current_steps": 84, "total_steps": 690, "loss": 1.4109995365142822, "lr": 2.707794076305724e-05, "epoch": 0.3652173913043478, "percentage": 12.17, "elapsed_time": "0:36:35", "remaining_time": "4:24:01"}
|
| 43 |
+
{"current_steps": 86, "total_steps": 690, "loss": 1.8156630992889404, "lr": 2.6840156459872887e-05, "epoch": 0.3739130434782609, "percentage": 12.46, "elapsed_time": "0:37:47", "remaining_time": "4:25:25"}
|
| 44 |
+
{"current_steps": 88, "total_steps": 690, "loss": 1.2095890045166016, "lr": 2.6594430422152184e-05, "epoch": 0.3826086956521739, "percentage": 12.75, "elapsed_time": "0:38:34", "remaining_time": "4:23:54"}
|
| 45 |
+
{"current_steps": 90, "total_steps": 690, "loss": 1.3283032178878784, "lr": 2.6340966138854725e-05, "epoch": 0.391304347826087, "percentage": 13.04, "elapsed_time": "0:39:53", "remaining_time": "4:25:58"}
|
| 46 |
+
{"current_steps": 92, "total_steps": 690, "loss": 0.3713761866092682, "lr": 2.607997350708289e-05, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:40:18", "remaining_time": "4:21:58"}
|
| 47 |
+
{"current_steps": 94, "total_steps": 690, "loss": 1.2495781183242798, "lr": 2.5811668658263345e-05, "epoch": 0.40869565217391307, "percentage": 13.62, "elapsed_time": "0:41:11", "remaining_time": "4:21:07"}
|
| 48 |
+
{"current_steps": 96, "total_steps": 690, "loss": 0.892501950263977, "lr": 2.5536273779165707e-05, "epoch": 0.41739130434782606, "percentage": 13.91, "elapsed_time": "0:41:59", "remaining_time": "4:19:51"}
|
| 49 |
+
{"current_steps": 98, "total_steps": 690, "loss": 0.99811190366745, "lr": 2.5254016927906833e-05, "epoch": 0.4260869565217391, "percentage": 14.2, "elapsed_time": "0:42:47", "remaining_time": "4:18:32"}
|
| 50 |
+
{"current_steps": 100, "total_steps": 690, "loss": 0.9439688324928284, "lr": 2.4965131845092846e-05, "epoch": 0.43478260869565216, "percentage": 14.49, "elapsed_time": "0:43:37", "remaining_time": "4:17:22"}
|
| 51 |
+
{"current_steps": 102, "total_steps": 690, "loss": 1.434984803199768, "lr": 2.466985776025548e-05, "epoch": 0.4434782608695652, "percentage": 14.78, "elapsed_time": "0:44:50", "remaining_time": "4:18:32"}
|
| 52 |
+
{"current_steps": 104, "total_steps": 690, "loss": 1.6902875900268555, "lr": 2.4368439193742983e-05, "epoch": 0.45217391304347826, "percentage": 15.07, "elapsed_time": "0:46:03", "remaining_time": "4:19:30"}
|
| 53 |
+
{"current_steps": 106, "total_steps": 690, "loss": 0.3920702636241913, "lr": 2.4061125754229576e-05, "epoch": 0.4608695652173913, "percentage": 15.36, "elapsed_time": "0:46:29", "remaining_time": "4:16:06"}
|
| 54 |
+
{"current_steps": 108, "total_steps": 690, "loss": 1.1952660083770752, "lr": 2.3748171932011248e-05, "epoch": 0.46956521739130436, "percentage": 15.65, "elapsed_time": "0:47:21", "remaining_time": "4:15:11"}
|
| 55 |
+
{"current_steps": 110, "total_steps": 690, "loss": 1.0627365112304688, "lr": 2.3429836888259e-05, "epoch": 0.4782608695652174, "percentage": 15.94, "elapsed_time": "0:48:02", "remaining_time": "4:13:19"}
|
| 56 |
+
{"current_steps": 112, "total_steps": 690, "loss": 1.4079805612564087, "lr": 2.310638424040406e-05, "epoch": 0.48695652173913045, "percentage": 16.23, "elapsed_time": "0:49:16", "remaining_time": "4:14:17"}
|
| 57 |
+
{"current_steps": 114, "total_steps": 690, "loss": 0.8712098002433777, "lr": 2.2778081843832856e-05, "epoch": 0.4956521739130435, "percentage": 16.52, "elapsed_time": "0:49:51", "remaining_time": "4:11:56"}
|
| 58 |
+
{"current_steps": 116, "total_steps": 690, "loss": 1.3538367748260498, "lr": 2.2445201570072414e-05, "epoch": 0.5043478260869565, "percentage": 16.81, "elapsed_time": "0:51:06", "remaining_time": "4:12:52"}
|
| 59 |
+
{"current_steps": 118, "total_steps": 690, "loss": 1.612799048423767, "lr": 2.2108019081649993e-05, "epoch": 0.5130434782608696, "percentage": 17.1, "elapsed_time": "0:52:10", "remaining_time": "4:12:55"}
|
| 60 |
+
{"current_steps": 120, "total_steps": 690, "loss": 0.8653756380081177, "lr": 2.1766813603813334e-05, "epoch": 0.5217391304347826, "percentage": 17.39, "elapsed_time": "0:53:01", "remaining_time": "4:11:49"}
|
| 61 |
+
{"current_steps": 122, "total_steps": 690, "loss": 0.7663818597793579, "lr": 2.1421867693300552e-05, "epoch": 0.5304347826086957, "percentage": 17.68, "elapsed_time": "0:53:51", "remaining_time": "4:10:44"}
|
| 62 |
+
{"current_steps": 124, "total_steps": 690, "loss": 0.7496420741081238, "lr": 2.1073467004351202e-05, "epoch": 0.5391304347826087, "percentage": 17.97, "elapsed_time": "0:54:40", "remaining_time": "4:09:33"}
|
| 63 |
+
{"current_steps": 126, "total_steps": 690, "loss": 0.7726188898086548, "lr": 2.0721900052152227e-05, "epoch": 0.5478260869565217, "percentage": 18.26, "elapsed_time": "0:55:08", "remaining_time": "4:06:51"}
|
| 64 |
+
{"current_steps": 128, "total_steps": 690, "loss": 0.7957323789596558, "lr": 2.036745797391477e-05, "epoch": 0.5565217391304348, "percentage": 18.55, "elapsed_time": "0:55:59", "remaining_time": "4:05:48"}
|
| 65 |
+
{"current_steps": 130, "total_steps": 690, "loss": 1.3306431770324707, "lr": 2.0010434287779607e-05, "epoch": 0.5652173913043478, "percentage": 18.84, "elapsed_time": "0:57:13", "remaining_time": "4:06:29"}
|
| 66 |
+
{"current_steps": 132, "total_steps": 690, "loss": 1.3570564985275269, "lr": 1.965112464975093e-05, "epoch": 0.5739130434782609, "percentage": 19.13, "elapsed_time": "0:58:36", "remaining_time": "4:07:46"}
|
| 67 |
+
{"current_steps": 134, "total_steps": 690, "loss": 1.3512859344482422, "lr": 1.928982660885971e-05, "epoch": 0.5826086956521739, "percentage": 19.42, "elapsed_time": "0:59:51", "remaining_time": "4:08:24"}
|
| 68 |
+
{"current_steps": 136, "total_steps": 690, "loss": 1.3253053426742554, "lr": 1.8926839360759467e-05, "epoch": 0.591304347826087, "percentage": 19.71, "elapsed_time": "1:00:56", "remaining_time": "4:08:14"}
|
| 69 |
+
{"current_steps": 138, "total_steps": 690, "loss": 1.363409161567688, "lr": 1.856246349995838e-05, "epoch": 0.6, "percentage": 20.0, "elapsed_time": "1:02:10", "remaining_time": "4:08:40"}
|
| 70 |
+
{"current_steps": 140, "total_steps": 690, "loss": 0.9811846613883972, "lr": 1.8197000770893056e-05, "epoch": 0.6086956521739131, "percentage": 20.29, "elapsed_time": "1:02:59", "remaining_time": "4:07:26"}
|
| 71 |
+
{"current_steps": 142, "total_steps": 690, "loss": 1.3022255897521973, "lr": 1.7830753818049987e-05, "epoch": 0.6173913043478261, "percentage": 20.58, "elapsed_time": "1:04:13", "remaining_time": "4:07:52"}
|
| 72 |
+
{"current_steps": 144, "total_steps": 690, "loss": 0.7987528443336487, "lr": 1.7464025935341674e-05, "epoch": 0.6260869565217392, "percentage": 20.87, "elapsed_time": "1:05:03", "remaining_time": "4:06:42"}
|
| 73 |
+
{"current_steps": 146, "total_steps": 690, "loss": 0.790221095085144, "lr": 1.709712081494495e-05, "epoch": 0.6347826086956522, "percentage": 21.16, "elapsed_time": "1:05:53", "remaining_time": "4:05:32"}
|
| 74 |
+
{"current_steps": 148, "total_steps": 690, "loss": 0.8017470240592957, "lr": 1.673034229580953e-05, "epoch": 0.6434782608695652, "percentage": 21.45, "elapsed_time": "1:06:43", "remaining_time": "4:04:19"}
|
| 75 |
+
{"current_steps": 150, "total_steps": 690, "loss": 0.8057210445404053, "lr": 1.6363994112044934e-05, "epoch": 0.6521739130434783, "percentage": 21.74, "elapsed_time": "1:07:15", "remaining_time": "4:02:09"}
|
| 76 |
+
{"current_steps": 152, "total_steps": 690, "loss": 0.8728779554367065, "lr": 1.5998379641394322e-05, "epoch": 0.6608695652173913, "percentage": 22.03, "elapsed_time": "1:08:04", "remaining_time": "4:00:55"}
|
| 77 |
+
{"current_steps": 154, "total_steps": 690, "loss": 1.3450850248336792, "lr": 1.5633801654003383e-05, "epoch": 0.6695652173913044, "percentage": 22.32, "elapsed_time": "1:08:59", "remaining_time": "4:00:06"}
|
| 78 |
+
{"current_steps": 156, "total_steps": 690, "loss": 1.295073390007019, "lr": 1.5270562061692413e-05, "epoch": 0.6782608695652174, "percentage": 22.61, "elapsed_time": "1:10:15", "remaining_time": "4:00:30"}
|
| 79 |
+
{"current_steps": 158, "total_steps": 690, "loss": 1.3460811376571655, "lr": 1.4908961667939148e-05, "epoch": 0.6869565217391305, "percentage": 22.9, "elapsed_time": "1:11:19", "remaining_time": "4:00:10"}
|
| 80 |
+
{"current_steps": 160, "total_steps": 690, "loss": 1.4722148180007935, "lr": 1.4549299918779476e-05, "epoch": 0.6956521739130435, "percentage": 23.19, "elapsed_time": "1:12:31", "remaining_time": "4:00:13"}
|
| 81 |
+
{"current_steps": 162, "total_steps": 690, "loss": 1.301584243774414, "lr": 1.4191874654832224e-05, "epoch": 0.7043478260869566, "percentage": 23.48, "elapsed_time": "1:13:46", "remaining_time": "4:00:27"}
|
| 82 |
+
{"current_steps": 164, "total_steps": 690, "loss": 0.8648190498352051, "lr": 1.3836981864653448e-05, "epoch": 0.7130434782608696, "percentage": 23.77, "elapsed_time": "1:14:36", "remaining_time": "3:59:18"}
|
| 83 |
+
{"current_steps": 166, "total_steps": 690, "loss": 1.2689242362976074, "lr": 1.3484915439624399e-05, "epoch": 0.7217391304347827, "percentage": 24.06, "elapsed_time": "1:15:51", "remaining_time": "3:59:26"}
|
| 84 |
+
{"current_steps": 168, "total_steps": 690, "loss": 0.9420109987258911, "lr": 1.3135966930576233e-05, "epoch": 0.7304347826086957, "percentage": 24.35, "elapsed_time": "1:16:31", "remaining_time": "3:57:45"}
|
| 85 |
+
{"current_steps": 170, "total_steps": 690, "loss": 1.3050771951675415, "lr": 1.2790425306352913e-05, "epoch": 0.7391304347826086, "percentage": 24.64, "elapsed_time": "1:17:45", "remaining_time": "3:57:51"}
|
| 86 |
+
{"current_steps": 172, "total_steps": 690, "loss": 1.160625696182251, "lr": 1.2448576714512348e-05, "epoch": 0.7478260869565218, "percentage": 24.93, "elapsed_time": "1:18:40", "remaining_time": "3:56:57"}
|
| 87 |
+
{"current_steps": 174, "total_steps": 690, "loss": 0.5953898429870605, "lr": 1.2110704244363801e-05, "epoch": 0.7565217391304347, "percentage": 25.22, "elapsed_time": "1:19:07", "remaining_time": "3:54:39"}
|
| 88 |
+
{"current_steps": 176, "total_steps": 690, "loss": 0.6910260915756226, "lr": 1.1777087692537941e-05, "epoch": 0.7652173913043478, "percentage": 25.51, "elapsed_time": "1:19:58", "remaining_time": "3:53:33"}
|
| 89 |
+
{"current_steps": 178, "total_steps": 690, "loss": 1.332924723625183, "lr": 1.1448003331283567e-05, "epoch": 0.7739130434782608, "percentage": 25.8, "elapsed_time": "1:21:08", "remaining_time": "3:53:24"}
|
| 90 |
+
{"current_steps": 180, "total_steps": 690, "loss": 0.37987953424453735, "lr": 1.1123723679682947e-05, "epoch": 0.782608695652174, "percentage": 26.09, "elapsed_time": "1:21:33", "remaining_time": "3:51:04"}
|
| 91 |
+
{"current_steps": 182, "total_steps": 690, "loss": 0.6722633242607117, "lr": 1.0804517277975145e-05, "epoch": 0.7913043478260869, "percentage": 26.38, "elapsed_time": "1:22:00", "remaining_time": "3:48:53"}
|
| 92 |
+
{"current_steps": 184, "total_steps": 690, "loss": 0.6781936883926392, "lr": 1.0490648465174374e-05, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "1:22:31", "remaining_time": "3:46:57"}
|
| 93 |
+
{"current_steps": 186, "total_steps": 690, "loss": 1.3093880414962769, "lr": 1.0182377160167355e-05, "epoch": 0.808695652173913, "percentage": 26.96, "elapsed_time": "1:23:35", "remaining_time": "3:46:30"}
|
| 94 |
+
{"current_steps": 188, "total_steps": 690, "loss": 1.0597083568572998, "lr": 9.87995864647107e-06, "epoch": 0.8173913043478261, "percentage": 27.25, "elapsed_time": "1:24:17", "remaining_time": "3:45:04"}
|
| 95 |
+
{"current_steps": 190, "total_steps": 690, "loss": 1.113531231880188, "lr": 9.583643360829146e-06, "epoch": 0.8260869565217391, "percentage": 27.54, "elapsed_time": "1:25:12", "remaining_time": "3:44:14"}
|
| 96 |
+
{"current_steps": 192, "total_steps": 690, "loss": 0.7899190783500671, "lr": 9.293676685821879e-06, "epoch": 0.8347826086956521, "percentage": 27.83, "elapsed_time": "1:26:01", "remaining_time": "3:43:08"}
|
| 97 |
+
{"current_steps": 194, "total_steps": 690, "loss": 1.299129605293274, "lr": 9.010298746661722e-06, "epoch": 0.8434782608695652, "percentage": 28.12, "elapsed_time": "1:27:09", "remaining_time": "3:42:49"}
|
| 98 |
+
{"current_steps": 196, "total_steps": 690, "loss": 1.3935397863388062, "lr": 8.733744212342408e-06, "epoch": 0.8521739130434782, "percentage": 28.41, "elapsed_time": "1:28:13", "remaining_time": "3:42:20"}
|
| 99 |
+
{"current_steps": 198, "total_steps": 690, "loss": 1.3050575256347656, "lr": 8.46424210130651e-06, "epoch": 0.8608695652173913, "percentage": 28.7, "elapsed_time": "1:29:16", "remaining_time": "3:41:49"}
|
| 100 |
+
{"current_steps": 200, "total_steps": 690, "loss": 0.6221288442611694, "lr": 8.202015591792223e-06, "epoch": 0.8695652173913043, "percentage": 28.99, "elapsed_time": "1:29:43", "remaining_time": "3:39:49"}
|
| 101 |
+
{"current_steps": 202, "total_steps": 690, "loss": 0.8170241117477417, "lr": 7.947281837016573e-06, "epoch": 0.8782608695652174, "percentage": 29.28, "elapsed_time": "1:30:16", "remaining_time": "3:38:05"}
|
| 102 |
+
{"current_steps": 204, "total_steps": 690, "loss": 0.729548990726471, "lr": 7.70025178534795e-06, "epoch": 0.8869565217391304, "percentage": 29.57, "elapsed_time": "1:31:05", "remaining_time": "3:37:00"}
|
| 103 |
+
{"current_steps": 206, "total_steps": 690, "loss": 0.3102116882801056, "lr": 7.461130005617023e-06, "epoch": 0.8956521739130435, "percentage": 29.86, "elapsed_time": "1:31:29", "remaining_time": "3:34:58"}
|
| 104 |
+
{"current_steps": 208, "total_steps": 690, "loss": 1.066127061843872, "lr": 7.230114517710568e-06, "epoch": 0.9043478260869565, "percentage": 30.14, "elapsed_time": "1:32:16", "remaining_time": "3:33:49"}
|
| 105 |
+
{"current_steps": 210, "total_steps": 690, "loss": 1.1609755754470825, "lr": 7.007396628588649e-06, "epoch": 0.9130434782608695, "percentage": 30.43, "elapsed_time": "1:33:12", "remaining_time": "3:33:02"}
|
| 106 |
+
{"current_steps": 212, "total_steps": 690, "loss": 1.2955363988876343, "lr": 6.793160773860759e-06, "epoch": 0.9217391304347826, "percentage": 30.72, "elapsed_time": "1:34:27", "remaining_time": "3:32:57"}
|
| 107 |
+
{"current_steps": 214, "total_steps": 690, "loss": 0.22745762765407562, "lr": 6.587584365052308e-06, "epoch": 0.9304347826086956, "percentage": 31.01, "elapsed_time": "1:34:50", "remaining_time": "3:30:58"}
|
| 108 |
+
{"current_steps": 216, "total_steps": 690, "loss": 0.25208932161331177, "lr": 6.390837642687785e-06, "epoch": 0.9391304347826087, "percentage": 31.3, "elapsed_time": "1:35:15", "remaining_time": "3:29:02"}
|
| 109 |
+
{"current_steps": 218, "total_steps": 690, "loss": 0.7900155186653137, "lr": 6.203083535312356e-06, "epoch": 0.9478260869565217, "percentage": 31.59, "elapsed_time": "1:36:04", "remaining_time": "3:28:01"}
|
| 110 |
+
{"current_steps": 220, "total_steps": 690, "loss": 0.8592709302902222, "lr": 6.024477524568591e-06, "epoch": 0.9565217391304348, "percentage": 31.88, "elapsed_time": "1:36:44", "remaining_time": "3:26:40"}
|
| 111 |
+
{"current_steps": 222, "total_steps": 690, "loss": 1.3669737577438354, "lr": 5.855167516440076e-06, "epoch": 0.9652173913043478, "percentage": 32.17, "elapsed_time": "1:37:37", "remaining_time": "3:25:48"}
|
| 112 |
+
{"current_steps": 224, "total_steps": 690, "loss": 1.4519469738006592, "lr": 5.695293718768518e-06, "epoch": 0.9739130434782609, "percentage": 32.46, "elapsed_time": "1:38:50", "remaining_time": "3:25:37"}
|
| 113 |
+
{"current_steps": 226, "total_steps": 690, "loss": 1.3087224960327148, "lr": 5.5449885251458e-06, "epoch": 0.9826086956521739, "percentage": 32.75, "elapsed_time": "1:40:04", "remaining_time": "3:25:28"}
|
| 114 |
+
{"current_steps": 228, "total_steps": 690, "loss": 1.3946113586425781, "lr": 5.4043764052771e-06, "epoch": 0.991304347826087, "percentage": 33.04, "elapsed_time": "1:41:14", "remaining_time": "3:25:08"}
|
| 115 |
+
{"current_steps": 230, "total_steps": 690, "loss": 1.330439805984497, "lr": 5.273573801905901e-06, "epoch": 1.0, "percentage": 33.33, "elapsed_time": "1:42:18", "remaining_time": "3:24:37"}
|
| 116 |
+
{"current_steps": 232, "total_steps": 690, "loss": 1.014844536781311, "lr": 5.152689034386213e-06, "epoch": 1.008695652173913, "percentage": 33.62, "elapsed_time": "1:43:10", "remaining_time": "3:23:40"}
|
| 117 |
+
{"current_steps": 234, "total_steps": 690, "loss": 0.32737967371940613, "lr": 5.041822208981912e-06, "epoch": 1.017391304347826, "percentage": 33.91, "elapsed_time": "1:43:35", "remaining_time": "3:21:52"}
|
| 118 |
+
{"current_steps": 236, "total_steps": 690, "loss": 0.769230842590332, "lr": 4.941065135967408e-06, "epoch": 1.0260869565217392, "percentage": 34.2, "elapsed_time": "1:44:23", "remaining_time": "3:20:49"}
|
| 119 |
+
{"current_steps": 238, "total_steps": 690, "loss": 1.2364915609359741, "lr": 4.850501253598363e-06, "epoch": 1.0347826086956522, "percentage": 34.49, "elapsed_time": "1:45:38", "remaining_time": "3:20:38"}
|
| 120 |
+
{"current_steps": 240, "total_steps": 690, "loss": 1.2600164413452148, "lr": 4.770205559015373e-06, "epoch": 1.0434782608695652, "percentage": 34.78, "elapsed_time": "1:46:28", "remaining_time": "3:19:37"}
|
| 121 |
+
{"current_steps": 242, "total_steps": 690, "loss": 0.7779691815376282, "lr": 4.700244546137851e-06, "epoch": 1.0521739130434782, "percentage": 35.07, "elapsed_time": "1:47:17", "remaining_time": "3:18:37"}
|
| 122 |
+
{"current_steps": 244, "total_steps": 690, "loss": 1.0165550708770752, "lr": 4.640676150599536e-06, "epoch": 1.0608695652173914, "percentage": 35.36, "elapsed_time": "1:48:12", "remaining_time": "3:17:47"}
|
| 123 |
+
{"current_steps": 246, "total_steps": 690, "loss": 1.0626590251922607, "lr": 4.5915497017712385e-06, "epoch": 1.0695652173913044, "percentage": 35.65, "elapsed_time": "1:49:04", "remaining_time": "3:16:52"}
|
| 124 |
+
{"current_steps": 248, "total_steps": 690, "loss": 0.778892993927002, "lr": 4.552905881910531e-06, "epoch": 1.0782608695652174, "percentage": 35.94, "elapsed_time": "1:49:53", "remaining_time": "3:15:51"}
|
| 125 |
+
{"current_steps": 250, "total_steps": 690, "loss": 0.8480257391929626, "lr": 4.524776692472253e-06, "epoch": 1.0869565217391304, "percentage": 36.23, "elapsed_time": "1:50:42", "remaining_time": "3:14:51"}
|
| 126 |
+
{"current_steps": 252, "total_steps": 690, "loss": 0.15872906148433685, "lr": 4.507185427607667e-06, "epoch": 1.0956521739130434, "percentage": 36.52, "elapsed_time": "1:51:07", "remaining_time": "3:13:08"}
|
| 127 |
+
{"current_steps": 254, "total_steps": 690, "loss": 1.3229949474334717, "lr": 4.500146654874281e-06, "epoch": 1.1043478260869566, "percentage": 36.81, "elapsed_time": "1:52:19", "remaining_time": "3:12:48"}
|
| 128 |
+
{"current_steps": 256, "total_steps": 690, "loss": 1.2751566171646118, "lr": 4.50366620317225e-06, "epoch": 1.1130434782608696, "percentage": 37.1, "elapsed_time": "1:53:16", "remaining_time": "3:12:01"}
|
| 129 |
+
{"current_steps": 258, "total_steps": 690, "loss": 0.7979919910430908, "lr": 4.517741157917401e-06, "epoch": 1.1217391304347826, "percentage": 37.39, "elapsed_time": "1:54:06", "remaining_time": "3:11:03"}
|
| 130 |
+
{"current_steps": 260, "total_steps": 690, "loss": 1.2487938404083252, "lr": 4.542359863454825e-06, "epoch": 1.1304347826086956, "percentage": 37.68, "elapsed_time": "1:55:12", "remaining_time": "3:10:32"}
|
| 131 |
+
{"current_steps": 262, "total_steps": 690, "loss": 1.503760814666748, "lr": 4.577501932711088e-06, "epoch": 1.1391304347826088, "percentage": 37.97, "elapsed_time": "1:56:24", "remaining_time": "3:10:09"}
|
| 132 |
+
{"current_steps": 264, "total_steps": 690, "loss": 1.349209189414978, "lr": 4.623138264077027e-06, "epoch": 1.1478260869565218, "percentage": 38.26, "elapsed_time": "1:57:38", "remaining_time": "3:09:50"}
|
| 133 |
+
{"current_steps": 266, "total_steps": 690, "loss": 1.3860739469528198, "lr": 4.679231065507181e-06, "epoch": 1.1565217391304348, "percentage": 38.55, "elapsed_time": "1:58:52", "remaining_time": "3:09:28"}
|
| 134 |
+
{"current_steps": 268, "total_steps": 690, "loss": 0.7751848101615906, "lr": 4.745733885815875e-06, "epoch": 1.1652173913043478, "percentage": 38.84, "elapsed_time": "1:59:46", "remaining_time": "3:08:35"}
|
| 135 |
+
{"current_steps": 270, "total_steps": 690, "loss": 0.8347904086112976, "lr": 4.822591653144063e-06, "epoch": 1.1739130434782608, "percentage": 39.13, "elapsed_time": "2:00:35", "remaining_time": "3:07:34"}
|
| 136 |
+
{"current_steps": 272, "total_steps": 690, "loss": 1.281104564666748, "lr": 4.90974072056505e-06, "epoch": 1.182608695652174, "percentage": 39.42, "elapsed_time": "2:01:49", "remaining_time": "3:07:12"}
|
| 137 |
+
{"current_steps": 274, "total_steps": 690, "loss": 1.2953712940216064, "lr": 5.0071089187913535e-06, "epoch": 1.191304347826087, "percentage": 39.71, "elapsed_time": "2:03:00", "remaining_time": "3:06:45"}
|
| 138 |
+
{"current_steps": 276, "total_steps": 690, "loss": 1.0042020082473755, "lr": 5.114615615939042e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "2:03:50", "remaining_time": "3:05:46"}
|
| 139 |
+
{"current_steps": 278, "total_steps": 690, "loss": 0.8485981225967407, "lr": 5.232171784300044e-06, "epoch": 1.208695652173913, "percentage": 40.29, "elapsed_time": "2:04:39", "remaining_time": "3:04:45"}
|
| 140 |
+
{"current_steps": 280, "total_steps": 690, "loss": 0.7609320282936096, "lr": 5.359680074067178e-06, "epoch": 1.2173913043478262, "percentage": 40.58, "elapsed_time": "2:05:13", "remaining_time": "3:03:21"}
|
| 141 |
+
{"current_steps": 282, "total_steps": 690, "loss": 1.2442917823791504, "lr": 5.4970348939507965e-06, "epoch": 1.2260869565217392, "percentage": 40.87, "elapsed_time": "2:06:24", "remaining_time": "3:02:53"}
|
| 142 |
+
{"current_steps": 284, "total_steps": 690, "loss": 0.7213406562805176, "lr": 5.644122498620322e-06, "epoch": 1.2347826086956522, "percentage": 41.16, "elapsed_time": "2:06:54", "remaining_time": "3:01:24"}
|
| 143 |
+
{"current_steps": 286, "total_steps": 690, "loss": 1.2524417638778687, "lr": 5.800821082898257e-06, "epoch": 1.2434782608695651, "percentage": 41.45, "elapsed_time": "2:08:10", "remaining_time": "3:01:03"}
|
| 144 |
+
{"current_steps": 288, "total_steps": 690, "loss": 0.7535306215286255, "lr": 5.9670008826286325e-06, "epoch": 1.2521739130434781, "percentage": 41.74, "elapsed_time": "2:08:50", "remaining_time": "2:59:50"}
|
| 145 |
+
{"current_steps": 290, "total_steps": 690, "loss": 1.0591073036193848, "lr": 6.142524282136437e-06, "epoch": 1.2608695652173914, "percentage": 42.03, "elapsed_time": "2:09:45", "remaining_time": "2:58:59"}
|
| 146 |
+
{"current_steps": 292, "total_steps": 690, "loss": 1.2697545289993286, "lr": 6.327245928188936e-06, "epoch": 1.2695652173913043, "percentage": 42.32, "elapsed_time": "2:10:34", "remaining_time": "2:57:58"}
|
| 147 |
+
{"current_steps": 294, "total_steps": 690, "loss": 0.8120895624160767, "lr": 6.52101285036462e-06, "epoch": 1.2782608695652173, "percentage": 42.61, "elapsed_time": "2:11:13", "remaining_time": "2:56:45"}
|
| 148 |
+
{"current_steps": 296, "total_steps": 690, "loss": 0.16801220178604126, "lr": 6.7236645877299985e-06, "epoch": 1.2869565217391306, "percentage": 42.9, "elapsed_time": "2:11:38", "remaining_time": "2:55:13"}
|
| 149 |
+
{"current_steps": 298, "total_steps": 690, "loss": 0.6829316020011902, "lr": 6.935033321719419e-06, "epoch": 1.2956521739130435, "percentage": 43.19, "elapsed_time": "2:12:27", "remaining_time": "2:54:13"}
|
| 150 |
+
{"current_steps": 300, "total_steps": 690, "loss": 0.24555981159210205, "lr": 7.15494401510782e-06, "epoch": 1.3043478260869565, "percentage": 43.48, "elapsed_time": "2:12:52", "remaining_time": "2:52:43"}
|
| 151 |
+
{"current_steps": 302, "total_steps": 690, "loss": 0.8401697874069214, "lr": 7.383214556961368e-06, "epoch": 1.3130434782608695, "percentage": 43.77, "elapsed_time": "2:13:41", "remaining_time": "2:51:45"}
|
| 152 |
+
{"current_steps": 304, "total_steps": 690, "loss": 1.6956262588500977, "lr": 7.619655913445883e-06, "epoch": 1.3217391304347825, "percentage": 44.06, "elapsed_time": "2:14:43", "remaining_time": "2:51:03"}
|
| 153 |
+
{"current_steps": 306, "total_steps": 690, "loss": 0.7533000111579895, "lr": 7.864072284368284e-06, "epoch": 1.3304347826086955, "percentage": 44.35, "elapsed_time": "2:15:32", "remaining_time": "2:50:05"}
|
| 154 |
+
{"current_steps": 308, "total_steps": 690, "loss": 1.0896899700164795, "lr": 8.11626126532126e-06, "epoch": 1.3391304347826087, "percentage": 44.64, "elapsed_time": "2:16:30", "remaining_time": "2:49:18"}
|
| 155 |
+
{"current_steps": 310, "total_steps": 690, "loss": 1.1746755838394165, "lr": 8.376014015297057e-06, "epoch": 1.3478260869565217, "percentage": 44.93, "elapsed_time": "2:17:20", "remaining_time": "2:48:21"}
|
| 156 |
+
{"current_steps": 312, "total_steps": 690, "loss": 0.28953975439071655, "lr": 8.643115429631413e-06, "epoch": 1.3565217391304347, "percentage": 45.22, "elapsed_time": "2:17:44", "remaining_time": "2:46:53"}
|
| 157 |
+
{"current_steps": 314, "total_steps": 690, "loss": 1.2791374921798706, "lr": 8.917344318134601e-06, "epoch": 1.365217391304348, "percentage": 45.51, "elapsed_time": "2:18:39", "remaining_time": "2:46:02"}
|
| 158 |
+
{"current_steps": 316, "total_steps": 690, "loss": 1.5186599493026733, "lr": 9.198473588261906e-06, "epoch": 1.373913043478261, "percentage": 45.8, "elapsed_time": "2:19:53", "remaining_time": "2:45:33"}
|
| 159 |
+
{"current_steps": 318, "total_steps": 690, "loss": 0.7900709509849548, "lr": 9.48627043317196e-06, "epoch": 1.382608695652174, "percentage": 46.09, "elapsed_time": "2:20:33", "remaining_time": "2:44:25"}
|
| 160 |
+
{"current_steps": 320, "total_steps": 690, "loss": 1.5395351648330688, "lr": 9.780496524517107e-06, "epoch": 1.391304347826087, "percentage": 46.38, "elapsed_time": "2:21:45", "remaining_time": "2:43:54"}
|
| 161 |
+
{"current_steps": 322, "total_steps": 690, "loss": 0.7073770761489868, "lr": 1.0080908209806292e-05, "epoch": 1.4, "percentage": 46.67, "elapsed_time": "2:22:26", "remaining_time": "2:42:47"}
|
| 162 |
+
{"current_steps": 324, "total_steps": 690, "loss": 1.3696300983428955, "lr": 1.0387256714176855e-05, "epoch": 1.4086956521739131, "percentage": 46.96, "elapsed_time": "2:23:30", "remaining_time": "2:42:06"}
|
| 163 |
+
{"current_steps": 326, "total_steps": 690, "loss": 0.7893473505973816, "lr": 1.0699288346408284e-05, "epoch": 1.4173913043478261, "percentage": 47.25, "elapsed_time": "2:24:16", "remaining_time": "2:41:05"}
|
| 164 |
+
{"current_steps": 328, "total_steps": 690, "loss": 1.0100047588348389, "lr": 1.1016744709007203e-05, "epoch": 1.4260869565217391, "percentage": 47.54, "elapsed_time": "2:25:04", "remaining_time": "2:40:06"}
|
| 165 |
+
{"current_steps": 330, "total_steps": 690, "loss": 0.8350800275802612, "lr": 1.1339362912189803e-05, "epoch": 1.434782608695652, "percentage": 47.83, "elapsed_time": "2:25:44", "remaining_time": "2:38:59"}
|
| 166 |
+
{"current_steps": 332, "total_steps": 690, "loss": 1.2977509498596191, "lr": 1.1666875791584241e-05, "epoch": 1.4434782608695653, "percentage": 48.12, "elapsed_time": "2:26:58", "remaining_time": "2:38:28"}
|
| 167 |
+
{"current_steps": 334, "total_steps": 690, "loss": 0.7434523105621338, "lr": 1.1999012129473044e-05, "epoch": 1.4521739130434783, "percentage": 48.41, "elapsed_time": "2:27:46", "remaining_time": "2:37:30"}
|
| 168 |
+
{"current_steps": 336, "total_steps": 690, "loss": 0.9966728091239929, "lr": 1.2335496879392006e-05, "epoch": 1.4608695652173913, "percentage": 48.7, "elapsed_time": "2:28:38", "remaining_time": "2:36:36"}
|
| 169 |
+
{"current_steps": 338, "total_steps": 690, "loss": 1.2345221042633057, "lr": 1.267605139389983e-05, "epoch": 1.4695652173913043, "percentage": 48.99, "elapsed_time": "2:29:54", "remaining_time": "2:36:06"}
|
| 170 |
+
{"current_steps": 340, "total_steps": 690, "loss": 0.4076097905635834, "lr": 1.3020393655329656e-05, "epoch": 1.4782608695652173, "percentage": 49.28, "elapsed_time": "2:30:19", "remaining_time": "2:34:44"}
|
| 171 |
+
{"current_steps": 342, "total_steps": 690, "loss": 1.0471733808517456, "lr": 1.3368238509331685e-05, "epoch": 1.4869565217391305, "percentage": 49.57, "elapsed_time": "2:31:12", "remaining_time": "2:33:51"}
|
| 172 |
+
{"current_steps": 344, "total_steps": 690, "loss": 1.2860357761383057, "lr": 1.3719297901013182e-05, "epoch": 1.4956521739130435, "percentage": 49.86, "elapsed_time": "2:32:17", "remaining_time": "2:33:10"}
|
| 173 |
+
{"current_steps": 346, "total_steps": 690, "loss": 1.0981141328811646, "lr": 1.4073281113480556e-05, "epoch": 1.5043478260869565, "percentage": 50.14, "elapsed_time": "2:33:07", "remaining_time": "2:32:14"}
|
| 174 |
+
{"current_steps": 348, "total_steps": 690, "loss": 1.5693000555038452, "lr": 1.4429895008585773e-05, "epoch": 1.5130434782608697, "percentage": 50.43, "elapsed_time": "2:34:20", "remaining_time": "2:31:40"}
|
| 175 |
+
{"current_steps": 350, "total_steps": 690, "loss": 0.15966485440731049, "lr": 1.4788844269678e-05, "epoch": 1.5217391304347827, "percentage": 50.72, "elapsed_time": "2:34:45", "remaining_time": "2:30:20"}
|
| 176 |
+
{"current_steps": 352, "total_steps": 690, "loss": 0.7595433592796326, "lr": 1.514983164615912e-05, "epoch": 1.5304347826086957, "percentage": 51.01, "elapsed_time": "2:35:25", "remaining_time": "2:29:14"}
|
| 177 |
+
{"current_steps": 354, "total_steps": 690, "loss": 0.8960363268852234, "lr": 1.5512558199640922e-05, "epoch": 1.5391304347826087, "percentage": 51.3, "elapsed_time": "2:36:14", "remaining_time": "2:28:18"}
|
| 178 |
+
{"current_steps": 356, "total_steps": 690, "loss": 0.7889991998672485, "lr": 1.587672355149983e-05, "epoch": 1.5478260869565217, "percentage": 51.59, "elapsed_time": "2:37:03", "remaining_time": "2:27:21"}
|
| 179 |
+
{"current_steps": 358, "total_steps": 690, "loss": 0.74623703956604, "lr": 1.6242026131624477e-05, "epoch": 1.5565217391304347, "percentage": 51.88, "elapsed_time": "2:37:54", "remaining_time": "2:26:25"}
|
| 180 |
+
{"current_steps": 360, "total_steps": 690, "loss": 1.2382371425628662, "lr": 1.6608163428149812e-05, "epoch": 1.5652173913043477, "percentage": 52.17, "elapsed_time": "2:39:08", "remaining_time": "2:25:52"}
|
| 181 |
+
{"current_steps": 362, "total_steps": 690, "loss": 0.7253771424293518, "lr": 1.697483223797118e-05, "epoch": 1.5739130434782609, "percentage": 52.46, "elapsed_time": "2:39:58", "remaining_time": "2:24:56"}
|
| 182 |
+
{"current_steps": 364, "total_steps": 690, "loss": 0.6049482822418213, "lr": 1.734172891783075e-05, "epoch": 1.5826086956521739, "percentage": 52.75, "elapsed_time": "2:40:26", "remaining_time": "2:23:41"}
|
| 183 |
+
{"current_steps": 366, "total_steps": 690, "loss": 0.658636212348938, "lr": 1.7708549635768553e-05, "epoch": 1.591304347826087, "percentage": 53.04, "elapsed_time": "2:40:57", "remaining_time": "2:22:29"}
|
| 184 |
+
{"current_steps": 368, "total_steps": 690, "loss": 1.2467550039291382, "lr": 1.8074990622729676e-05, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "2:42:11", "remaining_time": "2:21:55"}
|
| 185 |
+
{"current_steps": 370, "total_steps": 690, "loss": 0.332572340965271, "lr": 1.8440748424119435e-05, "epoch": 1.608695652173913, "percentage": 53.62, "elapsed_time": "2:42:36", "remaining_time": "2:20:38"}
|
| 186 |
+
{"current_steps": 372, "total_steps": 690, "loss": 0.7649952173233032, "lr": 1.8805520151098043e-05, "epoch": 1.617391304347826, "percentage": 53.91, "elapsed_time": "2:43:26", "remaining_time": "2:19:42"}
|
| 187 |
+
{"current_steps": 374, "total_steps": 690, "loss": 0.8258912563323975, "lr": 1.916900373140691e-05, "epoch": 1.626086956521739, "percentage": 54.2, "elapsed_time": "2:44:14", "remaining_time": "2:18:46"}
|
| 188 |
+
{"current_steps": 376, "total_steps": 690, "loss": 1.243992805480957, "lr": 1.9530898159518646e-05, "epoch": 1.634782608695652, "percentage": 54.49, "elapsed_time": "2:45:28", "remaining_time": "2:18:11"}
|
| 189 |
+
{"current_steps": 378, "total_steps": 690, "loss": 0.7369431853294373, "lr": 1.9890903745903662e-05, "epoch": 1.643478260869565, "percentage": 54.78, "elapsed_time": "2:46:17", "remaining_time": "2:17:15"}
|
| 190 |
+
{"current_steps": 380, "total_steps": 690, "loss": 1.2425155639648438, "lr": 2.0248722365206985e-05, "epoch": 1.6521739130434783, "percentage": 55.07, "elapsed_time": "2:47:14", "remaining_time": "2:16:26"}
|
| 191 |
+
{"current_steps": 382, "total_steps": 690, "loss": 0.8069741129875183, "lr": 2.060405770312981e-05, "epoch": 1.6608695652173913, "percentage": 55.36, "elapsed_time": "2:48:04", "remaining_time": "2:15:30"}
|
| 192 |
+
{"current_steps": 384, "total_steps": 690, "loss": 0.7547456622123718, "lr": 2.0956615501811323e-05, "epoch": 1.6695652173913045, "percentage": 55.65, "elapsed_time": "2:48:54", "remaining_time": "2:14:35"}
|
| 193 |
+
{"current_steps": 386, "total_steps": 690, "loss": 1.0529491901397705, "lr": 2.1306103803507364e-05, "epoch": 1.6782608695652175, "percentage": 55.94, "elapsed_time": "2:49:47", "remaining_time": "2:13:42"}
|
| 194 |
+
{"current_steps": 388, "total_steps": 690, "loss": 1.4707834720611572, "lr": 2.1652233192364604e-05, "epoch": 1.6869565217391305, "percentage": 56.23, "elapsed_time": "2:50:52", "remaining_time": "2:12:59"}
|
| 195 |
+
{"current_steps": 390, "total_steps": 690, "loss": 0.7649831771850586, "lr": 2.1994717034089493e-05, "epoch": 1.6956521739130435, "percentage": 56.52, "elapsed_time": "2:51:41", "remaining_time": "2:12:04"}
|
| 196 |
+
{"current_steps": 392, "total_steps": 690, "loss": 1.237856388092041, "lr": 2.2333271713314037e-05, "epoch": 1.7043478260869565, "percentage": 56.81, "elapsed_time": "2:52:47", "remaining_time": "2:11:21"}
|
| 197 |
+
{"current_steps": 394, "total_steps": 690, "loss": 1.2670764923095703, "lr": 2.2667616868461238e-05, "epoch": 1.7130434782608694, "percentage": 57.1, "elapsed_time": "2:54:01", "remaining_time": "2:10:44"}
|
| 198 |
+
{"current_steps": 396, "total_steps": 690, "loss": 1.2364072799682617, "lr": 2.299747562391633e-05, "epoch": 1.7217391304347827, "percentage": 57.39, "elapsed_time": "2:55:16", "remaining_time": "2:10:07"}
|
| 199 |
+
{"current_steps": 398, "total_steps": 690, "loss": 0.7167130708694458, "lr": 2.332257481931103e-05, "epoch": 1.7304347826086957, "percentage": 57.68, "elapsed_time": "2:56:06", "remaining_time": "2:09:12"}
|
| 200 |
+
{"current_steps": 400, "total_steps": 690, "loss": 0.7211905717849731, "lr": 2.3642645235731285e-05, "epoch": 1.7391304347826086, "percentage": 57.97, "elapsed_time": "2:56:55", "remaining_time": "2:08:16"}
|
| 201 |
+
{"current_steps": 402, "total_steps": 690, "loss": 0.7387893795967102, "lr": 2.3957421818660958e-05, "epoch": 1.7478260869565219, "percentage": 58.26, "elapsed_time": "2:57:45", "remaining_time": "2:07:20"}
|
| 202 |
+
{"current_steps": 404, "total_steps": 690, "loss": 1.2366782426834106, "lr": 2.4266643897476975e-05, "epoch": 1.7565217391304349, "percentage": 58.55, "elapsed_time": "2:59:01", "remaining_time": "2:06:43"}
|
| 203 |
+
{"current_steps": 406, "total_steps": 690, "loss": 0.7809978127479553, "lr": 2.457005540131405e-05, "epoch": 1.7652173913043478, "percentage": 58.84, "elapsed_time": "2:59:41", "remaining_time": "2:05:41"}
|
| 204 |
+
{"current_steps": 408, "total_steps": 690, "loss": 1.1861432790756226, "lr": 2.4867405071120378e-05, "epoch": 1.7739130434782608, "percentage": 59.13, "elapsed_time": "3:00:37", "remaining_time": "2:04:50"}
|
| 205 |
+
{"current_steps": 410, "total_steps": 690, "loss": 1.2835782766342163, "lr": 2.5158446667728563e-05, "epoch": 1.7826086956521738, "percentage": 59.42, "elapsed_time": "3:01:41", "remaining_time": "2:04:04"}
|
| 206 |
+
{"current_steps": 412, "total_steps": 690, "loss": 0.26566827297210693, "lr": 2.5442939175769457e-05, "epoch": 1.7913043478260868, "percentage": 59.71, "elapsed_time": "3:02:05", "remaining_time": "2:02:52"}
|
| 207 |
+
{"current_steps": 414, "total_steps": 690, "loss": 1.253092646598816, "lr": 2.5720647003260177e-05, "epoch": 1.8, "percentage": 60.0, "elapsed_time": "3:03:01", "remaining_time": "2:02:00"}
|
| 208 |
+
{"current_steps": 416, "total_steps": 690, "loss": 1.298421859741211, "lr": 2.5991340176700945e-05, "epoch": 1.808695652173913, "percentage": 60.29, "elapsed_time": "3:04:04", "remaining_time": "2:01:14"}
|
| 209 |
+
{"current_steps": 418, "total_steps": 690, "loss": 1.5727579593658447, "lr": 2.6254794531519122e-05, "epoch": 1.8173913043478263, "percentage": 60.58, "elapsed_time": "3:05:17", "remaining_time": "2:00:34"}
|
| 210 |
+
{"current_steps": 420, "total_steps": 690, "loss": 1.372650146484375, "lr": 2.6510791897702884e-05, "epoch": 1.8260869565217392, "percentage": 60.87, "elapsed_time": "3:06:30", "remaining_time": "1:59:53"}
|
| 211 |
+
{"current_steps": 422, "total_steps": 690, "loss": 1.5493252277374268, "lr": 2.675912028047062e-05, "epoch": 1.8347826086956522, "percentage": 61.16, "elapsed_time": "3:07:42", "remaining_time": "1:59:12"}
|
| 212 |
+
{"current_steps": 424, "total_steps": 690, "loss": 0.7752541899681091, "lr": 2.6999574035826618e-05, "epoch": 1.8434782608695652, "percentage": 61.45, "elapsed_time": "3:08:22", "remaining_time": "1:58:10"}
|
| 213 |
+
{"current_steps": 426, "total_steps": 690, "loss": 1.3314841985702515, "lr": 2.7231954040857604e-05, "epoch": 1.8521739130434782, "percentage": 61.74, "elapsed_time": "3:09:33", "remaining_time": "1:57:28"}
|
| 214 |
+
{"current_steps": 428, "total_steps": 690, "loss": 0.36442431807518005, "lr": 2.745606785862895e-05, "epoch": 1.8608695652173912, "percentage": 62.03, "elapsed_time": "3:09:57", "remaining_time": "1:56:17"}
|
| 215 |
+
{"current_steps": 430, "total_steps": 690, "loss": 0.6660992503166199, "lr": 2.767172989754432e-05, "epoch": 1.8695652173913042, "percentage": 62.32, "elapsed_time": "3:10:25", "remaining_time": "1:55:08"}
|
| 216 |
+
{"current_steps": 432, "total_steps": 690, "loss": 1.5394024848937988, "lr": 2.7878761565036436e-05, "epoch": 1.8782608695652174, "percentage": 62.61, "elapsed_time": "3:11:28", "remaining_time": "1:54:20"}
|
| 217 |
+
{"current_steps": 434, "total_steps": 690, "loss": 0.7698279619216919, "lr": 2.807699141546199e-05, "epoch": 1.8869565217391304, "percentage": 62.9, "elapsed_time": "3:12:17", "remaining_time": "1:53:25"}
|
| 218 |
+
{"current_steps": 436, "total_steps": 690, "loss": 1.2329353094100952, "lr": 2.826625529207797e-05, "epoch": 1.8956521739130436, "percentage": 63.19, "elapsed_time": "3:13:31", "remaining_time": "1:52:44"}
|
| 219 |
+
{"current_steps": 438, "total_steps": 690, "loss": 1.2454890012741089, "lr": 2.844639646298208e-05, "epoch": 1.9043478260869566, "percentage": 63.48, "elapsed_time": "3:14:37", "remaining_time": "1:51:58"}
|
| 220 |
+
{"current_steps": 440, "total_steps": 690, "loss": 1.2287697792053223, "lr": 2.8617265750904434e-05, "epoch": 1.9130434782608696, "percentage": 63.77, "elapsed_time": "3:15:43", "remaining_time": "1:51:12"}
|
| 221 |
+
{"current_steps": 442, "total_steps": 690, "loss": 0.7477931976318359, "lr": 2.8778721656743252e-05, "epoch": 1.9217391304347826, "percentage": 64.06, "elapsed_time": "3:16:32", "remaining_time": "1:50:16"}
|
| 222 |
+
{"current_steps": 444, "total_steps": 690, "loss": 1.2804430723190308, "lr": 2.893063047674209e-05, "epoch": 1.9304347826086956, "percentage": 64.35, "elapsed_time": "3:17:47", "remaining_time": "1:49:35"}
|
| 223 |
+
{"current_steps": 446, "total_steps": 690, "loss": 0.7825669646263123, "lr": 2.90728664132117e-05, "epoch": 1.9391304347826086, "percentage": 64.64, "elapsed_time": "3:18:36", "remaining_time": "1:48:39"}
|
| 224 |
+
{"current_steps": 448, "total_steps": 690, "loss": 0.6581708192825317, "lr": 2.9205311678704742e-05, "epoch": 1.9478260869565216, "percentage": 64.93, "elapsed_time": "3:19:26", "remaining_time": "1:47:44"}
|
| 225 |
+
{"current_steps": 450, "total_steps": 690, "loss": 0.7231730222702026, "lr": 2.932785659355714e-05, "epoch": 1.9565217391304348, "percentage": 65.22, "elapsed_time": "3:20:02", "remaining_time": "1:46:41"}
|
| 226 |
+
{"current_steps": 452, "total_steps": 690, "loss": 0.7730036973953247, "lr": 2.944039967671519e-05, "epoch": 1.9652173913043478, "percentage": 65.51, "elapsed_time": "3:20:52", "remaining_time": "1:45:46"}
|
| 227 |
+
{"current_steps": 454, "total_steps": 690, "loss": 0.736638069152832, "lr": 2.9542847729773423e-05, "epoch": 1.973913043478261, "percentage": 65.8, "elapsed_time": "3:21:42", "remaining_time": "1:44:51"}
|
| 228 |
+
{"current_steps": 456, "total_steps": 690, "loss": 0.9782851934432983, "lr": 2.9635115914153388e-05, "epoch": 1.982608695652174, "percentage": 66.09, "elapsed_time": "3:22:31", "remaining_time": "1:43:55"}
|
| 229 |
+
{"current_steps": 458, "total_steps": 690, "loss": 1.236344337463379, "lr": 2.971712782135961e-05, "epoch": 1.991304347826087, "percentage": 66.38, "elapsed_time": "3:23:44", "remaining_time": "1:43:12"}
|
| 230 |
+
{"current_steps": 460, "total_steps": 690, "loss": 1.1338064670562744, "lr": 2.978881553625446e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "3:24:32", "remaining_time": "1:42:16"}
|
| 231 |
+
{"current_steps": 462, "total_steps": 690, "loss": 1.1988855600357056, "lr": 2.9850119693299577e-05, "epoch": 2.008695652173913, "percentage": 66.96, "elapsed_time": "3:25:48", "remaining_time": "1:41:33"}
|
| 232 |
+
{"current_steps": 464, "total_steps": 690, "loss": 0.1962333619594574, "lr": 2.9900989525717243e-05, "epoch": 2.017391304347826, "percentage": 67.25, "elapsed_time": "3:26:12", "remaining_time": "1:40:26"}
|
| 233 |
+
{"current_steps": 466, "total_steps": 690, "loss": 0.12543362379074097, "lr": 2.9941382907531037e-05, "epoch": 2.026086956521739, "percentage": 67.54, "elapsed_time": "3:26:36", "remaining_time": "1:39:18"}
|
| 234 |
+
{"current_steps": 468, "total_steps": 690, "loss": 0.7844517827033997, "lr": 2.9971266388450884e-05, "epoch": 2.034782608695652, "percentage": 67.83, "elapsed_time": "3:27:25", "remaining_time": "1:38:23"}
|
| 235 |
+
{"current_steps": 470, "total_steps": 690, "loss": 0.7644298076629639, "lr": 2.9990615221573707e-05, "epoch": 2.0434782608695654, "percentage": 68.12, "elapsed_time": "3:28:14", "remaining_time": "1:37:28"}
|
| 236 |
+
{"current_steps": 472, "total_steps": 690, "loss": 1.479148268699646, "lr": 2.999941338387663e-05, "epoch": 2.0521739130434784, "percentage": 68.41, "elapsed_time": "3:29:26", "remaining_time": "1:36:43"}
|
| 237 |
+
{"current_steps": 474, "total_steps": 690, "loss": 0.2585853636264801, "lr": 2.999765358948589e-05, "epoch": 2.0608695652173914, "percentage": 68.7, "elapsed_time": "3:29:50", "remaining_time": "1:35:37"}
|
| 238 |
+
{"current_steps": 476, "total_steps": 690, "loss": 1.2844960689544678, "lr": 2.998533729571033e-05, "epoch": 2.0695652173913044, "percentage": 68.99, "elapsed_time": "3:31:03", "remaining_time": "1:34:53"}
|
| 239 |
+
{"current_steps": 478, "total_steps": 690, "loss": 0.7490485906600952, "lr": 2.9962474701834602e-05, "epoch": 2.0782608695652174, "percentage": 69.28, "elapsed_time": "3:31:52", "remaining_time": "1:33:58"}
|
| 240 |
+
{"current_steps": 480, "total_steps": 690, "loss": 1.1616085767745972, "lr": 2.9929084740673027e-05, "epoch": 2.0869565217391304, "percentage": 69.57, "elapsed_time": "3:32:58", "remaining_time": "1:33:10"}
|
| 241 |
+
{"current_steps": 482, "total_steps": 690, "loss": 1.7963777780532837, "lr": 2.9885195062891023e-05, "epoch": 2.0956521739130434, "percentage": 69.86, "elapsed_time": "3:34:09", "remaining_time": "1:32:24"}
|
| 242 |
+
{"current_steps": 484, "total_steps": 690, "loss": 1.2623823881149292, "lr": 2.9830842014107273e-05, "epoch": 2.1043478260869564, "percentage": 70.14, "elapsed_time": "3:35:22", "remaining_time": "1:31:40"}
|
| 243 |
+
{"current_steps": 486, "total_steps": 690, "loss": 0.681275486946106, "lr": 2.9766070604795444e-05, "epoch": 2.1130434782608694, "percentage": 70.43, "elapsed_time": "3:36:12", "remaining_time": "1:30:45"}
|
| 244 |
+
{"current_steps": 488, "total_steps": 690, "loss": 0.6947782039642334, "lr": 2.969093447301039e-05, "epoch": 2.121739130434783, "percentage": 70.72, "elapsed_time": "3:37:02", "remaining_time": "1:29:50"}
|
| 245 |
+
{"current_steps": 490, "total_steps": 690, "loss": 0.6653367877006531, "lr": 2.9605495839969793e-05, "epoch": 2.130434782608696, "percentage": 71.01, "elapsed_time": "3:37:52", "remaining_time": "1:28:55"}
|
| 246 |
+
{"current_steps": 492, "total_steps": 690, "loss": 1.178207278251648, "lr": 2.9509825458527955e-05, "epoch": 2.139130434782609, "percentage": 71.3, "elapsed_time": "3:39:10", "remaining_time": "1:28:12"}
|
| 247 |
+
{"current_steps": 494, "total_steps": 690, "loss": 0.19959603250026703, "lr": 2.940400255458444e-05, "epoch": 2.1478260869565218, "percentage": 71.59, "elapsed_time": "3:39:34", "remaining_time": "1:27:07"}
|
| 248 |
+
{"current_steps": 496, "total_steps": 690, "loss": 1.1562106609344482, "lr": 2.9288114761476036e-05, "epoch": 2.1565217391304348, "percentage": 71.88, "elapsed_time": "3:40:48", "remaining_time": "1:26:21"}
|
| 249 |
+
{"current_steps": 498, "total_steps": 690, "loss": 1.1385471820831299, "lr": 2.916225804740647e-05, "epoch": 2.1652173913043478, "percentage": 72.17, "elapsed_time": "3:42:03", "remaining_time": "1:25:36"}
|
| 250 |
+
{"current_steps": 500, "total_steps": 690, "loss": 0.49375131726264954, "lr": 2.9026536635973857e-05, "epoch": 2.1739130434782608, "percentage": 72.46, "elapsed_time": "3:42:33", "remaining_time": "1:24:34"}
|
| 251 |
+
{"current_steps": 502, "total_steps": 690, "loss": 0.736272394657135, "lr": 2.888106291986178e-05, "epoch": 2.1826086956521737, "percentage": 72.75, "elapsed_time": "3:43:22", "remaining_time": "1:23:39"}
|
| 252 |
+
{"current_steps": 504, "total_steps": 690, "loss": 0.8101549744606018, "lr": 2.872595736776543e-05, "epoch": 2.1913043478260867, "percentage": 73.04, "elapsed_time": "3:44:11", "remaining_time": "1:22:44"}
|
| 253 |
+
{"current_steps": 506, "total_steps": 690, "loss": 0.2909260392189026, "lr": 2.8561348424629893e-05, "epoch": 2.2, "percentage": 73.33, "elapsed_time": "3:44:44", "remaining_time": "1:21:43"}
|
| 254 |
+
{"current_steps": 508, "total_steps": 690, "loss": 0.7722839713096619, "lr": 2.83873724052832e-05, "epoch": 2.208695652173913, "percentage": 73.62, "elapsed_time": "3:45:34", "remaining_time": "1:20:48"}
|
| 255 |
+
{"current_steps": 510, "total_steps": 690, "loss": 0.5638793110847473, "lr": 2.8204173381552252e-05, "epoch": 2.217391304347826, "percentage": 73.91, "elapsed_time": "3:46:00", "remaining_time": "1:19:45"}
|
| 256 |
+
{"current_steps": 512, "total_steps": 690, "loss": 0.31869935989379883, "lr": 2.8011903062955016e-05, "epoch": 2.226086956521739, "percentage": 74.2, "elapsed_time": "3:46:28", "remaining_time": "1:18:44"}
|
| 257 |
+
{"current_steps": 514, "total_steps": 690, "loss": 1.131230354309082, "lr": 2.7810720671067893e-05, "epoch": 2.234782608695652, "percentage": 74.49, "elapsed_time": "3:47:34", "remaining_time": "1:17:55"}
|
| 258 |
+
{"current_steps": 516, "total_steps": 690, "loss": 1.208681344985962, "lr": 2.7600792807672248e-05, "epoch": 2.243478260869565, "percentage": 74.78, "elapsed_time": "3:48:48", "remaining_time": "1:17:09"}
|
| 259 |
+
{"current_steps": 518, "total_steps": 690, "loss": 1.3903454542160034, "lr": 2.7382293316789273e-05, "epoch": 2.252173913043478, "percentage": 75.07, "elapsed_time": "3:49:50", "remaining_time": "1:16:19"}
|
| 260 |
+
{"current_steps": 520, "total_steps": 690, "loss": 0.7094644904136658, "lr": 2.7155403140717488e-05, "epoch": 2.260869565217391, "percentage": 75.36, "elapsed_time": "3:50:41", "remaining_time": "1:15:25"}
|
| 261 |
+
{"current_steps": 522, "total_steps": 690, "loss": 0.7558539509773254, "lr": 2.6920310170192024e-05, "epoch": 2.269565217391304, "percentage": 75.65, "elapsed_time": "3:51:32", "remaining_time": "1:14:31"}
|
| 262 |
+
{"current_steps": 524, "total_steps": 690, "loss": 1.140393853187561, "lr": 2.6677209088789823e-05, "epoch": 2.2782608695652176, "percentage": 75.94, "elapsed_time": "3:52:46", "remaining_time": "1:13:44"}
|
| 263 |
+
{"current_steps": 526, "total_steps": 690, "loss": 1.1117931604385376, "lr": 2.642630121170968e-05, "epoch": 2.2869565217391306, "percentage": 76.23, "elapsed_time": "3:53:51", "remaining_time": "1:12:54"}
|
| 264 |
+
{"current_steps": 528, "total_steps": 690, "loss": 0.6197381019592285, "lr": 2.616779431906042e-05, "epoch": 2.2956521739130435, "percentage": 76.52, "elapsed_time": "3:54:30", "remaining_time": "1:11:57"}
|
| 265 |
+
{"current_steps": 530, "total_steps": 690, "loss": 1.1404460668563843, "lr": 2.5901902483795464e-05, "epoch": 2.3043478260869565, "percentage": 76.81, "elapsed_time": "3:55:27", "remaining_time": "1:11:04"}
|
| 266 |
+
{"current_steps": 532, "total_steps": 690, "loss": 1.110768437385559, "lr": 2.5628845894436232e-05, "epoch": 2.3130434782608695, "percentage": 77.1, "elapsed_time": "3:56:29", "remaining_time": "1:10:14"}
|
| 267 |
+
{"current_steps": 534, "total_steps": 690, "loss": 0.18440936505794525, "lr": 2.5348850672731114e-05, "epoch": 2.3217391304347825, "percentage": 77.39, "elapsed_time": "3:56:54", "remaining_time": "1:09:12"}
|
| 268 |
+
{"current_steps": 536, "total_steps": 690, "loss": 0.6152647137641907, "lr": 2.506214868640111e-05, "epoch": 2.3304347826086955, "percentage": 77.68, "elapsed_time": "3:57:43", "remaining_time": "1:08:18"}
|
| 269 |
+
{"current_steps": 538, "total_steps": 690, "loss": 0.6943525075912476, "lr": 2.4768977357127068e-05, "epoch": 2.3391304347826085, "percentage": 77.97, "elapsed_time": "3:58:33", "remaining_time": "1:07:23"}
|
| 270 |
+
{"current_steps": 540, "total_steps": 690, "loss": 1.155451774597168, "lr": 2.4469579463937736e-05, "epoch": 2.3478260869565215, "percentage": 78.26, "elapsed_time": "3:59:46", "remaining_time": "1:06:36"}
|
| 271 |
+
{"current_steps": 542, "total_steps": 690, "loss": 0.6562126874923706, "lr": 2.4164202942161202e-05, "epoch": 2.356521739130435, "percentage": 78.55, "elapsed_time": "4:00:35", "remaining_time": "1:05:41"}
|
| 272 |
+
{"current_steps": 544, "total_steps": 690, "loss": 1.1728577613830566, "lr": 2.385310067810646e-05, "epoch": 2.365217391304348, "percentage": 78.84, "elapsed_time": "4:01:47", "remaining_time": "1:04:53"}
|
| 273 |
+
{"current_steps": 546, "total_steps": 690, "loss": 0.7028173208236694, "lr": 2.353653029964486e-05, "epoch": 2.373913043478261, "percentage": 79.13, "elapsed_time": "4:02:35", "remaining_time": "1:03:58"}
|
| 274 |
+
{"current_steps": 548, "total_steps": 690, "loss": 1.0240296125411987, "lr": 2.3214753962865128e-05, "epoch": 2.382608695652174, "percentage": 79.42, "elapsed_time": "4:03:23", "remaining_time": "1:03:04"}
|
| 275 |
+
{"current_steps": 550, "total_steps": 690, "loss": 0.6851329207420349, "lr": 2.2888038134978446e-05, "epoch": 2.391304347826087, "percentage": 79.71, "elapsed_time": "4:04:13", "remaining_time": "1:02:09"}
|
| 276 |
+
{"current_steps": 552, "total_steps": 690, "loss": 1.1324046850204468, "lr": 2.2556653373653506e-05, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "4:05:08", "remaining_time": "1:01:17"}
|
| 277 |
+
{"current_steps": 554, "total_steps": 690, "loss": 0.5204906463623047, "lr": 2.2220874102964066e-05, "epoch": 2.408695652173913, "percentage": 80.29, "elapsed_time": "4:05:35", "remaining_time": "1:00:17"}
|
| 278 |
+
{"current_steps": 556, "total_steps": 690, "loss": 1.3587431907653809, "lr": 2.1880978386134822e-05, "epoch": 2.417391304347826, "percentage": 80.58, "elapsed_time": "4:06:47", "remaining_time": "0:59:28"}
|
| 279 |
+
{"current_steps": 558, "total_steps": 690, "loss": 0.15599098801612854, "lr": 2.1537247695273588e-05, "epoch": 2.426086956521739, "percentage": 80.87, "elapsed_time": "4:07:12", "remaining_time": "0:58:28"}
|
| 280 |
+
{"current_steps": 560, "total_steps": 690, "loss": 1.1518821716308594, "lr": 2.1189966678280585e-05, "epoch": 2.4347826086956523, "percentage": 81.16, "elapsed_time": "4:08:06", "remaining_time": "0:57:35"}
|
| 281 |
+
{"current_steps": 562, "total_steps": 690, "loss": 0.5007261037826538, "lr": 2.0839422923127686e-05, "epoch": 2.4434782608695653, "percentage": 81.45, "elapsed_time": "4:08:35", "remaining_time": "0:56:37"}
|
| 282 |
+
{"current_steps": 564, "total_steps": 690, "loss": 1.1414357423782349, "lr": 2.0485906719703126e-05, "epoch": 2.4521739130434783, "percentage": 81.74, "elapsed_time": "4:09:40", "remaining_time": "0:55:46"}
|
| 283 |
+
{"current_steps": 566, "total_steps": 690, "loss": 0.6164332032203674, "lr": 2.0129710819418574e-05, "epoch": 2.4608695652173913, "percentage": 82.03, "elapsed_time": "4:10:31", "remaining_time": "0:54:53"}
|
| 284 |
+
{"current_steps": 568, "total_steps": 690, "loss": 1.0142958164215088, "lr": 1.9771130192777892e-05, "epoch": 2.4695652173913043, "percentage": 82.32, "elapsed_time": "4:11:05", "remaining_time": "0:53:55"}
|
| 285 |
+
{"current_steps": 570, "total_steps": 690, "loss": 0.7631978392601013, "lr": 1.9410461785108178e-05, "epoch": 2.4782608695652173, "percentage": 82.61, "elapsed_time": "4:12:03", "remaining_time": "0:53:03"}
|
| 286 |
+
{"current_steps": 572, "total_steps": 690, "loss": 1.2384475469589233, "lr": 1.9048004270655354e-05, "epoch": 2.4869565217391303, "percentage": 82.9, "elapsed_time": "4:13:16", "remaining_time": "0:52:15"}
|
| 287 |
+
{"current_steps": 574, "total_steps": 690, "loss": 0.38715630769729614, "lr": 1.868405780524824e-05, "epoch": 2.4956521739130437, "percentage": 83.19, "elapsed_time": "4:13:43", "remaining_time": "0:51:16"}
|
| 288 |
+
{"current_steps": 576, "total_steps": 690, "loss": 1.1841545104980469, "lr": 1.831892377773547e-05, "epoch": 2.5043478260869563, "percentage": 83.48, "elapsed_time": "4:14:57", "remaining_time": "0:50:27"}
|
| 289 |
+
{"current_steps": 578, "total_steps": 690, "loss": 1.3352640867233276, "lr": 1.795290456040148e-05, "epoch": 2.5130434782608697, "percentage": 83.77, "elapsed_time": "4:16:10", "remaining_time": "0:49:38"}
|
| 290 |
+
{"current_steps": 580, "total_steps": 690, "loss": 0.6390936374664307, "lr": 1.7586303258567964e-05, "epoch": 2.5217391304347827, "percentage": 84.06, "elapsed_time": "4:17:00", "remaining_time": "0:48:44"}
|
| 291 |
+
{"current_steps": 582, "total_steps": 690, "loss": 0.9683659672737122, "lr": 1.7219423459588513e-05, "epoch": 2.5304347826086957, "percentage": 84.35, "elapsed_time": "4:17:47", "remaining_time": "0:47:50"}
|
| 292 |
+
{"current_steps": 584, "total_steps": 690, "loss": 1.1052292585372925, "lr": 1.6852568981443806e-05, "epoch": 2.5391304347826087, "percentage": 84.64, "elapsed_time": "4:19:03", "remaining_time": "0:47:01"}
|
| 293 |
+
{"current_steps": 586, "total_steps": 690, "loss": 0.708678126335144, "lr": 1.648604362114606e-05, "epoch": 2.5478260869565217, "percentage": 84.93, "elapsed_time": "4:19:52", "remaining_time": "0:46:07"}
|
| 294 |
+
{"current_steps": 588, "total_steps": 690, "loss": 0.06356725841760635, "lr": 1.6120150903160605e-05, "epoch": 2.5565217391304347, "percentage": 85.22, "elapsed_time": "4:20:16", "remaining_time": "0:45:08"}
|
| 295 |
+
{"current_steps": 590, "total_steps": 690, "loss": 0.694472074508667, "lr": 1.5755193828053435e-05, "epoch": 2.5652173913043477, "percentage": 85.51, "elapsed_time": "4:21:06", "remaining_time": "0:44:15"}
|
| 296 |
+
{"current_steps": 592, "total_steps": 690, "loss": 0.09391395002603531, "lr": 1.539147462157235e-05, "epoch": 2.573913043478261, "percentage": 85.8, "elapsed_time": "4:21:30", "remaining_time": "0:43:17"}
|
| 297 |
+
{"current_steps": 594, "total_steps": 690, "loss": 1.3817299604415894, "lr": 1.5029294484369874e-05, "epoch": 2.5826086956521737, "percentage": 86.09, "elapsed_time": "4:22:38", "remaining_time": "0:42:26"}
|
| 298 |
+
{"current_steps": 596, "total_steps": 690, "loss": 0.28024399280548096, "lr": 1.4668953342575074e-05, "epoch": 2.591304347826087, "percentage": 86.38, "elapsed_time": "4:23:03", "remaining_time": "0:41:29"}
|
| 299 |
+
{"current_steps": 598, "total_steps": 690, "loss": 0.4380612373352051, "lr": 1.4310749599420711e-05, "epoch": 2.6, "percentage": 86.67, "elapsed_time": "4:23:29", "remaining_time": "0:40:32"}
|
| 300 |
+
{"current_steps": 600, "total_steps": 690, "loss": 1.1383816003799438, "lr": 1.3954979888131745e-05, "epoch": 2.608695652173913, "percentage": 86.96, "elapsed_time": "4:24:42", "remaining_time": "0:39:42"}
|
| 301 |
+
{"current_steps": 602, "total_steps": 690, "loss": 0.6719468235969543, "lr": 1.3601938826279298e-05, "epoch": 2.617391304347826, "percentage": 87.25, "elapsed_time": "4:25:34", "remaining_time": "0:38:49"}
|
| 302 |
+
{"current_steps": 604, "total_steps": 690, "loss": 0.8287115097045898, "lr": 1.325191877180408e-05, "epoch": 2.626086956521739, "percentage": 87.54, "elapsed_time": "4:26:21", "remaining_time": "0:37:55"}
|
| 303 |
+
{"current_steps": 606, "total_steps": 690, "loss": 0.6804332137107849, "lr": 1.2905209580910897e-05, "epoch": 2.634782608695652, "percentage": 87.83, "elapsed_time": "4:26:55", "remaining_time": "0:36:59"}
|
| 304 |
+
{"current_steps": 608, "total_steps": 690, "loss": 1.1206378936767578, "lr": 1.2562098368034954e-05, "epoch": 2.643478260869565, "percentage": 88.12, "elapsed_time": "4:28:08", "remaining_time": "0:36:09"}
|
| 305 |
+
{"current_steps": 610, "total_steps": 690, "loss": 0.7674025297164917, "lr": 1.2222869268078575e-05, "epoch": 2.6521739130434785, "percentage": 88.41, "elapsed_time": "4:28:42", "remaining_time": "0:35:14"}
|
| 306 |
+
{"current_steps": 612, "total_steps": 690, "loss": 1.1401374340057373, "lr": 1.1887803201115396e-05, "epoch": 2.660869565217391, "percentage": 88.7, "elapsed_time": "4:29:56", "remaining_time": "0:34:24"}
|
| 307 |
+
{"current_steps": 614, "total_steps": 690, "loss": 1.3836885690689087, "lr": 1.1557177639756725e-05, "epoch": 2.6695652173913045, "percentage": 88.99, "elapsed_time": "4:31:08", "remaining_time": "0:33:33"}
|
| 308 |
+
{"current_steps": 616, "total_steps": 690, "loss": 0.737335205078125, "lr": 1.1231266379372912e-05, "epoch": 2.6782608695652175, "percentage": 89.28, "elapsed_time": "4:31:52", "remaining_time": "0:32:39"}
|
| 309 |
+
{"current_steps": 618, "total_steps": 690, "loss": 0.6436473727226257, "lr": 1.0910339311359677e-05, "epoch": 2.6869565217391305, "percentage": 89.57, "elapsed_time": "4:32:42", "remaining_time": "0:31:46"}
|
| 310 |
+
{"current_steps": 620, "total_steps": 690, "loss": 0.7471338510513306, "lr": 1.0594662199637597e-05, "epoch": 2.6956521739130435, "percentage": 89.86, "elapsed_time": "4:33:30", "remaining_time": "0:30:52"}
|
| 311 |
+
{"current_steps": 622, "total_steps": 690, "loss": 1.1643157005310059, "lr": 1.028449646056948e-05, "epoch": 2.7043478260869565, "percentage": 90.14, "elapsed_time": "4:34:45", "remaining_time": "0:30:02"}
|
| 312 |
+
{"current_steps": 624, "total_steps": 690, "loss": 1.1436272859573364, "lr": 9.980098946478024e-06, "epoch": 2.7130434782608694, "percentage": 90.43, "elapsed_time": "4:35:50", "remaining_time": "0:29:10"}
|
| 313 |
+
{"current_steps": 626, "total_steps": 690, "loss": 1.134834885597229, "lr": 9.68172173294313e-06, "epoch": 2.7217391304347824, "percentage": 90.72, "elapsed_time": "4:37:06", "remaining_time": "0:28:19"}
|
| 314 |
+
{"current_steps": 628, "total_steps": 690, "loss": 1.237627625465393, "lr": 9.389611910054602e-06, "epoch": 2.730434782608696, "percentage": 91.01, "elapsed_time": "4:38:19", "remaining_time": "0:27:28"}
|
| 315 |
+
{"current_steps": 630, "total_steps": 690, "loss": 1.1352347135543823, "lr": 9.10401137779385e-06, "epoch": 2.7391304347826084, "percentage": 91.3, "elapsed_time": "4:39:34", "remaining_time": "0:26:37"}
|
| 316 |
+
{"current_steps": 632, "total_steps": 690, "loss": 0.46068328619003296, "lr": 8.825156645713136e-06, "epoch": 2.747826086956522, "percentage": 91.59, "elapsed_time": "4:40:02", "remaining_time": "0:25:42"}
|
| 317 |
+
{"current_steps": 634, "total_steps": 690, "loss": 0.6736262440681458, "lr": 8.553278637079007e-06, "epoch": 2.756521739130435, "percentage": 91.88, "elapsed_time": "4:40:52", "remaining_time": "0:24:48"}
|
| 318 |
+
{"current_steps": 636, "total_steps": 690, "loss": 0.6648976802825928, "lr": 8.28860249764168e-06, "epoch": 2.765217391304348, "percentage": 92.17, "elapsed_time": "4:41:41", "remaining_time": "0:23:55"}
|
| 319 |
+
{"current_steps": 638, "total_steps": 690, "loss": 1.132703423500061, "lr": 8.031347409188885e-06, "epoch": 2.773913043478261, "percentage": 92.46, "elapsed_time": "4:42:46", "remaining_time": "0:23:02"}
|
| 320 |
+
{"current_steps": 640, "total_steps": 690, "loss": 1.2038984298706055, "lr": 7.78172640803854e-06, "epoch": 2.782608695652174, "percentage": 92.75, "elapsed_time": "4:43:49", "remaining_time": "0:22:10"}
|
| 321 |
+
{"current_steps": 642, "total_steps": 690, "loss": 1.206749677658081, "lr": 7.539946208620638e-06, "epoch": 2.791304347826087, "percentage": 93.04, "elapsed_time": "4:45:00", "remaining_time": "0:21:18"}
|
| 322 |
+
{"current_steps": 644, "total_steps": 690, "loss": 0.7191698551177979, "lr": 7.306207032294216e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "4:45:49", "remaining_time": "0:20:24"}
|
| 323 |
+
{"current_steps": 646, "total_steps": 690, "loss": 0.7605520486831665, "lr": 7.08070244154148e-06, "epoch": 2.8086956521739133, "percentage": 93.62, "elapsed_time": "4:46:36", "remaining_time": "0:19:31"}
|
| 324 |
+
{"current_steps": 648, "total_steps": 690, "loss": 0.6928582787513733, "lr": 6.8636191796761585e-06, "epoch": 2.8173913043478263, "percentage": 93.91, "elapsed_time": "4:47:12", "remaining_time": "0:18:36"}
|
| 325 |
+
{"current_steps": 650, "total_steps": 690, "loss": 1.3508784770965576, "lr": 6.655137016198907e-06, "epoch": 2.8260869565217392, "percentage": 94.2, "elapsed_time": "4:48:25", "remaining_time": "0:17:44"}
|
| 326 |
+
{"current_steps": 652, "total_steps": 690, "loss": 0.9979486465454102, "lr": 6.455428597927829e-06, "epoch": 2.8347826086956522, "percentage": 94.49, "elapsed_time": "4:49:02", "remaining_time": "0:16:50"}
|
| 327 |
+
{"current_steps": 654, "total_steps": 690, "loss": 1.139778971672058, "lr": 6.264659306027376e-06, "epoch": 2.8434782608695652, "percentage": 94.78, "elapsed_time": "4:50:16", "remaining_time": "0:15:58"}
|
| 328 |
+
{"current_steps": 656, "total_steps": 690, "loss": 0.8573166728019714, "lr": 6.082987119054014e-06, "epoch": 2.8521739130434782, "percentage": 95.07, "elapsed_time": "4:50:49", "remaining_time": "0:15:04"}
|
| 329 |
+
{"current_steps": 658, "total_steps": 690, "loss": 1.1786668300628662, "lr": 5.910562482132162e-06, "epoch": 2.860869565217391, "percentage": 95.36, "elapsed_time": "4:51:46", "remaining_time": "0:14:11"}
|
| 330 |
+
{"current_steps": 660, "total_steps": 690, "loss": 1.1484174728393555, "lr": 5.747528182368537e-06, "epoch": 2.869565217391304, "percentage": 95.65, "elapsed_time": "4:52:36", "remaining_time": "0:13:18"}
|
| 331 |
+
{"current_steps": 662, "total_steps": 690, "loss": 1.2150859832763672, "lr": 5.594019230608316e-06, "epoch": 2.878260869565217, "percentage": 95.94, "elapsed_time": "4:53:41", "remaining_time": "0:12:25"}
|
| 332 |
+
{"current_steps": 664, "total_steps": 690, "loss": 1.1722112894058228, "lr": 5.4501627496308754e-06, "epoch": 2.8869565217391306, "percentage": 96.23, "elapsed_time": "4:54:55", "remaining_time": "0:11:32"}
|
| 333 |
+
{"current_steps": 666, "total_steps": 690, "loss": 1.1153019666671753, "lr": 5.316077868877737e-06, "epoch": 2.8956521739130436, "percentage": 96.52, "elapsed_time": "4:56:10", "remaining_time": "0:10:40"}
|
| 334 |
+
{"current_steps": 668, "total_steps": 690, "loss": 1.164955496788025, "lr": 5.191875625799956e-06, "epoch": 2.9043478260869566, "percentage": 96.81, "elapsed_time": "4:57:15", "remaining_time": "0:09:47"}
|
| 335 |
+
{"current_steps": 670, "total_steps": 690, "loss": 1.1394230127334595, "lr": 5.077658873906456e-06, "epoch": 2.9130434782608696, "percentage": 97.1, "elapsed_time": "4:58:29", "remaining_time": "0:08:54"}
|
| 336 |
+
{"current_steps": 672, "total_steps": 690, "loss": 0.6004053354263306, "lr": 4.973522197589804e-06, "epoch": 2.9217391304347826, "percentage": 97.39, "elapsed_time": "4:59:01", "remaining_time": "0:08:00"}
|
| 337 |
+
{"current_steps": 674, "total_steps": 690, "loss": 0.8902421593666077, "lr": 4.87955183379954e-06, "epoch": 2.9304347826086956, "percentage": 97.68, "elapsed_time": "4:59:52", "remaining_time": "0:07:07"}
|
| 338 |
+
{"current_steps": 676, "total_steps": 690, "loss": 1.1788089275360107, "lr": 4.795825600628273e-06, "epoch": 2.9391304347826086, "percentage": 97.97, "elapsed_time": "5:01:07", "remaining_time": "0:06:14"}
|
| 339 |
+
{"current_steps": 678, "total_steps": 690, "loss": 1.0090527534484863, "lr": 4.722412832869478e-06, "epoch": 2.9478260869565216, "percentage": 98.26, "elapsed_time": "5:01:53", "remaining_time": "0:05:20"}
|
| 340 |
+
{"current_steps": 680, "total_steps": 690, "loss": 1.156622290611267, "lr": 4.659374324600457e-06, "epoch": 2.9565217391304346, "percentage": 98.55, "elapsed_time": "5:02:58", "remaining_time": "0:04:27"}
|
| 341 |
+
{"current_steps": 682, "total_steps": 690, "loss": 0.44529619812965393, "lr": 4.606762278837947e-06, "epoch": 2.965217391304348, "percentage": 98.84, "elapsed_time": "5:03:29", "remaining_time": "0:03:33"}
|
| 342 |
+
{"current_steps": 684, "total_steps": 690, "loss": 0.7129748463630676, "lr": 4.5646202643081405e-06, "epoch": 2.973913043478261, "percentage": 99.13, "elapsed_time": "5:04:17", "remaining_time": "0:02:40"}
|
| 343 |
+
{"current_steps": 686, "total_steps": 690, "loss": 0.8244656920433044, "lr": 4.532983179366819e-06, "epoch": 2.982608695652174, "percentage": 99.42, "elapsed_time": "5:04:58", "remaining_time": "0:01:46"}
|
| 344 |
+
{"current_steps": 688, "total_steps": 690, "loss": 1.285622477531433, "lr": 4.511877223099601e-06, "epoch": 2.991304347826087, "percentage": 99.71, "elapsed_time": "5:06:02", "remaining_time": "0:00:53"}
|
| 345 |
+
{"current_steps": 690, "total_steps": 690, "loss": 0.6546279191970825, "lr": 4.501319873626102e-06, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:06:50", "remaining_time": "0:00:00"}
|
| 346 |
+
{"current_steps": 690, "total_steps": 690, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "5:07:13", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2458 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 3.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 690,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.008695652173913044,
|
| 14 |
+
"grad_norm": 0.732024610042572,
|
| 15 |
+
"learning_rate": 8.571428571428571e-07,
|
| 16 |
+
"loss": 2.46012020111084,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.017391304347826087,
|
| 21 |
+
"grad_norm": 1.1184877157211304,
|
| 22 |
+
"learning_rate": 2.5714285714285716e-06,
|
| 23 |
+
"loss": 2.301504135131836,
|
| 24 |
+
"step": 4
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02608695652173913,
|
| 28 |
+
"grad_norm": 3.1666553020477295,
|
| 29 |
+
"learning_rate": 4.2857142857142855e-06,
|
| 30 |
+
"loss": 2.9570844173431396,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.034782608695652174,
|
| 35 |
+
"grad_norm": 0.25166502594947815,
|
| 36 |
+
"learning_rate": 6e-06,
|
| 37 |
+
"loss": 1.8961513042449951,
|
| 38 |
+
"step": 8
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.043478260869565216,
|
| 42 |
+
"grad_norm": 0.20189805328845978,
|
| 43 |
+
"learning_rate": 7.714285714285714e-06,
|
| 44 |
+
"loss": 3.0871455669403076,
|
| 45 |
+
"step": 10
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05217391304347826,
|
| 49 |
+
"grad_norm": 0.20353659987449646,
|
| 50 |
+
"learning_rate": 9.428571428571428e-06,
|
| 51 |
+
"loss": 2.292584180831909,
|
| 52 |
+
"step": 12
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.06086956521739131,
|
| 56 |
+
"grad_norm": 0.6789005994796753,
|
| 57 |
+
"learning_rate": 1.1142857142857143e-05,
|
| 58 |
+
"loss": 2.5501410961151123,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06956521739130435,
|
| 63 |
+
"grad_norm": 0.2317086160182953,
|
| 64 |
+
"learning_rate": 1.2857142857142857e-05,
|
| 65 |
+
"loss": 1.931159257888794,
|
| 66 |
+
"step": 16
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.0782608695652174,
|
| 70 |
+
"grad_norm": 1.7764248847961426,
|
| 71 |
+
"learning_rate": 1.4571428571428571e-05,
|
| 72 |
+
"loss": 2.571274518966675,
|
| 73 |
+
"step": 18
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.08695652173913043,
|
| 77 |
+
"grad_norm": 0.4352605640888214,
|
| 78 |
+
"learning_rate": 1.6285714285714283e-05,
|
| 79 |
+
"loss": 1.9101747274398804,
|
| 80 |
+
"step": 20
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.09565217391304348,
|
| 84 |
+
"grad_norm": 0.18403619527816772,
|
| 85 |
+
"learning_rate": 1.8e-05,
|
| 86 |
+
"loss": 1.8424170017242432,
|
| 87 |
+
"step": 22
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.10434782608695652,
|
| 91 |
+
"grad_norm": 0.16127634048461914,
|
| 92 |
+
"learning_rate": 1.9714285714285714e-05,
|
| 93 |
+
"loss": 5.551755905151367,
|
| 94 |
+
"step": 24
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.11304347826086956,
|
| 98 |
+
"grad_norm": 0.1956806778907776,
|
| 99 |
+
"learning_rate": 2.1428571428571428e-05,
|
| 100 |
+
"loss": 1.828694224357605,
|
| 101 |
+
"step": 26
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.12173913043478261,
|
| 105 |
+
"grad_norm": 2.0333733558654785,
|
| 106 |
+
"learning_rate": 2.3142857142857145e-05,
|
| 107 |
+
"loss": 2.4214303493499756,
|
| 108 |
+
"step": 28
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.13043478260869565,
|
| 112 |
+
"grad_norm": 0.24648341536521912,
|
| 113 |
+
"learning_rate": 2.485714285714286e-05,
|
| 114 |
+
"loss": 3.56320858001709,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.1391304347826087,
|
| 119 |
+
"grad_norm": 0.17006301879882812,
|
| 120 |
+
"learning_rate": 2.657142857142857e-05,
|
| 121 |
+
"loss": 1.7686303853988647,
|
| 122 |
+
"step": 32
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14782608695652175,
|
| 126 |
+
"grad_norm": 1.2820721864700317,
|
| 127 |
+
"learning_rate": 2.8285714285714287e-05,
|
| 128 |
+
"loss": 1.9711768627166748,
|
| 129 |
+
"step": 34
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.1565217391304348,
|
| 133 |
+
"grad_norm": 1.2253106832504272,
|
| 134 |
+
"learning_rate": 3e-05,
|
| 135 |
+
"loss": 1.890865683555603,
|
| 136 |
+
"step": 36
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.16521739130434782,
|
| 140 |
+
"grad_norm": 0.15150298178195953,
|
| 141 |
+
"learning_rate": 2.9994720778760907e-05,
|
| 142 |
+
"loss": 1.682741641998291,
|
| 143 |
+
"step": 38
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.17391304347826086,
|
| 147 |
+
"grad_norm": 0.14206662774085999,
|
| 148 |
+
"learning_rate": 2.9978887486836082e-05,
|
| 149 |
+
"loss": 1.8588255643844604,
|
| 150 |
+
"step": 40
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.1826086956521739,
|
| 154 |
+
"grad_norm": 0.18157699704170227,
|
| 155 |
+
"learning_rate": 2.9952513235982553e-05,
|
| 156 |
+
"loss": 1.7579265832901,
|
| 157 |
+
"step": 42
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.19130434782608696,
|
| 161 |
+
"grad_norm": 0.13783733546733856,
|
| 162 |
+
"learning_rate": 2.991561986706388e-05,
|
| 163 |
+
"loss": 3.504922389984131,
|
| 164 |
+
"step": 44
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.2,
|
| 168 |
+
"grad_norm": 0.4945126473903656,
|
| 169 |
+
"learning_rate": 2.9868237931963492e-05,
|
| 170 |
+
"loss": 1.5656976699829102,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.20869565217391303,
|
| 175 |
+
"grad_norm": 1.3513635396957397,
|
| 176 |
+
"learning_rate": 2.9810406668284216e-05,
|
| 177 |
+
"loss": 1.2987524271011353,
|
| 178 |
+
"step": 48
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.21739130434782608,
|
| 182 |
+
"grad_norm": 0.3287999629974365,
|
| 183 |
+
"learning_rate": 2.9742173966855167e-05,
|
| 184 |
+
"loss": 1.316739797592163,
|
| 185 |
+
"step": 50
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.22608695652173913,
|
| 189 |
+
"grad_norm": 0.6960898041725159,
|
| 190 |
+
"learning_rate": 2.9663596332072664e-05,
|
| 191 |
+
"loss": 1.020365595817566,
|
| 192 |
+
"step": 52
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.23478260869565218,
|
| 196 |
+
"grad_norm": 0.3621000051498413,
|
| 197 |
+
"learning_rate": 2.9574738835108235e-05,
|
| 198 |
+
"loss": 0.9612956047058105,
|
| 199 |
+
"step": 54
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.24347826086956523,
|
| 203 |
+
"grad_norm": 0.36931225657463074,
|
| 204 |
+
"learning_rate": 2.94756750600223e-05,
|
| 205 |
+
"loss": 1.4254815578460693,
|
| 206 |
+
"step": 56
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.25217391304347825,
|
| 210 |
+
"grad_norm": 0.11330584436655045,
|
| 211 |
+
"learning_rate": 2.9366487042828275e-05,
|
| 212 |
+
"loss": 1.4714879989624023,
|
| 213 |
+
"step": 58
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2608695652173913,
|
| 217 |
+
"grad_norm": 0.13919749855995178,
|
| 218 |
+
"learning_rate": 2.9247265203557428e-05,
|
| 219 |
+
"loss": 1.8500466346740723,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.26956521739130435,
|
| 224 |
+
"grad_norm": 1.1177152395248413,
|
| 225 |
+
"learning_rate": 2.9118108271380923e-05,
|
| 226 |
+
"loss": 1.0420849323272705,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.2782608695652174,
|
| 231 |
+
"grad_norm": 0.14357954263687134,
|
| 232 |
+
"learning_rate": 2.8979123202850823e-05,
|
| 233 |
+
"loss": 1.2155001163482666,
|
| 234 |
+
"step": 64
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.28695652173913044,
|
| 238 |
+
"grad_norm": 0.29200610518455505,
|
| 239 |
+
"learning_rate": 2.8830425093328024e-05,
|
| 240 |
+
"loss": 0.5274585485458374,
|
| 241 |
+
"step": 66
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.2956521739130435,
|
| 245 |
+
"grad_norm": 0.14065444469451904,
|
| 246 |
+
"learning_rate": 2.8672137081670264e-05,
|
| 247 |
+
"loss": 0.9751191735267639,
|
| 248 |
+
"step": 68
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.30434782608695654,
|
| 252 |
+
"grad_norm": 1.254546046257019,
|
| 253 |
+
"learning_rate": 2.850439024825919e-05,
|
| 254 |
+
"loss": 0.45779138803482056,
|
| 255 |
+
"step": 70
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.3130434782608696,
|
| 259 |
+
"grad_norm": 2.3761823177337646,
|
| 260 |
+
"learning_rate": 2.8327323506450993e-05,
|
| 261 |
+
"loss": 1.0098928213119507,
|
| 262 |
+
"step": 72
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3217391304347826,
|
| 266 |
+
"grad_norm": 0.19490118324756622,
|
| 267 |
+
"learning_rate": 2.8141083487540432e-05,
|
| 268 |
+
"loss": 1.4895820617675781,
|
| 269 |
+
"step": 74
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.33043478260869563,
|
| 273 |
+
"grad_norm": 1.0330501794815063,
|
| 274 |
+
"learning_rate": 2.794582441933354e-05,
|
| 275 |
+
"loss": 0.339144766330719,
|
| 276 |
+
"step": 76
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.3391304347826087,
|
| 280 |
+
"grad_norm": 0.17919474840164185,
|
| 281 |
+
"learning_rate": 2.7741707998429524e-05,
|
| 282 |
+
"loss": 1.4342169761657715,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.34782608695652173,
|
| 287 |
+
"grad_norm": 0.189740389585495,
|
| 288 |
+
"learning_rate": 2.7528903256317714e-05,
|
| 289 |
+
"loss": 1.676353931427002,
|
| 290 |
+
"step": 80
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.3565217391304348,
|
| 294 |
+
"grad_norm": 0.152068629860878,
|
| 295 |
+
"learning_rate": 2.7307586419400365e-05,
|
| 296 |
+
"loss": 1.4120248556137085,
|
| 297 |
+
"step": 82
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3652173913043478,
|
| 301 |
+
"grad_norm": 0.11617185920476913,
|
| 302 |
+
"learning_rate": 2.707794076305724e-05,
|
| 303 |
+
"loss": 1.4109995365142822,
|
| 304 |
+
"step": 84
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3739130434782609,
|
| 308 |
+
"grad_norm": 0.5076650977134705,
|
| 309 |
+
"learning_rate": 2.6840156459872887e-05,
|
| 310 |
+
"loss": 1.8156630992889404,
|
| 311 |
+
"step": 86
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.3826086956521739,
|
| 315 |
+
"grad_norm": 0.3797202408313751,
|
| 316 |
+
"learning_rate": 2.6594430422152184e-05,
|
| 317 |
+
"loss": 1.2095890045166016,
|
| 318 |
+
"step": 88
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.391304347826087,
|
| 322 |
+
"grad_norm": 0.1064012348651886,
|
| 323 |
+
"learning_rate": 2.6340966138854725e-05,
|
| 324 |
+
"loss": 1.3283032178878784,
|
| 325 |
+
"step": 90
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.4,
|
| 329 |
+
"grad_norm": 0.2617345452308655,
|
| 330 |
+
"learning_rate": 2.607997350708289e-05,
|
| 331 |
+
"loss": 0.3713761866092682,
|
| 332 |
+
"step": 92
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.40869565217391307,
|
| 336 |
+
"grad_norm": 0.14992359280586243,
|
| 337 |
+
"learning_rate": 2.5811668658263345e-05,
|
| 338 |
+
"loss": 1.2495781183242798,
|
| 339 |
+
"step": 94
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.41739130434782606,
|
| 343 |
+
"grad_norm": 0.8707973957061768,
|
| 344 |
+
"learning_rate": 2.5536273779165707e-05,
|
| 345 |
+
"loss": 0.892501950263977,
|
| 346 |
+
"step": 96
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.4260869565217391,
|
| 350 |
+
"grad_norm": 0.18348021805286407,
|
| 351 |
+
"learning_rate": 2.5254016927906833e-05,
|
| 352 |
+
"loss": 0.99811190366745,
|
| 353 |
+
"step": 98
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.43478260869565216,
|
| 357 |
+
"grad_norm": 0.28490695357322693,
|
| 358 |
+
"learning_rate": 2.4965131845092846e-05,
|
| 359 |
+
"loss": 0.9439688324928284,
|
| 360 |
+
"step": 100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4434782608695652,
|
| 364 |
+
"grad_norm": 0.19018062949180603,
|
| 365 |
+
"learning_rate": 2.466985776025548e-05,
|
| 366 |
+
"loss": 1.434984803199768,
|
| 367 |
+
"step": 102
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.45217391304347826,
|
| 371 |
+
"grad_norm": 0.3262655436992645,
|
| 372 |
+
"learning_rate": 2.4368439193742983e-05,
|
| 373 |
+
"loss": 1.6902875900268555,
|
| 374 |
+
"step": 104
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.4608695652173913,
|
| 378 |
+
"grad_norm": 0.1134955883026123,
|
| 379 |
+
"learning_rate": 2.4061125754229576e-05,
|
| 380 |
+
"loss": 0.3920702636241913,
|
| 381 |
+
"step": 106
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.46956521739130436,
|
| 385 |
+
"grad_norm": 0.15943671762943268,
|
| 386 |
+
"learning_rate": 2.3748171932011248e-05,
|
| 387 |
+
"loss": 1.1952660083770752,
|
| 388 |
+
"step": 108
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.4782608695652174,
|
| 392 |
+
"grad_norm": 0.17980021238327026,
|
| 393 |
+
"learning_rate": 2.3429836888259e-05,
|
| 394 |
+
"loss": 1.0627365112304688,
|
| 395 |
+
"step": 110
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.48695652173913045,
|
| 399 |
+
"grad_norm": 0.20388175547122955,
|
| 400 |
+
"learning_rate": 2.310638424040406e-05,
|
| 401 |
+
"loss": 1.4079805612564087,
|
| 402 |
+
"step": 112
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4956521739130435,
|
| 406 |
+
"grad_norm": 0.0773826614022255,
|
| 407 |
+
"learning_rate": 2.2778081843832856e-05,
|
| 408 |
+
"loss": 0.8712098002433777,
|
| 409 |
+
"step": 114
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.5043478260869565,
|
| 413 |
+
"grad_norm": 0.1742291897535324,
|
| 414 |
+
"learning_rate": 2.2445201570072414e-05,
|
| 415 |
+
"loss": 1.3538367748260498,
|
| 416 |
+
"step": 116
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.5130434782608696,
|
| 420 |
+
"grad_norm": 0.15458093583583832,
|
| 421 |
+
"learning_rate": 2.2108019081649993e-05,
|
| 422 |
+
"loss": 1.612799048423767,
|
| 423 |
+
"step": 118
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5217391304347826,
|
| 427 |
+
"grad_norm": 0.5128660202026367,
|
| 428 |
+
"learning_rate": 2.1766813603813334e-05,
|
| 429 |
+
"loss": 0.8653756380081177,
|
| 430 |
+
"step": 120
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5304347826086957,
|
| 434 |
+
"grad_norm": 0.6170827150344849,
|
| 435 |
+
"learning_rate": 2.1421867693300552e-05,
|
| 436 |
+
"loss": 0.7663818597793579,
|
| 437 |
+
"step": 122
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5391304347826087,
|
| 441 |
+
"grad_norm": 0.17489704489707947,
|
| 442 |
+
"learning_rate": 2.1073467004351202e-05,
|
| 443 |
+
"loss": 0.7496420741081238,
|
| 444 |
+
"step": 124
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5478260869565217,
|
| 448 |
+
"grad_norm": 0.7850053906440735,
|
| 449 |
+
"learning_rate": 2.0721900052152227e-05,
|
| 450 |
+
"loss": 0.7726188898086548,
|
| 451 |
+
"step": 126
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5565217391304348,
|
| 455 |
+
"grad_norm": 0.09144008904695511,
|
| 456 |
+
"learning_rate": 2.036745797391477e-05,
|
| 457 |
+
"loss": 0.7957323789596558,
|
| 458 |
+
"step": 128
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5652173913043478,
|
| 462 |
+
"grad_norm": 0.11362311989068985,
|
| 463 |
+
"learning_rate": 2.0010434287779607e-05,
|
| 464 |
+
"loss": 1.3306431770324707,
|
| 465 |
+
"step": 130
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5739130434782609,
|
| 469 |
+
"grad_norm": 0.13353990018367767,
|
| 470 |
+
"learning_rate": 1.965112464975093e-05,
|
| 471 |
+
"loss": 1.3570564985275269,
|
| 472 |
+
"step": 132
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5826086956521739,
|
| 476 |
+
"grad_norm": 0.16489805281162262,
|
| 477 |
+
"learning_rate": 1.928982660885971e-05,
|
| 478 |
+
"loss": 1.3512859344482422,
|
| 479 |
+
"step": 134
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.591304347826087,
|
| 483 |
+
"grad_norm": 0.12622074782848358,
|
| 484 |
+
"learning_rate": 1.8926839360759467e-05,
|
| 485 |
+
"loss": 1.3253053426742554,
|
| 486 |
+
"step": 136
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.6,
|
| 490 |
+
"grad_norm": 0.18052835762500763,
|
| 491 |
+
"learning_rate": 1.856246349995838e-05,
|
| 492 |
+
"loss": 1.363409161567688,
|
| 493 |
+
"step": 138
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.6086956521739131,
|
| 497 |
+
"grad_norm": 1.0225669145584106,
|
| 498 |
+
"learning_rate": 1.8197000770893056e-05,
|
| 499 |
+
"loss": 0.9811846613883972,
|
| 500 |
+
"step": 140
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6173913043478261,
|
| 504 |
+
"grad_norm": 0.12899279594421387,
|
| 505 |
+
"learning_rate": 1.7830753818049987e-05,
|
| 506 |
+
"loss": 1.3022255897521973,
|
| 507 |
+
"step": 142
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6260869565217392,
|
| 511 |
+
"grad_norm": 0.15879316627979279,
|
| 512 |
+
"learning_rate": 1.7464025935341674e-05,
|
| 513 |
+
"loss": 0.7987528443336487,
|
| 514 |
+
"step": 144
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6347826086956522,
|
| 518 |
+
"grad_norm": 0.15264292061328888,
|
| 519 |
+
"learning_rate": 1.709712081494495e-05,
|
| 520 |
+
"loss": 0.790221095085144,
|
| 521 |
+
"step": 146
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6434782608695652,
|
| 525 |
+
"grad_norm": 0.24214515089988708,
|
| 526 |
+
"learning_rate": 1.673034229580953e-05,
|
| 527 |
+
"loss": 0.8017470240592957,
|
| 528 |
+
"step": 148
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6521739130434783,
|
| 532 |
+
"grad_norm": 0.6817665696144104,
|
| 533 |
+
"learning_rate": 1.6363994112044934e-05,
|
| 534 |
+
"loss": 0.8057210445404053,
|
| 535 |
+
"step": 150
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.6608695652173913,
|
| 539 |
+
"grad_norm": 0.2915583848953247,
|
| 540 |
+
"learning_rate": 1.5998379641394322e-05,
|
| 541 |
+
"loss": 0.8728779554367065,
|
| 542 |
+
"step": 152
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6695652173913044,
|
| 546 |
+
"grad_norm": 0.22204452753067017,
|
| 547 |
+
"learning_rate": 1.5633801654003383e-05,
|
| 548 |
+
"loss": 1.3450850248336792,
|
| 549 |
+
"step": 154
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6782608695652174,
|
| 553 |
+
"grad_norm": 0.13754141330718994,
|
| 554 |
+
"learning_rate": 1.5270562061692413e-05,
|
| 555 |
+
"loss": 1.295073390007019,
|
| 556 |
+
"step": 156
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6869565217391305,
|
| 560 |
+
"grad_norm": 0.1301906257867813,
|
| 561 |
+
"learning_rate": 1.4908961667939148e-05,
|
| 562 |
+
"loss": 1.3460811376571655,
|
| 563 |
+
"step": 158
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6956521739130435,
|
| 567 |
+
"grad_norm": 0.2238963395357132,
|
| 568 |
+
"learning_rate": 1.4549299918779476e-05,
|
| 569 |
+
"loss": 1.4722148180007935,
|
| 570 |
+
"step": 160
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.7043478260869566,
|
| 574 |
+
"grad_norm": 0.1082434207201004,
|
| 575 |
+
"learning_rate": 1.4191874654832224e-05,
|
| 576 |
+
"loss": 1.301584243774414,
|
| 577 |
+
"step": 162
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.7130434782608696,
|
| 581 |
+
"grad_norm": 0.29728466272354126,
|
| 582 |
+
"learning_rate": 1.3836981864653448e-05,
|
| 583 |
+
"loss": 0.8648190498352051,
|
| 584 |
+
"step": 164
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7217391304347827,
|
| 588 |
+
"grad_norm": 0.12261836230754852,
|
| 589 |
+
"learning_rate": 1.3484915439624399e-05,
|
| 590 |
+
"loss": 1.2689242362976074,
|
| 591 |
+
"step": 166
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7304347826086957,
|
| 595 |
+
"grad_norm": 0.09543546289205551,
|
| 596 |
+
"learning_rate": 1.3135966930576233e-05,
|
| 597 |
+
"loss": 0.9420109987258911,
|
| 598 |
+
"step": 168
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.7391304347826086,
|
| 602 |
+
"grad_norm": 0.1176115870475769,
|
| 603 |
+
"learning_rate": 1.2790425306352913e-05,
|
| 604 |
+
"loss": 1.3050771951675415,
|
| 605 |
+
"step": 170
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.7478260869565218,
|
| 609 |
+
"grad_norm": 0.16124227643013,
|
| 610 |
+
"learning_rate": 1.2448576714512348e-05,
|
| 611 |
+
"loss": 1.160625696182251,
|
| 612 |
+
"step": 172
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7565217391304347,
|
| 616 |
+
"grad_norm": 0.45197612047195435,
|
| 617 |
+
"learning_rate": 1.2110704244363801e-05,
|
| 618 |
+
"loss": 0.5953898429870605,
|
| 619 |
+
"step": 174
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.7652173913043478,
|
| 623 |
+
"grad_norm": 0.09739059209823608,
|
| 624 |
+
"learning_rate": 1.1777087692537941e-05,
|
| 625 |
+
"loss": 0.6910260915756226,
|
| 626 |
+
"step": 176
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7739130434782608,
|
| 630 |
+
"grad_norm": 0.1326562613248825,
|
| 631 |
+
"learning_rate": 1.1448003331283567e-05,
|
| 632 |
+
"loss": 1.332924723625183,
|
| 633 |
+
"step": 178
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.782608695652174,
|
| 637 |
+
"grad_norm": 0.3839710056781769,
|
| 638 |
+
"learning_rate": 1.1123723679682947e-05,
|
| 639 |
+
"loss": 0.37987953424453735,
|
| 640 |
+
"step": 180
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.7913043478260869,
|
| 644 |
+
"grad_norm": 0.20606131851673126,
|
| 645 |
+
"learning_rate": 1.0804517277975145e-05,
|
| 646 |
+
"loss": 0.6722633242607117,
|
| 647 |
+
"step": 182
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.8,
|
| 651 |
+
"grad_norm": 0.2714339792728424,
|
| 652 |
+
"learning_rate": 1.0490648465174374e-05,
|
| 653 |
+
"loss": 0.6781936883926392,
|
| 654 |
+
"step": 184
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.808695652173913,
|
| 658 |
+
"grad_norm": 0.12319911271333694,
|
| 659 |
+
"learning_rate": 1.0182377160167355e-05,
|
| 660 |
+
"loss": 1.3093880414962769,
|
| 661 |
+
"step": 186
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8173913043478261,
|
| 665 |
+
"grad_norm": 0.19812533259391785,
|
| 666 |
+
"learning_rate": 9.87995864647107e-06,
|
| 667 |
+
"loss": 1.0597083568572998,
|
| 668 |
+
"step": 188
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8260869565217391,
|
| 672 |
+
"grad_norm": 0.18480421602725983,
|
| 673 |
+
"learning_rate": 9.583643360829146e-06,
|
| 674 |
+
"loss": 1.113531231880188,
|
| 675 |
+
"step": 190
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.8347826086956521,
|
| 679 |
+
"grad_norm": 0.170735701918602,
|
| 680 |
+
"learning_rate": 9.293676685821879e-06,
|
| 681 |
+
"loss": 0.7899190783500671,
|
| 682 |
+
"step": 192
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.8434782608695652,
|
| 686 |
+
"grad_norm": 0.16350802779197693,
|
| 687 |
+
"learning_rate": 9.010298746661722e-06,
|
| 688 |
+
"loss": 1.299129605293274,
|
| 689 |
+
"step": 194
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.8521739130434782,
|
| 693 |
+
"grad_norm": 0.18414396047592163,
|
| 694 |
+
"learning_rate": 8.733744212342408e-06,
|
| 695 |
+
"loss": 1.3935397863388062,
|
| 696 |
+
"step": 196
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8608695652173913,
|
| 700 |
+
"grad_norm": 0.2395719736814499,
|
| 701 |
+
"learning_rate": 8.46424210130651e-06,
|
| 702 |
+
"loss": 1.3050575256347656,
|
| 703 |
+
"step": 198
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.8695652173913043,
|
| 707 |
+
"grad_norm": 0.33917221426963806,
|
| 708 |
+
"learning_rate": 8.202015591792223e-06,
|
| 709 |
+
"loss": 0.6221288442611694,
|
| 710 |
+
"step": 200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.8782608695652174,
|
| 714 |
+
"grad_norm": 0.24979734420776367,
|
| 715 |
+
"learning_rate": 7.947281837016573e-06,
|
| 716 |
+
"loss": 0.8170241117477417,
|
| 717 |
+
"step": 202
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8869565217391304,
|
| 721 |
+
"grad_norm": 0.06852871179580688,
|
| 722 |
+
"learning_rate": 7.70025178534795e-06,
|
| 723 |
+
"loss": 0.729548990726471,
|
| 724 |
+
"step": 204
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8956521739130435,
|
| 728 |
+
"grad_norm": 3.180227756500244,
|
| 729 |
+
"learning_rate": 7.461130005617023e-06,
|
| 730 |
+
"loss": 0.3102116882801056,
|
| 731 |
+
"step": 206
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.9043478260869565,
|
| 735 |
+
"grad_norm": 0.5475708246231079,
|
| 736 |
+
"learning_rate": 7.230114517710568e-06,
|
| 737 |
+
"loss": 1.066127061843872,
|
| 738 |
+
"step": 208
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.9130434782608695,
|
| 742 |
+
"grad_norm": 0.21181726455688477,
|
| 743 |
+
"learning_rate": 7.007396628588649e-06,
|
| 744 |
+
"loss": 1.1609755754470825,
|
| 745 |
+
"step": 210
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.9217391304347826,
|
| 749 |
+
"grad_norm": 0.3930780589580536,
|
| 750 |
+
"learning_rate": 6.793160773860759e-06,
|
| 751 |
+
"loss": 1.2955363988876343,
|
| 752 |
+
"step": 212
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.9304347826086956,
|
| 756 |
+
"grad_norm": 0.2640330195426941,
|
| 757 |
+
"learning_rate": 6.587584365052308e-06,
|
| 758 |
+
"loss": 0.22745762765407562,
|
| 759 |
+
"step": 214
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.9391304347826087,
|
| 763 |
+
"grad_norm": 0.5837603807449341,
|
| 764 |
+
"learning_rate": 6.390837642687785e-06,
|
| 765 |
+
"loss": 0.25208932161331177,
|
| 766 |
+
"step": 216
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.9478260869565217,
|
| 770 |
+
"grad_norm": 0.09962380677461624,
|
| 771 |
+
"learning_rate": 6.203083535312356e-06,
|
| 772 |
+
"loss": 0.7900155186653137,
|
| 773 |
+
"step": 218
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9565217391304348,
|
| 777 |
+
"grad_norm": 0.6199167966842651,
|
| 778 |
+
"learning_rate": 6.024477524568591e-06,
|
| 779 |
+
"loss": 0.8592709302902222,
|
| 780 |
+
"step": 220
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.9652173913043478,
|
| 784 |
+
"grad_norm": 0.2959963381290436,
|
| 785 |
+
"learning_rate": 5.855167516440076e-06,
|
| 786 |
+
"loss": 1.3669737577438354,
|
| 787 |
+
"step": 222
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.9739130434782609,
|
| 791 |
+
"grad_norm": 0.13669747114181519,
|
| 792 |
+
"learning_rate": 5.695293718768518e-06,
|
| 793 |
+
"loss": 1.4519469738006592,
|
| 794 |
+
"step": 224
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.9826086956521739,
|
| 798 |
+
"grad_norm": 0.15183264017105103,
|
| 799 |
+
"learning_rate": 5.5449885251458e-06,
|
| 800 |
+
"loss": 1.3087224960327148,
|
| 801 |
+
"step": 226
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.991304347826087,
|
| 805 |
+
"grad_norm": 0.2697318196296692,
|
| 806 |
+
"learning_rate": 5.4043764052771e-06,
|
| 807 |
+
"loss": 1.3946113586425781,
|
| 808 |
+
"step": 228
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 1.0,
|
| 812 |
+
"grad_norm": 0.14553771913051605,
|
| 813 |
+
"learning_rate": 5.273573801905901e-06,
|
| 814 |
+
"loss": 1.330439805984497,
|
| 815 |
+
"step": 230
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 1.008695652173913,
|
| 819 |
+
"grad_norm": 0.16245104372501373,
|
| 820 |
+
"learning_rate": 5.152689034386213e-06,
|
| 821 |
+
"loss": 1.014844536781311,
|
| 822 |
+
"step": 232
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 1.017391304347826,
|
| 826 |
+
"grad_norm": 0.2378685176372528,
|
| 827 |
+
"learning_rate": 5.041822208981912e-06,
|
| 828 |
+
"loss": 0.32737967371940613,
|
| 829 |
+
"step": 234
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.0260869565217392,
|
| 833 |
+
"grad_norm": 0.20699624717235565,
|
| 834 |
+
"learning_rate": 4.941065135967408e-06,
|
| 835 |
+
"loss": 0.769230842590332,
|
| 836 |
+
"step": 236
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.0347826086956522,
|
| 840 |
+
"grad_norm": 0.12227105349302292,
|
| 841 |
+
"learning_rate": 4.850501253598363e-06,
|
| 842 |
+
"loss": 1.2364915609359741,
|
| 843 |
+
"step": 238
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.0434782608695652,
|
| 847 |
+
"grad_norm": 0.17606157064437866,
|
| 848 |
+
"learning_rate": 4.770205559015373e-06,
|
| 849 |
+
"loss": 1.2600164413452148,
|
| 850 |
+
"step": 240
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.0521739130434782,
|
| 854 |
+
"grad_norm": 0.24245694279670715,
|
| 855 |
+
"learning_rate": 4.700244546137851e-06,
|
| 856 |
+
"loss": 0.7779691815376282,
|
| 857 |
+
"step": 242
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.0608695652173914,
|
| 861 |
+
"grad_norm": 0.2091401368379593,
|
| 862 |
+
"learning_rate": 4.640676150599536e-06,
|
| 863 |
+
"loss": 1.0165550708770752,
|
| 864 |
+
"step": 244
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.0695652173913044,
|
| 868 |
+
"grad_norm": 0.12267211079597473,
|
| 869 |
+
"learning_rate": 4.5915497017712385e-06,
|
| 870 |
+
"loss": 1.0626590251922607,
|
| 871 |
+
"step": 246
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.0782608695652174,
|
| 875 |
+
"grad_norm": 0.1428578644990921,
|
| 876 |
+
"learning_rate": 4.552905881910531e-06,
|
| 877 |
+
"loss": 0.778892993927002,
|
| 878 |
+
"step": 248
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.0869565217391304,
|
| 882 |
+
"grad_norm": 0.12415514886379242,
|
| 883 |
+
"learning_rate": 4.524776692472253e-06,
|
| 884 |
+
"loss": 0.8480257391929626,
|
| 885 |
+
"step": 250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.0956521739130434,
|
| 889 |
+
"grad_norm": 0.311179518699646,
|
| 890 |
+
"learning_rate": 4.507185427607667e-06,
|
| 891 |
+
"loss": 0.15872906148433685,
|
| 892 |
+
"step": 252
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.1043478260869566,
|
| 896 |
+
"grad_norm": 0.26307570934295654,
|
| 897 |
+
"learning_rate": 4.500146654874281e-06,
|
| 898 |
+
"loss": 1.3229949474334717,
|
| 899 |
+
"step": 254
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.1130434782608696,
|
| 903 |
+
"grad_norm": 0.12678803503513336,
|
| 904 |
+
"learning_rate": 4.50366620317225e-06,
|
| 905 |
+
"loss": 1.2751566171646118,
|
| 906 |
+
"step": 256
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.1217391304347826,
|
| 910 |
+
"grad_norm": 0.12393500655889511,
|
| 911 |
+
"learning_rate": 4.517741157917401e-06,
|
| 912 |
+
"loss": 0.7979919910430908,
|
| 913 |
+
"step": 258
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.1304347826086956,
|
| 917 |
+
"grad_norm": 0.11631522327661514,
|
| 918 |
+
"learning_rate": 4.542359863454825e-06,
|
| 919 |
+
"loss": 1.2487938404083252,
|
| 920 |
+
"step": 260
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.1391304347826088,
|
| 924 |
+
"grad_norm": 0.1201433464884758,
|
| 925 |
+
"learning_rate": 4.577501932711088e-06,
|
| 926 |
+
"loss": 1.503760814666748,
|
| 927 |
+
"step": 262
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.1478260869565218,
|
| 931 |
+
"grad_norm": 0.16790546476840973,
|
| 932 |
+
"learning_rate": 4.623138264077027e-06,
|
| 933 |
+
"loss": 1.349209189414978,
|
| 934 |
+
"step": 264
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1565217391304348,
|
| 938 |
+
"grad_norm": 0.12929458916187286,
|
| 939 |
+
"learning_rate": 4.679231065507181e-06,
|
| 940 |
+
"loss": 1.3860739469528198,
|
| 941 |
+
"step": 266
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.1652173913043478,
|
| 945 |
+
"grad_norm": 1.2671191692352295,
|
| 946 |
+
"learning_rate": 4.745733885815875e-06,
|
| 947 |
+
"loss": 0.7751848101615906,
|
| 948 |
+
"step": 268
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.1739130434782608,
|
| 952 |
+
"grad_norm": 2.0448155403137207,
|
| 953 |
+
"learning_rate": 4.822591653144063e-06,
|
| 954 |
+
"loss": 0.8347904086112976,
|
| 955 |
+
"step": 270
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.182608695652174,
|
| 959 |
+
"grad_norm": 0.12114833295345306,
|
| 960 |
+
"learning_rate": 4.90974072056505e-06,
|
| 961 |
+
"loss": 1.281104564666748,
|
| 962 |
+
"step": 272
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.191304347826087,
|
| 966 |
+
"grad_norm": 0.1411694884300232,
|
| 967 |
+
"learning_rate": 5.0071089187913535e-06,
|
| 968 |
+
"loss": 1.2953712940216064,
|
| 969 |
+
"step": 274
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.2,
|
| 973 |
+
"grad_norm": 0.12283624708652496,
|
| 974 |
+
"learning_rate": 5.114615615939042e-06,
|
| 975 |
+
"loss": 1.0042020082473755,
|
| 976 |
+
"step": 276
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.208695652173913,
|
| 980 |
+
"grad_norm": 0.5199421048164368,
|
| 981 |
+
"learning_rate": 5.232171784300044e-06,
|
| 982 |
+
"loss": 0.8485981225967407,
|
| 983 |
+
"step": 278
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.2173913043478262,
|
| 987 |
+
"grad_norm": 0.25646281242370605,
|
| 988 |
+
"learning_rate": 5.359680074067178e-06,
|
| 989 |
+
"loss": 0.7609320282936096,
|
| 990 |
+
"step": 280
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.2260869565217392,
|
| 994 |
+
"grad_norm": 0.17641501128673553,
|
| 995 |
+
"learning_rate": 5.4970348939507965e-06,
|
| 996 |
+
"loss": 1.2442917823791504,
|
| 997 |
+
"step": 282
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.2347826086956522,
|
| 1001 |
+
"grad_norm": 0.12078163027763367,
|
| 1002 |
+
"learning_rate": 5.644122498620322e-06,
|
| 1003 |
+
"loss": 0.7213406562805176,
|
| 1004 |
+
"step": 284
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.2434782608695651,
|
| 1008 |
+
"grad_norm": 0.2121657282114029,
|
| 1009 |
+
"learning_rate": 5.800821082898257e-06,
|
| 1010 |
+
"loss": 1.2524417638778687,
|
| 1011 |
+
"step": 286
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.2521739130434781,
|
| 1015 |
+
"grad_norm": 0.17032301425933838,
|
| 1016 |
+
"learning_rate": 5.9670008826286325e-06,
|
| 1017 |
+
"loss": 0.7535306215286255,
|
| 1018 |
+
"step": 288
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.2608695652173914,
|
| 1022 |
+
"grad_norm": 0.1459963470697403,
|
| 1023 |
+
"learning_rate": 6.142524282136437e-06,
|
| 1024 |
+
"loss": 1.0591073036193848,
|
| 1025 |
+
"step": 290
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.2695652173913043,
|
| 1029 |
+
"grad_norm": 0.10334640741348267,
|
| 1030 |
+
"learning_rate": 6.327245928188936e-06,
|
| 1031 |
+
"loss": 1.2697545289993286,
|
| 1032 |
+
"step": 292
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.2782608695652173,
|
| 1036 |
+
"grad_norm": 0.6387373805046082,
|
| 1037 |
+
"learning_rate": 6.52101285036462e-06,
|
| 1038 |
+
"loss": 0.8120895624160767,
|
| 1039 |
+
"step": 294
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.2869565217391306,
|
| 1043 |
+
"grad_norm": 0.09141097217798233,
|
| 1044 |
+
"learning_rate": 6.7236645877299985e-06,
|
| 1045 |
+
"loss": 0.16801220178604126,
|
| 1046 |
+
"step": 296
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.2956521739130435,
|
| 1050 |
+
"grad_norm": 0.14008603990077972,
|
| 1051 |
+
"learning_rate": 6.935033321719419e-06,
|
| 1052 |
+
"loss": 0.6829316020011902,
|
| 1053 |
+
"step": 298
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.3043478260869565,
|
| 1057 |
+
"grad_norm": 0.13336972892284393,
|
| 1058 |
+
"learning_rate": 7.15494401510782e-06,
|
| 1059 |
+
"loss": 0.24555981159210205,
|
| 1060 |
+
"step": 300
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.3130434782608695,
|
| 1064 |
+
"grad_norm": 0.15153667330741882,
|
| 1065 |
+
"learning_rate": 7.383214556961368e-06,
|
| 1066 |
+
"loss": 0.8401697874069214,
|
| 1067 |
+
"step": 302
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.3217391304347825,
|
| 1071 |
+
"grad_norm": 0.39388230443000793,
|
| 1072 |
+
"learning_rate": 7.619655913445883e-06,
|
| 1073 |
+
"loss": 1.6956262588500977,
|
| 1074 |
+
"step": 304
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.3304347826086955,
|
| 1078 |
+
"grad_norm": 0.0983978733420372,
|
| 1079 |
+
"learning_rate": 7.864072284368284e-06,
|
| 1080 |
+
"loss": 0.7533000111579895,
|
| 1081 |
+
"step": 306
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.3391304347826087,
|
| 1085 |
+
"grad_norm": 0.27145856618881226,
|
| 1086 |
+
"learning_rate": 8.11626126532126e-06,
|
| 1087 |
+
"loss": 1.0896899700164795,
|
| 1088 |
+
"step": 308
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.3478260869565217,
|
| 1092 |
+
"grad_norm": 0.16908416152000427,
|
| 1093 |
+
"learning_rate": 8.376014015297057e-06,
|
| 1094 |
+
"loss": 1.1746755838394165,
|
| 1095 |
+
"step": 310
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.3565217391304347,
|
| 1099 |
+
"grad_norm": 0.5621324777603149,
|
| 1100 |
+
"learning_rate": 8.643115429631413e-06,
|
| 1101 |
+
"loss": 0.28953975439071655,
|
| 1102 |
+
"step": 312
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.365217391304348,
|
| 1106 |
+
"grad_norm": 0.1343858242034912,
|
| 1107 |
+
"learning_rate": 8.917344318134601e-06,
|
| 1108 |
+
"loss": 1.2791374921798706,
|
| 1109 |
+
"step": 314
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.373913043478261,
|
| 1113 |
+
"grad_norm": 0.12179627269506454,
|
| 1114 |
+
"learning_rate": 9.198473588261906e-06,
|
| 1115 |
+
"loss": 1.5186599493026733,
|
| 1116 |
+
"step": 316
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.382608695652174,
|
| 1120 |
+
"grad_norm": 0.6460802555084229,
|
| 1121 |
+
"learning_rate": 9.48627043317196e-06,
|
| 1122 |
+
"loss": 0.7900709509849548,
|
| 1123 |
+
"step": 318
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.391304347826087,
|
| 1127 |
+
"grad_norm": 0.1162571832537651,
|
| 1128 |
+
"learning_rate": 9.780496524517107e-06,
|
| 1129 |
+
"loss": 1.5395351648330688,
|
| 1130 |
+
"step": 320
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.4,
|
| 1134 |
+
"grad_norm": 0.26111987233161926,
|
| 1135 |
+
"learning_rate": 1.0080908209806292e-05,
|
| 1136 |
+
"loss": 0.7073770761489868,
|
| 1137 |
+
"step": 322
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.4086956521739131,
|
| 1141 |
+
"grad_norm": 0.21174176037311554,
|
| 1142 |
+
"learning_rate": 1.0387256714176855e-05,
|
| 1143 |
+
"loss": 1.3696300983428955,
|
| 1144 |
+
"step": 324
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.4173913043478261,
|
| 1148 |
+
"grad_norm": 0.18966367840766907,
|
| 1149 |
+
"learning_rate": 1.0699288346408284e-05,
|
| 1150 |
+
"loss": 0.7893473505973816,
|
| 1151 |
+
"step": 326
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.4260869565217391,
|
| 1155 |
+
"grad_norm": 0.28794315457344055,
|
| 1156 |
+
"learning_rate": 1.1016744709007203e-05,
|
| 1157 |
+
"loss": 1.0100047588348389,
|
| 1158 |
+
"step": 328
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.434782608695652,
|
| 1162 |
+
"grad_norm": 0.26700359582901,
|
| 1163 |
+
"learning_rate": 1.1339362912189803e-05,
|
| 1164 |
+
"loss": 0.8350800275802612,
|
| 1165 |
+
"step": 330
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.4434782608695653,
|
| 1169 |
+
"grad_norm": 0.34453895688056946,
|
| 1170 |
+
"learning_rate": 1.1666875791584241e-05,
|
| 1171 |
+
"loss": 1.2977509498596191,
|
| 1172 |
+
"step": 332
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.4521739130434783,
|
| 1176 |
+
"grad_norm": 0.12350393086671829,
|
| 1177 |
+
"learning_rate": 1.1999012129473044e-05,
|
| 1178 |
+
"loss": 0.7434523105621338,
|
| 1179 |
+
"step": 334
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.4608695652173913,
|
| 1183 |
+
"grad_norm": 0.12331763654947281,
|
| 1184 |
+
"learning_rate": 1.2335496879392006e-05,
|
| 1185 |
+
"loss": 0.9966728091239929,
|
| 1186 |
+
"step": 336
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.4695652173913043,
|
| 1190 |
+
"grad_norm": 0.12660405039787292,
|
| 1191 |
+
"learning_rate": 1.267605139389983e-05,
|
| 1192 |
+
"loss": 1.2345221042633057,
|
| 1193 |
+
"step": 338
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.4782608695652173,
|
| 1197 |
+
"grad_norm": 0.5481416583061218,
|
| 1198 |
+
"learning_rate": 1.3020393655329656e-05,
|
| 1199 |
+
"loss": 0.4076097905635834,
|
| 1200 |
+
"step": 340
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.4869565217391305,
|
| 1204 |
+
"grad_norm": 0.1473967432975769,
|
| 1205 |
+
"learning_rate": 1.3368238509331685e-05,
|
| 1206 |
+
"loss": 1.0471733808517456,
|
| 1207 |
+
"step": 342
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.4956521739130435,
|
| 1211 |
+
"grad_norm": 0.14102469384670258,
|
| 1212 |
+
"learning_rate": 1.3719297901013182e-05,
|
| 1213 |
+
"loss": 1.2860357761383057,
|
| 1214 |
+
"step": 344
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.5043478260869565,
|
| 1218 |
+
"grad_norm": 0.29168060421943665,
|
| 1219 |
+
"learning_rate": 1.4073281113480556e-05,
|
| 1220 |
+
"loss": 1.0981141328811646,
|
| 1221 |
+
"step": 346
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.5130434782608697,
|
| 1225 |
+
"grad_norm": 0.12084399163722992,
|
| 1226 |
+
"learning_rate": 1.4429895008585773e-05,
|
| 1227 |
+
"loss": 1.5693000555038452,
|
| 1228 |
+
"step": 348
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.5217391304347827,
|
| 1232 |
+
"grad_norm": 0.3121376931667328,
|
| 1233 |
+
"learning_rate": 1.4788844269678e-05,
|
| 1234 |
+
"loss": 0.15966485440731049,
|
| 1235 |
+
"step": 350
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.5304347826086957,
|
| 1239 |
+
"grad_norm": 0.7553597092628479,
|
| 1240 |
+
"learning_rate": 1.514983164615912e-05,
|
| 1241 |
+
"loss": 0.7595433592796326,
|
| 1242 |
+
"step": 352
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.5391304347826087,
|
| 1246 |
+
"grad_norm": 0.4193861484527588,
|
| 1247 |
+
"learning_rate": 1.5512558199640922e-05,
|
| 1248 |
+
"loss": 0.8960363268852234,
|
| 1249 |
+
"step": 354
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.5478260869565217,
|
| 1253 |
+
"grad_norm": 2.7174839973449707,
|
| 1254 |
+
"learning_rate": 1.587672355149983e-05,
|
| 1255 |
+
"loss": 0.7889991998672485,
|
| 1256 |
+
"step": 356
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.5565217391304347,
|
| 1260 |
+
"grad_norm": 0.24500806629657745,
|
| 1261 |
+
"learning_rate": 1.6242026131624477e-05,
|
| 1262 |
+
"loss": 0.74623703956604,
|
| 1263 |
+
"step": 358
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.5652173913043477,
|
| 1267 |
+
"grad_norm": 0.12118079513311386,
|
| 1268 |
+
"learning_rate": 1.6608163428149812e-05,
|
| 1269 |
+
"loss": 1.2382371425628662,
|
| 1270 |
+
"step": 360
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.5739130434782609,
|
| 1274 |
+
"grad_norm": 0.21043698489665985,
|
| 1275 |
+
"learning_rate": 1.697483223797118e-05,
|
| 1276 |
+
"loss": 0.7253771424293518,
|
| 1277 |
+
"step": 362
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.5826086956521739,
|
| 1281 |
+
"grad_norm": 0.1428501456975937,
|
| 1282 |
+
"learning_rate": 1.734172891783075e-05,
|
| 1283 |
+
"loss": 0.6049482822418213,
|
| 1284 |
+
"step": 364
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.591304347826087,
|
| 1288 |
+
"grad_norm": 0.24034124612808228,
|
| 1289 |
+
"learning_rate": 1.7708549635768553e-05,
|
| 1290 |
+
"loss": 0.658636212348938,
|
| 1291 |
+
"step": 366
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.6,
|
| 1295 |
+
"grad_norm": 0.15072523057460785,
|
| 1296 |
+
"learning_rate": 1.8074990622729676e-05,
|
| 1297 |
+
"loss": 1.2467550039291382,
|
| 1298 |
+
"step": 368
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.608695652173913,
|
| 1302 |
+
"grad_norm": 0.29888659715652466,
|
| 1303 |
+
"learning_rate": 1.8440748424119435e-05,
|
| 1304 |
+
"loss": 0.332572340965271,
|
| 1305 |
+
"step": 370
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.617391304347826,
|
| 1309 |
+
"grad_norm": 0.4121609926223755,
|
| 1310 |
+
"learning_rate": 1.8805520151098043e-05,
|
| 1311 |
+
"loss": 0.7649952173233032,
|
| 1312 |
+
"step": 372
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.626086956521739,
|
| 1316 |
+
"grad_norm": 0.14216536283493042,
|
| 1317 |
+
"learning_rate": 1.916900373140691e-05,
|
| 1318 |
+
"loss": 0.8258912563323975,
|
| 1319 |
+
"step": 374
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.634782608695652,
|
| 1323 |
+
"grad_norm": 0.12106224149465561,
|
| 1324 |
+
"learning_rate": 1.9530898159518646e-05,
|
| 1325 |
+
"loss": 1.243992805480957,
|
| 1326 |
+
"step": 376
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.643478260869565,
|
| 1330 |
+
"grad_norm": 0.1799318641424179,
|
| 1331 |
+
"learning_rate": 1.9890903745903662e-05,
|
| 1332 |
+
"loss": 0.7369431853294373,
|
| 1333 |
+
"step": 378
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.6521739130434783,
|
| 1337 |
+
"grad_norm": 0.23679573833942413,
|
| 1338 |
+
"learning_rate": 2.0248722365206985e-05,
|
| 1339 |
+
"loss": 1.2425155639648438,
|
| 1340 |
+
"step": 380
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.6608695652173913,
|
| 1344 |
+
"grad_norm": 0.16253520548343658,
|
| 1345 |
+
"learning_rate": 2.060405770312981e-05,
|
| 1346 |
+
"loss": 0.8069741129875183,
|
| 1347 |
+
"step": 382
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.6695652173913045,
|
| 1351 |
+
"grad_norm": 0.12619397044181824,
|
| 1352 |
+
"learning_rate": 2.0956615501811323e-05,
|
| 1353 |
+
"loss": 0.7547456622123718,
|
| 1354 |
+
"step": 384
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.6782608695652175,
|
| 1358 |
+
"grad_norm": 0.2577739953994751,
|
| 1359 |
+
"learning_rate": 2.1306103803507364e-05,
|
| 1360 |
+
"loss": 1.0529491901397705,
|
| 1361 |
+
"step": 386
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.6869565217391305,
|
| 1365 |
+
"grad_norm": 0.32050907611846924,
|
| 1366 |
+
"learning_rate": 2.1652233192364604e-05,
|
| 1367 |
+
"loss": 1.4707834720611572,
|
| 1368 |
+
"step": 388
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.6956521739130435,
|
| 1372 |
+
"grad_norm": 0.1691839098930359,
|
| 1373 |
+
"learning_rate": 2.1994717034089493e-05,
|
| 1374 |
+
"loss": 0.7649831771850586,
|
| 1375 |
+
"step": 390
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.7043478260869565,
|
| 1379 |
+
"grad_norm": 0.11284446716308594,
|
| 1380 |
+
"learning_rate": 2.2333271713314037e-05,
|
| 1381 |
+
"loss": 1.237856388092041,
|
| 1382 |
+
"step": 392
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.7130434782608694,
|
| 1386 |
+
"grad_norm": 0.15681013464927673,
|
| 1387 |
+
"learning_rate": 2.2667616868461238e-05,
|
| 1388 |
+
"loss": 1.2670764923095703,
|
| 1389 |
+
"step": 394
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.7217391304347827,
|
| 1393 |
+
"grad_norm": 0.40354123711586,
|
| 1394 |
+
"learning_rate": 2.299747562391633e-05,
|
| 1395 |
+
"loss": 1.2364072799682617,
|
| 1396 |
+
"step": 396
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.7304347826086957,
|
| 1400 |
+
"grad_norm": 0.1340729296207428,
|
| 1401 |
+
"learning_rate": 2.332257481931103e-05,
|
| 1402 |
+
"loss": 0.7167130708694458,
|
| 1403 |
+
"step": 398
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.7391304347826086,
|
| 1407 |
+
"grad_norm": 0.11962085962295532,
|
| 1408 |
+
"learning_rate": 2.3642645235731285e-05,
|
| 1409 |
+
"loss": 0.7211905717849731,
|
| 1410 |
+
"step": 400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.7478260869565219,
|
| 1414 |
+
"grad_norm": 0.1367277204990387,
|
| 1415 |
+
"learning_rate": 2.3957421818660958e-05,
|
| 1416 |
+
"loss": 0.7387893795967102,
|
| 1417 |
+
"step": 402
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.7565217391304349,
|
| 1421 |
+
"grad_norm": 0.12049642205238342,
|
| 1422 |
+
"learning_rate": 2.4266643897476975e-05,
|
| 1423 |
+
"loss": 1.2366782426834106,
|
| 1424 |
+
"step": 404
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.7652173913043478,
|
| 1428 |
+
"grad_norm": 0.19714173674583435,
|
| 1429 |
+
"learning_rate": 2.457005540131405e-05,
|
| 1430 |
+
"loss": 0.7809978127479553,
|
| 1431 |
+
"step": 406
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.7739130434782608,
|
| 1435 |
+
"grad_norm": 0.18713834881782532,
|
| 1436 |
+
"learning_rate": 2.4867405071120378e-05,
|
| 1437 |
+
"loss": 1.1861432790756226,
|
| 1438 |
+
"step": 408
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.7826086956521738,
|
| 1442 |
+
"grad_norm": 0.18612703680992126,
|
| 1443 |
+
"learning_rate": 2.5158446667728563e-05,
|
| 1444 |
+
"loss": 1.2835782766342163,
|
| 1445 |
+
"step": 410
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.7913043478260868,
|
| 1449 |
+
"grad_norm": 0.5197505354881287,
|
| 1450 |
+
"learning_rate": 2.5442939175769457e-05,
|
| 1451 |
+
"loss": 0.26566827297210693,
|
| 1452 |
+
"step": 412
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.8,
|
| 1456 |
+
"grad_norm": 0.16716937720775604,
|
| 1457 |
+
"learning_rate": 2.5720647003260177e-05,
|
| 1458 |
+
"loss": 1.253092646598816,
|
| 1459 |
+
"step": 414
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.808695652173913,
|
| 1463 |
+
"grad_norm": 0.16784952580928802,
|
| 1464 |
+
"learning_rate": 2.5991340176700945e-05,
|
| 1465 |
+
"loss": 1.298421859741211,
|
| 1466 |
+
"step": 416
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.8173913043478263,
|
| 1470 |
+
"grad_norm": 0.12985093891620636,
|
| 1471 |
+
"learning_rate": 2.6254794531519122e-05,
|
| 1472 |
+
"loss": 1.5727579593658447,
|
| 1473 |
+
"step": 418
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.8260869565217392,
|
| 1477 |
+
"grad_norm": 0.30004414916038513,
|
| 1478 |
+
"learning_rate": 2.6510791897702884e-05,
|
| 1479 |
+
"loss": 1.372650146484375,
|
| 1480 |
+
"step": 420
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.8347826086956522,
|
| 1484 |
+
"grad_norm": 0.16396737098693848,
|
| 1485 |
+
"learning_rate": 2.675912028047062e-05,
|
| 1486 |
+
"loss": 1.5493252277374268,
|
| 1487 |
+
"step": 422
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.8434782608695652,
|
| 1491 |
+
"grad_norm": 0.14453765749931335,
|
| 1492 |
+
"learning_rate": 2.6999574035826618e-05,
|
| 1493 |
+
"loss": 0.7752541899681091,
|
| 1494 |
+
"step": 424
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.8521739130434782,
|
| 1498 |
+
"grad_norm": 0.3888326585292816,
|
| 1499 |
+
"learning_rate": 2.7231954040857604e-05,
|
| 1500 |
+
"loss": 1.3314841985702515,
|
| 1501 |
+
"step": 426
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.8608695652173912,
|
| 1505 |
+
"grad_norm": 0.4329335391521454,
|
| 1506 |
+
"learning_rate": 2.745606785862895e-05,
|
| 1507 |
+
"loss": 0.36442431807518005,
|
| 1508 |
+
"step": 428
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.8695652173913042,
|
| 1512 |
+
"grad_norm": 0.19990986585617065,
|
| 1513 |
+
"learning_rate": 2.767172989754432e-05,
|
| 1514 |
+
"loss": 0.6660992503166199,
|
| 1515 |
+
"step": 430
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.8782608695652174,
|
| 1519 |
+
"grad_norm": 0.11110001057386398,
|
| 1520 |
+
"learning_rate": 2.7878761565036436e-05,
|
| 1521 |
+
"loss": 1.5394024848937988,
|
| 1522 |
+
"step": 432
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.8869565217391304,
|
| 1526 |
+
"grad_norm": 0.1121024340391159,
|
| 1527 |
+
"learning_rate": 2.807699141546199e-05,
|
| 1528 |
+
"loss": 0.7698279619216919,
|
| 1529 |
+
"step": 434
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.8956521739130436,
|
| 1533 |
+
"grad_norm": 0.15248660743236542,
|
| 1534 |
+
"learning_rate": 2.826625529207797e-05,
|
| 1535 |
+
"loss": 1.2329353094100952,
|
| 1536 |
+
"step": 436
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.9043478260869566,
|
| 1540 |
+
"grad_norm": 0.10831912606954575,
|
| 1541 |
+
"learning_rate": 2.844639646298208e-05,
|
| 1542 |
+
"loss": 1.2454890012741089,
|
| 1543 |
+
"step": 438
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.9130434782608696,
|
| 1547 |
+
"grad_norm": 0.1683008074760437,
|
| 1548 |
+
"learning_rate": 2.8617265750904434e-05,
|
| 1549 |
+
"loss": 1.2287697792053223,
|
| 1550 |
+
"step": 440
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.9217391304347826,
|
| 1554 |
+
"grad_norm": 0.08259912580251694,
|
| 1555 |
+
"learning_rate": 2.8778721656743252e-05,
|
| 1556 |
+
"loss": 0.7477931976318359,
|
| 1557 |
+
"step": 442
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.9304347826086956,
|
| 1561 |
+
"grad_norm": 0.11279872059822083,
|
| 1562 |
+
"learning_rate": 2.893063047674209e-05,
|
| 1563 |
+
"loss": 1.2804430723190308,
|
| 1564 |
+
"step": 444
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.9391304347826086,
|
| 1568 |
+
"grad_norm": 0.16371870040893555,
|
| 1569 |
+
"learning_rate": 2.90728664132117e-05,
|
| 1570 |
+
"loss": 0.7825669646263123,
|
| 1571 |
+
"step": 446
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.9478260869565216,
|
| 1575 |
+
"grad_norm": 0.08895144611597061,
|
| 1576 |
+
"learning_rate": 2.9205311678704742e-05,
|
| 1577 |
+
"loss": 0.6581708192825317,
|
| 1578 |
+
"step": 448
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.9565217391304348,
|
| 1582 |
+
"grad_norm": 0.3610806465148926,
|
| 1583 |
+
"learning_rate": 2.932785659355714e-05,
|
| 1584 |
+
"loss": 0.7231730222702026,
|
| 1585 |
+
"step": 450
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.9652173913043478,
|
| 1589 |
+
"grad_norm": 0.15365619957447052,
|
| 1590 |
+
"learning_rate": 2.944039967671519e-05,
|
| 1591 |
+
"loss": 0.7730036973953247,
|
| 1592 |
+
"step": 452
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.973913043478261,
|
| 1596 |
+
"grad_norm": 0.13084781169891357,
|
| 1597 |
+
"learning_rate": 2.9542847729773423e-05,
|
| 1598 |
+
"loss": 0.736638069152832,
|
| 1599 |
+
"step": 454
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.982608695652174,
|
| 1603 |
+
"grad_norm": 0.18188992142677307,
|
| 1604 |
+
"learning_rate": 2.9635115914153388e-05,
|
| 1605 |
+
"loss": 0.9782851934432983,
|
| 1606 |
+
"step": 456
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.991304347826087,
|
| 1610 |
+
"grad_norm": 0.18510757386684418,
|
| 1611 |
+
"learning_rate": 2.971712782135961e-05,
|
| 1612 |
+
"loss": 1.236344337463379,
|
| 1613 |
+
"step": 458
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 2.0,
|
| 1617 |
+
"grad_norm": 1.4175490140914917,
|
| 1618 |
+
"learning_rate": 2.978881553625446e-05,
|
| 1619 |
+
"loss": 1.1338064670562744,
|
| 1620 |
+
"step": 460
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 2.008695652173913,
|
| 1624 |
+
"grad_norm": 0.18492577970027924,
|
| 1625 |
+
"learning_rate": 2.9850119693299577e-05,
|
| 1626 |
+
"loss": 1.1988855600357056,
|
| 1627 |
+
"step": 462
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 2.017391304347826,
|
| 1631 |
+
"grad_norm": 0.24838964641094208,
|
| 1632 |
+
"learning_rate": 2.9900989525717243e-05,
|
| 1633 |
+
"loss": 0.1962333619594574,
|
| 1634 |
+
"step": 464
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 2.026086956521739,
|
| 1638 |
+
"grad_norm": 0.9311656951904297,
|
| 1639 |
+
"learning_rate": 2.9941382907531037e-05,
|
| 1640 |
+
"loss": 0.12543362379074097,
|
| 1641 |
+
"step": 466
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 2.034782608695652,
|
| 1645 |
+
"grad_norm": 0.22585399448871613,
|
| 1646 |
+
"learning_rate": 2.9971266388450884e-05,
|
| 1647 |
+
"loss": 0.7844517827033997,
|
| 1648 |
+
"step": 468
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.0434782608695654,
|
| 1652 |
+
"grad_norm": 0.29823383688926697,
|
| 1653 |
+
"learning_rate": 2.9990615221573707e-05,
|
| 1654 |
+
"loss": 0.7644298076629639,
|
| 1655 |
+
"step": 470
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.0521739130434784,
|
| 1659 |
+
"grad_norm": 0.1510343700647354,
|
| 1660 |
+
"learning_rate": 2.999941338387663e-05,
|
| 1661 |
+
"loss": 1.479148268699646,
|
| 1662 |
+
"step": 472
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.0608695652173914,
|
| 1666 |
+
"grad_norm": 0.7294149994850159,
|
| 1667 |
+
"learning_rate": 2.999765358948589e-05,
|
| 1668 |
+
"loss": 0.2585853636264801,
|
| 1669 |
+
"step": 474
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.0695652173913044,
|
| 1673 |
+
"grad_norm": 0.1448172628879547,
|
| 1674 |
+
"learning_rate": 2.998533729571033e-05,
|
| 1675 |
+
"loss": 1.2844960689544678,
|
| 1676 |
+
"step": 476
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.0782608695652174,
|
| 1680 |
+
"grad_norm": 0.25449809432029724,
|
| 1681 |
+
"learning_rate": 2.9962474701834602e-05,
|
| 1682 |
+
"loss": 0.7490485906600952,
|
| 1683 |
+
"step": 478
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.0869565217391304,
|
| 1687 |
+
"grad_norm": 0.1117057353258133,
|
| 1688 |
+
"learning_rate": 2.9929084740673027e-05,
|
| 1689 |
+
"loss": 1.1616085767745972,
|
| 1690 |
+
"step": 480
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.0956521739130434,
|
| 1694 |
+
"grad_norm": 0.5241631269454956,
|
| 1695 |
+
"learning_rate": 2.9885195062891023e-05,
|
| 1696 |
+
"loss": 1.7963777780532837,
|
| 1697 |
+
"step": 482
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.1043478260869564,
|
| 1701 |
+
"grad_norm": 0.16556978225708008,
|
| 1702 |
+
"learning_rate": 2.9830842014107273e-05,
|
| 1703 |
+
"loss": 1.2623823881149292,
|
| 1704 |
+
"step": 484
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.1130434782608694,
|
| 1708 |
+
"grad_norm": 0.5851399302482605,
|
| 1709 |
+
"learning_rate": 2.9766070604795444e-05,
|
| 1710 |
+
"loss": 0.681275486946106,
|
| 1711 |
+
"step": 486
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.121739130434783,
|
| 1715 |
+
"grad_norm": 0.4062120020389557,
|
| 1716 |
+
"learning_rate": 2.969093447301039e-05,
|
| 1717 |
+
"loss": 0.6947782039642334,
|
| 1718 |
+
"step": 488
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.130434782608696,
|
| 1722 |
+
"grad_norm": 0.14548048377037048,
|
| 1723 |
+
"learning_rate": 2.9605495839969793e-05,
|
| 1724 |
+
"loss": 0.6653367877006531,
|
| 1725 |
+
"step": 490
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.139130434782609,
|
| 1729 |
+
"grad_norm": 0.1378212869167328,
|
| 1730 |
+
"learning_rate": 2.9509825458527955e-05,
|
| 1731 |
+
"loss": 1.178207278251648,
|
| 1732 |
+
"step": 492
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.1478260869565218,
|
| 1736 |
+
"grad_norm": 0.5637624263763428,
|
| 1737 |
+
"learning_rate": 2.940400255458444e-05,
|
| 1738 |
+
"loss": 0.19959603250026703,
|
| 1739 |
+
"step": 494
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.1565217391304348,
|
| 1743 |
+
"grad_norm": 0.12706081569194794,
|
| 1744 |
+
"learning_rate": 2.9288114761476036e-05,
|
| 1745 |
+
"loss": 1.1562106609344482,
|
| 1746 |
+
"step": 496
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.1652173913043478,
|
| 1750 |
+
"grad_norm": 0.15716660022735596,
|
| 1751 |
+
"learning_rate": 2.916225804740647e-05,
|
| 1752 |
+
"loss": 1.1385471820831299,
|
| 1753 |
+
"step": 498
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.1739130434782608,
|
| 1757 |
+
"grad_norm": 0.11568231880664825,
|
| 1758 |
+
"learning_rate": 2.9026536635973857e-05,
|
| 1759 |
+
"loss": 0.49375131726264954,
|
| 1760 |
+
"step": 500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.1826086956521737,
|
| 1764 |
+
"grad_norm": 0.16767719388008118,
|
| 1765 |
+
"learning_rate": 2.888106291986178e-05,
|
| 1766 |
+
"loss": 0.736272394657135,
|
| 1767 |
+
"step": 502
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.1913043478260867,
|
| 1771 |
+
"grad_norm": 0.1770874410867691,
|
| 1772 |
+
"learning_rate": 2.872595736776543e-05,
|
| 1773 |
+
"loss": 0.8101549744606018,
|
| 1774 |
+
"step": 504
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.2,
|
| 1778 |
+
"grad_norm": 0.8240585327148438,
|
| 1779 |
+
"learning_rate": 2.8561348424629893e-05,
|
| 1780 |
+
"loss": 0.2909260392189026,
|
| 1781 |
+
"step": 506
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.208695652173913,
|
| 1785 |
+
"grad_norm": 0.1195528656244278,
|
| 1786 |
+
"learning_rate": 2.83873724052832e-05,
|
| 1787 |
+
"loss": 0.7722839713096619,
|
| 1788 |
+
"step": 508
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.217391304347826,
|
| 1792 |
+
"grad_norm": 0.8490219712257385,
|
| 1793 |
+
"learning_rate": 2.8204173381552252e-05,
|
| 1794 |
+
"loss": 0.5638793110847473,
|
| 1795 |
+
"step": 510
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.226086956521739,
|
| 1799 |
+
"grad_norm": 0.3193603754043579,
|
| 1800 |
+
"learning_rate": 2.8011903062955016e-05,
|
| 1801 |
+
"loss": 0.31869935989379883,
|
| 1802 |
+
"step": 512
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.234782608695652,
|
| 1806 |
+
"grad_norm": 0.12175068259239197,
|
| 1807 |
+
"learning_rate": 2.7810720671067893e-05,
|
| 1808 |
+
"loss": 1.131230354309082,
|
| 1809 |
+
"step": 514
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.243478260869565,
|
| 1813 |
+
"grad_norm": 0.1269245743751526,
|
| 1814 |
+
"learning_rate": 2.7600792807672248e-05,
|
| 1815 |
+
"loss": 1.208681344985962,
|
| 1816 |
+
"step": 516
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.252173913043478,
|
| 1820 |
+
"grad_norm": 0.18002073466777802,
|
| 1821 |
+
"learning_rate": 2.7382293316789273e-05,
|
| 1822 |
+
"loss": 1.3903454542160034,
|
| 1823 |
+
"step": 518
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.260869565217391,
|
| 1827 |
+
"grad_norm": 0.6649693250656128,
|
| 1828 |
+
"learning_rate": 2.7155403140717488e-05,
|
| 1829 |
+
"loss": 0.7094644904136658,
|
| 1830 |
+
"step": 520
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.269565217391304,
|
| 1834 |
+
"grad_norm": 0.13027699291706085,
|
| 1835 |
+
"learning_rate": 2.6920310170192024e-05,
|
| 1836 |
+
"loss": 0.7558539509773254,
|
| 1837 |
+
"step": 522
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.2782608695652176,
|
| 1841 |
+
"grad_norm": 0.13726165890693665,
|
| 1842 |
+
"learning_rate": 2.6677209088789823e-05,
|
| 1843 |
+
"loss": 1.140393853187561,
|
| 1844 |
+
"step": 524
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.2869565217391306,
|
| 1848 |
+
"grad_norm": 0.21993081271648407,
|
| 1849 |
+
"learning_rate": 2.642630121170968e-05,
|
| 1850 |
+
"loss": 1.1117931604385376,
|
| 1851 |
+
"step": 526
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.2956521739130435,
|
| 1855 |
+
"grad_norm": 0.1521347314119339,
|
| 1856 |
+
"learning_rate": 2.616779431906042e-05,
|
| 1857 |
+
"loss": 0.6197381019592285,
|
| 1858 |
+
"step": 528
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.3043478260869565,
|
| 1862 |
+
"grad_norm": 0.17388762533664703,
|
| 1863 |
+
"learning_rate": 2.5901902483795464e-05,
|
| 1864 |
+
"loss": 1.1404460668563843,
|
| 1865 |
+
"step": 530
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.3130434782608695,
|
| 1869 |
+
"grad_norm": 0.19341905415058136,
|
| 1870 |
+
"learning_rate": 2.5628845894436232e-05,
|
| 1871 |
+
"loss": 1.110768437385559,
|
| 1872 |
+
"step": 532
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.3217391304347825,
|
| 1876 |
+
"grad_norm": 0.11132687330245972,
|
| 1877 |
+
"learning_rate": 2.5348850672731114e-05,
|
| 1878 |
+
"loss": 0.18440936505794525,
|
| 1879 |
+
"step": 534
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.3304347826086955,
|
| 1883 |
+
"grad_norm": 0.12755344808101654,
|
| 1884 |
+
"learning_rate": 2.506214868640111e-05,
|
| 1885 |
+
"loss": 0.6152647137641907,
|
| 1886 |
+
"step": 536
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.3391304347826085,
|
| 1890 |
+
"grad_norm": 0.07117603719234467,
|
| 1891 |
+
"learning_rate": 2.4768977357127068e-05,
|
| 1892 |
+
"loss": 0.6943525075912476,
|
| 1893 |
+
"step": 538
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.3478260869565215,
|
| 1897 |
+
"grad_norm": 0.22992900013923645,
|
| 1898 |
+
"learning_rate": 2.4469579463937736e-05,
|
| 1899 |
+
"loss": 1.155451774597168,
|
| 1900 |
+
"step": 540
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.356521739130435,
|
| 1904 |
+
"grad_norm": 0.13336700201034546,
|
| 1905 |
+
"learning_rate": 2.4164202942161202e-05,
|
| 1906 |
+
"loss": 0.6562126874923706,
|
| 1907 |
+
"step": 542
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.365217391304348,
|
| 1911 |
+
"grad_norm": 0.17184697091579437,
|
| 1912 |
+
"learning_rate": 2.385310067810646e-05,
|
| 1913 |
+
"loss": 1.1728577613830566,
|
| 1914 |
+
"step": 544
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.373913043478261,
|
| 1918 |
+
"grad_norm": 0.24630305171012878,
|
| 1919 |
+
"learning_rate": 2.353653029964486e-05,
|
| 1920 |
+
"loss": 0.7028173208236694,
|
| 1921 |
+
"step": 546
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.382608695652174,
|
| 1925 |
+
"grad_norm": 0.4979984164237976,
|
| 1926 |
+
"learning_rate": 2.3214753962865128e-05,
|
| 1927 |
+
"loss": 1.0240296125411987,
|
| 1928 |
+
"step": 548
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.391304347826087,
|
| 1932 |
+
"grad_norm": 0.786608099937439,
|
| 1933 |
+
"learning_rate": 2.2888038134978446e-05,
|
| 1934 |
+
"loss": 0.6851329207420349,
|
| 1935 |
+
"step": 550
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.4,
|
| 1939 |
+
"grad_norm": 0.21292582154273987,
|
| 1940 |
+
"learning_rate": 2.2556653373653506e-05,
|
| 1941 |
+
"loss": 1.1324046850204468,
|
| 1942 |
+
"step": 552
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.408695652173913,
|
| 1946 |
+
"grad_norm": 0.07219722867012024,
|
| 1947 |
+
"learning_rate": 2.2220874102964066e-05,
|
| 1948 |
+
"loss": 0.5204906463623047,
|
| 1949 |
+
"step": 554
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.417391304347826,
|
| 1953 |
+
"grad_norm": 0.37272965908050537,
|
| 1954 |
+
"learning_rate": 2.1880978386134822e-05,
|
| 1955 |
+
"loss": 1.3587431907653809,
|
| 1956 |
+
"step": 556
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.426086956521739,
|
| 1960 |
+
"grad_norm": 0.1551341414451599,
|
| 1961 |
+
"learning_rate": 2.1537247695273588e-05,
|
| 1962 |
+
"loss": 0.15599098801612854,
|
| 1963 |
+
"step": 558
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.4347826086956523,
|
| 1967 |
+
"grad_norm": 0.10612637549638748,
|
| 1968 |
+
"learning_rate": 2.1189966678280585e-05,
|
| 1969 |
+
"loss": 1.1518821716308594,
|
| 1970 |
+
"step": 560
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.4434782608695653,
|
| 1974 |
+
"grad_norm": 0.2193143665790558,
|
| 1975 |
+
"learning_rate": 2.0839422923127686e-05,
|
| 1976 |
+
"loss": 0.5007261037826538,
|
| 1977 |
+
"step": 562
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.4521739130434783,
|
| 1981 |
+
"grad_norm": 0.45728591084480286,
|
| 1982 |
+
"learning_rate": 2.0485906719703126e-05,
|
| 1983 |
+
"loss": 1.1414357423782349,
|
| 1984 |
+
"step": 564
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.4608695652173913,
|
| 1988 |
+
"grad_norm": 0.19980177283287048,
|
| 1989 |
+
"learning_rate": 2.0129710819418574e-05,
|
| 1990 |
+
"loss": 0.6164332032203674,
|
| 1991 |
+
"step": 566
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.4695652173913043,
|
| 1995 |
+
"grad_norm": 0.12282229214906693,
|
| 1996 |
+
"learning_rate": 1.9771130192777892e-05,
|
| 1997 |
+
"loss": 1.0142958164215088,
|
| 1998 |
+
"step": 568
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.4782608695652173,
|
| 2002 |
+
"grad_norm": 0.4857296347618103,
|
| 2003 |
+
"learning_rate": 1.9410461785108178e-05,
|
| 2004 |
+
"loss": 0.7631978392601013,
|
| 2005 |
+
"step": 570
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.4869565217391303,
|
| 2009 |
+
"grad_norm": 0.2022370547056198,
|
| 2010 |
+
"learning_rate": 1.9048004270655354e-05,
|
| 2011 |
+
"loss": 1.2384475469589233,
|
| 2012 |
+
"step": 572
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.4956521739130437,
|
| 2016 |
+
"grad_norm": 1.394151210784912,
|
| 2017 |
+
"learning_rate": 1.868405780524824e-05,
|
| 2018 |
+
"loss": 0.38715630769729614,
|
| 2019 |
+
"step": 574
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.5043478260869563,
|
| 2023 |
+
"grad_norm": 0.1383918970823288,
|
| 2024 |
+
"learning_rate": 1.831892377773547e-05,
|
| 2025 |
+
"loss": 1.1841545104980469,
|
| 2026 |
+
"step": 576
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.5130434782608697,
|
| 2030 |
+
"grad_norm": 0.19289281964302063,
|
| 2031 |
+
"learning_rate": 1.795290456040148e-05,
|
| 2032 |
+
"loss": 1.3352640867233276,
|
| 2033 |
+
"step": 578
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.5217391304347827,
|
| 2037 |
+
"grad_norm": 0.26483142375946045,
|
| 2038 |
+
"learning_rate": 1.7586303258567964e-05,
|
| 2039 |
+
"loss": 0.6390936374664307,
|
| 2040 |
+
"step": 580
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.5304347826086957,
|
| 2044 |
+
"grad_norm": 0.4453805088996887,
|
| 2045 |
+
"learning_rate": 1.7219423459588513e-05,
|
| 2046 |
+
"loss": 0.9683659672737122,
|
| 2047 |
+
"step": 582
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.5391304347826087,
|
| 2051 |
+
"grad_norm": 0.12072495371103287,
|
| 2052 |
+
"learning_rate": 1.6852568981443806e-05,
|
| 2053 |
+
"loss": 1.1052292585372925,
|
| 2054 |
+
"step": 584
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.5478260869565217,
|
| 2058 |
+
"grad_norm": 0.13637158274650574,
|
| 2059 |
+
"learning_rate": 1.648604362114606e-05,
|
| 2060 |
+
"loss": 0.708678126335144,
|
| 2061 |
+
"step": 586
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.5565217391304347,
|
| 2065 |
+
"grad_norm": 0.10113801807165146,
|
| 2066 |
+
"learning_rate": 1.6120150903160605e-05,
|
| 2067 |
+
"loss": 0.06356725841760635,
|
| 2068 |
+
"step": 588
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.5652173913043477,
|
| 2072 |
+
"grad_norm": 0.1465790867805481,
|
| 2073 |
+
"learning_rate": 1.5755193828053435e-05,
|
| 2074 |
+
"loss": 0.694472074508667,
|
| 2075 |
+
"step": 590
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.573913043478261,
|
| 2079 |
+
"grad_norm": 0.4859929382801056,
|
| 2080 |
+
"learning_rate": 1.539147462157235e-05,
|
| 2081 |
+
"loss": 0.09391395002603531,
|
| 2082 |
+
"step": 592
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.5826086956521737,
|
| 2086 |
+
"grad_norm": 0.4653010368347168,
|
| 2087 |
+
"learning_rate": 1.5029294484369874e-05,
|
| 2088 |
+
"loss": 1.3817299604415894,
|
| 2089 |
+
"step": 594
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.591304347826087,
|
| 2093 |
+
"grad_norm": 0.23374710977077484,
|
| 2094 |
+
"learning_rate": 1.4668953342575074e-05,
|
| 2095 |
+
"loss": 0.28024399280548096,
|
| 2096 |
+
"step": 596
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.6,
|
| 2100 |
+
"grad_norm": 0.19562578201293945,
|
| 2101 |
+
"learning_rate": 1.4310749599420711e-05,
|
| 2102 |
+
"loss": 0.4380612373352051,
|
| 2103 |
+
"step": 598
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.608695652173913,
|
| 2107 |
+
"grad_norm": 0.11721507459878922,
|
| 2108 |
+
"learning_rate": 1.3954979888131745e-05,
|
| 2109 |
+
"loss": 1.1383816003799438,
|
| 2110 |
+
"step": 600
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.617391304347826,
|
| 2114 |
+
"grad_norm": 0.12313393503427505,
|
| 2115 |
+
"learning_rate": 1.3601938826279298e-05,
|
| 2116 |
+
"loss": 0.6719468235969543,
|
| 2117 |
+
"step": 602
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.626086956521739,
|
| 2121 |
+
"grad_norm": 0.2674733102321625,
|
| 2122 |
+
"learning_rate": 1.325191877180408e-05,
|
| 2123 |
+
"loss": 0.8287115097045898,
|
| 2124 |
+
"step": 604
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.634782608695652,
|
| 2128 |
+
"grad_norm": 0.1634570211172104,
|
| 2129 |
+
"learning_rate": 1.2905209580910897e-05,
|
| 2130 |
+
"loss": 0.6804332137107849,
|
| 2131 |
+
"step": 606
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.643478260869565,
|
| 2135 |
+
"grad_norm": 0.2214396893978119,
|
| 2136 |
+
"learning_rate": 1.2562098368034954e-05,
|
| 2137 |
+
"loss": 1.1206378936767578,
|
| 2138 |
+
"step": 608
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.6521739130434785,
|
| 2142 |
+
"grad_norm": 0.17025478184223175,
|
| 2143 |
+
"learning_rate": 1.2222869268078575e-05,
|
| 2144 |
+
"loss": 0.7674025297164917,
|
| 2145 |
+
"step": 610
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.660869565217391,
|
| 2149 |
+
"grad_norm": 0.17491810023784637,
|
| 2150 |
+
"learning_rate": 1.1887803201115396e-05,
|
| 2151 |
+
"loss": 1.1401374340057373,
|
| 2152 |
+
"step": 612
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.6695652173913045,
|
| 2156 |
+
"grad_norm": 0.12606146931648254,
|
| 2157 |
+
"learning_rate": 1.1557177639756725e-05,
|
| 2158 |
+
"loss": 1.3836885690689087,
|
| 2159 |
+
"step": 614
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.6782608695652175,
|
| 2163 |
+
"grad_norm": 0.1093195304274559,
|
| 2164 |
+
"learning_rate": 1.1231266379372912e-05,
|
| 2165 |
+
"loss": 0.737335205078125,
|
| 2166 |
+
"step": 616
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.6869565217391305,
|
| 2170 |
+
"grad_norm": 0.14942651987075806,
|
| 2171 |
+
"learning_rate": 1.0910339311359677e-05,
|
| 2172 |
+
"loss": 0.6436473727226257,
|
| 2173 |
+
"step": 618
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.6956521739130435,
|
| 2177 |
+
"grad_norm": 0.6913372874259949,
|
| 2178 |
+
"learning_rate": 1.0594662199637597e-05,
|
| 2179 |
+
"loss": 0.7471338510513306,
|
| 2180 |
+
"step": 620
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.7043478260869565,
|
| 2184 |
+
"grad_norm": 0.14125873148441315,
|
| 2185 |
+
"learning_rate": 1.028449646056948e-05,
|
| 2186 |
+
"loss": 1.1643157005310059,
|
| 2187 |
+
"step": 622
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.7130434782608694,
|
| 2191 |
+
"grad_norm": 0.13380275666713715,
|
| 2192 |
+
"learning_rate": 9.980098946478024e-06,
|
| 2193 |
+
"loss": 1.1436272859573364,
|
| 2194 |
+
"step": 624
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.7217391304347824,
|
| 2198 |
+
"grad_norm": 0.1280951350927353,
|
| 2199 |
+
"learning_rate": 9.68172173294313e-06,
|
| 2200 |
+
"loss": 1.134834885597229,
|
| 2201 |
+
"step": 626
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.730434782608696,
|
| 2205 |
+
"grad_norm": 0.15834616124629974,
|
| 2206 |
+
"learning_rate": 9.389611910054602e-06,
|
| 2207 |
+
"loss": 1.237627625465393,
|
| 2208 |
+
"step": 628
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.7391304347826084,
|
| 2212 |
+
"grad_norm": 0.20524626970291138,
|
| 2213 |
+
"learning_rate": 9.10401137779385e-06,
|
| 2214 |
+
"loss": 1.1352347135543823,
|
| 2215 |
+
"step": 630
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.747826086956522,
|
| 2219 |
+
"grad_norm": 0.6567396521568298,
|
| 2220 |
+
"learning_rate": 8.825156645713136e-06,
|
| 2221 |
+
"loss": 0.46068328619003296,
|
| 2222 |
+
"step": 632
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.756521739130435,
|
| 2226 |
+
"grad_norm": 0.11645974218845367,
|
| 2227 |
+
"learning_rate": 8.553278637079007e-06,
|
| 2228 |
+
"loss": 0.6736262440681458,
|
| 2229 |
+
"step": 634
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.765217391304348,
|
| 2233 |
+
"grad_norm": 0.14792583882808685,
|
| 2234 |
+
"learning_rate": 8.28860249764168e-06,
|
| 2235 |
+
"loss": 0.6648976802825928,
|
| 2236 |
+
"step": 636
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.773913043478261,
|
| 2240 |
+
"grad_norm": 0.17419379949569702,
|
| 2241 |
+
"learning_rate": 8.031347409188885e-06,
|
| 2242 |
+
"loss": 1.132703423500061,
|
| 2243 |
+
"step": 638
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.782608695652174,
|
| 2247 |
+
"grad_norm": 0.323537677526474,
|
| 2248 |
+
"learning_rate": 7.78172640803854e-06,
|
| 2249 |
+
"loss": 1.2038984298706055,
|
| 2250 |
+
"step": 640
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.791304347826087,
|
| 2254 |
+
"grad_norm": 0.2815156877040863,
|
| 2255 |
+
"learning_rate": 7.539946208620638e-06,
|
| 2256 |
+
"loss": 1.206749677658081,
|
| 2257 |
+
"step": 642
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.8,
|
| 2261 |
+
"grad_norm": 0.5039319396018982,
|
| 2262 |
+
"learning_rate": 7.306207032294216e-06,
|
| 2263 |
+
"loss": 0.7191698551177979,
|
| 2264 |
+
"step": 644
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.8086956521739133,
|
| 2268 |
+
"grad_norm": 0.18908892571926117,
|
| 2269 |
+
"learning_rate": 7.08070244154148e-06,
|
| 2270 |
+
"loss": 0.7605520486831665,
|
| 2271 |
+
"step": 646
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.8173913043478263,
|
| 2275 |
+
"grad_norm": 0.2733303904533386,
|
| 2276 |
+
"learning_rate": 6.8636191796761585e-06,
|
| 2277 |
+
"loss": 0.6928582787513733,
|
| 2278 |
+
"step": 648
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.8260869565217392,
|
| 2282 |
+
"grad_norm": 0.30275958776474,
|
| 2283 |
+
"learning_rate": 6.655137016198907e-06,
|
| 2284 |
+
"loss": 1.3508784770965576,
|
| 2285 |
+
"step": 650
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.8347826086956522,
|
| 2289 |
+
"grad_norm": 0.1958470344543457,
|
| 2290 |
+
"learning_rate": 6.455428597927829e-06,
|
| 2291 |
+
"loss": 0.9979486465454102,
|
| 2292 |
+
"step": 652
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.8434782608695652,
|
| 2296 |
+
"grad_norm": 0.14218895137310028,
|
| 2297 |
+
"learning_rate": 6.264659306027376e-06,
|
| 2298 |
+
"loss": 1.139778971672058,
|
| 2299 |
+
"step": 654
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.8521739130434782,
|
| 2303 |
+
"grad_norm": 0.17221413552761078,
|
| 2304 |
+
"learning_rate": 6.082987119054014e-06,
|
| 2305 |
+
"loss": 0.8573166728019714,
|
| 2306 |
+
"step": 656
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.860869565217391,
|
| 2310 |
+
"grad_norm": 0.13826826214790344,
|
| 2311 |
+
"learning_rate": 5.910562482132162e-06,
|
| 2312 |
+
"loss": 1.1786668300628662,
|
| 2313 |
+
"step": 658
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.869565217391304,
|
| 2317 |
+
"grad_norm": 0.3460427522659302,
|
| 2318 |
+
"learning_rate": 5.747528182368537e-06,
|
| 2319 |
+
"loss": 1.1484174728393555,
|
| 2320 |
+
"step": 660
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.878260869565217,
|
| 2324 |
+
"grad_norm": 0.21556347608566284,
|
| 2325 |
+
"learning_rate": 5.594019230608316e-06,
|
| 2326 |
+
"loss": 1.2150859832763672,
|
| 2327 |
+
"step": 662
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.8869565217391306,
|
| 2331 |
+
"grad_norm": 0.17000877857208252,
|
| 2332 |
+
"learning_rate": 5.4501627496308754e-06,
|
| 2333 |
+
"loss": 1.1722112894058228,
|
| 2334 |
+
"step": 664
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.8956521739130436,
|
| 2338 |
+
"grad_norm": 0.1485866904258728,
|
| 2339 |
+
"learning_rate": 5.316077868877737e-06,
|
| 2340 |
+
"loss": 1.1153019666671753,
|
| 2341 |
+
"step": 666
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.9043478260869566,
|
| 2345 |
+
"grad_norm": 0.12437450885772705,
|
| 2346 |
+
"learning_rate": 5.191875625799956e-06,
|
| 2347 |
+
"loss": 1.164955496788025,
|
| 2348 |
+
"step": 668
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.9130434782608696,
|
| 2352 |
+
"grad_norm": 0.14834971725940704,
|
| 2353 |
+
"learning_rate": 5.077658873906456e-06,
|
| 2354 |
+
"loss": 1.1394230127334595,
|
| 2355 |
+
"step": 670
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.9217391304347826,
|
| 2359 |
+
"grad_norm": 1.5700373649597168,
|
| 2360 |
+
"learning_rate": 4.973522197589804e-06,
|
| 2361 |
+
"loss": 0.6004053354263306,
|
| 2362 |
+
"step": 672
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.9304347826086956,
|
| 2366 |
+
"grad_norm": 0.3607974648475647,
|
| 2367 |
+
"learning_rate": 4.87955183379954e-06,
|
| 2368 |
+
"loss": 0.8902421593666077,
|
| 2369 |
+
"step": 674
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.9391304347826086,
|
| 2373 |
+
"grad_norm": 0.12654371559619904,
|
| 2374 |
+
"learning_rate": 4.795825600628273e-06,
|
| 2375 |
+
"loss": 1.1788089275360107,
|
| 2376 |
+
"step": 676
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.9478260869565216,
|
| 2380 |
+
"grad_norm": 0.18413525819778442,
|
| 2381 |
+
"learning_rate": 4.722412832869478e-06,
|
| 2382 |
+
"loss": 1.0090527534484863,
|
| 2383 |
+
"step": 678
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.9565217391304346,
|
| 2387 |
+
"grad_norm": 0.13298968970775604,
|
| 2388 |
+
"learning_rate": 4.659374324600457e-06,
|
| 2389 |
+
"loss": 1.156622290611267,
|
| 2390 |
+
"step": 680
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.965217391304348,
|
| 2394 |
+
"grad_norm": 0.27358752489089966,
|
| 2395 |
+
"learning_rate": 4.606762278837947e-06,
|
| 2396 |
+
"loss": 0.44529619812965393,
|
| 2397 |
+
"step": 682
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.973913043478261,
|
| 2401 |
+
"grad_norm": 0.2820883095264435,
|
| 2402 |
+
"learning_rate": 4.5646202643081405e-06,
|
| 2403 |
+
"loss": 0.7129748463630676,
|
| 2404 |
+
"step": 684
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.982608695652174,
|
| 2408 |
+
"grad_norm": 0.09756142646074295,
|
| 2409 |
+
"learning_rate": 4.532983179366819e-06,
|
| 2410 |
+
"loss": 0.8244656920433044,
|
| 2411 |
+
"step": 686
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.991304347826087,
|
| 2415 |
+
"grad_norm": 0.19994956254959106,
|
| 2416 |
+
"learning_rate": 4.511877223099601e-06,
|
| 2417 |
+
"loss": 1.285622477531433,
|
| 2418 |
+
"step": 688
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 3.0,
|
| 2422 |
+
"grad_norm": 0.058878399431705475,
|
| 2423 |
+
"learning_rate": 4.501319873626102e-06,
|
| 2424 |
+
"loss": 0.6546279191970825,
|
| 2425 |
+
"step": 690
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 3.0,
|
| 2429 |
+
"step": 690,
|
| 2430 |
+
"total_flos": 2.5683697677065257e+18,
|
| 2431 |
+
"train_loss": 1.0660493817018426,
|
| 2432 |
+
"train_runtime": 18433.9416,
|
| 2433 |
+
"train_samples_per_second": 2.396,
|
| 2434 |
+
"train_steps_per_second": 0.037
|
| 2435 |
+
}
|
| 2436 |
+
],
|
| 2437 |
+
"logging_steps": 2,
|
| 2438 |
+
"max_steps": 690,
|
| 2439 |
+
"num_input_tokens_seen": 0,
|
| 2440 |
+
"num_train_epochs": 3,
|
| 2441 |
+
"save_steps": 99999,
|
| 2442 |
+
"stateful_callbacks": {
|
| 2443 |
+
"TrainerControl": {
|
| 2444 |
+
"args": {
|
| 2445 |
+
"should_epoch_stop": false,
|
| 2446 |
+
"should_evaluate": false,
|
| 2447 |
+
"should_log": false,
|
| 2448 |
+
"should_save": true,
|
| 2449 |
+
"should_training_stop": true
|
| 2450 |
+
},
|
| 2451 |
+
"attributes": {}
|
| 2452 |
+
}
|
| 2453 |
+
},
|
| 2454 |
+
"total_flos": 2.5683697677065257e+18,
|
| 2455 |
+
"train_batch_size": 1,
|
| 2456 |
+
"trial_name": null,
|
| 2457 |
+
"trial_params": null
|
| 2458 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c17453eaee22c7c634f955419bb66db918101553b86694937b1841dbab43b4f9
|
| 3 |
+
size 5649
|
training_loss.png
ADDED
|