Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- .ipynb_checkpoints/README-checkpoint.md +69 -0
- .ipynb_checkpoints/tokenizer_config-checkpoint.json +33 -0
- README.md +69 -0
- all_results.json +9 -0
- chat_template.jinja +154 -0
- config.json +113 -0
- generation_config.json +10 -0
- model.safetensors +3 -0
- processor_config.json +60 -0
- tokenizer.json +3 -0
- tokenizer_config.json +33 -0
- train_results.json +9 -0
- trainer_log.jsonl +353 -0
- trainer_state.json +2507 -0
- training_args.bin +3 -0
- training_loss.png +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
.ipynb_checkpoints/README-checkpoint.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen3.5-9B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: qwen35_caption_galore
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# qwen35_caption_galore
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
9b-41-2 but with max grad 0.025 and no frozen lower lang
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- family_to_muon_lr = {
|
| 39 |
+
"language": _fallback(getattr(training_args, "language_muon_lr", 3e-5), language_lr),
|
| 40 |
+
"vision": _fallback(getattr(training_args, "vision_muon_lr", 3e-5), vision_lr),
|
| 41 |
+
"merger": _fallback(getattr(training_args, "merger_muon_lr", 3e-5), merger_lr),
|
| 42 |
+
}
|
| 43 |
+
|
| 44 |
+
family_to_adamw_lr = {
|
| 45 |
+
"language": _fallback(getattr(training_args, "language_adamw_lr", 3e-5), language_lr),
|
| 46 |
+
"vision": _fallback(getattr(training_args, "vision_adamw_lr", 3e-6), vision_lr),
|
| 47 |
+
"merger": _fallback(getattr(training_args, "merger_adamw_lr", 3e-5), merger_lr),
|
| 48 |
+
}
|
| 49 |
+
- train_batch_size: 2
|
| 50 |
+
- eval_batch_size: 8
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- gradient_accumulation_steps: 32
|
| 54 |
+
- total_train_batch_size: 64
|
| 55 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 56 |
+
- lr_scheduler_type: cosine_with_min_lr
|
| 57 |
+
- lr_scheduler_warmup_steps: 0.05
|
| 58 |
+
- num_epochs: 3
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 5.5.3
|
| 67 |
+
- Pytorch 2.11.0+cu130
|
| 68 |
+
- Datasets 4.0.0
|
| 69 |
+
- Tokenizers 0.22.2
|
.ipynb_checkpoints/tokenizer_config-checkpoint.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 |
+
}
|
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen3.5-9B
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: qwen35_caption_galore
|
| 11 |
+
results: []
|
| 12 |
+
---
|
| 13 |
+
|
| 14 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
| 15 |
+
should probably proofread and complete it, then remove this comment. -->
|
| 16 |
+
|
| 17 |
+
# qwen35_caption_galore
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [/workspace/models/Qwen3.5-9B](https://huggingface.co//workspace/models/Qwen3.5-9B) on the my_caption dataset.
|
| 20 |
+
|
| 21 |
+
## Model description
|
| 22 |
+
|
| 23 |
+
More information needed
|
| 24 |
+
|
| 25 |
+
## Intended uses & limitations
|
| 26 |
+
|
| 27 |
+
More information needed
|
| 28 |
+
|
| 29 |
+
## Training and evaluation data
|
| 30 |
+
|
| 31 |
+
9b-41-2 but with max grad 0.025 and no frozen lower lang
|
| 32 |
+
|
| 33 |
+
## Training procedure
|
| 34 |
+
|
| 35 |
+
### Training hyperparameters
|
| 36 |
+
|
| 37 |
+
The following hyperparameters were used during training:
|
| 38 |
+
- family_to_muon_lr = {
|
| 39 |
+
"language": _fallback(getattr(training_args, "language_muon_lr", 3e-5), language_lr),
|
| 40 |
+
"vision": _fallback(getattr(training_args, "vision_muon_lr", 3e-5), vision_lr),
|
| 41 |
+
"merger": _fallback(getattr(training_args, "merger_muon_lr", 3e-5), merger_lr),
|
| 42 |
+
}
|
| 43 |
+
|
| 44 |
+
family_to_adamw_lr = {
|
| 45 |
+
"language": _fallback(getattr(training_args, "language_adamw_lr", 3e-5), language_lr),
|
| 46 |
+
"vision": _fallback(getattr(training_args, "vision_adamw_lr", 3e-6), vision_lr),
|
| 47 |
+
"merger": _fallback(getattr(training_args, "merger_adamw_lr", 3e-5), merger_lr),
|
| 48 |
+
}
|
| 49 |
+
- train_batch_size: 2
|
| 50 |
+
- eval_batch_size: 8
|
| 51 |
+
- seed: 42
|
| 52 |
+
- distributed_type: multi-GPU
|
| 53 |
+
- gradient_accumulation_steps: 32
|
| 54 |
+
- total_train_batch_size: 64
|
| 55 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 56 |
+
- lr_scheduler_type: cosine_with_min_lr
|
| 57 |
+
- lr_scheduler_warmup_steps: 0.05
|
| 58 |
+
- num_epochs: 3
|
| 59 |
+
|
| 60 |
+
### Training results
|
| 61 |
+
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 5.5.3
|
| 67 |
+
- Pytorch 2.11.0+cu130
|
| 68 |
+
- Datasets 4.0.0
|
| 69 |
+
- Tokenizers 0.22.2
|
all_results.json
ADDED
|
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"effective_tokens_per_sec": 6353.293364414007,
|
| 3 |
+
"epoch": 3.0,
|
| 4 |
+
"total_flos": 2.502111532985352e+18,
|
| 5 |
+
"train_loss": 0.8120331417161523,
|
| 6 |
+
"train_runtime": 7663.1544,
|
| 7 |
+
"train_samples_per_second": 5.888,
|
| 8 |
+
"train_steps_per_second": 0.092
|
| 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": "float32",
|
| 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:d31631e3703fd1c7471ca6a0c99a4f5439166d12d8d5ffac39b8657203826755
|
| 3 |
+
size 37639354416
|
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": 6353.293364414007,
|
| 3 |
+
"epoch": 3.0,
|
| 4 |
+
"total_flos": 2.502111532985352e+18,
|
| 5 |
+
"train_loss": 0.8120331417161523,
|
| 6 |
+
"train_runtime": 7663.1544,
|
| 7 |
+
"train_samples_per_second": 5.888,
|
| 8 |
+
"train_steps_per_second": 0.092
|
| 9 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,353 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 2, "total_steps": 705, "loss": 4.0039777755737305, "lr": 8.333333333333333e-07, "epoch": 0.00851063829787234, "percentage": 0.28, "elapsed_time": "0:00:20", "remaining_time": "2:00:39"}
|
| 2 |
+
{"current_steps": 4, "total_steps": 705, "loss": 2.092726945877075, "lr": 2.4999999999999998e-06, "epoch": 0.01702127659574468, "percentage": 0.57, "elapsed_time": "0:00:44", "remaining_time": "2:08:47"}
|
| 3 |
+
{"current_steps": 6, "total_steps": 705, "loss": 1.9236807823181152, "lr": 4.166666666666667e-06, "epoch": 0.02553191489361702, "percentage": 0.85, "elapsed_time": "0:01:09", "remaining_time": "2:15:22"}
|
| 4 |
+
{"current_steps": 8, "total_steps": 705, "loss": 1.7322841882705688, "lr": 5.833333333333334e-06, "epoch": 0.03404255319148936, "percentage": 1.13, "elapsed_time": "0:01:27", "remaining_time": "2:07:01"}
|
| 5 |
+
{"current_steps": 10, "total_steps": 705, "loss": 1.7557320594787598, "lr": 7.5e-06, "epoch": 0.0425531914893617, "percentage": 1.42, "elapsed_time": "0:01:55", "remaining_time": "2:13:30"}
|
| 6 |
+
{"current_steps": 12, "total_steps": 705, "loss": 2.0681214332580566, "lr": 9.166666666666668e-06, "epoch": 0.05106382978723404, "percentage": 1.7, "elapsed_time": "0:02:16", "remaining_time": "2:11:26"}
|
| 7 |
+
{"current_steps": 14, "total_steps": 705, "loss": 1.6496400833129883, "lr": 1.0833333333333334e-05, "epoch": 0.059574468085106386, "percentage": 1.99, "elapsed_time": "0:02:39", "remaining_time": "2:10:54"}
|
| 8 |
+
{"current_steps": 16, "total_steps": 705, "loss": 1.78928804397583, "lr": 1.25e-05, "epoch": 0.06808510638297872, "percentage": 2.27, "elapsed_time": "0:03:01", "remaining_time": "2:10:29"}
|
| 9 |
+
{"current_steps": 18, "total_steps": 705, "loss": 1.4100672006607056, "lr": 1.4166666666666666e-05, "epoch": 0.07659574468085106, "percentage": 2.55, "elapsed_time": "0:03:20", "remaining_time": "2:07:39"}
|
| 10 |
+
{"current_steps": 20, "total_steps": 705, "loss": 1.4046533107757568, "lr": 1.5833333333333333e-05, "epoch": 0.0851063829787234, "percentage": 2.84, "elapsed_time": "0:03:43", "remaining_time": "2:07:20"}
|
| 11 |
+
{"current_steps": 22, "total_steps": 705, "loss": 1.4094287157058716, "lr": 1.7500000000000002e-05, "epoch": 0.09361702127659574, "percentage": 3.12, "elapsed_time": "0:04:10", "remaining_time": "2:09:51"}
|
| 12 |
+
{"current_steps": 24, "total_steps": 705, "loss": 1.0651377439498901, "lr": 1.9166666666666667e-05, "epoch": 0.10212765957446808, "percentage": 3.4, "elapsed_time": "0:04:28", "remaining_time": "2:06:50"}
|
| 13 |
+
{"current_steps": 26, "total_steps": 705, "loss": 1.187571406364441, "lr": 2.0833333333333333e-05, "epoch": 0.11063829787234042, "percentage": 3.69, "elapsed_time": "0:04:47", "remaining_time": "2:05:20"}
|
| 14 |
+
{"current_steps": 28, "total_steps": 705, "loss": 0.8422402739524841, "lr": 2.25e-05, "epoch": 0.11914893617021277, "percentage": 3.97, "elapsed_time": "0:05:06", "remaining_time": "2:03:24"}
|
| 15 |
+
{"current_steps": 30, "total_steps": 705, "loss": 1.3952103853225708, "lr": 2.4166666666666667e-05, "epoch": 0.1276595744680851, "percentage": 4.26, "elapsed_time": "0:05:31", "remaining_time": "2:04:21"}
|
| 16 |
+
{"current_steps": 32, "total_steps": 705, "loss": 0.6625706553459167, "lr": 2.5833333333333336e-05, "epoch": 0.13617021276595745, "percentage": 4.54, "elapsed_time": "0:05:46", "remaining_time": "2:01:21"}
|
| 17 |
+
{"current_steps": 34, "total_steps": 705, "loss": 1.233126163482666, "lr": 2.75e-05, "epoch": 0.14468085106382977, "percentage": 4.82, "elapsed_time": "0:06:08", "remaining_time": "2:01:19"}
|
| 18 |
+
{"current_steps": 36, "total_steps": 705, "loss": 1.522036075592041, "lr": 2.9166666666666666e-05, "epoch": 0.15319148936170213, "percentage": 5.11, "elapsed_time": "0:06:34", "remaining_time": "2:02:04"}
|
| 19 |
+
{"current_steps": 38, "total_steps": 705, "loss": 1.4075392484664917, "lr": 2.9998734788806287e-05, "epoch": 0.16170212765957448, "percentage": 5.39, "elapsed_time": "0:06:55", "remaining_time": "2:01:35"}
|
| 20 |
+
{"current_steps": 40, "total_steps": 705, "loss": 1.0875834226608276, "lr": 2.9988614605803806e-05, "epoch": 0.1702127659574468, "percentage": 5.67, "elapsed_time": "0:07:17", "remaining_time": "2:01:15"}
|
| 21 |
+
{"current_steps": 42, "total_steps": 705, "loss": 1.2082504034042358, "lr": 2.99683822733885e-05, "epoch": 0.17872340425531916, "percentage": 5.96, "elapsed_time": "0:07:40", "remaining_time": "2:01:07"}
|
| 22 |
+
{"current_steps": 44, "total_steps": 705, "loss": 1.2259453535079956, "lr": 2.9938053852362484e-05, "epoch": 0.18723404255319148, "percentage": 6.24, "elapsed_time": "0:08:02", "remaining_time": "2:00:41"}
|
| 23 |
+
{"current_steps": 46, "total_steps": 705, "loss": 1.3428634405136108, "lr": 2.989765341799095e-05, "epoch": 0.19574468085106383, "percentage": 6.52, "elapsed_time": "0:08:27", "remaining_time": "2:01:12"}
|
| 24 |
+
{"current_steps": 48, "total_steps": 705, "loss": 0.7827966213226318, "lr": 2.9847213040890793e-05, "epoch": 0.20425531914893616, "percentage": 6.81, "elapsed_time": "0:08:45", "remaining_time": "1:59:54"}
|
| 25 |
+
{"current_steps": 50, "total_steps": 705, "loss": 0.9074859023094177, "lr": 2.9786772761572335e-05, "epoch": 0.2127659574468085, "percentage": 7.09, "elapsed_time": "0:08:59", "remaining_time": "1:57:51"}
|
| 26 |
+
{"current_steps": 52, "total_steps": 705, "loss": 1.321467399597168, "lr": 2.9716380558654445e-05, "epoch": 0.22127659574468084, "percentage": 7.38, "elapsed_time": "0:09:25", "remaining_time": "1:58:24"}
|
| 27 |
+
{"current_steps": 54, "total_steps": 705, "loss": 1.1002169847488403, "lr": 2.9636092310778195e-05, "epoch": 0.2297872340425532, "percentage": 7.66, "elapsed_time": "0:09:47", "remaining_time": "1:58:05"}
|
| 28 |
+
{"current_steps": 56, "total_steps": 705, "loss": 0.8815129399299622, "lr": 2.954597175224938e-05, "epoch": 0.23829787234042554, "percentage": 7.94, "elapsed_time": "0:10:05", "remaining_time": "1:56:59"}
|
| 29 |
+
{"current_steps": 58, "total_steps": 705, "loss": 1.0324469804763794, "lr": 2.9446090422445016e-05, "epoch": 0.24680851063829787, "percentage": 8.23, "elapsed_time": "0:10:27", "remaining_time": "1:56:45"}
|
| 30 |
+
{"current_steps": 60, "total_steps": 705, "loss": 1.3160098791122437, "lr": 2.9336527609024072e-05, "epoch": 0.2553191489361702, "percentage": 8.51, "elapsed_time": "0:10:52", "remaining_time": "1:56:58"}
|
| 31 |
+
{"current_steps": 62, "total_steps": 705, "loss": 1.2711020708084106, "lr": 2.9217370284987434e-05, "epoch": 0.26382978723404255, "percentage": 8.79, "elapsed_time": "0:11:20", "remaining_time": "1:57:38"}
|
| 32 |
+
{"current_steps": 64, "total_steps": 705, "loss": 1.2588579654693604, "lr": 2.9088713039637117e-05, "epoch": 0.2723404255319149, "percentage": 9.08, "elapsed_time": "0:11:46", "remaining_time": "1:57:57"}
|
| 33 |
+
{"current_steps": 66, "total_steps": 705, "loss": 1.371834635734558, "lr": 2.8950658003489534e-05, "epoch": 0.28085106382978725, "percentage": 9.36, "elapsed_time": "0:12:07", "remaining_time": "1:57:27"}
|
| 34 |
+
{"current_steps": 68, "total_steps": 705, "loss": 1.227813720703125, "lr": 2.880331476720238e-05, "epoch": 0.28936170212765955, "percentage": 9.65, "elapsed_time": "0:12:35", "remaining_time": "1:57:53"}
|
| 35 |
+
{"current_steps": 70, "total_steps": 705, "loss": 1.4304167032241821, "lr": 2.8646800294579517e-05, "epoch": 0.2978723404255319, "percentage": 9.93, "elapsed_time": "0:12:56", "remaining_time": "1:57:20"}
|
| 36 |
+
{"current_steps": 72, "total_steps": 705, "loss": 1.328366756439209, "lr": 2.848123882972295e-05, "epoch": 0.30638297872340425, "percentage": 10.21, "elapsed_time": "0:13:18", "remaining_time": "1:57:00"}
|
| 37 |
+
{"current_steps": 74, "total_steps": 705, "loss": 0.8880937695503235, "lr": 2.8306761798405526e-05, "epoch": 0.3148936170212766, "percentage": 10.5, "elapsed_time": "0:13:36", "remaining_time": "1:56:03"}
|
| 38 |
+
{"current_steps": 76, "total_steps": 705, "loss": 1.3181480169296265, "lr": 2.812350770374273e-05, "epoch": 0.32340425531914896, "percentage": 10.78, "elapsed_time": "0:13:58", "remaining_time": "1:55:35"}
|
| 39 |
+
{"current_steps": 78, "total_steps": 705, "loss": 1.2563281059265137, "lr": 2.793162201624631e-05, "epoch": 0.33191489361702126, "percentage": 11.06, "elapsed_time": "0:14:21", "remaining_time": "1:55:24"}
|
| 40 |
+
{"current_steps": 80, "total_steps": 705, "loss": 0.903084933757782, "lr": 2.77312570583471e-05, "epoch": 0.3404255319148936, "percentage": 11.35, "elapsed_time": "0:14:35", "remaining_time": "1:54:02"}
|
| 41 |
+
{"current_steps": 82, "total_steps": 705, "loss": 1.2202683687210083, "lr": 2.752257188347862e-05, "epoch": 0.34893617021276596, "percentage": 11.63, "elapsed_time": "0:14:56", "remaining_time": "1:53:29"}
|
| 42 |
+
{"current_steps": 84, "total_steps": 705, "loss": 1.021187424659729, "lr": 2.730573214981751e-05, "epoch": 0.3574468085106383, "percentage": 11.91, "elapsed_time": "0:15:16", "remaining_time": "1:52:55"}
|
| 43 |
+
{"current_steps": 86, "total_steps": 705, "loss": 0.955544650554657, "lr": 2.7080909988780982e-05, "epoch": 0.3659574468085106, "percentage": 12.2, "elapsed_time": "0:15:38", "remaining_time": "1:52:33"}
|
| 44 |
+
{"current_steps": 88, "total_steps": 705, "loss": 1.1776865720748901, "lr": 2.684828386838569e-05, "epoch": 0.37446808510638296, "percentage": 12.48, "elapsed_time": "0:16:00", "remaining_time": "1:52:13"}
|
| 45 |
+
{"current_steps": 90, "total_steps": 705, "loss": 0.8726862668991089, "lr": 2.6608038451576528e-05, "epoch": 0.3829787234042553, "percentage": 12.77, "elapsed_time": "0:16:18", "remaining_time": "1:51:24"}
|
| 46 |
+
{"current_steps": 92, "total_steps": 705, "loss": 1.2601391077041626, "lr": 2.636036444963769e-05, "epoch": 0.39148936170212767, "percentage": 13.05, "elapsed_time": "0:16:39", "remaining_time": "1:50:57"}
|
| 47 |
+
{"current_steps": 94, "total_steps": 705, "loss": 1.246147871017456, "lr": 2.6105458470802563e-05, "epoch": 0.4, "percentage": 13.33, "elapsed_time": "0:17:01", "remaining_time": "1:50:40"}
|
| 48 |
+
{"current_steps": 96, "total_steps": 705, "loss": 1.1205939054489136, "lr": 2.5843522864182394e-05, "epoch": 0.4085106382978723, "percentage": 13.62, "elapsed_time": "0:17:24", "remaining_time": "1:50:23"}
|
| 49 |
+
{"current_steps": 98, "total_steps": 705, "loss": 1.029671549797058, "lr": 2.557476555913785e-05, "epoch": 0.41702127659574467, "percentage": 13.9, "elapsed_time": "0:17:43", "remaining_time": "1:49:48"}
|
| 50 |
+
{"current_steps": 100, "total_steps": 705, "loss": 1.0204272270202637, "lr": 2.5299399900220803e-05, "epoch": 0.425531914893617, "percentage": 14.18, "elapsed_time": "0:18:03", "remaining_time": "1:49:14"}
|
| 51 |
+
{"current_steps": 102, "total_steps": 705, "loss": 1.2801953554153442, "lr": 2.5017644477817424e-05, "epoch": 0.4340425531914894, "percentage": 14.47, "elapsed_time": "0:18:25", "remaining_time": "1:48:57"}
|
| 52 |
+
{"current_steps": 104, "total_steps": 705, "loss": 0.9845929741859436, "lr": 2.47297229546271e-05, "epoch": 0.4425531914893617, "percentage": 14.75, "elapsed_time": "0:18:47", "remaining_time": "1:48:35"}
|
| 53 |
+
{"current_steps": 106, "total_steps": 705, "loss": 0.8531012535095215, "lr": 2.4435863888114814e-05, "epoch": 0.451063829787234, "percentage": 15.04, "elapsed_time": "0:19:05", "remaining_time": "1:47:53"}
|
| 54 |
+
{"current_steps": 108, "total_steps": 705, "loss": 1.256201148033142, "lr": 2.4136300549077976e-05, "epoch": 0.4595744680851064, "percentage": 15.32, "elapsed_time": "0:19:31", "remaining_time": "1:47:54"}
|
| 55 |
+
{"current_steps": 110, "total_steps": 705, "loss": 1.2275390625, "lr": 2.3831270736471703e-05, "epoch": 0.46808510638297873, "percentage": 15.6, "elapsed_time": "0:19:57", "remaining_time": "1:47:55"}
|
| 56 |
+
{"current_steps": 112, "total_steps": 705, "loss": 1.5093128681182861, "lr": 2.352101658863959e-05, "epoch": 0.4765957446808511, "percentage": 15.89, "elapsed_time": "0:20:18", "remaining_time": "1:47:30"}
|
| 57 |
+
{"current_steps": 114, "total_steps": 705, "loss": 1.0485801696777344, "lr": 2.32057843910998e-05, "epoch": 0.4851063829787234, "percentage": 16.17, "elapsed_time": "0:20:40", "remaining_time": "1:47:10"}
|
| 58 |
+
{"current_steps": 116, "total_steps": 705, "loss": 1.0241464376449585, "lr": 2.288582438103903e-05, "epoch": 0.49361702127659574, "percentage": 16.45, "elapsed_time": "0:21:02", "remaining_time": "1:46:50"}
|
| 59 |
+
{"current_steps": 118, "total_steps": 705, "loss": 1.259883999824524, "lr": 2.256139054866955e-05, "epoch": 0.502127659574468, "percentage": 16.74, "elapsed_time": "0:21:28", "remaining_time": "1:46:49"}
|
| 60 |
+
{"current_steps": 120, "total_steps": 705, "loss": 0.8736612796783447, "lr": 2.2232740435607067e-05, "epoch": 0.5106382978723404, "percentage": 17.02, "elapsed_time": "0:21:46", "remaining_time": "1:46:09"}
|
| 61 |
+
{"current_steps": 122, "total_steps": 705, "loss": 1.2946780920028687, "lr": 2.19001349304294e-05, "epoch": 0.5191489361702127, "percentage": 17.3, "elapsed_time": "0:22:11", "remaining_time": "1:46:03"}
|
| 62 |
+
{"current_steps": 124, "total_steps": 705, "loss": 1.2013747692108154, "lr": 2.156383806157826e-05, "epoch": 0.5276595744680851, "percentage": 17.59, "elapsed_time": "0:22:37", "remaining_time": "1:45:59"}
|
| 63 |
+
{"current_steps": 126, "total_steps": 705, "loss": 1.2230784893035889, "lr": 2.1224116787768552e-05, "epoch": 0.5361702127659574, "percentage": 17.87, "elapsed_time": "0:23:03", "remaining_time": "1:45:56"}
|
| 64 |
+
{"current_steps": 128, "total_steps": 705, "loss": 1.0054576396942139, "lr": 2.0881240786071588e-05, "epoch": 0.5446808510638298, "percentage": 18.16, "elapsed_time": "0:23:24", "remaining_time": "1:45:29"}
|
| 65 |
+
{"current_steps": 130, "total_steps": 705, "loss": 1.0494941473007202, "lr": 2.05354822378404e-05, "epoch": 0.5531914893617021, "percentage": 18.44, "elapsed_time": "0:23:45", "remaining_time": "1:45:06"}
|
| 66 |
+
{"current_steps": 132, "total_steps": 705, "loss": 1.2933894395828247, "lr": 2.018711561264714e-05, "epoch": 0.5617021276595745, "percentage": 18.72, "elapsed_time": "0:24:11", "remaining_time": "1:45:01"}
|
| 67 |
+
{"current_steps": 134, "total_steps": 705, "loss": 1.172606110572815, "lr": 1.9836417450403978e-05, "epoch": 0.5702127659574469, "percentage": 19.01, "elapsed_time": "0:24:34", "remaining_time": "1:44:43"}
|
| 68 |
+
{"current_steps": 136, "total_steps": 705, "loss": 0.9525983929634094, "lr": 1.9483666141840615e-05, "epoch": 0.5787234042553191, "percentage": 19.29, "elapsed_time": "0:24:56", "remaining_time": "1:44:21"}
|
| 69 |
+
{"current_steps": 138, "total_steps": 705, "loss": 0.6214677095413208, "lr": 1.9129141707512508e-05, "epoch": 0.5872340425531914, "percentage": 19.57, "elapsed_time": "0:25:11", "remaining_time": "1:43:31"}
|
| 70 |
+
{"current_steps": 140, "total_steps": 705, "loss": 1.0034734010696411, "lr": 1.8773125575515364e-05, "epoch": 0.5957446808510638, "percentage": 19.86, "elapsed_time": "0:25:34", "remaining_time": "1:43:10"}
|
| 71 |
+
{"current_steps": 142, "total_steps": 705, "loss": 1.2574905157089233, "lr": 1.8415900358082268e-05, "epoch": 0.6042553191489362, "percentage": 20.14, "elapsed_time": "0:26:01", "remaining_time": "1:43:10"}
|
| 72 |
+
{"current_steps": 144, "total_steps": 705, "loss": 1.039708137512207, "lr": 1.805774962724083e-05, "epoch": 0.6127659574468085, "percentage": 20.43, "elapsed_time": "0:26:18", "remaining_time": "1:42:28"}
|
| 73 |
+
{"current_steps": 146, "total_steps": 705, "loss": 1.1023411750793457, "lr": 1.7698957689708426e-05, "epoch": 0.6212765957446809, "percentage": 20.71, "elapsed_time": "0:26:39", "remaining_time": "1:42:05"}
|
| 74 |
+
{"current_steps": 148, "total_steps": 705, "loss": 1.2206919193267822, "lr": 1.7339809361204252e-05, "epoch": 0.6297872340425532, "percentage": 20.99, "elapsed_time": "0:27:07", "remaining_time": "1:42:05"}
|
| 75 |
+
{"current_steps": 150, "total_steps": 705, "loss": 1.327172875404358, "lr": 1.6980589740357294e-05, "epoch": 0.6382978723404256, "percentage": 21.28, "elapsed_time": "0:27:33", "remaining_time": "1:41:56"}
|
| 76 |
+
{"current_steps": 152, "total_steps": 705, "loss": 1.3268358707427979, "lr": 1.6621583982389707e-05, "epoch": 0.6468085106382979, "percentage": 21.56, "elapsed_time": "0:27:53", "remaining_time": "1:41:28"}
|
| 77 |
+
{"current_steps": 154, "total_steps": 705, "loss": 0.7203034162521362, "lr": 1.6263077072755326e-05, "epoch": 0.6553191489361702, "percentage": 21.84, "elapsed_time": "0:28:09", "remaining_time": "1:40:45"}
|
| 78 |
+
{"current_steps": 156, "total_steps": 705, "loss": 0.9463112354278564, "lr": 1.5905353600912898e-05, "epoch": 0.6638297872340425, "percentage": 22.13, "elapsed_time": "0:28:25", "remaining_time": "1:40:01"}
|
| 79 |
+
{"current_steps": 158, "total_steps": 705, "loss": 0.9798778891563416, "lr": 1.5548697534413646e-05, "epoch": 0.6723404255319149, "percentage": 22.41, "elapsed_time": "0:28:41", "remaining_time": "1:39:19"}
|
| 80 |
+
{"current_steps": 160, "total_steps": 705, "loss": 1.1495308876037598, "lr": 1.5193391993482582e-05, "epoch": 0.6808510638297872, "percentage": 22.7, "elapsed_time": "0:29:07", "remaining_time": "1:39:11"}
|
| 81 |
+
{"current_steps": 162, "total_steps": 705, "loss": 1.0284472703933716, "lr": 1.4839719026272377e-05, "epoch": 0.6893617021276596, "percentage": 22.98, "elapsed_time": "0:29:28", "remaining_time": "1:38:49"}
|
| 82 |
+
{"current_steps": 164, "total_steps": 705, "loss": 0.8173097968101501, "lr": 1.4487959384968272e-05, "epoch": 0.6978723404255319, "percentage": 23.26, "elapsed_time": "0:29:47", "remaining_time": "1:38:15"}
|
| 83 |
+
{"current_steps": 166, "total_steps": 705, "loss": 0.994484007358551, "lr": 1.4138392302921813e-05, "epoch": 0.7063829787234043, "percentage": 23.55, "elapsed_time": "0:30:09", "remaining_time": "1:37:54"}
|
| 84 |
+
{"current_steps": 168, "total_steps": 705, "loss": 1.1443301439285278, "lr": 1.3791295272990175e-05, "epoch": 0.7148936170212766, "percentage": 23.83, "elapsed_time": "0:30:31", "remaining_time": "1:37:32"}
|
| 85 |
+
{"current_steps": 170, "total_steps": 705, "loss": 1.0067280530929565, "lr": 1.344694382725718e-05, "epoch": 0.723404255319149, "percentage": 24.11, "elapsed_time": "0:30:51", "remaining_time": "1:37:07"}
|
| 86 |
+
{"current_steps": 172, "total_steps": 705, "loss": 0.9691381454467773, "lr": 1.3105611318310818e-05, "epoch": 0.7319148936170212, "percentage": 24.4, "elapsed_time": "0:31:09", "remaining_time": "1:36:32"}
|
| 87 |
+
{"current_steps": 174, "total_steps": 705, "loss": 1.0925947427749634, "lr": 1.2767568702250844e-05, "epoch": 0.7404255319148936, "percentage": 24.68, "elapsed_time": "0:31:33", "remaining_time": "1:36:17"}
|
| 88 |
+
{"current_steps": 176, "total_steps": 705, "loss": 0.6399118304252625, "lr": 1.2433084323598791e-05, "epoch": 0.7489361702127659, "percentage": 24.96, "elapsed_time": "0:31:46", "remaining_time": "1:35:30"}
|
| 89 |
+
{"current_steps": 178, "total_steps": 705, "loss": 1.0284110307693481, "lr": 1.2102423702281116e-05, "epoch": 0.7574468085106383, "percentage": 25.25, "elapsed_time": "0:32:09", "remaining_time": "1:35:13"}
|
| 90 |
+
{"current_steps": 180, "total_steps": 705, "loss": 1.0611108541488647, "lr": 1.1775849322854516e-05, "epoch": 0.7659574468085106, "percentage": 25.53, "elapsed_time": "0:32:30", "remaining_time": "1:34:49"}
|
| 91 |
+
{"current_steps": 182, "total_steps": 705, "loss": 0.7678611278533936, "lr": 1.1453620426140795e-05, "epoch": 0.774468085106383, "percentage": 25.82, "elapsed_time": "0:32:48", "remaining_time": "1:34:17"}
|
| 92 |
+
{"current_steps": 184, "total_steps": 705, "loss": 0.954198956489563, "lr": 1.1135992803436695e-05, "epoch": 0.7829787234042553, "percentage": 26.1, "elapsed_time": "0:33:09", "remaining_time": "1:33:53"}
|
| 93 |
+
{"current_steps": 186, "total_steps": 705, "loss": 1.0221017599105835, "lr": 1.0823218593461992e-05, "epoch": 0.7914893617021277, "percentage": 26.38, "elapsed_time": "0:33:27", "remaining_time": "1:33:22"}
|
| 94 |
+
{"current_steps": 188, "total_steps": 705, "loss": 0.7189929485321045, "lr": 1.0515546082207097e-05, "epoch": 0.8, "percentage": 26.67, "elapsed_time": "0:33:45", "remaining_time": "1:32:50"}
|
| 95 |
+
{"current_steps": 190, "total_steps": 705, "loss": 1.0886459350585938, "lr": 1.0213219505838983e-05, "epoch": 0.8085106382978723, "percentage": 26.95, "elapsed_time": "0:34:07", "remaining_time": "1:32:29"}
|
| 96 |
+
{"current_steps": 192, "total_steps": 705, "loss": 1.2072498798370361, "lr": 9.91647885682201e-06, "epoch": 0.8170212765957446, "percentage": 27.23, "elapsed_time": "0:34:33", "remaining_time": "1:32:19"}
|
| 97 |
+
{"current_steps": 194, "total_steps": 705, "loss": 1.1986221075057983, "lr": 9.625559693407413e-06, "epoch": 0.825531914893617, "percentage": 27.52, "elapsed_time": "0:34:59", "remaining_time": "1:32:09"}
|
| 98 |
+
{"current_steps": 196, "total_steps": 705, "loss": 0.720963180065155, "lr": 9.340692952642789e-06, "epoch": 0.8340425531914893, "percentage": 27.8, "elapsed_time": "0:35:14", "remaining_time": "1:31:30"}
|
| 99 |
+
{"current_steps": 198, "total_steps": 705, "loss": 1.1722772121429443, "lr": 9.062104767049956e-06, "epoch": 0.8425531914893617, "percentage": 28.09, "elapsed_time": "0:35:40", "remaining_time": "1:31:20"}
|
| 100 |
+
{"current_steps": 200, "total_steps": 705, "loss": 1.0002360343933105, "lr": 8.790016285116763e-06, "epoch": 0.851063829787234, "percentage": 28.37, "elapsed_time": "0:36:02", "remaining_time": "1:31:00"}
|
| 101 |
+
{"current_steps": 202, "total_steps": 705, "loss": 0.9713231325149536, "lr": 8.524643495745306e-06, "epoch": 0.8595744680851064, "percentage": 28.65, "elapsed_time": "0:36:25", "remaining_time": "1:30:43"}
|
| 102 |
+
{"current_steps": 204, "total_steps": 705, "loss": 1.3201754093170166, "lr": 8.26619705679589e-06, "epoch": 0.8680851063829788, "percentage": 28.94, "elapsed_time": "0:36:51", "remaining_time": "1:30:30"}
|
| 103 |
+
{"current_steps": 206, "total_steps": 705, "loss": 1.282568335533142, "lr": 8.014882127862923e-06, "epoch": 0.8765957446808511, "percentage": 29.22, "elapsed_time": "0:37:13", "remaining_time": "1:30:10"}
|
| 104 |
+
{"current_steps": 208, "total_steps": 705, "loss": 0.9211198091506958, "lr": 7.770898207415416e-06, "epoch": 0.8851063829787233, "percentage": 29.5, "elapsed_time": "0:37:35", "remaining_time": "1:29:49"}
|
| 105 |
+
{"current_steps": 210, "total_steps": 705, "loss": 1.167230248451233, "lr": 7.534438974431351e-06, "epoch": 0.8936170212765957, "percentage": 29.79, "elapsed_time": "0:38:02", "remaining_time": "1:29:39"}
|
| 106 |
+
{"current_steps": 212, "total_steps": 705, "loss": 0.7129737138748169, "lr": 7.305692134651742e-06, "epoch": 0.902127659574468, "percentage": 30.07, "elapsed_time": "0:38:20", "remaining_time": "1:29:09"}
|
| 107 |
+
{"current_steps": 214, "total_steps": 705, "loss": 0.8392055034637451, "lr": 7.084839271576291e-06, "epoch": 0.9106382978723404, "percentage": 30.35, "elapsed_time": "0:38:40", "remaining_time": "1:28:43"}
|
| 108 |
+
{"current_steps": 216, "total_steps": 705, "loss": 0.5692006349563599, "lr": 6.872055702319054e-06, "epoch": 0.9191489361702128, "percentage": 30.64, "elapsed_time": "0:38:58", "remaining_time": "1:28:13"}
|
| 109 |
+
{"current_steps": 218, "total_steps": 705, "loss": 1.1953270435333252, "lr": 6.667510338438419e-06, "epoch": 0.9276595744680851, "percentage": 30.92, "elapsed_time": "0:39:23", "remaining_time": "1:28:00"}
|
| 110 |
+
{"current_steps": 220, "total_steps": 705, "loss": 0.3942694067955017, "lr": 6.471365551852012e-06, "epoch": 0.9361702127659575, "percentage": 31.21, "elapsed_time": "0:39:34", "remaining_time": "1:27:14"}
|
| 111 |
+
{"current_steps": 222, "total_steps": 705, "loss": 1.3081778287887573, "lr": 6.2837770459428e-06, "epoch": 0.9446808510638298, "percentage": 31.49, "elapsed_time": "0:40:00", "remaining_time": "1:27:02"}
|
| 112 |
+
{"current_steps": 224, "total_steps": 705, "loss": 1.3682390451431274, "lr": 6.1048937319588676e-06, "epoch": 0.9531914893617022, "percentage": 31.77, "elapsed_time": "0:40:24", "remaining_time": "1:26:46"}
|
| 113 |
+
{"current_steps": 226, "total_steps": 705, "loss": 0.894014835357666, "lr": 5.9348576108049065e-06, "epoch": 0.9617021276595744, "percentage": 32.06, "elapsed_time": "0:40:41", "remaining_time": "1:26:15"}
|
| 114 |
+
{"current_steps": 228, "total_steps": 705, "loss": 1.0522630214691162, "lr": 5.773803660319234e-06, "epoch": 0.9702127659574468, "percentage": 32.34, "elapsed_time": "0:41:03", "remaining_time": "1:25:54"}
|
| 115 |
+
{"current_steps": 230, "total_steps": 705, "loss": 1.2654610872268677, "lr": 5.621859728125884e-06, "epoch": 0.9787234042553191, "percentage": 32.62, "elapsed_time": "0:41:29", "remaining_time": "1:25:41"}
|
| 116 |
+
{"current_steps": 232, "total_steps": 705, "loss": 1.0047165155410767, "lr": 5.479146430146781e-06, "epoch": 0.9872340425531915, "percentage": 32.91, "elapsed_time": "0:41:51", "remaining_time": "1:25:21"}
|
| 117 |
+
{"current_steps": 234, "total_steps": 705, "loss": 0.9647661447525024, "lr": 5.345777054854579e-06, "epoch": 0.9957446808510638, "percentage": 33.19, "elapsed_time": "0:42:10", "remaining_time": "1:24:52"}
|
| 118 |
+
{"current_steps": 236, "total_steps": 705, "loss": 0.9735086560249329, "lr": 5.221857473342149e-06, "epoch": 1.004255319148936, "percentage": 33.48, "elapsed_time": "0:42:31", "remaining_time": "1:24:30"}
|
| 119 |
+
{"current_steps": 238, "total_steps": 705, "loss": 0.8922760486602783, "lr": 5.10748605528015e-06, "epoch": 1.0127659574468084, "percentage": 33.76, "elapsed_time": "0:42:57", "remaining_time": "1:24:17"}
|
| 120 |
+
{"current_steps": 240, "total_steps": 705, "loss": 0.6222575306892395, "lr": 5.002753590829349e-06, "epoch": 1.0212765957446808, "percentage": 34.04, "elapsed_time": "0:43:16", "remaining_time": "1:23:50"}
|
| 121 |
+
{"current_steps": 242, "total_steps": 705, "loss": 0.8671458959579468, "lr": 4.9077432185697e-06, "epoch": 1.0297872340425531, "percentage": 34.33, "elapsed_time": "0:43:41", "remaining_time": "1:23:36"}
|
| 122 |
+
{"current_steps": 244, "total_steps": 705, "loss": 0.9555956721305847, "lr": 4.822530359503393e-06, "epoch": 1.0382978723404255, "percentage": 34.61, "elapsed_time": "0:44:07", "remaining_time": "1:23:21"}
|
| 123 |
+
{"current_steps": 246, "total_steps": 705, "loss": 0.6556552052497864, "lr": 4.747182657184251e-06, "epoch": 1.0468085106382978, "percentage": 34.89, "elapsed_time": "0:44:25", "remaining_time": "1:22:53"}
|
| 124 |
+
{"current_steps": 248, "total_steps": 705, "loss": 0.7056201100349426, "lr": 4.681759924021033e-06, "epoch": 1.0553191489361702, "percentage": 35.18, "elapsed_time": "0:44:49", "remaining_time": "1:22:36"}
|
| 125 |
+
{"current_steps": 250, "total_steps": 705, "loss": 0.6993778347969055, "lr": 4.626314093797213e-06, "epoch": 1.0638297872340425, "percentage": 35.46, "elapsed_time": "0:45:11", "remaining_time": "1:22:14"}
|
| 126 |
+
{"current_steps": 252, "total_steps": 705, "loss": 0.5365909337997437, "lr": 4.580889180444988e-06, "epoch": 1.0723404255319149, "percentage": 35.74, "elapsed_time": "0:45:26", "remaining_time": "1:21:40"}
|
| 127 |
+
{"current_steps": 254, "total_steps": 705, "loss": 0.8809426426887512, "lr": 4.545521243106197e-06, "epoch": 1.0808510638297872, "percentage": 36.03, "elapsed_time": "0:45:51", "remaining_time": "1:21:25"}
|
| 128 |
+
{"current_steps": 256, "total_steps": 705, "loss": 0.8317233324050903, "lr": 4.520238357507899e-06, "epoch": 1.0893617021276596, "percentage": 36.31, "elapsed_time": "0:46:17", "remaining_time": "1:21:11"}
|
| 129 |
+
{"current_steps": 258, "total_steps": 705, "loss": 0.9430326819419861, "lr": 4.505060593675342e-06, "epoch": 1.097872340425532, "percentage": 36.6, "elapsed_time": "0:46:41", "remaining_time": "1:20:52"}
|
| 130 |
+
{"current_steps": 260, "total_steps": 705, "loss": 0.7370553612709045, "lr": 4.5e-06, "epoch": 1.1063829787234043, "percentage": 36.88, "elapsed_time": "0:47:02", "remaining_time": "1:20:31"}
|
| 131 |
+
{"current_steps": 262, "total_steps": 705, "loss": 0.7691786289215088, "lr": 4.505060593675342e-06, "epoch": 1.1148936170212767, "percentage": 37.16, "elapsed_time": "0:47:24", "remaining_time": "1:20:09"}
|
| 132 |
+
{"current_steps": 264, "total_steps": 705, "loss": 0.7104212045669556, "lr": 4.520238357507899e-06, "epoch": 1.123404255319149, "percentage": 37.45, "elapsed_time": "0:47:45", "remaining_time": "1:19:46"}
|
| 133 |
+
{"current_steps": 266, "total_steps": 705, "loss": 0.8642681837081909, "lr": 4.545521243106197e-06, "epoch": 1.1319148936170214, "percentage": 37.73, "elapsed_time": "0:48:06", "remaining_time": "1:19:24"}
|
| 134 |
+
{"current_steps": 268, "total_steps": 705, "loss": 0.770044207572937, "lr": 4.580889180444988e-06, "epoch": 1.1404255319148937, "percentage": 38.01, "elapsed_time": "0:48:30", "remaining_time": "1:19:05"}
|
| 135 |
+
{"current_steps": 270, "total_steps": 705, "loss": 0.9661275148391724, "lr": 4.6263140937972124e-06, "epoch": 1.148936170212766, "percentage": 38.3, "elapsed_time": "0:48:53", "remaining_time": "1:18:46"}
|
| 136 |
+
{"current_steps": 272, "total_steps": 705, "loss": 0.6838027238845825, "lr": 4.6817599240210315e-06, "epoch": 1.1574468085106382, "percentage": 38.58, "elapsed_time": "0:49:13", "remaining_time": "1:18:21"}
|
| 137 |
+
{"current_steps": 274, "total_steps": 705, "loss": 0.8435700535774231, "lr": 4.747182657184251e-06, "epoch": 1.1659574468085105, "percentage": 38.87, "elapsed_time": "0:49:36", "remaining_time": "1:18:01"}
|
| 138 |
+
{"current_steps": 276, "total_steps": 705, "loss": 0.6485944986343384, "lr": 4.822530359503391e-06, "epoch": 1.174468085106383, "percentage": 39.15, "elapsed_time": "0:49:58", "remaining_time": "1:17:40"}
|
| 139 |
+
{"current_steps": 278, "total_steps": 705, "loss": 0.5239860415458679, "lr": 4.9077432185697e-06, "epoch": 1.1829787234042553, "percentage": 39.43, "elapsed_time": "0:50:17", "remaining_time": "1:17:14"}
|
| 140 |
+
{"current_steps": 280, "total_steps": 705, "loss": 0.524198055267334, "lr": 5.002753590829348e-06, "epoch": 1.1914893617021276, "percentage": 39.72, "elapsed_time": "0:50:36", "remaining_time": "1:16:49"}
|
| 141 |
+
{"current_steps": 282, "total_steps": 705, "loss": 0.8808120489120483, "lr": 5.1074860552801466e-06, "epoch": 1.2, "percentage": 40.0, "elapsed_time": "0:50:57", "remaining_time": "1:16:26"}
|
| 142 |
+
{"current_steps": 284, "total_steps": 705, "loss": 0.6656435132026672, "lr": 5.2218574733421455e-06, "epoch": 1.2085106382978723, "percentage": 40.28, "elapsed_time": "0:51:16", "remaining_time": "1:16:00"}
|
| 143 |
+
{"current_steps": 286, "total_steps": 705, "loss": 0.9856959581375122, "lr": 5.345777054854578e-06, "epoch": 1.2170212765957447, "percentage": 40.57, "elapsed_time": "0:51:40", "remaining_time": "1:15:41"}
|
| 144 |
+
{"current_steps": 288, "total_steps": 705, "loss": 0.8170779943466187, "lr": 5.479146430146783e-06, "epoch": 1.225531914893617, "percentage": 40.85, "elapsed_time": "0:52:04", "remaining_time": "1:15:24"}
|
| 145 |
+
{"current_steps": 290, "total_steps": 705, "loss": 0.44949835538864136, "lr": 5.6218597281258834e-06, "epoch": 1.2340425531914894, "percentage": 41.13, "elapsed_time": "0:52:24", "remaining_time": "1:14:59"}
|
| 146 |
+
{"current_steps": 292, "total_steps": 705, "loss": 0.9233723282814026, "lr": 5.773803660319232e-06, "epoch": 1.2425531914893617, "percentage": 41.42, "elapsed_time": "0:52:44", "remaining_time": "1:14:36"}
|
| 147 |
+
{"current_steps": 294, "total_steps": 705, "loss": 0.846575140953064, "lr": 5.934857610804904e-06, "epoch": 1.251063829787234, "percentage": 41.7, "elapsed_time": "0:53:10", "remaining_time": "1:14:20"}
|
| 148 |
+
{"current_steps": 296, "total_steps": 705, "loss": 0.6937251687049866, "lr": 6.1048937319588676e-06, "epoch": 1.2595744680851064, "percentage": 41.99, "elapsed_time": "0:53:31", "remaining_time": "1:13:56"}
|
| 149 |
+
{"current_steps": 298, "total_steps": 705, "loss": 0.8138055205345154, "lr": 6.283777045942798e-06, "epoch": 1.2680851063829788, "percentage": 42.27, "elapsed_time": "0:53:53", "remaining_time": "1:13:35"}
|
| 150 |
+
{"current_steps": 300, "total_steps": 705, "loss": 0.9583751559257507, "lr": 6.471365551852011e-06, "epoch": 1.2765957446808511, "percentage": 42.55, "elapsed_time": "0:54:18", "remaining_time": "1:13:18"}
|
| 151 |
+
{"current_steps": 302, "total_steps": 705, "loss": 0.38521289825439453, "lr": 6.66751033843842e-06, "epoch": 1.2851063829787235, "percentage": 42.84, "elapsed_time": "0:54:32", "remaining_time": "1:12:46"}
|
| 152 |
+
{"current_steps": 304, "total_steps": 705, "loss": 0.9158145189285278, "lr": 6.872055702319048e-06, "epoch": 1.2936170212765958, "percentage": 43.12, "elapsed_time": "0:54:58", "remaining_time": "1:12:30"}
|
| 153 |
+
{"current_steps": 306, "total_steps": 705, "loss": 0.9535613059997559, "lr": 7.084839271576289e-06, "epoch": 1.302127659574468, "percentage": 43.4, "elapsed_time": "0:55:23", "remaining_time": "1:12:13"}
|
| 154 |
+
{"current_steps": 308, "total_steps": 705, "loss": 0.5246633887290955, "lr": 7.30569213465174e-06, "epoch": 1.3106382978723405, "percentage": 43.69, "elapsed_time": "0:55:40", "remaining_time": "1:11:46"}
|
| 155 |
+
{"current_steps": 310, "total_steps": 705, "loss": 0.5024292469024658, "lr": 7.534438974431351e-06, "epoch": 1.3191489361702127, "percentage": 43.97, "elapsed_time": "0:55:58", "remaining_time": "1:11:20"}
|
| 156 |
+
{"current_steps": 312, "total_steps": 705, "loss": 0.5716067552566528, "lr": 7.770898207415414e-06, "epoch": 1.327659574468085, "percentage": 44.26, "elapsed_time": "0:56:19", "remaining_time": "1:10:57"}
|
| 157 |
+
{"current_steps": 314, "total_steps": 705, "loss": 0.5070632100105286, "lr": 8.014882127862923e-06, "epoch": 1.3361702127659574, "percentage": 44.54, "elapsed_time": "0:56:35", "remaining_time": "1:10:28"}
|
| 158 |
+
{"current_steps": 316, "total_steps": 705, "loss": 0.6399731040000916, "lr": 8.266197056795886e-06, "epoch": 1.3446808510638297, "percentage": 44.82, "elapsed_time": "0:56:57", "remaining_time": "1:10:06"}
|
| 159 |
+
{"current_steps": 318, "total_steps": 705, "loss": 0.5720309019088745, "lr": 8.5246434957453e-06, "epoch": 1.353191489361702, "percentage": 45.11, "elapsed_time": "0:57:14", "remaining_time": "1:09:39"}
|
| 160 |
+
{"current_steps": 320, "total_steps": 705, "loss": 0.49866631627082825, "lr": 8.790016285116766e-06, "epoch": 1.3617021276595744, "percentage": 45.39, "elapsed_time": "0:57:32", "remaining_time": "1:09:13"}
|
| 161 |
+
{"current_steps": 322, "total_steps": 705, "loss": 0.8831391334533691, "lr": 9.062104767049957e-06, "epoch": 1.3702127659574468, "percentage": 45.67, "elapsed_time": "0:57:57", "remaining_time": "1:08:56"}
|
| 162 |
+
{"current_steps": 324, "total_steps": 705, "loss": 0.6558242440223694, "lr": 9.340692952642787e-06, "epoch": 1.3787234042553191, "percentage": 45.96, "elapsed_time": "0:58:15", "remaining_time": "1:08:30"}
|
| 163 |
+
{"current_steps": 326, "total_steps": 705, "loss": 0.8320285677909851, "lr": 9.625559693407413e-06, "epoch": 1.3872340425531915, "percentage": 46.24, "elapsed_time": "0:58:41", "remaining_time": "1:08:14"}
|
| 164 |
+
{"current_steps": 328, "total_steps": 705, "loss": 0.6791567802429199, "lr": 9.916478856822006e-06, "epoch": 1.3957446808510638, "percentage": 46.52, "elapsed_time": "0:59:03", "remaining_time": "1:07:52"}
|
| 165 |
+
{"current_steps": 330, "total_steps": 705, "loss": 0.7776432633399963, "lr": 1.0213219505838985e-05, "epoch": 1.4042553191489362, "percentage": 46.81, "elapsed_time": "0:59:24", "remaining_time": "1:07:31"}
|
| 166 |
+
{"current_steps": 332, "total_steps": 705, "loss": 0.8018679022789001, "lr": 1.0515546082207094e-05, "epoch": 1.4127659574468086, "percentage": 47.09, "elapsed_time": "0:59:46", "remaining_time": "1:07:09"}
|
| 167 |
+
{"current_steps": 334, "total_steps": 705, "loss": 0.6729298830032349, "lr": 1.082321859346199e-05, "epoch": 1.421276595744681, "percentage": 47.38, "elapsed_time": "1:00:07", "remaining_time": "1:06:47"}
|
| 168 |
+
{"current_steps": 336, "total_steps": 705, "loss": 0.6063901782035828, "lr": 1.1135992803436696e-05, "epoch": 1.4297872340425533, "percentage": 47.66, "elapsed_time": "1:00:26", "remaining_time": "1:06:22"}
|
| 169 |
+
{"current_steps": 338, "total_steps": 705, "loss": 0.6617997288703918, "lr": 1.1453620426140791e-05, "epoch": 1.4382978723404256, "percentage": 47.94, "elapsed_time": "1:00:48", "remaining_time": "1:06:02"}
|
| 170 |
+
{"current_steps": 340, "total_steps": 705, "loss": 0.5969347953796387, "lr": 1.1775849322854508e-05, "epoch": 1.4468085106382977, "percentage": 48.23, "elapsed_time": "1:01:09", "remaining_time": "1:05:38"}
|
| 171 |
+
{"current_steps": 342, "total_steps": 705, "loss": 0.6071085333824158, "lr": 1.210242370228112e-05, "epoch": 1.4553191489361703, "percentage": 48.51, "elapsed_time": "1:01:29", "remaining_time": "1:05:16"}
|
| 172 |
+
{"current_steps": 344, "total_steps": 705, "loss": 0.9178237915039062, "lr": 1.2433084323598791e-05, "epoch": 1.4638297872340424, "percentage": 48.79, "elapsed_time": "1:01:57", "remaining_time": "1:05:01"}
|
| 173 |
+
{"current_steps": 346, "total_steps": 705, "loss": 0.8496959209442139, "lr": 1.2767568702250838e-05, "epoch": 1.472340425531915, "percentage": 49.08, "elapsed_time": "1:02:23", "remaining_time": "1:04:44"}
|
| 174 |
+
{"current_steps": 348, "total_steps": 705, "loss": 0.7014995813369751, "lr": 1.3105611318310811e-05, "epoch": 1.4808510638297872, "percentage": 49.36, "elapsed_time": "1:02:46", "remaining_time": "1:04:23"}
|
| 175 |
+
{"current_steps": 350, "total_steps": 705, "loss": 0.7825354337692261, "lr": 1.3446943827257184e-05, "epoch": 1.4893617021276595, "percentage": 49.65, "elapsed_time": "1:03:08", "remaining_time": "1:04:02"}
|
| 176 |
+
{"current_steps": 352, "total_steps": 705, "loss": 0.33443060517311096, "lr": 1.3791295272990172e-05, "epoch": 1.4978723404255319, "percentage": 49.93, "elapsed_time": "1:03:22", "remaining_time": "1:03:33"}
|
| 177 |
+
{"current_steps": 354, "total_steps": 705, "loss": 0.6189748048782349, "lr": 1.413839230292182e-05, "epoch": 1.5063829787234042, "percentage": 50.21, "elapsed_time": "1:03:41", "remaining_time": "1:03:08"}
|
| 178 |
+
{"current_steps": 356, "total_steps": 705, "loss": 0.46220940351486206, "lr": 1.4487959384968276e-05, "epoch": 1.5148936170212766, "percentage": 50.5, "elapsed_time": "1:04:02", "remaining_time": "1:02:47"}
|
| 179 |
+
{"current_steps": 358, "total_steps": 705, "loss": 0.4545080363750458, "lr": 1.4839719026272373e-05, "epoch": 1.523404255319149, "percentage": 50.78, "elapsed_time": "1:04:21", "remaining_time": "1:02:22"}
|
| 180 |
+
{"current_steps": 360, "total_steps": 705, "loss": 0.9656761288642883, "lr": 1.5193391993482579e-05, "epoch": 1.5319148936170213, "percentage": 51.06, "elapsed_time": "1:04:46", "remaining_time": "1:02:04"}
|
| 181 |
+
{"current_steps": 362, "total_steps": 705, "loss": 0.44390690326690674, "lr": 1.5548697534413636e-05, "epoch": 1.5404255319148936, "percentage": 51.35, "elapsed_time": "1:05:03", "remaining_time": "1:01:39"}
|
| 182 |
+
{"current_steps": 364, "total_steps": 705, "loss": 0.9684057235717773, "lr": 1.5905353600912894e-05, "epoch": 1.548936170212766, "percentage": 51.63, "elapsed_time": "1:05:29", "remaining_time": "1:01:20"}
|
| 183 |
+
{"current_steps": 366, "total_steps": 705, "loss": 0.8047466278076172, "lr": 1.6263077072755323e-05, "epoch": 1.5574468085106383, "percentage": 51.91, "elapsed_time": "1:05:51", "remaining_time": "1:01:00"}
|
| 184 |
+
{"current_steps": 368, "total_steps": 705, "loss": 0.6687026619911194, "lr": 1.6621583982389707e-05, "epoch": 1.5659574468085107, "percentage": 52.2, "elapsed_time": "1:06:10", "remaining_time": "1:00:35"}
|
| 185 |
+
{"current_steps": 370, "total_steps": 705, "loss": 0.5913136601448059, "lr": 1.6980589740357294e-05, "epoch": 1.574468085106383, "percentage": 52.48, "elapsed_time": "1:06:32", "remaining_time": "1:00:14"}
|
| 186 |
+
{"current_steps": 372, "total_steps": 705, "loss": 0.7752522230148315, "lr": 1.733980936120425e-05, "epoch": 1.5829787234042554, "percentage": 52.77, "elapsed_time": "1:06:58", "remaining_time": "0:59:57"}
|
| 187 |
+
{"current_steps": 374, "total_steps": 705, "loss": 0.9753284454345703, "lr": 1.7698957689708416e-05, "epoch": 1.5914893617021275, "percentage": 53.05, "elapsed_time": "1:07:26", "remaining_time": "0:59:41"}
|
| 188 |
+
{"current_steps": 376, "total_steps": 705, "loss": 0.7318065762519836, "lr": 1.805774962724083e-05, "epoch": 1.6, "percentage": 53.33, "elapsed_time": "1:07:50", "remaining_time": "0:59:21"}
|
| 189 |
+
{"current_steps": 378, "total_steps": 705, "loss": 0.5247442126274109, "lr": 1.8415900358082265e-05, "epoch": 1.6085106382978722, "percentage": 53.62, "elapsed_time": "1:08:09", "remaining_time": "0:58:57"}
|
| 190 |
+
{"current_steps": 380, "total_steps": 705, "loss": 0.5938118696212769, "lr": 1.8773125575515357e-05, "epoch": 1.6170212765957448, "percentage": 53.9, "elapsed_time": "1:08:27", "remaining_time": "0:58:33"}
|
| 191 |
+
{"current_steps": 382, "total_steps": 705, "loss": 0.761189341545105, "lr": 1.912914170751251e-05, "epoch": 1.625531914893617, "percentage": 54.18, "elapsed_time": "1:08:51", "remaining_time": "0:58:13"}
|
| 192 |
+
{"current_steps": 384, "total_steps": 705, "loss": 0.9914259910583496, "lr": 1.9483666141840612e-05, "epoch": 1.6340425531914895, "percentage": 54.47, "elapsed_time": "1:09:16", "remaining_time": "0:57:54"}
|
| 193 |
+
{"current_steps": 386, "total_steps": 705, "loss": 0.8401809930801392, "lr": 1.9836417450403974e-05, "epoch": 1.6425531914893616, "percentage": 54.75, "elapsed_time": "1:09:36", "remaining_time": "0:57:31"}
|
| 194 |
+
{"current_steps": 388, "total_steps": 705, "loss": 0.694261372089386, "lr": 2.0187115612647133e-05, "epoch": 1.6510638297872342, "percentage": 55.04, "elapsed_time": "1:09:59", "remaining_time": "0:57:10"}
|
| 195 |
+
{"current_steps": 390, "total_steps": 705, "loss": 0.8252889513969421, "lr": 2.05354822378404e-05, "epoch": 1.6595744680851063, "percentage": 55.32, "elapsed_time": "1:10:20", "remaining_time": "0:56:49"}
|
| 196 |
+
{"current_steps": 392, "total_steps": 705, "loss": 0.8890981078147888, "lr": 2.0881240786071595e-05, "epoch": 1.6680851063829787, "percentage": 55.6, "elapsed_time": "1:10:46", "remaining_time": "0:56:30"}
|
| 197 |
+
{"current_steps": 394, "total_steps": 705, "loss": 0.6046314835548401, "lr": 2.122411678776854e-05, "epoch": 1.676595744680851, "percentage": 55.89, "elapsed_time": "1:11:04", "remaining_time": "0:56:05"}
|
| 198 |
+
{"current_steps": 396, "total_steps": 705, "loss": 0.8832032084465027, "lr": 2.1563838061578258e-05, "epoch": 1.6851063829787234, "percentage": 56.17, "elapsed_time": "1:11:25", "remaining_time": "0:55:44"}
|
| 199 |
+
{"current_steps": 398, "total_steps": 705, "loss": 1.0986517667770386, "lr": 2.1900134930429396e-05, "epoch": 1.6936170212765957, "percentage": 56.45, "elapsed_time": "1:11:51", "remaining_time": "0:55:25"}
|
| 200 |
+
{"current_steps": 400, "total_steps": 705, "loss": 0.9784438610076904, "lr": 2.223274043560706e-05, "epoch": 1.702127659574468, "percentage": 56.74, "elapsed_time": "1:12:16", "remaining_time": "0:55:06"}
|
| 201 |
+
{"current_steps": 402, "total_steps": 705, "loss": 0.47277578711509705, "lr": 2.256139054866954e-05, "epoch": 1.7106382978723405, "percentage": 57.02, "elapsed_time": "1:12:32", "remaining_time": "0:54:40"}
|
| 202 |
+
{"current_steps": 404, "total_steps": 705, "loss": 0.6571931838989258, "lr": 2.2885824381039028e-05, "epoch": 1.7191489361702128, "percentage": 57.3, "elapsed_time": "1:12:52", "remaining_time": "0:54:17"}
|
| 203 |
+
{"current_steps": 406, "total_steps": 705, "loss": 0.5199674367904663, "lr": 2.3205784391099808e-05, "epoch": 1.7276595744680852, "percentage": 57.59, "elapsed_time": "1:13:08", "remaining_time": "0:53:51"}
|
| 204 |
+
{"current_steps": 408, "total_steps": 705, "loss": 0.7460405230522156, "lr": 2.352101658863958e-05, "epoch": 1.7361702127659573, "percentage": 57.87, "elapsed_time": "1:13:29", "remaining_time": "0:53:29"}
|
| 205 |
+
{"current_steps": 410, "total_steps": 705, "loss": 0.9135586023330688, "lr": 2.3831270736471703e-05, "epoch": 1.7446808510638299, "percentage": 58.16, "elapsed_time": "1:13:50", "remaining_time": "0:53:07"}
|
| 206 |
+
{"current_steps": 412, "total_steps": 705, "loss": 0.906153678894043, "lr": 2.4136300549077973e-05, "epoch": 1.753191489361702, "percentage": 58.44, "elapsed_time": "1:14:15", "remaining_time": "0:52:48"}
|
| 207 |
+
{"current_steps": 414, "total_steps": 705, "loss": 0.7806675434112549, "lr": 2.443586388811481e-05, "epoch": 1.7617021276595746, "percentage": 58.72, "elapsed_time": "1:14:35", "remaining_time": "0:52:25"}
|
| 208 |
+
{"current_steps": 416, "total_steps": 705, "loss": 0.6440402865409851, "lr": 2.47297229546271e-05, "epoch": 1.7702127659574467, "percentage": 59.01, "elapsed_time": "1:14:53", "remaining_time": "0:52:01"}
|
| 209 |
+
{"current_steps": 418, "total_steps": 705, "loss": 0.7717803120613098, "lr": 2.5017644477817418e-05, "epoch": 1.7787234042553193, "percentage": 59.29, "elapsed_time": "1:15:13", "remaining_time": "0:51:38"}
|
| 210 |
+
{"current_steps": 420, "total_steps": 705, "loss": 0.6290927529335022, "lr": 2.5299399900220807e-05, "epoch": 1.7872340425531914, "percentage": 59.57, "elapsed_time": "1:15:33", "remaining_time": "0:51:16"}
|
| 211 |
+
{"current_steps": 422, "total_steps": 705, "loss": 0.7530769109725952, "lr": 2.5574765559137848e-05, "epoch": 1.795744680851064, "percentage": 59.86, "elapsed_time": "1:15:54", "remaining_time": "0:50:54"}
|
| 212 |
+
{"current_steps": 424, "total_steps": 705, "loss": 0.8429850935935974, "lr": 2.584352286418239e-05, "epoch": 1.804255319148936, "percentage": 60.14, "elapsed_time": "1:16:16", "remaining_time": "0:50:32"}
|
| 213 |
+
{"current_steps": 426, "total_steps": 705, "loss": 0.8456153869628906, "lr": 2.6105458470802563e-05, "epoch": 1.8127659574468085, "percentage": 60.43, "elapsed_time": "1:16:38", "remaining_time": "0:50:11"}
|
| 214 |
+
{"current_steps": 428, "total_steps": 705, "loss": 0.8607503771781921, "lr": 2.6360364449637683e-05, "epoch": 1.8212765957446808, "percentage": 60.71, "elapsed_time": "1:17:00", "remaining_time": "0:49:50"}
|
| 215 |
+
{"current_steps": 430, "total_steps": 705, "loss": 0.9603878259658813, "lr": 2.6608038451576528e-05, "epoch": 1.8297872340425532, "percentage": 60.99, "elapsed_time": "1:17:21", "remaining_time": "0:49:28"}
|
| 216 |
+
{"current_steps": 432, "total_steps": 705, "loss": 0.7366024255752563, "lr": 2.684828386838569e-05, "epoch": 1.8382978723404255, "percentage": 61.28, "elapsed_time": "1:17:41", "remaining_time": "0:49:06"}
|
| 217 |
+
{"current_steps": 434, "total_steps": 705, "loss": 0.9086182117462158, "lr": 2.7080909988780982e-05, "epoch": 1.8468085106382979, "percentage": 61.56, "elapsed_time": "1:18:04", "remaining_time": "0:48:45"}
|
| 218 |
+
{"current_steps": 436, "total_steps": 705, "loss": 0.642800509929657, "lr": 2.7305732149817502e-05, "epoch": 1.8553191489361702, "percentage": 61.84, "elapsed_time": "1:18:24", "remaining_time": "0:48:22"}
|
| 219 |
+
{"current_steps": 438, "total_steps": 705, "loss": 1.0462186336517334, "lr": 2.7522571883478617e-05, "epoch": 1.8638297872340426, "percentage": 62.13, "elapsed_time": "1:18:49", "remaining_time": "0:48:03"}
|
| 220 |
+
{"current_steps": 440, "total_steps": 705, "loss": 0.9516323804855347, "lr": 2.77312570583471e-05, "epoch": 1.872340425531915, "percentage": 62.41, "elapsed_time": "1:19:11", "remaining_time": "0:47:41"}
|
| 221 |
+
{"current_steps": 442, "total_steps": 705, "loss": 0.9153946042060852, "lr": 2.7931622016246304e-05, "epoch": 1.8808510638297873, "percentage": 62.7, "elapsed_time": "1:19:36", "remaining_time": "0:47:22"}
|
| 222 |
+
{"current_steps": 444, "total_steps": 705, "loss": 0.8443633913993835, "lr": 2.8123507703742727e-05, "epoch": 1.8893617021276596, "percentage": 62.98, "elapsed_time": "1:20:02", "remaining_time": "0:47:02"}
|
| 223 |
+
{"current_steps": 446, "total_steps": 705, "loss": 1.0077768564224243, "lr": 2.8306761798405522e-05, "epoch": 1.8978723404255318, "percentage": 63.26, "elapsed_time": "1:20:27", "remaining_time": "0:46:43"}
|
| 224 |
+
{"current_steps": 448, "total_steps": 705, "loss": 0.9472059607505798, "lr": 2.848123882972295e-05, "epoch": 1.9063829787234043, "percentage": 63.55, "elapsed_time": "1:20:51", "remaining_time": "0:46:22"}
|
| 225 |
+
{"current_steps": 450, "total_steps": 705, "loss": 0.6875810623168945, "lr": 2.8646800294579514e-05, "epoch": 1.9148936170212765, "percentage": 63.83, "elapsed_time": "1:21:11", "remaining_time": "0:46:00"}
|
| 226 |
+
{"current_steps": 452, "total_steps": 705, "loss": 0.5654004812240601, "lr": 2.8803314767202376e-05, "epoch": 1.923404255319149, "percentage": 64.11, "elapsed_time": "1:21:28", "remaining_time": "0:45:36"}
|
| 227 |
+
{"current_steps": 454, "total_steps": 705, "loss": 0.8492231965065002, "lr": 2.8950658003489534e-05, "epoch": 1.9319148936170212, "percentage": 64.4, "elapsed_time": "1:21:50", "remaining_time": "0:45:14"}
|
| 228 |
+
{"current_steps": 456, "total_steps": 705, "loss": 0.9699692130088806, "lr": 2.908871303963711e-05, "epoch": 1.9404255319148938, "percentage": 64.68, "elapsed_time": "1:22:13", "remaining_time": "0:44:54"}
|
| 229 |
+
{"current_steps": 458, "total_steps": 705, "loss": 0.7598567605018616, "lr": 2.9217370284987434e-05, "epoch": 1.9489361702127659, "percentage": 64.96, "elapsed_time": "1:22:36", "remaining_time": "0:44:33"}
|
| 230 |
+
{"current_steps": 460, "total_steps": 705, "loss": 1.0349591970443726, "lr": 2.9336527609024075e-05, "epoch": 1.9574468085106385, "percentage": 65.25, "elapsed_time": "1:23:01", "remaining_time": "0:44:13"}
|
| 231 |
+
{"current_steps": 462, "total_steps": 705, "loss": 0.7465431094169617, "lr": 2.9446090422445016e-05, "epoch": 1.9659574468085106, "percentage": 65.53, "elapsed_time": "1:23:23", "remaining_time": "0:43:51"}
|
| 232 |
+
{"current_steps": 464, "total_steps": 705, "loss": 0.8450900316238403, "lr": 2.9545971752249376e-05, "epoch": 1.974468085106383, "percentage": 65.82, "elapsed_time": "1:23:46", "remaining_time": "0:43:30"}
|
| 233 |
+
{"current_steps": 466, "total_steps": 705, "loss": 0.8825825452804565, "lr": 2.9636092310778195e-05, "epoch": 1.9829787234042553, "percentage": 66.1, "elapsed_time": "1:24:05", "remaining_time": "0:43:07"}
|
| 234 |
+
{"current_steps": 468, "total_steps": 705, "loss": 0.6045427918434143, "lr": 2.9716380558654445e-05, "epoch": 1.9914893617021276, "percentage": 66.38, "elapsed_time": "1:24:24", "remaining_time": "0:42:44"}
|
| 235 |
+
{"current_steps": 470, "total_steps": 705, "loss": 0.6623026728630066, "lr": 2.9786772761572338e-05, "epoch": 2.0, "percentage": 66.67, "elapsed_time": "1:24:41", "remaining_time": "0:42:20"}
|
| 236 |
+
{"current_steps": 472, "total_steps": 705, "loss": 0.36443179845809937, "lr": 2.9847213040890793e-05, "epoch": 2.008510638297872, "percentage": 66.95, "elapsed_time": "1:24:57", "remaining_time": "0:41:56"}
|
| 237 |
+
{"current_steps": 474, "total_steps": 705, "loss": 0.75254225730896, "lr": 2.989765341799095e-05, "epoch": 2.0170212765957447, "percentage": 67.23, "elapsed_time": "1:25:23", "remaining_time": "0:41:36"}
|
| 238 |
+
{"current_steps": 476, "total_steps": 705, "loss": 0.47092172503471375, "lr": 2.9938053852362484e-05, "epoch": 2.025531914893617, "percentage": 67.52, "elapsed_time": "1:25:41", "remaining_time": "0:41:13"}
|
| 239 |
+
{"current_steps": 478, "total_steps": 705, "loss": 0.6583607196807861, "lr": 2.99683822733885e-05, "epoch": 2.0340425531914894, "percentage": 67.8, "elapsed_time": "1:26:02", "remaining_time": "0:40:51"}
|
| 240 |
+
{"current_steps": 480, "total_steps": 705, "loss": 0.5634033679962158, "lr": 2.9988614605803806e-05, "epoch": 2.0425531914893615, "percentage": 68.09, "elapsed_time": "1:26:20", "remaining_time": "0:40:28"}
|
| 241 |
+
{"current_steps": 482, "total_steps": 705, "loss": 0.4582347571849823, "lr": 2.9998734788806287e-05, "epoch": 2.051063829787234, "percentage": 68.37, "elapsed_time": "1:26:42", "remaining_time": "0:40:07"}
|
| 242 |
+
{"current_steps": 484, "total_steps": 705, "loss": 0.24273234605789185, "lr": 2.9998734788806287e-05, "epoch": 2.0595744680851062, "percentage": 68.65, "elapsed_time": "1:26:55", "remaining_time": "0:39:41"}
|
| 243 |
+
{"current_steps": 486, "total_steps": 705, "loss": 0.6905072331428528, "lr": 2.9988614605803806e-05, "epoch": 2.068085106382979, "percentage": 68.94, "elapsed_time": "1:27:17", "remaining_time": "0:39:20"}
|
| 244 |
+
{"current_steps": 488, "total_steps": 705, "loss": 0.4559966027736664, "lr": 2.99683822733885e-05, "epoch": 2.076595744680851, "percentage": 69.22, "elapsed_time": "1:27:39", "remaining_time": "0:38:58"}
|
| 245 |
+
{"current_steps": 490, "total_steps": 705, "loss": 0.5135046243667603, "lr": 2.9938053852362484e-05, "epoch": 2.0851063829787235, "percentage": 69.5, "elapsed_time": "1:28:01", "remaining_time": "0:38:37"}
|
| 246 |
+
{"current_steps": 492, "total_steps": 705, "loss": 0.7977150678634644, "lr": 2.989765341799095e-05, "epoch": 2.0936170212765957, "percentage": 69.79, "elapsed_time": "1:28:24", "remaining_time": "0:38:16"}
|
| 247 |
+
{"current_steps": 494, "total_steps": 705, "loss": 0.6057368516921997, "lr": 2.9847213040890793e-05, "epoch": 2.1021276595744682, "percentage": 70.07, "elapsed_time": "1:28:50", "remaining_time": "0:37:56"}
|
| 248 |
+
{"current_steps": 496, "total_steps": 705, "loss": 0.7654038071632385, "lr": 2.9786772761572338e-05, "epoch": 2.1106382978723404, "percentage": 70.35, "elapsed_time": "1:29:14", "remaining_time": "0:37:36"}
|
| 249 |
+
{"current_steps": 498, "total_steps": 705, "loss": 0.8083907961845398, "lr": 2.9716380558654445e-05, "epoch": 2.119148936170213, "percentage": 70.64, "elapsed_time": "1:29:43", "remaining_time": "0:37:17"}
|
| 250 |
+
{"current_steps": 500, "total_steps": 705, "loss": 0.5940195322036743, "lr": 2.9636092310778195e-05, "epoch": 2.127659574468085, "percentage": 70.92, "elapsed_time": "1:30:06", "remaining_time": "0:36:56"}
|
| 251 |
+
{"current_steps": 502, "total_steps": 705, "loss": 0.5825145244598389, "lr": 2.9545971752249383e-05, "epoch": 2.1361702127659576, "percentage": 71.21, "elapsed_time": "1:30:24", "remaining_time": "0:36:33"}
|
| 252 |
+
{"current_steps": 504, "total_steps": 705, "loss": 0.5060111284255981, "lr": 2.9446090422445016e-05, "epoch": 2.1446808510638298, "percentage": 71.49, "elapsed_time": "1:30:50", "remaining_time": "0:36:13"}
|
| 253 |
+
{"current_steps": 506, "total_steps": 705, "loss": 0.5895789265632629, "lr": 2.933652760902408e-05, "epoch": 2.153191489361702, "percentage": 71.77, "elapsed_time": "1:31:15", "remaining_time": "0:35:53"}
|
| 254 |
+
{"current_steps": 508, "total_steps": 705, "loss": 0.3788684010505676, "lr": 2.9217370284987434e-05, "epoch": 2.1617021276595745, "percentage": 72.06, "elapsed_time": "1:31:37", "remaining_time": "0:35:31"}
|
| 255 |
+
{"current_steps": 510, "total_steps": 705, "loss": 0.3065789043903351, "lr": 2.908871303963712e-05, "epoch": 2.1702127659574466, "percentage": 72.34, "elapsed_time": "1:31:56", "remaining_time": "0:35:09"}
|
| 256 |
+
{"current_steps": 512, "total_steps": 705, "loss": 0.3498597741127014, "lr": 2.8950658003489534e-05, "epoch": 2.178723404255319, "percentage": 72.62, "elapsed_time": "1:32:15", "remaining_time": "0:34:46"}
|
| 257 |
+
{"current_steps": 514, "total_steps": 705, "loss": 0.3588785231113434, "lr": 2.8803314767202387e-05, "epoch": 2.1872340425531913, "percentage": 72.91, "elapsed_time": "1:32:35", "remaining_time": "0:34:24"}
|
| 258 |
+
{"current_steps": 516, "total_steps": 705, "loss": 0.4839470088481903, "lr": 2.864680029457952e-05, "epoch": 2.195744680851064, "percentage": 73.19, "elapsed_time": "1:33:00", "remaining_time": "0:34:04"}
|
| 259 |
+
{"current_steps": 518, "total_steps": 705, "loss": 0.6455433368682861, "lr": 2.8481238829722946e-05, "epoch": 2.204255319148936, "percentage": 73.48, "elapsed_time": "1:33:22", "remaining_time": "0:33:42"}
|
| 260 |
+
{"current_steps": 520, "total_steps": 705, "loss": 0.5413359999656677, "lr": 2.8306761798405533e-05, "epoch": 2.2127659574468086, "percentage": 73.76, "elapsed_time": "1:33:43", "remaining_time": "0:33:20"}
|
| 261 |
+
{"current_steps": 522, "total_steps": 705, "loss": 0.33399829268455505, "lr": 2.812350770374273e-05, "epoch": 2.2212765957446807, "percentage": 74.04, "elapsed_time": "1:34:02", "remaining_time": "0:32:57"}
|
| 262 |
+
{"current_steps": 524, "total_steps": 705, "loss": 0.4370644688606262, "lr": 2.793162201624631e-05, "epoch": 2.2297872340425533, "percentage": 74.33, "elapsed_time": "1:34:18", "remaining_time": "0:32:34"}
|
| 263 |
+
{"current_steps": 526, "total_steps": 705, "loss": 0.6098963618278503, "lr": 2.7731257058347098e-05, "epoch": 2.2382978723404254, "percentage": 74.61, "elapsed_time": "1:34:44", "remaining_time": "0:32:14"}
|
| 264 |
+
{"current_steps": 528, "total_steps": 705, "loss": 0.6518822908401489, "lr": 2.752257188347862e-05, "epoch": 2.246808510638298, "percentage": 74.89, "elapsed_time": "1:35:05", "remaining_time": "0:31:52"}
|
| 265 |
+
{"current_steps": 530, "total_steps": 705, "loss": 0.6883822679519653, "lr": 2.7305732149817512e-05, "epoch": 2.25531914893617, "percentage": 75.18, "elapsed_time": "1:35:29", "remaining_time": "0:31:31"}
|
| 266 |
+
{"current_steps": 532, "total_steps": 705, "loss": 0.5799202919006348, "lr": 2.708090998878098e-05, "epoch": 2.2638297872340427, "percentage": 75.46, "elapsed_time": "1:35:53", "remaining_time": "0:31:11"}
|
| 267 |
+
{"current_steps": 534, "total_steps": 705, "loss": 0.30189117789268494, "lr": 2.68482838683857e-05, "epoch": 2.272340425531915, "percentage": 75.74, "elapsed_time": "1:36:12", "remaining_time": "0:30:48"}
|
| 268 |
+
{"current_steps": 536, "total_steps": 705, "loss": 0.5066512823104858, "lr": 2.6608038451576528e-05, "epoch": 2.2808510638297874, "percentage": 76.03, "elapsed_time": "1:36:38", "remaining_time": "0:30:28"}
|
| 269 |
+
{"current_steps": 538, "total_steps": 705, "loss": 0.7329890131950378, "lr": 2.6360364449637686e-05, "epoch": 2.2893617021276595, "percentage": 76.31, "elapsed_time": "1:37:04", "remaining_time": "0:30:07"}
|
| 270 |
+
{"current_steps": 540, "total_steps": 705, "loss": 0.23619456589221954, "lr": 2.6105458470802563e-05, "epoch": 2.297872340425532, "percentage": 76.6, "elapsed_time": "1:37:20", "remaining_time": "0:29:44"}
|
| 271 |
+
{"current_steps": 542, "total_steps": 705, "loss": 0.2426261454820633, "lr": 2.5843522864182397e-05, "epoch": 2.3063829787234043, "percentage": 76.88, "elapsed_time": "1:37:33", "remaining_time": "0:29:20"}
|
| 272 |
+
{"current_steps": 544, "total_steps": 705, "loss": 0.4293208420276642, "lr": 2.557476555913786e-05, "epoch": 2.3148936170212764, "percentage": 77.16, "elapsed_time": "1:37:51", "remaining_time": "0:28:57"}
|
| 273 |
+
{"current_steps": 546, "total_steps": 705, "loss": 0.317562460899353, "lr": 2.52993999002208e-05, "epoch": 2.323404255319149, "percentage": 77.45, "elapsed_time": "1:38:12", "remaining_time": "0:28:35"}
|
| 274 |
+
{"current_steps": 548, "total_steps": 705, "loss": 0.7331305742263794, "lr": 2.501764447781743e-05, "epoch": 2.331914893617021, "percentage": 77.73, "elapsed_time": "1:38:33", "remaining_time": "0:28:14"}
|
| 275 |
+
{"current_steps": 550, "total_steps": 705, "loss": 0.4494149088859558, "lr": 2.4729722954627106e-05, "epoch": 2.3404255319148937, "percentage": 78.01, "elapsed_time": "1:38:52", "remaining_time": "0:27:51"}
|
| 276 |
+
{"current_steps": 552, "total_steps": 705, "loss": 0.5373607873916626, "lr": 2.4435863888114814e-05, "epoch": 2.348936170212766, "percentage": 78.3, "elapsed_time": "1:39:14", "remaining_time": "0:27:30"}
|
| 277 |
+
{"current_steps": 554, "total_steps": 705, "loss": 0.7187270522117615, "lr": 2.413630054907798e-05, "epoch": 2.3574468085106384, "percentage": 78.58, "elapsed_time": "1:39:35", "remaining_time": "0:27:08"}
|
| 278 |
+
{"current_steps": 556, "total_steps": 705, "loss": 0.5384994745254517, "lr": 2.383127073647171e-05, "epoch": 2.3659574468085105, "percentage": 78.87, "elapsed_time": "1:39:58", "remaining_time": "0:26:47"}
|
| 279 |
+
{"current_steps": 558, "total_steps": 705, "loss": 0.5281667709350586, "lr": 2.3521016588639598e-05, "epoch": 2.374468085106383, "percentage": 79.15, "elapsed_time": "1:40:17", "remaining_time": "0:26:25"}
|
| 280 |
+
{"current_steps": 560, "total_steps": 705, "loss": 0.47801631689071655, "lr": 2.32057843910998e-05, "epoch": 2.382978723404255, "percentage": 79.43, "elapsed_time": "1:40:42", "remaining_time": "0:26:04"}
|
| 281 |
+
{"current_steps": 562, "total_steps": 705, "loss": 0.5657482147216797, "lr": 2.2885824381039024e-05, "epoch": 2.391489361702128, "percentage": 79.72, "elapsed_time": "1:41:04", "remaining_time": "0:25:42"}
|
| 282 |
+
{"current_steps": 564, "total_steps": 705, "loss": 0.43637847900390625, "lr": 2.2561390548669552e-05, "epoch": 2.4, "percentage": 80.0, "elapsed_time": "1:41:19", "remaining_time": "0:25:19"}
|
| 283 |
+
{"current_steps": 566, "total_steps": 705, "loss": 0.4490112364292145, "lr": 2.2232740435607067e-05, "epoch": 2.4085106382978725, "percentage": 80.28, "elapsed_time": "1:41:39", "remaining_time": "0:24:58"}
|
| 284 |
+
{"current_steps": 568, "total_steps": 705, "loss": 0.5125418901443481, "lr": 2.1900134930429403e-05, "epoch": 2.4170212765957446, "percentage": 80.57, "elapsed_time": "1:42:01", "remaining_time": "0:24:36"}
|
| 285 |
+
{"current_steps": 570, "total_steps": 705, "loss": 0.4947648346424103, "lr": 2.1563838061578264e-05, "epoch": 2.425531914893617, "percentage": 80.85, "elapsed_time": "1:42:23", "remaining_time": "0:24:14"}
|
| 286 |
+
{"current_steps": 572, "total_steps": 705, "loss": 0.40764039754867554, "lr": 2.122411678776855e-05, "epoch": 2.4340425531914893, "percentage": 81.13, "elapsed_time": "1:42:44", "remaining_time": "0:23:53"}
|
| 287 |
+
{"current_steps": 574, "total_steps": 705, "loss": 0.402820885181427, "lr": 2.0881240786071588e-05, "epoch": 2.4425531914893615, "percentage": 81.42, "elapsed_time": "1:43:04", "remaining_time": "0:23:31"}
|
| 288 |
+
{"current_steps": 576, "total_steps": 705, "loss": 0.5862278342247009, "lr": 2.0535482237840398e-05, "epoch": 2.451063829787234, "percentage": 81.7, "elapsed_time": "1:43:24", "remaining_time": "0:23:09"}
|
| 289 |
+
{"current_steps": 578, "total_steps": 705, "loss": 0.5663528442382812, "lr": 2.018711561264715e-05, "epoch": 2.4595744680851066, "percentage": 81.99, "elapsed_time": "1:43:46", "remaining_time": "0:22:48"}
|
| 290 |
+
{"current_steps": 580, "total_steps": 705, "loss": 0.3827342689037323, "lr": 1.9836417450403978e-05, "epoch": 2.4680851063829787, "percentage": 82.27, "elapsed_time": "1:44:08", "remaining_time": "0:22:26"}
|
| 291 |
+
{"current_steps": 582, "total_steps": 705, "loss": 0.5597113966941833, "lr": 1.948366614184062e-05, "epoch": 2.476595744680851, "percentage": 82.55, "elapsed_time": "1:44:29", "remaining_time": "0:22:05"}
|
| 292 |
+
{"current_steps": 584, "total_steps": 705, "loss": 0.6160271763801575, "lr": 1.9129141707512514e-05, "epoch": 2.4851063829787234, "percentage": 82.84, "elapsed_time": "1:44:54", "remaining_time": "0:21:44"}
|
| 293 |
+
{"current_steps": 586, "total_steps": 705, "loss": 0.5502729415893555, "lr": 1.877312557551536e-05, "epoch": 2.4936170212765956, "percentage": 83.12, "elapsed_time": "1:45:15", "remaining_time": "0:21:22"}
|
| 294 |
+
{"current_steps": 588, "total_steps": 705, "loss": 0.7185637354850769, "lr": 1.841590035808227e-05, "epoch": 2.502127659574468, "percentage": 83.4, "elapsed_time": "1:45:37", "remaining_time": "0:21:01"}
|
| 295 |
+
{"current_steps": 590, "total_steps": 705, "loss": 0.6139054894447327, "lr": 1.8057749627240822e-05, "epoch": 2.5106382978723403, "percentage": 83.69, "elapsed_time": "1:45:58", "remaining_time": "0:20:39"}
|
| 296 |
+
{"current_steps": 592, "total_steps": 705, "loss": 0.7389253973960876, "lr": 1.7698957689708436e-05, "epoch": 2.519148936170213, "percentage": 83.97, "elapsed_time": "1:46:24", "remaining_time": "0:20:18"}
|
| 297 |
+
{"current_steps": 594, "total_steps": 705, "loss": 0.35956406593322754, "lr": 1.7339809361204255e-05, "epoch": 2.527659574468085, "percentage": 84.26, "elapsed_time": "1:46:44", "remaining_time": "0:19:56"}
|
| 298 |
+
{"current_steps": 596, "total_steps": 705, "loss": 0.5801402926445007, "lr": 1.6980589740357287e-05, "epoch": 2.5361702127659576, "percentage": 84.54, "elapsed_time": "1:47:08", "remaining_time": "0:19:35"}
|
| 299 |
+
{"current_steps": 598, "total_steps": 705, "loss": 0.4474773108959198, "lr": 1.6621583982389714e-05, "epoch": 2.5446808510638297, "percentage": 84.82, "elapsed_time": "1:47:26", "remaining_time": "0:19:13"}
|
| 300 |
+
{"current_steps": 600, "total_steps": 705, "loss": 0.5679066777229309, "lr": 1.626307707275533e-05, "epoch": 2.5531914893617023, "percentage": 85.11, "elapsed_time": "1:47:48", "remaining_time": "0:18:51"}
|
| 301 |
+
{"current_steps": 602, "total_steps": 705, "loss": 0.5999655723571777, "lr": 1.59053536009129e-05, "epoch": 2.5617021276595744, "percentage": 85.39, "elapsed_time": "1:48:14", "remaining_time": "0:18:31"}
|
| 302 |
+
{"current_steps": 604, "total_steps": 705, "loss": 0.577793300151825, "lr": 1.5548697534413653e-05, "epoch": 2.570212765957447, "percentage": 85.67, "elapsed_time": "1:48:38", "remaining_time": "0:18:09"}
|
| 303 |
+
{"current_steps": 606, "total_steps": 705, "loss": 0.6178088188171387, "lr": 1.5193391993482573e-05, "epoch": 2.578723404255319, "percentage": 85.96, "elapsed_time": "1:49:03", "remaining_time": "0:17:49"}
|
| 304 |
+
{"current_steps": 608, "total_steps": 705, "loss": 0.2757226824760437, "lr": 1.483971902627239e-05, "epoch": 2.5872340425531917, "percentage": 86.24, "elapsed_time": "1:49:22", "remaining_time": "0:17:26"}
|
| 305 |
+
{"current_steps": 610, "total_steps": 705, "loss": 0.5488746762275696, "lr": 1.4487959384968272e-05, "epoch": 2.595744680851064, "percentage": 86.52, "elapsed_time": "1:49:44", "remaining_time": "0:17:05"}
|
| 306 |
+
{"current_steps": 612, "total_steps": 705, "loss": 0.6341690421104431, "lr": 1.4138392302921813e-05, "epoch": 2.604255319148936, "percentage": 86.81, "elapsed_time": "1:50:07", "remaining_time": "0:16:44"}
|
| 307 |
+
{"current_steps": 614, "total_steps": 705, "loss": 0.6712806224822998, "lr": 1.3791295272990178e-05, "epoch": 2.6127659574468085, "percentage": 87.09, "elapsed_time": "1:50:33", "remaining_time": "0:16:23"}
|
| 308 |
+
{"current_steps": 616, "total_steps": 705, "loss": 0.45013314485549927, "lr": 1.344694382725719e-05, "epoch": 2.621276595744681, "percentage": 87.38, "elapsed_time": "1:50:55", "remaining_time": "0:16:01"}
|
| 309 |
+
{"current_steps": 618, "total_steps": 705, "loss": 0.6572415828704834, "lr": 1.3105611318310828e-05, "epoch": 2.629787234042553, "percentage": 87.66, "elapsed_time": "1:51:17", "remaining_time": "0:15:39"}
|
| 310 |
+
{"current_steps": 620, "total_steps": 705, "loss": 0.41325774788856506, "lr": 1.2767568702250834e-05, "epoch": 2.6382978723404253, "percentage": 87.94, "elapsed_time": "1:51:36", "remaining_time": "0:15:18"}
|
| 311 |
+
{"current_steps": 622, "total_steps": 705, "loss": 0.4483058750629425, "lr": 1.2433084323598806e-05, "epoch": 2.646808510638298, "percentage": 88.23, "elapsed_time": "1:51:58", "remaining_time": "0:14:56"}
|
| 312 |
+
{"current_steps": 624, "total_steps": 705, "loss": 0.6922531127929688, "lr": 1.2102423702281114e-05, "epoch": 2.65531914893617, "percentage": 88.51, "elapsed_time": "1:52:23", "remaining_time": "0:14:35"}
|
| 313 |
+
{"current_steps": 626, "total_steps": 705, "loss": 0.5280181169509888, "lr": 1.1775849322854515e-05, "epoch": 2.6638297872340426, "percentage": 88.79, "elapsed_time": "1:52:45", "remaining_time": "0:14:13"}
|
| 314 |
+
{"current_steps": 628, "total_steps": 705, "loss": 0.5663700699806213, "lr": 1.1453620426140796e-05, "epoch": 2.6723404255319148, "percentage": 89.08, "elapsed_time": "1:53:04", "remaining_time": "0:13:51"}
|
| 315 |
+
{"current_steps": 630, "total_steps": 705, "loss": 0.5217815637588501, "lr": 1.1135992803436701e-05, "epoch": 2.6808510638297873, "percentage": 89.36, "elapsed_time": "1:53:24", "remaining_time": "0:13:30"}
|
| 316 |
+
{"current_steps": 632, "total_steps": 705, "loss": 0.5002037882804871, "lr": 1.0823218593462006e-05, "epoch": 2.6893617021276595, "percentage": 89.65, "elapsed_time": "1:53:46", "remaining_time": "0:13:08"}
|
| 317 |
+
{"current_steps": 634, "total_steps": 705, "loss": 0.7550774812698364, "lr": 1.0515546082207089e-05, "epoch": 2.697872340425532, "percentage": 89.93, "elapsed_time": "1:54:08", "remaining_time": "0:12:46"}
|
| 318 |
+
{"current_steps": 636, "total_steps": 705, "loss": 0.7289509773254395, "lr": 1.0213219505839e-05, "epoch": 2.706382978723404, "percentage": 90.21, "elapsed_time": "1:54:33", "remaining_time": "0:12:25"}
|
| 319 |
+
{"current_steps": 638, "total_steps": 705, "loss": 0.4343630075454712, "lr": 9.916478856822011e-06, "epoch": 2.7148936170212767, "percentage": 90.5, "elapsed_time": "1:54:56", "remaining_time": "0:12:04"}
|
| 320 |
+
{"current_steps": 640, "total_steps": 705, "loss": 0.8249025940895081, "lr": 9.625559693407416e-06, "epoch": 2.723404255319149, "percentage": 90.78, "elapsed_time": "1:55:24", "remaining_time": "0:11:43"}
|
| 321 |
+
{"current_steps": 642, "total_steps": 705, "loss": 0.7887688875198364, "lr": 9.34069295264279e-06, "epoch": 2.731914893617021, "percentage": 91.06, "elapsed_time": "1:55:51", "remaining_time": "0:11:22"}
|
| 322 |
+
{"current_steps": 644, "total_steps": 705, "loss": 0.8136211037635803, "lr": 9.062104767049962e-06, "epoch": 2.7404255319148936, "percentage": 91.35, "elapsed_time": "1:56:16", "remaining_time": "0:11:00"}
|
| 323 |
+
{"current_steps": 646, "total_steps": 705, "loss": 0.3323878347873688, "lr": 8.790016285116773e-06, "epoch": 2.748936170212766, "percentage": 91.63, "elapsed_time": "1:56:35", "remaining_time": "0:10:38"}
|
| 324 |
+
{"current_steps": 648, "total_steps": 705, "loss": 0.31487664580345154, "lr": 8.5246434957453e-06, "epoch": 2.7574468085106383, "percentage": 91.91, "elapsed_time": "1:56:53", "remaining_time": "0:10:16"}
|
| 325 |
+
{"current_steps": 650, "total_steps": 705, "loss": 0.43204954266548157, "lr": 8.266197056795886e-06, "epoch": 2.7659574468085104, "percentage": 92.2, "elapsed_time": "1:57:12", "remaining_time": "0:09:55"}
|
| 326 |
+
{"current_steps": 652, "total_steps": 705, "loss": 0.562320351600647, "lr": 8.014882127862926e-06, "epoch": 2.774468085106383, "percentage": 92.48, "elapsed_time": "1:57:33", "remaining_time": "0:09:33"}
|
| 327 |
+
{"current_steps": 654, "total_steps": 705, "loss": 0.5608207583427429, "lr": 7.77089820741542e-06, "epoch": 2.7829787234042556, "percentage": 92.77, "elapsed_time": "1:57:58", "remaining_time": "0:09:12"}
|
| 328 |
+
{"current_steps": 656, "total_steps": 705, "loss": 0.44889208674430847, "lr": 7.534438974431356e-06, "epoch": 2.7914893617021277, "percentage": 93.05, "elapsed_time": "1:58:17", "remaining_time": "0:08:50"}
|
| 329 |
+
{"current_steps": 658, "total_steps": 705, "loss": 0.5233709216117859, "lr": 7.305692134651748e-06, "epoch": 2.8, "percentage": 93.33, "elapsed_time": "1:58:43", "remaining_time": "0:08:28"}
|
| 330 |
+
{"current_steps": 660, "total_steps": 705, "loss": 0.41444164514541626, "lr": 7.0848392715763e-06, "epoch": 2.8085106382978724, "percentage": 93.62, "elapsed_time": "1:59:05", "remaining_time": "0:08:07"}
|
| 331 |
+
{"current_steps": 662, "total_steps": 705, "loss": 0.2203376591205597, "lr": 6.872055702319048e-06, "epoch": 2.8170212765957445, "percentage": 93.9, "elapsed_time": "1:59:22", "remaining_time": "0:07:45"}
|
| 332 |
+
{"current_steps": 664, "total_steps": 705, "loss": 0.4634183943271637, "lr": 6.66751033843842e-06, "epoch": 2.825531914893617, "percentage": 94.18, "elapsed_time": "1:59:43", "remaining_time": "0:07:23"}
|
| 333 |
+
{"current_steps": 666, "total_steps": 705, "loss": 0.36938074231147766, "lr": 6.471365551852014e-06, "epoch": 2.8340425531914892, "percentage": 94.47, "elapsed_time": "1:59:59", "remaining_time": "0:07:01"}
|
| 334 |
+
{"current_steps": 668, "total_steps": 705, "loss": 0.5424007177352905, "lr": 6.283777045942801e-06, "epoch": 2.842553191489362, "percentage": 94.75, "elapsed_time": "2:00:21", "remaining_time": "0:06:40"}
|
| 335 |
+
{"current_steps": 670, "total_steps": 705, "loss": 0.7605326175689697, "lr": 6.104893731958872e-06, "epoch": 2.851063829787234, "percentage": 95.04, "elapsed_time": "2:00:44", "remaining_time": "0:06:18"}
|
| 336 |
+
{"current_steps": 672, "total_steps": 705, "loss": 0.4137082099914551, "lr": 5.934857610804912e-06, "epoch": 2.8595744680851065, "percentage": 95.32, "elapsed_time": "2:01:06", "remaining_time": "0:05:56"}
|
| 337 |
+
{"current_steps": 674, "total_steps": 705, "loss": 0.5575495362281799, "lr": 5.773803660319231e-06, "epoch": 2.8680851063829786, "percentage": 95.6, "elapsed_time": "2:01:31", "remaining_time": "0:05:35"}
|
| 338 |
+
{"current_steps": 676, "total_steps": 705, "loss": 0.3841201961040497, "lr": 5.6218597281258834e-06, "epoch": 2.876595744680851, "percentage": 95.89, "elapsed_time": "2:01:52", "remaining_time": "0:05:13"}
|
| 339 |
+
{"current_steps": 678, "total_steps": 705, "loss": 0.3572618365287781, "lr": 5.479146430146783e-06, "epoch": 2.8851063829787233, "percentage": 96.17, "elapsed_time": "2:02:14", "remaining_time": "0:04:52"}
|
| 340 |
+
{"current_steps": 680, "total_steps": 705, "loss": 0.4105460047721863, "lr": 5.3457770548545805e-06, "epoch": 2.8936170212765955, "percentage": 96.45, "elapsed_time": "2:02:36", "remaining_time": "0:04:30"}
|
| 341 |
+
{"current_steps": 682, "total_steps": 705, "loss": 0.5799260139465332, "lr": 5.22185747334215e-06, "epoch": 2.902127659574468, "percentage": 96.74, "elapsed_time": "2:02:59", "remaining_time": "0:04:08"}
|
| 342 |
+
{"current_steps": 684, "total_steps": 705, "loss": 0.4056027829647064, "lr": 5.107486055280145e-06, "epoch": 2.9106382978723406, "percentage": 97.02, "elapsed_time": "2:03:16", "remaining_time": "0:03:47"}
|
| 343 |
+
{"current_steps": 686, "total_steps": 705, "loss": 0.23622764647006989, "lr": 5.002753590829352e-06, "epoch": 2.9191489361702128, "percentage": 97.3, "elapsed_time": "2:03:30", "remaining_time": "0:03:25"}
|
| 344 |
+
{"current_steps": 688, "total_steps": 705, "loss": 0.33212676644325256, "lr": 4.9077432185697e-06, "epoch": 2.927659574468085, "percentage": 97.59, "elapsed_time": "2:03:49", "remaining_time": "0:03:03"}
|
| 345 |
+
{"current_steps": 690, "total_steps": 705, "loss": 0.7329955697059631, "lr": 4.822530359503391e-06, "epoch": 2.9361702127659575, "percentage": 97.87, "elapsed_time": "2:04:15", "remaining_time": "0:02:42"}
|
| 346 |
+
{"current_steps": 692, "total_steps": 705, "loss": 0.43970412015914917, "lr": 4.747182657184251e-06, "epoch": 2.94468085106383, "percentage": 98.16, "elapsed_time": "2:04:40", "remaining_time": "0:02:20"}
|
| 347 |
+
{"current_steps": 694, "total_steps": 705, "loss": 0.642443835735321, "lr": 4.681759924021033e-06, "epoch": 2.953191489361702, "percentage": 98.44, "elapsed_time": "2:05:04", "remaining_time": "0:01:58"}
|
| 348 |
+
{"current_steps": 696, "total_steps": 705, "loss": 0.35701537132263184, "lr": 4.626314093797213e-06, "epoch": 2.9617021276595743, "percentage": 98.72, "elapsed_time": "2:05:26", "remaining_time": "0:01:37"}
|
| 349 |
+
{"current_steps": 698, "total_steps": 705, "loss": 0.48086193203926086, "lr": 4.580889180444988e-06, "epoch": 2.970212765957447, "percentage": 99.01, "elapsed_time": "2:05:53", "remaining_time": "0:01:15"}
|
| 350 |
+
{"current_steps": 700, "total_steps": 705, "loss": 0.4837539792060852, "lr": 4.5455212431061985e-06, "epoch": 2.978723404255319, "percentage": 99.29, "elapsed_time": "2:06:11", "remaining_time": "0:00:54"}
|
| 351 |
+
{"current_steps": 702, "total_steps": 705, "loss": 0.5840956568717957, "lr": 4.520238357507899e-06, "epoch": 2.9872340425531916, "percentage": 99.57, "elapsed_time": "2:06:32", "remaining_time": "0:00:32"}
|
| 352 |
+
{"current_steps": 704, "total_steps": 705, "loss": 0.34119483828544617, "lr": 4.505060593675342e-06, "epoch": 2.9957446808510637, "percentage": 99.86, "elapsed_time": "2:06:55", "remaining_time": "0:00:10"}
|
| 353 |
+
{"current_steps": 705, "total_steps": 705, "epoch": 3.0, "percentage": 100.0, "elapsed_time": "2:07:43", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2507 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 705,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.00851063829787234,
|
| 14 |
+
"grad_norm": 1.2625373601913452,
|
| 15 |
+
"learning_rate": 8.333333333333333e-07,
|
| 16 |
+
"loss": 4.0039777755737305,
|
| 17 |
+
"step": 2
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.01702127659574468,
|
| 21 |
+
"grad_norm": 0.8850640654563904,
|
| 22 |
+
"learning_rate": 2.4999999999999998e-06,
|
| 23 |
+
"loss": 2.092726945877075,
|
| 24 |
+
"step": 4
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.02553191489361702,
|
| 28 |
+
"grad_norm": 0.42879173159599304,
|
| 29 |
+
"learning_rate": 4.166666666666667e-06,
|
| 30 |
+
"loss": 1.9236807823181152,
|
| 31 |
+
"step": 6
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.03404255319148936,
|
| 35 |
+
"grad_norm": 0.8568687438964844,
|
| 36 |
+
"learning_rate": 5.833333333333334e-06,
|
| 37 |
+
"loss": 1.7322841882705688,
|
| 38 |
+
"step": 8
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.0425531914893617,
|
| 42 |
+
"grad_norm": 0.3813435435295105,
|
| 43 |
+
"learning_rate": 7.5e-06,
|
| 44 |
+
"loss": 1.7557320594787598,
|
| 45 |
+
"step": 10
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.05106382978723404,
|
| 49 |
+
"grad_norm": 3.289834499359131,
|
| 50 |
+
"learning_rate": 9.166666666666668e-06,
|
| 51 |
+
"loss": 2.0681214332580566,
|
| 52 |
+
"step": 12
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.059574468085106386,
|
| 56 |
+
"grad_norm": 0.8551011085510254,
|
| 57 |
+
"learning_rate": 1.0833333333333334e-05,
|
| 58 |
+
"loss": 1.6496400833129883,
|
| 59 |
+
"step": 14
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.06808510638297872,
|
| 63 |
+
"grad_norm": 0.6510457396507263,
|
| 64 |
+
"learning_rate": 1.25e-05,
|
| 65 |
+
"loss": 1.78928804397583,
|
| 66 |
+
"step": 16
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.07659574468085106,
|
| 70 |
+
"grad_norm": 0.9583740830421448,
|
| 71 |
+
"learning_rate": 1.4166666666666666e-05,
|
| 72 |
+
"loss": 1.4100672006607056,
|
| 73 |
+
"step": 18
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.0851063829787234,
|
| 77 |
+
"grad_norm": 0.25010502338409424,
|
| 78 |
+
"learning_rate": 1.5833333333333333e-05,
|
| 79 |
+
"loss": 1.4046533107757568,
|
| 80 |
+
"step": 20
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.09361702127659574,
|
| 84 |
+
"grad_norm": 0.2605890929698944,
|
| 85 |
+
"learning_rate": 1.7500000000000002e-05,
|
| 86 |
+
"loss": 1.4094287157058716,
|
| 87 |
+
"step": 22
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.10212765957446808,
|
| 91 |
+
"grad_norm": 1.3786605596542358,
|
| 92 |
+
"learning_rate": 1.9166666666666667e-05,
|
| 93 |
+
"loss": 1.0651377439498901,
|
| 94 |
+
"step": 24
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.11063829787234042,
|
| 98 |
+
"grad_norm": 0.5269911289215088,
|
| 99 |
+
"learning_rate": 2.0833333333333333e-05,
|
| 100 |
+
"loss": 1.187571406364441,
|
| 101 |
+
"step": 26
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.11914893617021277,
|
| 105 |
+
"grad_norm": 0.24545100331306458,
|
| 106 |
+
"learning_rate": 2.25e-05,
|
| 107 |
+
"loss": 0.8422402739524841,
|
| 108 |
+
"step": 28
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.1276595744680851,
|
| 112 |
+
"grad_norm": 0.3340352475643158,
|
| 113 |
+
"learning_rate": 2.4166666666666667e-05,
|
| 114 |
+
"loss": 1.3952103853225708,
|
| 115 |
+
"step": 30
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.13617021276595745,
|
| 119 |
+
"grad_norm": 1.0275627374649048,
|
| 120 |
+
"learning_rate": 2.5833333333333336e-05,
|
| 121 |
+
"loss": 0.6625706553459167,
|
| 122 |
+
"step": 32
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.14468085106382977,
|
| 126 |
+
"grad_norm": 0.27028778195381165,
|
| 127 |
+
"learning_rate": 2.75e-05,
|
| 128 |
+
"loss": 1.233126163482666,
|
| 129 |
+
"step": 34
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.15319148936170213,
|
| 133 |
+
"grad_norm": 0.3007853627204895,
|
| 134 |
+
"learning_rate": 2.9166666666666666e-05,
|
| 135 |
+
"loss": 1.522036075592041,
|
| 136 |
+
"step": 36
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.16170212765957448,
|
| 140 |
+
"grad_norm": 0.25563573837280273,
|
| 141 |
+
"learning_rate": 2.9998734788806287e-05,
|
| 142 |
+
"loss": 1.4075392484664917,
|
| 143 |
+
"step": 38
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.1702127659574468,
|
| 147 |
+
"grad_norm": 0.3948342502117157,
|
| 148 |
+
"learning_rate": 2.9988614605803806e-05,
|
| 149 |
+
"loss": 1.0875834226608276,
|
| 150 |
+
"step": 40
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.17872340425531916,
|
| 154 |
+
"grad_norm": 0.189285010099411,
|
| 155 |
+
"learning_rate": 2.99683822733885e-05,
|
| 156 |
+
"loss": 1.2082504034042358,
|
| 157 |
+
"step": 42
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.18723404255319148,
|
| 161 |
+
"grad_norm": 0.6968986988067627,
|
| 162 |
+
"learning_rate": 2.9938053852362484e-05,
|
| 163 |
+
"loss": 1.2259453535079956,
|
| 164 |
+
"step": 44
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.19574468085106383,
|
| 168 |
+
"grad_norm": 0.2155912071466446,
|
| 169 |
+
"learning_rate": 2.989765341799095e-05,
|
| 170 |
+
"loss": 1.3428634405136108,
|
| 171 |
+
"step": 46
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.20425531914893616,
|
| 175 |
+
"grad_norm": 1.266939401626587,
|
| 176 |
+
"learning_rate": 2.9847213040890793e-05,
|
| 177 |
+
"loss": 0.7827966213226318,
|
| 178 |
+
"step": 48
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.2127659574468085,
|
| 182 |
+
"grad_norm": 0.738777756690979,
|
| 183 |
+
"learning_rate": 2.9786772761572335e-05,
|
| 184 |
+
"loss": 0.9074859023094177,
|
| 185 |
+
"step": 50
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.22127659574468084,
|
| 189 |
+
"grad_norm": 0.2421567142009735,
|
| 190 |
+
"learning_rate": 2.9716380558654445e-05,
|
| 191 |
+
"loss": 1.321467399597168,
|
| 192 |
+
"step": 52
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.2297872340425532,
|
| 196 |
+
"grad_norm": 0.16079238057136536,
|
| 197 |
+
"learning_rate": 2.9636092310778195e-05,
|
| 198 |
+
"loss": 1.1002169847488403,
|
| 199 |
+
"step": 54
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.23829787234042554,
|
| 203 |
+
"grad_norm": 1.2075369358062744,
|
| 204 |
+
"learning_rate": 2.954597175224938e-05,
|
| 205 |
+
"loss": 0.8815129399299622,
|
| 206 |
+
"step": 56
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.24680851063829787,
|
| 210 |
+
"grad_norm": 0.17142559587955475,
|
| 211 |
+
"learning_rate": 2.9446090422445016e-05,
|
| 212 |
+
"loss": 1.0324469804763794,
|
| 213 |
+
"step": 58
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.2553191489361702,
|
| 217 |
+
"grad_norm": 0.1944112330675125,
|
| 218 |
+
"learning_rate": 2.9336527609024072e-05,
|
| 219 |
+
"loss": 1.3160098791122437,
|
| 220 |
+
"step": 60
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.26382978723404255,
|
| 224 |
+
"grad_norm": 0.3625730574131012,
|
| 225 |
+
"learning_rate": 2.9217370284987434e-05,
|
| 226 |
+
"loss": 1.2711020708084106,
|
| 227 |
+
"step": 62
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.2723404255319149,
|
| 231 |
+
"grad_norm": 0.1674957275390625,
|
| 232 |
+
"learning_rate": 2.9088713039637117e-05,
|
| 233 |
+
"loss": 1.2588579654693604,
|
| 234 |
+
"step": 64
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.28085106382978725,
|
| 238 |
+
"grad_norm": 0.2627532184123993,
|
| 239 |
+
"learning_rate": 2.8950658003489534e-05,
|
| 240 |
+
"loss": 1.371834635734558,
|
| 241 |
+
"step": 66
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.28936170212765955,
|
| 245 |
+
"grad_norm": 0.1840338557958603,
|
| 246 |
+
"learning_rate": 2.880331476720238e-05,
|
| 247 |
+
"loss": 1.227813720703125,
|
| 248 |
+
"step": 68
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.2978723404255319,
|
| 252 |
+
"grad_norm": 0.5450706481933594,
|
| 253 |
+
"learning_rate": 2.8646800294579517e-05,
|
| 254 |
+
"loss": 1.4304167032241821,
|
| 255 |
+
"step": 70
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.30638297872340425,
|
| 259 |
+
"grad_norm": 0.197848379611969,
|
| 260 |
+
"learning_rate": 2.848123882972295e-05,
|
| 261 |
+
"loss": 1.328366756439209,
|
| 262 |
+
"step": 72
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.3148936170212766,
|
| 266 |
+
"grad_norm": 0.2317323237657547,
|
| 267 |
+
"learning_rate": 2.8306761798405526e-05,
|
| 268 |
+
"loss": 0.8880937695503235,
|
| 269 |
+
"step": 74
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.32340425531914896,
|
| 273 |
+
"grad_norm": 2.356330156326294,
|
| 274 |
+
"learning_rate": 2.812350770374273e-05,
|
| 275 |
+
"loss": 1.3181480169296265,
|
| 276 |
+
"step": 76
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.33191489361702126,
|
| 280 |
+
"grad_norm": 0.24451768398284912,
|
| 281 |
+
"learning_rate": 2.793162201624631e-05,
|
| 282 |
+
"loss": 1.2563281059265137,
|
| 283 |
+
"step": 78
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.3404255319148936,
|
| 287 |
+
"grad_norm": 0.38318371772766113,
|
| 288 |
+
"learning_rate": 2.77312570583471e-05,
|
| 289 |
+
"loss": 0.903084933757782,
|
| 290 |
+
"step": 80
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.34893617021276596,
|
| 294 |
+
"grad_norm": 0.3278236389160156,
|
| 295 |
+
"learning_rate": 2.752257188347862e-05,
|
| 296 |
+
"loss": 1.2202683687210083,
|
| 297 |
+
"step": 82
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.3574468085106383,
|
| 301 |
+
"grad_norm": 0.12423935532569885,
|
| 302 |
+
"learning_rate": 2.730573214981751e-05,
|
| 303 |
+
"loss": 1.021187424659729,
|
| 304 |
+
"step": 84
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.3659574468085106,
|
| 308 |
+
"grad_norm": 0.15058887004852295,
|
| 309 |
+
"learning_rate": 2.7080909988780982e-05,
|
| 310 |
+
"loss": 0.955544650554657,
|
| 311 |
+
"step": 86
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.37446808510638296,
|
| 315 |
+
"grad_norm": 0.2629765272140503,
|
| 316 |
+
"learning_rate": 2.684828386838569e-05,
|
| 317 |
+
"loss": 1.1776865720748901,
|
| 318 |
+
"step": 88
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.3829787234042553,
|
| 322 |
+
"grad_norm": 0.5266962647438049,
|
| 323 |
+
"learning_rate": 2.6608038451576528e-05,
|
| 324 |
+
"loss": 0.8726862668991089,
|
| 325 |
+
"step": 90
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.39148936170212767,
|
| 329 |
+
"grad_norm": 0.20310066640377045,
|
| 330 |
+
"learning_rate": 2.636036444963769e-05,
|
| 331 |
+
"loss": 1.2601391077041626,
|
| 332 |
+
"step": 92
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.4,
|
| 336 |
+
"grad_norm": 0.21515996754169464,
|
| 337 |
+
"learning_rate": 2.6105458470802563e-05,
|
| 338 |
+
"loss": 1.246147871017456,
|
| 339 |
+
"step": 94
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.4085106382978723,
|
| 343 |
+
"grad_norm": 0.28013795614242554,
|
| 344 |
+
"learning_rate": 2.5843522864182394e-05,
|
| 345 |
+
"loss": 1.1205939054489136,
|
| 346 |
+
"step": 96
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.41702127659574467,
|
| 350 |
+
"grad_norm": 0.27731189131736755,
|
| 351 |
+
"learning_rate": 2.557476555913785e-05,
|
| 352 |
+
"loss": 1.029671549797058,
|
| 353 |
+
"step": 98
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.425531914893617,
|
| 357 |
+
"grad_norm": 0.5619083046913147,
|
| 358 |
+
"learning_rate": 2.5299399900220803e-05,
|
| 359 |
+
"loss": 1.0204272270202637,
|
| 360 |
+
"step": 100
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.4340425531914894,
|
| 364 |
+
"grad_norm": 0.18958072364330292,
|
| 365 |
+
"learning_rate": 2.5017644477817424e-05,
|
| 366 |
+
"loss": 1.2801953554153442,
|
| 367 |
+
"step": 102
|
| 368 |
+
},
|
| 369 |
+
{
|
| 370 |
+
"epoch": 0.4425531914893617,
|
| 371 |
+
"grad_norm": 0.14192377030849457,
|
| 372 |
+
"learning_rate": 2.47297229546271e-05,
|
| 373 |
+
"loss": 0.9845929741859436,
|
| 374 |
+
"step": 104
|
| 375 |
+
},
|
| 376 |
+
{
|
| 377 |
+
"epoch": 0.451063829787234,
|
| 378 |
+
"grad_norm": 1.0689587593078613,
|
| 379 |
+
"learning_rate": 2.4435863888114814e-05,
|
| 380 |
+
"loss": 0.8531012535095215,
|
| 381 |
+
"step": 106
|
| 382 |
+
},
|
| 383 |
+
{
|
| 384 |
+
"epoch": 0.4595744680851064,
|
| 385 |
+
"grad_norm": 0.22902530431747437,
|
| 386 |
+
"learning_rate": 2.4136300549077976e-05,
|
| 387 |
+
"loss": 1.256201148033142,
|
| 388 |
+
"step": 108
|
| 389 |
+
},
|
| 390 |
+
{
|
| 391 |
+
"epoch": 0.46808510638297873,
|
| 392 |
+
"grad_norm": 0.15747293829917908,
|
| 393 |
+
"learning_rate": 2.3831270736471703e-05,
|
| 394 |
+
"loss": 1.2275390625,
|
| 395 |
+
"step": 110
|
| 396 |
+
},
|
| 397 |
+
{
|
| 398 |
+
"epoch": 0.4765957446808511,
|
| 399 |
+
"grad_norm": 0.2964925467967987,
|
| 400 |
+
"learning_rate": 2.352101658863959e-05,
|
| 401 |
+
"loss": 1.5093128681182861,
|
| 402 |
+
"step": 112
|
| 403 |
+
},
|
| 404 |
+
{
|
| 405 |
+
"epoch": 0.4851063829787234,
|
| 406 |
+
"grad_norm": 0.23254844546318054,
|
| 407 |
+
"learning_rate": 2.32057843910998e-05,
|
| 408 |
+
"loss": 1.0485801696777344,
|
| 409 |
+
"step": 114
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"epoch": 0.49361702127659574,
|
| 413 |
+
"grad_norm": 0.2164650410413742,
|
| 414 |
+
"learning_rate": 2.288582438103903e-05,
|
| 415 |
+
"loss": 1.0241464376449585,
|
| 416 |
+
"step": 116
|
| 417 |
+
},
|
| 418 |
+
{
|
| 419 |
+
"epoch": 0.502127659574468,
|
| 420 |
+
"grad_norm": 0.2963908612728119,
|
| 421 |
+
"learning_rate": 2.256139054866955e-05,
|
| 422 |
+
"loss": 1.259883999824524,
|
| 423 |
+
"step": 118
|
| 424 |
+
},
|
| 425 |
+
{
|
| 426 |
+
"epoch": 0.5106382978723404,
|
| 427 |
+
"grad_norm": 0.3361697494983673,
|
| 428 |
+
"learning_rate": 2.2232740435607067e-05,
|
| 429 |
+
"loss": 0.8736612796783447,
|
| 430 |
+
"step": 120
|
| 431 |
+
},
|
| 432 |
+
{
|
| 433 |
+
"epoch": 0.5191489361702127,
|
| 434 |
+
"grad_norm": 0.2727033495903015,
|
| 435 |
+
"learning_rate": 2.19001349304294e-05,
|
| 436 |
+
"loss": 1.2946780920028687,
|
| 437 |
+
"step": 122
|
| 438 |
+
},
|
| 439 |
+
{
|
| 440 |
+
"epoch": 0.5276595744680851,
|
| 441 |
+
"grad_norm": 0.2193780094385147,
|
| 442 |
+
"learning_rate": 2.156383806157826e-05,
|
| 443 |
+
"loss": 1.2013747692108154,
|
| 444 |
+
"step": 124
|
| 445 |
+
},
|
| 446 |
+
{
|
| 447 |
+
"epoch": 0.5361702127659574,
|
| 448 |
+
"grad_norm": 0.18866108357906342,
|
| 449 |
+
"learning_rate": 2.1224116787768552e-05,
|
| 450 |
+
"loss": 1.2230784893035889,
|
| 451 |
+
"step": 126
|
| 452 |
+
},
|
| 453 |
+
{
|
| 454 |
+
"epoch": 0.5446808510638298,
|
| 455 |
+
"grad_norm": 0.4698742926120758,
|
| 456 |
+
"learning_rate": 2.0881240786071588e-05,
|
| 457 |
+
"loss": 1.0054576396942139,
|
| 458 |
+
"step": 128
|
| 459 |
+
},
|
| 460 |
+
{
|
| 461 |
+
"epoch": 0.5531914893617021,
|
| 462 |
+
"grad_norm": 0.2406734824180603,
|
| 463 |
+
"learning_rate": 2.05354822378404e-05,
|
| 464 |
+
"loss": 1.0494941473007202,
|
| 465 |
+
"step": 130
|
| 466 |
+
},
|
| 467 |
+
{
|
| 468 |
+
"epoch": 0.5617021276595745,
|
| 469 |
+
"grad_norm": 0.20684203505516052,
|
| 470 |
+
"learning_rate": 2.018711561264714e-05,
|
| 471 |
+
"loss": 1.2933894395828247,
|
| 472 |
+
"step": 132
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"epoch": 0.5702127659574469,
|
| 476 |
+
"grad_norm": 0.18240053951740265,
|
| 477 |
+
"learning_rate": 1.9836417450403978e-05,
|
| 478 |
+
"loss": 1.172606110572815,
|
| 479 |
+
"step": 134
|
| 480 |
+
},
|
| 481 |
+
{
|
| 482 |
+
"epoch": 0.5787234042553191,
|
| 483 |
+
"grad_norm": 0.27221980690956116,
|
| 484 |
+
"learning_rate": 1.9483666141840615e-05,
|
| 485 |
+
"loss": 0.9525983929634094,
|
| 486 |
+
"step": 136
|
| 487 |
+
},
|
| 488 |
+
{
|
| 489 |
+
"epoch": 0.5872340425531914,
|
| 490 |
+
"grad_norm": 0.45265427231788635,
|
| 491 |
+
"learning_rate": 1.9129141707512508e-05,
|
| 492 |
+
"loss": 0.6214677095413208,
|
| 493 |
+
"step": 138
|
| 494 |
+
},
|
| 495 |
+
{
|
| 496 |
+
"epoch": 0.5957446808510638,
|
| 497 |
+
"grad_norm": 0.27331340312957764,
|
| 498 |
+
"learning_rate": 1.8773125575515364e-05,
|
| 499 |
+
"loss": 1.0034734010696411,
|
| 500 |
+
"step": 140
|
| 501 |
+
},
|
| 502 |
+
{
|
| 503 |
+
"epoch": 0.6042553191489362,
|
| 504 |
+
"grad_norm": 0.5351057648658752,
|
| 505 |
+
"learning_rate": 1.8415900358082268e-05,
|
| 506 |
+
"loss": 1.2574905157089233,
|
| 507 |
+
"step": 142
|
| 508 |
+
},
|
| 509 |
+
{
|
| 510 |
+
"epoch": 0.6127659574468085,
|
| 511 |
+
"grad_norm": 2.15321946144104,
|
| 512 |
+
"learning_rate": 1.805774962724083e-05,
|
| 513 |
+
"loss": 1.039708137512207,
|
| 514 |
+
"step": 144
|
| 515 |
+
},
|
| 516 |
+
{
|
| 517 |
+
"epoch": 0.6212765957446809,
|
| 518 |
+
"grad_norm": 0.19406694173812866,
|
| 519 |
+
"learning_rate": 1.7698957689708426e-05,
|
| 520 |
+
"loss": 1.1023411750793457,
|
| 521 |
+
"step": 146
|
| 522 |
+
},
|
| 523 |
+
{
|
| 524 |
+
"epoch": 0.6297872340425532,
|
| 525 |
+
"grad_norm": 0.28949815034866333,
|
| 526 |
+
"learning_rate": 1.7339809361204252e-05,
|
| 527 |
+
"loss": 1.2206919193267822,
|
| 528 |
+
"step": 148
|
| 529 |
+
},
|
| 530 |
+
{
|
| 531 |
+
"epoch": 0.6382978723404256,
|
| 532 |
+
"grad_norm": 0.17495916783809662,
|
| 533 |
+
"learning_rate": 1.6980589740357294e-05,
|
| 534 |
+
"loss": 1.327172875404358,
|
| 535 |
+
"step": 150
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"epoch": 0.6468085106382979,
|
| 539 |
+
"grad_norm": 0.3632895052433014,
|
| 540 |
+
"learning_rate": 1.6621583982389707e-05,
|
| 541 |
+
"loss": 1.3268358707427979,
|
| 542 |
+
"step": 152
|
| 543 |
+
},
|
| 544 |
+
{
|
| 545 |
+
"epoch": 0.6553191489361702,
|
| 546 |
+
"grad_norm": 0.3797944486141205,
|
| 547 |
+
"learning_rate": 1.6263077072755326e-05,
|
| 548 |
+
"loss": 0.7203034162521362,
|
| 549 |
+
"step": 154
|
| 550 |
+
},
|
| 551 |
+
{
|
| 552 |
+
"epoch": 0.6638297872340425,
|
| 553 |
+
"grad_norm": 0.3124215602874756,
|
| 554 |
+
"learning_rate": 1.5905353600912898e-05,
|
| 555 |
+
"loss": 0.9463112354278564,
|
| 556 |
+
"step": 156
|
| 557 |
+
},
|
| 558 |
+
{
|
| 559 |
+
"epoch": 0.6723404255319149,
|
| 560 |
+
"grad_norm": 0.20629045367240906,
|
| 561 |
+
"learning_rate": 1.5548697534413646e-05,
|
| 562 |
+
"loss": 0.9798778891563416,
|
| 563 |
+
"step": 158
|
| 564 |
+
},
|
| 565 |
+
{
|
| 566 |
+
"epoch": 0.6808510638297872,
|
| 567 |
+
"grad_norm": 0.17236708104610443,
|
| 568 |
+
"learning_rate": 1.5193391993482582e-05,
|
| 569 |
+
"loss": 1.1495308876037598,
|
| 570 |
+
"step": 160
|
| 571 |
+
},
|
| 572 |
+
{
|
| 573 |
+
"epoch": 0.6893617021276596,
|
| 574 |
+
"grad_norm": 0.17647439241409302,
|
| 575 |
+
"learning_rate": 1.4839719026272377e-05,
|
| 576 |
+
"loss": 1.0284472703933716,
|
| 577 |
+
"step": 162
|
| 578 |
+
},
|
| 579 |
+
{
|
| 580 |
+
"epoch": 0.6978723404255319,
|
| 581 |
+
"grad_norm": 0.21520790457725525,
|
| 582 |
+
"learning_rate": 1.4487959384968272e-05,
|
| 583 |
+
"loss": 0.8173097968101501,
|
| 584 |
+
"step": 164
|
| 585 |
+
},
|
| 586 |
+
{
|
| 587 |
+
"epoch": 0.7063829787234043,
|
| 588 |
+
"grad_norm": 0.22225292026996613,
|
| 589 |
+
"learning_rate": 1.4138392302921813e-05,
|
| 590 |
+
"loss": 0.994484007358551,
|
| 591 |
+
"step": 166
|
| 592 |
+
},
|
| 593 |
+
{
|
| 594 |
+
"epoch": 0.7148936170212766,
|
| 595 |
+
"grad_norm": 0.8280470967292786,
|
| 596 |
+
"learning_rate": 1.3791295272990175e-05,
|
| 597 |
+
"loss": 1.1443301439285278,
|
| 598 |
+
"step": 168
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"epoch": 0.723404255319149,
|
| 602 |
+
"grad_norm": 0.3155645430088043,
|
| 603 |
+
"learning_rate": 1.344694382725718e-05,
|
| 604 |
+
"loss": 1.0067280530929565,
|
| 605 |
+
"step": 170
|
| 606 |
+
},
|
| 607 |
+
{
|
| 608 |
+
"epoch": 0.7319148936170212,
|
| 609 |
+
"grad_norm": 0.269070029258728,
|
| 610 |
+
"learning_rate": 1.3105611318310818e-05,
|
| 611 |
+
"loss": 0.9691381454467773,
|
| 612 |
+
"step": 172
|
| 613 |
+
},
|
| 614 |
+
{
|
| 615 |
+
"epoch": 0.7404255319148936,
|
| 616 |
+
"grad_norm": 0.14885057508945465,
|
| 617 |
+
"learning_rate": 1.2767568702250844e-05,
|
| 618 |
+
"loss": 1.0925947427749634,
|
| 619 |
+
"step": 174
|
| 620 |
+
},
|
| 621 |
+
{
|
| 622 |
+
"epoch": 0.7489361702127659,
|
| 623 |
+
"grad_norm": 1.3091343641281128,
|
| 624 |
+
"learning_rate": 1.2433084323598791e-05,
|
| 625 |
+
"loss": 0.6399118304252625,
|
| 626 |
+
"step": 176
|
| 627 |
+
},
|
| 628 |
+
{
|
| 629 |
+
"epoch": 0.7574468085106383,
|
| 630 |
+
"grad_norm": 0.5745394825935364,
|
| 631 |
+
"learning_rate": 1.2102423702281116e-05,
|
| 632 |
+
"loss": 1.0284110307693481,
|
| 633 |
+
"step": 178
|
| 634 |
+
},
|
| 635 |
+
{
|
| 636 |
+
"epoch": 0.7659574468085106,
|
| 637 |
+
"grad_norm": 0.4978311061859131,
|
| 638 |
+
"learning_rate": 1.1775849322854516e-05,
|
| 639 |
+
"loss": 1.0611108541488647,
|
| 640 |
+
"step": 180
|
| 641 |
+
},
|
| 642 |
+
{
|
| 643 |
+
"epoch": 0.774468085106383,
|
| 644 |
+
"grad_norm": 0.3034535050392151,
|
| 645 |
+
"learning_rate": 1.1453620426140795e-05,
|
| 646 |
+
"loss": 0.7678611278533936,
|
| 647 |
+
"step": 182
|
| 648 |
+
},
|
| 649 |
+
{
|
| 650 |
+
"epoch": 0.7829787234042553,
|
| 651 |
+
"grad_norm": 0.1695900857448578,
|
| 652 |
+
"learning_rate": 1.1135992803436695e-05,
|
| 653 |
+
"loss": 0.954198956489563,
|
| 654 |
+
"step": 184
|
| 655 |
+
},
|
| 656 |
+
{
|
| 657 |
+
"epoch": 0.7914893617021277,
|
| 658 |
+
"grad_norm": 0.1768021285533905,
|
| 659 |
+
"learning_rate": 1.0823218593461992e-05,
|
| 660 |
+
"loss": 1.0221017599105835,
|
| 661 |
+
"step": 186
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"epoch": 0.8,
|
| 665 |
+
"grad_norm": 0.22744205594062805,
|
| 666 |
+
"learning_rate": 1.0515546082207097e-05,
|
| 667 |
+
"loss": 0.7189929485321045,
|
| 668 |
+
"step": 188
|
| 669 |
+
},
|
| 670 |
+
{
|
| 671 |
+
"epoch": 0.8085106382978723,
|
| 672 |
+
"grad_norm": 0.3399372100830078,
|
| 673 |
+
"learning_rate": 1.0213219505838983e-05,
|
| 674 |
+
"loss": 1.0886459350585938,
|
| 675 |
+
"step": 190
|
| 676 |
+
},
|
| 677 |
+
{
|
| 678 |
+
"epoch": 0.8170212765957446,
|
| 679 |
+
"grad_norm": 0.17291869223117828,
|
| 680 |
+
"learning_rate": 9.91647885682201e-06,
|
| 681 |
+
"loss": 1.2072498798370361,
|
| 682 |
+
"step": 192
|
| 683 |
+
},
|
| 684 |
+
{
|
| 685 |
+
"epoch": 0.825531914893617,
|
| 686 |
+
"grad_norm": 0.19541242718696594,
|
| 687 |
+
"learning_rate": 9.625559693407413e-06,
|
| 688 |
+
"loss": 1.1986221075057983,
|
| 689 |
+
"step": 194
|
| 690 |
+
},
|
| 691 |
+
{
|
| 692 |
+
"epoch": 0.8340425531914893,
|
| 693 |
+
"grad_norm": 0.14983496069908142,
|
| 694 |
+
"learning_rate": 9.340692952642789e-06,
|
| 695 |
+
"loss": 0.720963180065155,
|
| 696 |
+
"step": 196
|
| 697 |
+
},
|
| 698 |
+
{
|
| 699 |
+
"epoch": 0.8425531914893617,
|
| 700 |
+
"grad_norm": 0.22478389739990234,
|
| 701 |
+
"learning_rate": 9.062104767049956e-06,
|
| 702 |
+
"loss": 1.1722772121429443,
|
| 703 |
+
"step": 198
|
| 704 |
+
},
|
| 705 |
+
{
|
| 706 |
+
"epoch": 0.851063829787234,
|
| 707 |
+
"grad_norm": 0.22518520057201385,
|
| 708 |
+
"learning_rate": 8.790016285116763e-06,
|
| 709 |
+
"loss": 1.0002360343933105,
|
| 710 |
+
"step": 200
|
| 711 |
+
},
|
| 712 |
+
{
|
| 713 |
+
"epoch": 0.8595744680851064,
|
| 714 |
+
"grad_norm": 0.21948722004890442,
|
| 715 |
+
"learning_rate": 8.524643495745306e-06,
|
| 716 |
+
"loss": 0.9713231325149536,
|
| 717 |
+
"step": 202
|
| 718 |
+
},
|
| 719 |
+
{
|
| 720 |
+
"epoch": 0.8680851063829788,
|
| 721 |
+
"grad_norm": 0.15189974009990692,
|
| 722 |
+
"learning_rate": 8.26619705679589e-06,
|
| 723 |
+
"loss": 1.3201754093170166,
|
| 724 |
+
"step": 204
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"epoch": 0.8765957446808511,
|
| 728 |
+
"grad_norm": 0.24632404744625092,
|
| 729 |
+
"learning_rate": 8.014882127862923e-06,
|
| 730 |
+
"loss": 1.282568335533142,
|
| 731 |
+
"step": 206
|
| 732 |
+
},
|
| 733 |
+
{
|
| 734 |
+
"epoch": 0.8851063829787233,
|
| 735 |
+
"grad_norm": 0.13049790263175964,
|
| 736 |
+
"learning_rate": 7.770898207415416e-06,
|
| 737 |
+
"loss": 0.9211198091506958,
|
| 738 |
+
"step": 208
|
| 739 |
+
},
|
| 740 |
+
{
|
| 741 |
+
"epoch": 0.8936170212765957,
|
| 742 |
+
"grad_norm": 0.19982703030109406,
|
| 743 |
+
"learning_rate": 7.534438974431351e-06,
|
| 744 |
+
"loss": 1.167230248451233,
|
| 745 |
+
"step": 210
|
| 746 |
+
},
|
| 747 |
+
{
|
| 748 |
+
"epoch": 0.902127659574468,
|
| 749 |
+
"grad_norm": 0.18156394362449646,
|
| 750 |
+
"learning_rate": 7.305692134651742e-06,
|
| 751 |
+
"loss": 0.7129737138748169,
|
| 752 |
+
"step": 212
|
| 753 |
+
},
|
| 754 |
+
{
|
| 755 |
+
"epoch": 0.9106382978723404,
|
| 756 |
+
"grad_norm": 0.26700806617736816,
|
| 757 |
+
"learning_rate": 7.084839271576291e-06,
|
| 758 |
+
"loss": 0.8392055034637451,
|
| 759 |
+
"step": 214
|
| 760 |
+
},
|
| 761 |
+
{
|
| 762 |
+
"epoch": 0.9191489361702128,
|
| 763 |
+
"grad_norm": 0.1967747062444687,
|
| 764 |
+
"learning_rate": 6.872055702319054e-06,
|
| 765 |
+
"loss": 0.5692006349563599,
|
| 766 |
+
"step": 216
|
| 767 |
+
},
|
| 768 |
+
{
|
| 769 |
+
"epoch": 0.9276595744680851,
|
| 770 |
+
"grad_norm": 0.1744726002216339,
|
| 771 |
+
"learning_rate": 6.667510338438419e-06,
|
| 772 |
+
"loss": 1.1953270435333252,
|
| 773 |
+
"step": 218
|
| 774 |
+
},
|
| 775 |
+
{
|
| 776 |
+
"epoch": 0.9361702127659575,
|
| 777 |
+
"grad_norm": 0.38672754168510437,
|
| 778 |
+
"learning_rate": 6.471365551852012e-06,
|
| 779 |
+
"loss": 0.3942694067955017,
|
| 780 |
+
"step": 220
|
| 781 |
+
},
|
| 782 |
+
{
|
| 783 |
+
"epoch": 0.9446808510638298,
|
| 784 |
+
"grad_norm": 0.19522197544574738,
|
| 785 |
+
"learning_rate": 6.2837770459428e-06,
|
| 786 |
+
"loss": 1.3081778287887573,
|
| 787 |
+
"step": 222
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"epoch": 0.9531914893617022,
|
| 791 |
+
"grad_norm": 0.22507460415363312,
|
| 792 |
+
"learning_rate": 6.1048937319588676e-06,
|
| 793 |
+
"loss": 1.3682390451431274,
|
| 794 |
+
"step": 224
|
| 795 |
+
},
|
| 796 |
+
{
|
| 797 |
+
"epoch": 0.9617021276595744,
|
| 798 |
+
"grad_norm": 0.303733766078949,
|
| 799 |
+
"learning_rate": 5.9348576108049065e-06,
|
| 800 |
+
"loss": 0.894014835357666,
|
| 801 |
+
"step": 226
|
| 802 |
+
},
|
| 803 |
+
{
|
| 804 |
+
"epoch": 0.9702127659574468,
|
| 805 |
+
"grad_norm": 0.205647811293602,
|
| 806 |
+
"learning_rate": 5.773803660319234e-06,
|
| 807 |
+
"loss": 1.0522630214691162,
|
| 808 |
+
"step": 228
|
| 809 |
+
},
|
| 810 |
+
{
|
| 811 |
+
"epoch": 0.9787234042553191,
|
| 812 |
+
"grad_norm": 0.21294599771499634,
|
| 813 |
+
"learning_rate": 5.621859728125884e-06,
|
| 814 |
+
"loss": 1.2654610872268677,
|
| 815 |
+
"step": 230
|
| 816 |
+
},
|
| 817 |
+
{
|
| 818 |
+
"epoch": 0.9872340425531915,
|
| 819 |
+
"grad_norm": 0.3174782395362854,
|
| 820 |
+
"learning_rate": 5.479146430146781e-06,
|
| 821 |
+
"loss": 1.0047165155410767,
|
| 822 |
+
"step": 232
|
| 823 |
+
},
|
| 824 |
+
{
|
| 825 |
+
"epoch": 0.9957446808510638,
|
| 826 |
+
"grad_norm": 1.1156642436981201,
|
| 827 |
+
"learning_rate": 5.345777054854579e-06,
|
| 828 |
+
"loss": 0.9647661447525024,
|
| 829 |
+
"step": 234
|
| 830 |
+
},
|
| 831 |
+
{
|
| 832 |
+
"epoch": 1.004255319148936,
|
| 833 |
+
"grad_norm": 0.3331040143966675,
|
| 834 |
+
"learning_rate": 5.221857473342149e-06,
|
| 835 |
+
"loss": 0.9735086560249329,
|
| 836 |
+
"step": 236
|
| 837 |
+
},
|
| 838 |
+
{
|
| 839 |
+
"epoch": 1.0127659574468084,
|
| 840 |
+
"grad_norm": 0.18369407951831818,
|
| 841 |
+
"learning_rate": 5.10748605528015e-06,
|
| 842 |
+
"loss": 0.8922760486602783,
|
| 843 |
+
"step": 238
|
| 844 |
+
},
|
| 845 |
+
{
|
| 846 |
+
"epoch": 1.0212765957446808,
|
| 847 |
+
"grad_norm": 0.08912570774555206,
|
| 848 |
+
"learning_rate": 5.002753590829349e-06,
|
| 849 |
+
"loss": 0.6222575306892395,
|
| 850 |
+
"step": 240
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"epoch": 1.0297872340425531,
|
| 854 |
+
"grad_norm": 0.15733036398887634,
|
| 855 |
+
"learning_rate": 4.9077432185697e-06,
|
| 856 |
+
"loss": 0.8671458959579468,
|
| 857 |
+
"step": 242
|
| 858 |
+
},
|
| 859 |
+
{
|
| 860 |
+
"epoch": 1.0382978723404255,
|
| 861 |
+
"grad_norm": 0.22573904693126678,
|
| 862 |
+
"learning_rate": 4.822530359503393e-06,
|
| 863 |
+
"loss": 0.9555956721305847,
|
| 864 |
+
"step": 244
|
| 865 |
+
},
|
| 866 |
+
{
|
| 867 |
+
"epoch": 1.0468085106382978,
|
| 868 |
+
"grad_norm": 0.13159972429275513,
|
| 869 |
+
"learning_rate": 4.747182657184251e-06,
|
| 870 |
+
"loss": 0.6556552052497864,
|
| 871 |
+
"step": 246
|
| 872 |
+
},
|
| 873 |
+
{
|
| 874 |
+
"epoch": 1.0553191489361702,
|
| 875 |
+
"grad_norm": 0.19305525720119476,
|
| 876 |
+
"learning_rate": 4.681759924021033e-06,
|
| 877 |
+
"loss": 0.7056201100349426,
|
| 878 |
+
"step": 248
|
| 879 |
+
},
|
| 880 |
+
{
|
| 881 |
+
"epoch": 1.0638297872340425,
|
| 882 |
+
"grad_norm": 0.15075285732746124,
|
| 883 |
+
"learning_rate": 4.626314093797213e-06,
|
| 884 |
+
"loss": 0.6993778347969055,
|
| 885 |
+
"step": 250
|
| 886 |
+
},
|
| 887 |
+
{
|
| 888 |
+
"epoch": 1.0723404255319149,
|
| 889 |
+
"grad_norm": 0.2154897153377533,
|
| 890 |
+
"learning_rate": 4.580889180444988e-06,
|
| 891 |
+
"loss": 0.5365909337997437,
|
| 892 |
+
"step": 252
|
| 893 |
+
},
|
| 894 |
+
{
|
| 895 |
+
"epoch": 1.0808510638297872,
|
| 896 |
+
"grad_norm": 0.17837639153003693,
|
| 897 |
+
"learning_rate": 4.545521243106197e-06,
|
| 898 |
+
"loss": 0.8809426426887512,
|
| 899 |
+
"step": 254
|
| 900 |
+
},
|
| 901 |
+
{
|
| 902 |
+
"epoch": 1.0893617021276596,
|
| 903 |
+
"grad_norm": 0.13702534139156342,
|
| 904 |
+
"learning_rate": 4.520238357507899e-06,
|
| 905 |
+
"loss": 0.8317233324050903,
|
| 906 |
+
"step": 256
|
| 907 |
+
},
|
| 908 |
+
{
|
| 909 |
+
"epoch": 1.097872340425532,
|
| 910 |
+
"grad_norm": 0.23964199423789978,
|
| 911 |
+
"learning_rate": 4.505060593675342e-06,
|
| 912 |
+
"loss": 0.9430326819419861,
|
| 913 |
+
"step": 258
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"epoch": 1.1063829787234043,
|
| 917 |
+
"grad_norm": 0.2120589166879654,
|
| 918 |
+
"learning_rate": 4.5e-06,
|
| 919 |
+
"loss": 0.7370553612709045,
|
| 920 |
+
"step": 260
|
| 921 |
+
},
|
| 922 |
+
{
|
| 923 |
+
"epoch": 1.1148936170212767,
|
| 924 |
+
"grad_norm": 0.21252022683620453,
|
| 925 |
+
"learning_rate": 4.505060593675342e-06,
|
| 926 |
+
"loss": 0.7691786289215088,
|
| 927 |
+
"step": 262
|
| 928 |
+
},
|
| 929 |
+
{
|
| 930 |
+
"epoch": 1.123404255319149,
|
| 931 |
+
"grad_norm": 0.17547725141048431,
|
| 932 |
+
"learning_rate": 4.520238357507899e-06,
|
| 933 |
+
"loss": 0.7104212045669556,
|
| 934 |
+
"step": 264
|
| 935 |
+
},
|
| 936 |
+
{
|
| 937 |
+
"epoch": 1.1319148936170214,
|
| 938 |
+
"grad_norm": 0.1989092081785202,
|
| 939 |
+
"learning_rate": 4.545521243106197e-06,
|
| 940 |
+
"loss": 0.8642681837081909,
|
| 941 |
+
"step": 266
|
| 942 |
+
},
|
| 943 |
+
{
|
| 944 |
+
"epoch": 1.1404255319148937,
|
| 945 |
+
"grad_norm": 0.17653805017471313,
|
| 946 |
+
"learning_rate": 4.580889180444988e-06,
|
| 947 |
+
"loss": 0.770044207572937,
|
| 948 |
+
"step": 268
|
| 949 |
+
},
|
| 950 |
+
{
|
| 951 |
+
"epoch": 1.148936170212766,
|
| 952 |
+
"grad_norm": 0.18561692535877228,
|
| 953 |
+
"learning_rate": 4.6263140937972124e-06,
|
| 954 |
+
"loss": 0.9661275148391724,
|
| 955 |
+
"step": 270
|
| 956 |
+
},
|
| 957 |
+
{
|
| 958 |
+
"epoch": 1.1574468085106382,
|
| 959 |
+
"grad_norm": 0.2783913314342499,
|
| 960 |
+
"learning_rate": 4.6817599240210315e-06,
|
| 961 |
+
"loss": 0.6838027238845825,
|
| 962 |
+
"step": 272
|
| 963 |
+
},
|
| 964 |
+
{
|
| 965 |
+
"epoch": 1.1659574468085105,
|
| 966 |
+
"grad_norm": 0.17354853451251984,
|
| 967 |
+
"learning_rate": 4.747182657184251e-06,
|
| 968 |
+
"loss": 0.8435700535774231,
|
| 969 |
+
"step": 274
|
| 970 |
+
},
|
| 971 |
+
{
|
| 972 |
+
"epoch": 1.174468085106383,
|
| 973 |
+
"grad_norm": 0.19762302935123444,
|
| 974 |
+
"learning_rate": 4.822530359503391e-06,
|
| 975 |
+
"loss": 0.6485944986343384,
|
| 976 |
+
"step": 276
|
| 977 |
+
},
|
| 978 |
+
{
|
| 979 |
+
"epoch": 1.1829787234042553,
|
| 980 |
+
"grad_norm": 0.3056742250919342,
|
| 981 |
+
"learning_rate": 4.9077432185697e-06,
|
| 982 |
+
"loss": 0.5239860415458679,
|
| 983 |
+
"step": 278
|
| 984 |
+
},
|
| 985 |
+
{
|
| 986 |
+
"epoch": 1.1914893617021276,
|
| 987 |
+
"grad_norm": 0.14598001539707184,
|
| 988 |
+
"learning_rate": 5.002753590829348e-06,
|
| 989 |
+
"loss": 0.524198055267334,
|
| 990 |
+
"step": 280
|
| 991 |
+
},
|
| 992 |
+
{
|
| 993 |
+
"epoch": 1.2,
|
| 994 |
+
"grad_norm": 0.16965726017951965,
|
| 995 |
+
"learning_rate": 5.1074860552801466e-06,
|
| 996 |
+
"loss": 0.8808120489120483,
|
| 997 |
+
"step": 282
|
| 998 |
+
},
|
| 999 |
+
{
|
| 1000 |
+
"epoch": 1.2085106382978723,
|
| 1001 |
+
"grad_norm": 0.24560458958148956,
|
| 1002 |
+
"learning_rate": 5.2218574733421455e-06,
|
| 1003 |
+
"loss": 0.6656435132026672,
|
| 1004 |
+
"step": 284
|
| 1005 |
+
},
|
| 1006 |
+
{
|
| 1007 |
+
"epoch": 1.2170212765957447,
|
| 1008 |
+
"grad_norm": 0.23104996979236603,
|
| 1009 |
+
"learning_rate": 5.345777054854578e-06,
|
| 1010 |
+
"loss": 0.9856959581375122,
|
| 1011 |
+
"step": 286
|
| 1012 |
+
},
|
| 1013 |
+
{
|
| 1014 |
+
"epoch": 1.225531914893617,
|
| 1015 |
+
"grad_norm": 0.16903841495513916,
|
| 1016 |
+
"learning_rate": 5.479146430146783e-06,
|
| 1017 |
+
"loss": 0.8170779943466187,
|
| 1018 |
+
"step": 288
|
| 1019 |
+
},
|
| 1020 |
+
{
|
| 1021 |
+
"epoch": 1.2340425531914894,
|
| 1022 |
+
"grad_norm": 0.17953285574913025,
|
| 1023 |
+
"learning_rate": 5.6218597281258834e-06,
|
| 1024 |
+
"loss": 0.44949835538864136,
|
| 1025 |
+
"step": 290
|
| 1026 |
+
},
|
| 1027 |
+
{
|
| 1028 |
+
"epoch": 1.2425531914893617,
|
| 1029 |
+
"grad_norm": 0.4803825914859772,
|
| 1030 |
+
"learning_rate": 5.773803660319232e-06,
|
| 1031 |
+
"loss": 0.9233723282814026,
|
| 1032 |
+
"step": 292
|
| 1033 |
+
},
|
| 1034 |
+
{
|
| 1035 |
+
"epoch": 1.251063829787234,
|
| 1036 |
+
"grad_norm": 0.15944814682006836,
|
| 1037 |
+
"learning_rate": 5.934857610804904e-06,
|
| 1038 |
+
"loss": 0.846575140953064,
|
| 1039 |
+
"step": 294
|
| 1040 |
+
},
|
| 1041 |
+
{
|
| 1042 |
+
"epoch": 1.2595744680851064,
|
| 1043 |
+
"grad_norm": 0.17765574157238007,
|
| 1044 |
+
"learning_rate": 6.1048937319588676e-06,
|
| 1045 |
+
"loss": 0.6937251687049866,
|
| 1046 |
+
"step": 296
|
| 1047 |
+
},
|
| 1048 |
+
{
|
| 1049 |
+
"epoch": 1.2680851063829788,
|
| 1050 |
+
"grad_norm": 0.19115029275417328,
|
| 1051 |
+
"learning_rate": 6.283777045942798e-06,
|
| 1052 |
+
"loss": 0.8138055205345154,
|
| 1053 |
+
"step": 298
|
| 1054 |
+
},
|
| 1055 |
+
{
|
| 1056 |
+
"epoch": 1.2765957446808511,
|
| 1057 |
+
"grad_norm": 0.2789772152900696,
|
| 1058 |
+
"learning_rate": 6.471365551852011e-06,
|
| 1059 |
+
"loss": 0.9583751559257507,
|
| 1060 |
+
"step": 300
|
| 1061 |
+
},
|
| 1062 |
+
{
|
| 1063 |
+
"epoch": 1.2851063829787235,
|
| 1064 |
+
"grad_norm": 0.15571321547031403,
|
| 1065 |
+
"learning_rate": 6.66751033843842e-06,
|
| 1066 |
+
"loss": 0.38521289825439453,
|
| 1067 |
+
"step": 302
|
| 1068 |
+
},
|
| 1069 |
+
{
|
| 1070 |
+
"epoch": 1.2936170212765958,
|
| 1071 |
+
"grad_norm": 0.17477093636989594,
|
| 1072 |
+
"learning_rate": 6.872055702319048e-06,
|
| 1073 |
+
"loss": 0.9158145189285278,
|
| 1074 |
+
"step": 304
|
| 1075 |
+
},
|
| 1076 |
+
{
|
| 1077 |
+
"epoch": 1.302127659574468,
|
| 1078 |
+
"grad_norm": 0.18948765099048615,
|
| 1079 |
+
"learning_rate": 7.084839271576289e-06,
|
| 1080 |
+
"loss": 0.9535613059997559,
|
| 1081 |
+
"step": 306
|
| 1082 |
+
},
|
| 1083 |
+
{
|
| 1084 |
+
"epoch": 1.3106382978723405,
|
| 1085 |
+
"grad_norm": 0.4815928637981415,
|
| 1086 |
+
"learning_rate": 7.30569213465174e-06,
|
| 1087 |
+
"loss": 0.5246633887290955,
|
| 1088 |
+
"step": 308
|
| 1089 |
+
},
|
| 1090 |
+
{
|
| 1091 |
+
"epoch": 1.3191489361702127,
|
| 1092 |
+
"grad_norm": 0.4748033881187439,
|
| 1093 |
+
"learning_rate": 7.534438974431351e-06,
|
| 1094 |
+
"loss": 0.5024292469024658,
|
| 1095 |
+
"step": 310
|
| 1096 |
+
},
|
| 1097 |
+
{
|
| 1098 |
+
"epoch": 1.327659574468085,
|
| 1099 |
+
"grad_norm": 0.2643539607524872,
|
| 1100 |
+
"learning_rate": 7.770898207415414e-06,
|
| 1101 |
+
"loss": 0.5716067552566528,
|
| 1102 |
+
"step": 312
|
| 1103 |
+
},
|
| 1104 |
+
{
|
| 1105 |
+
"epoch": 1.3361702127659574,
|
| 1106 |
+
"grad_norm": 0.2274530827999115,
|
| 1107 |
+
"learning_rate": 8.014882127862923e-06,
|
| 1108 |
+
"loss": 0.5070632100105286,
|
| 1109 |
+
"step": 314
|
| 1110 |
+
},
|
| 1111 |
+
{
|
| 1112 |
+
"epoch": 1.3446808510638297,
|
| 1113 |
+
"grad_norm": 0.2692515254020691,
|
| 1114 |
+
"learning_rate": 8.266197056795886e-06,
|
| 1115 |
+
"loss": 0.6399731040000916,
|
| 1116 |
+
"step": 316
|
| 1117 |
+
},
|
| 1118 |
+
{
|
| 1119 |
+
"epoch": 1.353191489361702,
|
| 1120 |
+
"grad_norm": 0.17816181480884552,
|
| 1121 |
+
"learning_rate": 8.5246434957453e-06,
|
| 1122 |
+
"loss": 0.5720309019088745,
|
| 1123 |
+
"step": 318
|
| 1124 |
+
},
|
| 1125 |
+
{
|
| 1126 |
+
"epoch": 1.3617021276595744,
|
| 1127 |
+
"grad_norm": 0.427095890045166,
|
| 1128 |
+
"learning_rate": 8.790016285116766e-06,
|
| 1129 |
+
"loss": 0.49866631627082825,
|
| 1130 |
+
"step": 320
|
| 1131 |
+
},
|
| 1132 |
+
{
|
| 1133 |
+
"epoch": 1.3702127659574468,
|
| 1134 |
+
"grad_norm": 0.2689511179924011,
|
| 1135 |
+
"learning_rate": 9.062104767049957e-06,
|
| 1136 |
+
"loss": 0.8831391334533691,
|
| 1137 |
+
"step": 322
|
| 1138 |
+
},
|
| 1139 |
+
{
|
| 1140 |
+
"epoch": 1.3787234042553191,
|
| 1141 |
+
"grad_norm": 0.2776535451412201,
|
| 1142 |
+
"learning_rate": 9.340692952642787e-06,
|
| 1143 |
+
"loss": 0.6558242440223694,
|
| 1144 |
+
"step": 324
|
| 1145 |
+
},
|
| 1146 |
+
{
|
| 1147 |
+
"epoch": 1.3872340425531915,
|
| 1148 |
+
"grad_norm": 0.18160879611968994,
|
| 1149 |
+
"learning_rate": 9.625559693407413e-06,
|
| 1150 |
+
"loss": 0.8320285677909851,
|
| 1151 |
+
"step": 326
|
| 1152 |
+
},
|
| 1153 |
+
{
|
| 1154 |
+
"epoch": 1.3957446808510638,
|
| 1155 |
+
"grad_norm": 0.2418782263994217,
|
| 1156 |
+
"learning_rate": 9.916478856822006e-06,
|
| 1157 |
+
"loss": 0.6791567802429199,
|
| 1158 |
+
"step": 328
|
| 1159 |
+
},
|
| 1160 |
+
{
|
| 1161 |
+
"epoch": 1.4042553191489362,
|
| 1162 |
+
"grad_norm": 0.30612000823020935,
|
| 1163 |
+
"learning_rate": 1.0213219505838985e-05,
|
| 1164 |
+
"loss": 0.7776432633399963,
|
| 1165 |
+
"step": 330
|
| 1166 |
+
},
|
| 1167 |
+
{
|
| 1168 |
+
"epoch": 1.4127659574468086,
|
| 1169 |
+
"grad_norm": 0.2482786476612091,
|
| 1170 |
+
"learning_rate": 1.0515546082207094e-05,
|
| 1171 |
+
"loss": 0.8018679022789001,
|
| 1172 |
+
"step": 332
|
| 1173 |
+
},
|
| 1174 |
+
{
|
| 1175 |
+
"epoch": 1.421276595744681,
|
| 1176 |
+
"grad_norm": 0.2703081965446472,
|
| 1177 |
+
"learning_rate": 1.082321859346199e-05,
|
| 1178 |
+
"loss": 0.6729298830032349,
|
| 1179 |
+
"step": 334
|
| 1180 |
+
},
|
| 1181 |
+
{
|
| 1182 |
+
"epoch": 1.4297872340425533,
|
| 1183 |
+
"grad_norm": 0.21901671588420868,
|
| 1184 |
+
"learning_rate": 1.1135992803436696e-05,
|
| 1185 |
+
"loss": 0.6063901782035828,
|
| 1186 |
+
"step": 336
|
| 1187 |
+
},
|
| 1188 |
+
{
|
| 1189 |
+
"epoch": 1.4382978723404256,
|
| 1190 |
+
"grad_norm": 0.20921635627746582,
|
| 1191 |
+
"learning_rate": 1.1453620426140791e-05,
|
| 1192 |
+
"loss": 0.6617997288703918,
|
| 1193 |
+
"step": 338
|
| 1194 |
+
},
|
| 1195 |
+
{
|
| 1196 |
+
"epoch": 1.4468085106382977,
|
| 1197 |
+
"grad_norm": 0.19303618371486664,
|
| 1198 |
+
"learning_rate": 1.1775849322854508e-05,
|
| 1199 |
+
"loss": 0.5969347953796387,
|
| 1200 |
+
"step": 340
|
| 1201 |
+
},
|
| 1202 |
+
{
|
| 1203 |
+
"epoch": 1.4553191489361703,
|
| 1204 |
+
"grad_norm": 0.3104172646999359,
|
| 1205 |
+
"learning_rate": 1.210242370228112e-05,
|
| 1206 |
+
"loss": 0.6071085333824158,
|
| 1207 |
+
"step": 342
|
| 1208 |
+
},
|
| 1209 |
+
{
|
| 1210 |
+
"epoch": 1.4638297872340424,
|
| 1211 |
+
"grad_norm": 0.22875197231769562,
|
| 1212 |
+
"learning_rate": 1.2433084323598791e-05,
|
| 1213 |
+
"loss": 0.9178237915039062,
|
| 1214 |
+
"step": 344
|
| 1215 |
+
},
|
| 1216 |
+
{
|
| 1217 |
+
"epoch": 1.472340425531915,
|
| 1218 |
+
"grad_norm": 0.19736064970493317,
|
| 1219 |
+
"learning_rate": 1.2767568702250838e-05,
|
| 1220 |
+
"loss": 0.8496959209442139,
|
| 1221 |
+
"step": 346
|
| 1222 |
+
},
|
| 1223 |
+
{
|
| 1224 |
+
"epoch": 1.4808510638297872,
|
| 1225 |
+
"grad_norm": 0.24981622397899628,
|
| 1226 |
+
"learning_rate": 1.3105611318310811e-05,
|
| 1227 |
+
"loss": 0.7014995813369751,
|
| 1228 |
+
"step": 348
|
| 1229 |
+
},
|
| 1230 |
+
{
|
| 1231 |
+
"epoch": 1.4893617021276595,
|
| 1232 |
+
"grad_norm": 0.2884751558303833,
|
| 1233 |
+
"learning_rate": 1.3446943827257184e-05,
|
| 1234 |
+
"loss": 0.7825354337692261,
|
| 1235 |
+
"step": 350
|
| 1236 |
+
},
|
| 1237 |
+
{
|
| 1238 |
+
"epoch": 1.4978723404255319,
|
| 1239 |
+
"grad_norm": 0.42386531829833984,
|
| 1240 |
+
"learning_rate": 1.3791295272990172e-05,
|
| 1241 |
+
"loss": 0.33443060517311096,
|
| 1242 |
+
"step": 352
|
| 1243 |
+
},
|
| 1244 |
+
{
|
| 1245 |
+
"epoch": 1.5063829787234042,
|
| 1246 |
+
"grad_norm": 0.16379332542419434,
|
| 1247 |
+
"learning_rate": 1.413839230292182e-05,
|
| 1248 |
+
"loss": 0.6189748048782349,
|
| 1249 |
+
"step": 354
|
| 1250 |
+
},
|
| 1251 |
+
{
|
| 1252 |
+
"epoch": 1.5148936170212766,
|
| 1253 |
+
"grad_norm": 0.2462461143732071,
|
| 1254 |
+
"learning_rate": 1.4487959384968276e-05,
|
| 1255 |
+
"loss": 0.46220940351486206,
|
| 1256 |
+
"step": 356
|
| 1257 |
+
},
|
| 1258 |
+
{
|
| 1259 |
+
"epoch": 1.523404255319149,
|
| 1260 |
+
"grad_norm": 0.23771870136260986,
|
| 1261 |
+
"learning_rate": 1.4839719026272373e-05,
|
| 1262 |
+
"loss": 0.4545080363750458,
|
| 1263 |
+
"step": 358
|
| 1264 |
+
},
|
| 1265 |
+
{
|
| 1266 |
+
"epoch": 1.5319148936170213,
|
| 1267 |
+
"grad_norm": 0.18759848177433014,
|
| 1268 |
+
"learning_rate": 1.5193391993482579e-05,
|
| 1269 |
+
"loss": 0.9656761288642883,
|
| 1270 |
+
"step": 360
|
| 1271 |
+
},
|
| 1272 |
+
{
|
| 1273 |
+
"epoch": 1.5404255319148936,
|
| 1274 |
+
"grad_norm": 0.18730829656124115,
|
| 1275 |
+
"learning_rate": 1.5548697534413636e-05,
|
| 1276 |
+
"loss": 0.44390690326690674,
|
| 1277 |
+
"step": 362
|
| 1278 |
+
},
|
| 1279 |
+
{
|
| 1280 |
+
"epoch": 1.548936170212766,
|
| 1281 |
+
"grad_norm": 0.3202720582485199,
|
| 1282 |
+
"learning_rate": 1.5905353600912894e-05,
|
| 1283 |
+
"loss": 0.9684057235717773,
|
| 1284 |
+
"step": 364
|
| 1285 |
+
},
|
| 1286 |
+
{
|
| 1287 |
+
"epoch": 1.5574468085106383,
|
| 1288 |
+
"grad_norm": 0.13575418293476105,
|
| 1289 |
+
"learning_rate": 1.6263077072755323e-05,
|
| 1290 |
+
"loss": 0.8047466278076172,
|
| 1291 |
+
"step": 366
|
| 1292 |
+
},
|
| 1293 |
+
{
|
| 1294 |
+
"epoch": 1.5659574468085107,
|
| 1295 |
+
"grad_norm": 0.36194950342178345,
|
| 1296 |
+
"learning_rate": 1.6621583982389707e-05,
|
| 1297 |
+
"loss": 0.6687026619911194,
|
| 1298 |
+
"step": 368
|
| 1299 |
+
},
|
| 1300 |
+
{
|
| 1301 |
+
"epoch": 1.574468085106383,
|
| 1302 |
+
"grad_norm": 0.12254664301872253,
|
| 1303 |
+
"learning_rate": 1.6980589740357294e-05,
|
| 1304 |
+
"loss": 0.5913136601448059,
|
| 1305 |
+
"step": 370
|
| 1306 |
+
},
|
| 1307 |
+
{
|
| 1308 |
+
"epoch": 1.5829787234042554,
|
| 1309 |
+
"grad_norm": 0.13009262084960938,
|
| 1310 |
+
"learning_rate": 1.733980936120425e-05,
|
| 1311 |
+
"loss": 0.7752522230148315,
|
| 1312 |
+
"step": 372
|
| 1313 |
+
},
|
| 1314 |
+
{
|
| 1315 |
+
"epoch": 1.5914893617021275,
|
| 1316 |
+
"grad_norm": 0.5959559679031372,
|
| 1317 |
+
"learning_rate": 1.7698957689708416e-05,
|
| 1318 |
+
"loss": 0.9753284454345703,
|
| 1319 |
+
"step": 374
|
| 1320 |
+
},
|
| 1321 |
+
{
|
| 1322 |
+
"epoch": 1.6,
|
| 1323 |
+
"grad_norm": 0.5740659832954407,
|
| 1324 |
+
"learning_rate": 1.805774962724083e-05,
|
| 1325 |
+
"loss": 0.7318065762519836,
|
| 1326 |
+
"step": 376
|
| 1327 |
+
},
|
| 1328 |
+
{
|
| 1329 |
+
"epoch": 1.6085106382978722,
|
| 1330 |
+
"grad_norm": 0.5994616746902466,
|
| 1331 |
+
"learning_rate": 1.8415900358082265e-05,
|
| 1332 |
+
"loss": 0.5247442126274109,
|
| 1333 |
+
"step": 378
|
| 1334 |
+
},
|
| 1335 |
+
{
|
| 1336 |
+
"epoch": 1.6170212765957448,
|
| 1337 |
+
"grad_norm": 0.27797627449035645,
|
| 1338 |
+
"learning_rate": 1.8773125575515357e-05,
|
| 1339 |
+
"loss": 0.5938118696212769,
|
| 1340 |
+
"step": 380
|
| 1341 |
+
},
|
| 1342 |
+
{
|
| 1343 |
+
"epoch": 1.625531914893617,
|
| 1344 |
+
"grad_norm": 0.16901274025440216,
|
| 1345 |
+
"learning_rate": 1.912914170751251e-05,
|
| 1346 |
+
"loss": 0.761189341545105,
|
| 1347 |
+
"step": 382
|
| 1348 |
+
},
|
| 1349 |
+
{
|
| 1350 |
+
"epoch": 1.6340425531914895,
|
| 1351 |
+
"grad_norm": 0.2777624726295471,
|
| 1352 |
+
"learning_rate": 1.9483666141840612e-05,
|
| 1353 |
+
"loss": 0.9914259910583496,
|
| 1354 |
+
"step": 384
|
| 1355 |
+
},
|
| 1356 |
+
{
|
| 1357 |
+
"epoch": 1.6425531914893616,
|
| 1358 |
+
"grad_norm": 0.3253246247768402,
|
| 1359 |
+
"learning_rate": 1.9836417450403974e-05,
|
| 1360 |
+
"loss": 0.8401809930801392,
|
| 1361 |
+
"step": 386
|
| 1362 |
+
},
|
| 1363 |
+
{
|
| 1364 |
+
"epoch": 1.6510638297872342,
|
| 1365 |
+
"grad_norm": 0.16334128379821777,
|
| 1366 |
+
"learning_rate": 2.0187115612647133e-05,
|
| 1367 |
+
"loss": 0.694261372089386,
|
| 1368 |
+
"step": 388
|
| 1369 |
+
},
|
| 1370 |
+
{
|
| 1371 |
+
"epoch": 1.6595744680851063,
|
| 1372 |
+
"grad_norm": 0.16701728105545044,
|
| 1373 |
+
"learning_rate": 2.05354822378404e-05,
|
| 1374 |
+
"loss": 0.8252889513969421,
|
| 1375 |
+
"step": 390
|
| 1376 |
+
},
|
| 1377 |
+
{
|
| 1378 |
+
"epoch": 1.6680851063829787,
|
| 1379 |
+
"grad_norm": 0.10444586724042892,
|
| 1380 |
+
"learning_rate": 2.0881240786071595e-05,
|
| 1381 |
+
"loss": 0.8890981078147888,
|
| 1382 |
+
"step": 392
|
| 1383 |
+
},
|
| 1384 |
+
{
|
| 1385 |
+
"epoch": 1.676595744680851,
|
| 1386 |
+
"grad_norm": 0.4691241681575775,
|
| 1387 |
+
"learning_rate": 2.122411678776854e-05,
|
| 1388 |
+
"loss": 0.6046314835548401,
|
| 1389 |
+
"step": 394
|
| 1390 |
+
},
|
| 1391 |
+
{
|
| 1392 |
+
"epoch": 1.6851063829787234,
|
| 1393 |
+
"grad_norm": 0.11681725829839706,
|
| 1394 |
+
"learning_rate": 2.1563838061578258e-05,
|
| 1395 |
+
"loss": 0.8832032084465027,
|
| 1396 |
+
"step": 396
|
| 1397 |
+
},
|
| 1398 |
+
{
|
| 1399 |
+
"epoch": 1.6936170212765957,
|
| 1400 |
+
"grad_norm": 0.14530058205127716,
|
| 1401 |
+
"learning_rate": 2.1900134930429396e-05,
|
| 1402 |
+
"loss": 1.0986517667770386,
|
| 1403 |
+
"step": 398
|
| 1404 |
+
},
|
| 1405 |
+
{
|
| 1406 |
+
"epoch": 1.702127659574468,
|
| 1407 |
+
"grad_norm": 0.37800365686416626,
|
| 1408 |
+
"learning_rate": 2.223274043560706e-05,
|
| 1409 |
+
"loss": 0.9784438610076904,
|
| 1410 |
+
"step": 400
|
| 1411 |
+
},
|
| 1412 |
+
{
|
| 1413 |
+
"epoch": 1.7106382978723405,
|
| 1414 |
+
"grad_norm": 0.37573498487472534,
|
| 1415 |
+
"learning_rate": 2.256139054866954e-05,
|
| 1416 |
+
"loss": 0.47277578711509705,
|
| 1417 |
+
"step": 402
|
| 1418 |
+
},
|
| 1419 |
+
{
|
| 1420 |
+
"epoch": 1.7191489361702128,
|
| 1421 |
+
"grad_norm": 0.5493515729904175,
|
| 1422 |
+
"learning_rate": 2.2885824381039028e-05,
|
| 1423 |
+
"loss": 0.6571931838989258,
|
| 1424 |
+
"step": 404
|
| 1425 |
+
},
|
| 1426 |
+
{
|
| 1427 |
+
"epoch": 1.7276595744680852,
|
| 1428 |
+
"grad_norm": 0.24701279401779175,
|
| 1429 |
+
"learning_rate": 2.3205784391099808e-05,
|
| 1430 |
+
"loss": 0.5199674367904663,
|
| 1431 |
+
"step": 406
|
| 1432 |
+
},
|
| 1433 |
+
{
|
| 1434 |
+
"epoch": 1.7361702127659573,
|
| 1435 |
+
"grad_norm": 0.2061431109905243,
|
| 1436 |
+
"learning_rate": 2.352101658863958e-05,
|
| 1437 |
+
"loss": 0.7460405230522156,
|
| 1438 |
+
"step": 408
|
| 1439 |
+
},
|
| 1440 |
+
{
|
| 1441 |
+
"epoch": 1.7446808510638299,
|
| 1442 |
+
"grad_norm": 0.16800709068775177,
|
| 1443 |
+
"learning_rate": 2.3831270736471703e-05,
|
| 1444 |
+
"loss": 0.9135586023330688,
|
| 1445 |
+
"step": 410
|
| 1446 |
+
},
|
| 1447 |
+
{
|
| 1448 |
+
"epoch": 1.753191489361702,
|
| 1449 |
+
"grad_norm": 0.5365346074104309,
|
| 1450 |
+
"learning_rate": 2.4136300549077973e-05,
|
| 1451 |
+
"loss": 0.906153678894043,
|
| 1452 |
+
"step": 412
|
| 1453 |
+
},
|
| 1454 |
+
{
|
| 1455 |
+
"epoch": 1.7617021276595746,
|
| 1456 |
+
"grad_norm": 0.14748896658420563,
|
| 1457 |
+
"learning_rate": 2.443586388811481e-05,
|
| 1458 |
+
"loss": 0.7806675434112549,
|
| 1459 |
+
"step": 414
|
| 1460 |
+
},
|
| 1461 |
+
{
|
| 1462 |
+
"epoch": 1.7702127659574467,
|
| 1463 |
+
"grad_norm": 1.3085377216339111,
|
| 1464 |
+
"learning_rate": 2.47297229546271e-05,
|
| 1465 |
+
"loss": 0.6440402865409851,
|
| 1466 |
+
"step": 416
|
| 1467 |
+
},
|
| 1468 |
+
{
|
| 1469 |
+
"epoch": 1.7787234042553193,
|
| 1470 |
+
"grad_norm": 0.2483910322189331,
|
| 1471 |
+
"learning_rate": 2.5017644477817418e-05,
|
| 1472 |
+
"loss": 0.7717803120613098,
|
| 1473 |
+
"step": 418
|
| 1474 |
+
},
|
| 1475 |
+
{
|
| 1476 |
+
"epoch": 1.7872340425531914,
|
| 1477 |
+
"grad_norm": 0.4905950427055359,
|
| 1478 |
+
"learning_rate": 2.5299399900220807e-05,
|
| 1479 |
+
"loss": 0.6290927529335022,
|
| 1480 |
+
"step": 420
|
| 1481 |
+
},
|
| 1482 |
+
{
|
| 1483 |
+
"epoch": 1.795744680851064,
|
| 1484 |
+
"grad_norm": 0.11053664982318878,
|
| 1485 |
+
"learning_rate": 2.5574765559137848e-05,
|
| 1486 |
+
"loss": 0.7530769109725952,
|
| 1487 |
+
"step": 422
|
| 1488 |
+
},
|
| 1489 |
+
{
|
| 1490 |
+
"epoch": 1.804255319148936,
|
| 1491 |
+
"grad_norm": 0.11755101382732391,
|
| 1492 |
+
"learning_rate": 2.584352286418239e-05,
|
| 1493 |
+
"loss": 0.8429850935935974,
|
| 1494 |
+
"step": 424
|
| 1495 |
+
},
|
| 1496 |
+
{
|
| 1497 |
+
"epoch": 1.8127659574468085,
|
| 1498 |
+
"grad_norm": 0.14117616415023804,
|
| 1499 |
+
"learning_rate": 2.6105458470802563e-05,
|
| 1500 |
+
"loss": 0.8456153869628906,
|
| 1501 |
+
"step": 426
|
| 1502 |
+
},
|
| 1503 |
+
{
|
| 1504 |
+
"epoch": 1.8212765957446808,
|
| 1505 |
+
"grad_norm": 0.22968512773513794,
|
| 1506 |
+
"learning_rate": 2.6360364449637683e-05,
|
| 1507 |
+
"loss": 0.8607503771781921,
|
| 1508 |
+
"step": 428
|
| 1509 |
+
},
|
| 1510 |
+
{
|
| 1511 |
+
"epoch": 1.8297872340425532,
|
| 1512 |
+
"grad_norm": 0.3352075219154358,
|
| 1513 |
+
"learning_rate": 2.6608038451576528e-05,
|
| 1514 |
+
"loss": 0.9603878259658813,
|
| 1515 |
+
"step": 430
|
| 1516 |
+
},
|
| 1517 |
+
{
|
| 1518 |
+
"epoch": 1.8382978723404255,
|
| 1519 |
+
"grad_norm": 0.22618667781352997,
|
| 1520 |
+
"learning_rate": 2.684828386838569e-05,
|
| 1521 |
+
"loss": 0.7366024255752563,
|
| 1522 |
+
"step": 432
|
| 1523 |
+
},
|
| 1524 |
+
{
|
| 1525 |
+
"epoch": 1.8468085106382979,
|
| 1526 |
+
"grad_norm": 0.3134029805660248,
|
| 1527 |
+
"learning_rate": 2.7080909988780982e-05,
|
| 1528 |
+
"loss": 0.9086182117462158,
|
| 1529 |
+
"step": 434
|
| 1530 |
+
},
|
| 1531 |
+
{
|
| 1532 |
+
"epoch": 1.8553191489361702,
|
| 1533 |
+
"grad_norm": 0.12940463423728943,
|
| 1534 |
+
"learning_rate": 2.7305732149817502e-05,
|
| 1535 |
+
"loss": 0.642800509929657,
|
| 1536 |
+
"step": 436
|
| 1537 |
+
},
|
| 1538 |
+
{
|
| 1539 |
+
"epoch": 1.8638297872340426,
|
| 1540 |
+
"grad_norm": 0.3360910415649414,
|
| 1541 |
+
"learning_rate": 2.7522571883478617e-05,
|
| 1542 |
+
"loss": 1.0462186336517334,
|
| 1543 |
+
"step": 438
|
| 1544 |
+
},
|
| 1545 |
+
{
|
| 1546 |
+
"epoch": 1.872340425531915,
|
| 1547 |
+
"grad_norm": 0.18832530081272125,
|
| 1548 |
+
"learning_rate": 2.77312570583471e-05,
|
| 1549 |
+
"loss": 0.9516323804855347,
|
| 1550 |
+
"step": 440
|
| 1551 |
+
},
|
| 1552 |
+
{
|
| 1553 |
+
"epoch": 1.8808510638297873,
|
| 1554 |
+
"grad_norm": 0.12196290493011475,
|
| 1555 |
+
"learning_rate": 2.7931622016246304e-05,
|
| 1556 |
+
"loss": 0.9153946042060852,
|
| 1557 |
+
"step": 442
|
| 1558 |
+
},
|
| 1559 |
+
{
|
| 1560 |
+
"epoch": 1.8893617021276596,
|
| 1561 |
+
"grad_norm": 0.1658358871936798,
|
| 1562 |
+
"learning_rate": 2.8123507703742727e-05,
|
| 1563 |
+
"loss": 0.8443633913993835,
|
| 1564 |
+
"step": 444
|
| 1565 |
+
},
|
| 1566 |
+
{
|
| 1567 |
+
"epoch": 1.8978723404255318,
|
| 1568 |
+
"grad_norm": 0.19309784471988678,
|
| 1569 |
+
"learning_rate": 2.8306761798405522e-05,
|
| 1570 |
+
"loss": 1.0077768564224243,
|
| 1571 |
+
"step": 446
|
| 1572 |
+
},
|
| 1573 |
+
{
|
| 1574 |
+
"epoch": 1.9063829787234043,
|
| 1575 |
+
"grad_norm": 0.1583261489868164,
|
| 1576 |
+
"learning_rate": 2.848123882972295e-05,
|
| 1577 |
+
"loss": 0.9472059607505798,
|
| 1578 |
+
"step": 448
|
| 1579 |
+
},
|
| 1580 |
+
{
|
| 1581 |
+
"epoch": 1.9148936170212765,
|
| 1582 |
+
"grad_norm": 0.5723341107368469,
|
| 1583 |
+
"learning_rate": 2.8646800294579514e-05,
|
| 1584 |
+
"loss": 0.6875810623168945,
|
| 1585 |
+
"step": 450
|
| 1586 |
+
},
|
| 1587 |
+
{
|
| 1588 |
+
"epoch": 1.923404255319149,
|
| 1589 |
+
"grad_norm": 0.339374303817749,
|
| 1590 |
+
"learning_rate": 2.8803314767202376e-05,
|
| 1591 |
+
"loss": 0.5654004812240601,
|
| 1592 |
+
"step": 452
|
| 1593 |
+
},
|
| 1594 |
+
{
|
| 1595 |
+
"epoch": 1.9319148936170212,
|
| 1596 |
+
"grad_norm": 0.5859424471855164,
|
| 1597 |
+
"learning_rate": 2.8950658003489534e-05,
|
| 1598 |
+
"loss": 0.8492231965065002,
|
| 1599 |
+
"step": 454
|
| 1600 |
+
},
|
| 1601 |
+
{
|
| 1602 |
+
"epoch": 1.9404255319148938,
|
| 1603 |
+
"grad_norm": 0.422346830368042,
|
| 1604 |
+
"learning_rate": 2.908871303963711e-05,
|
| 1605 |
+
"loss": 0.9699692130088806,
|
| 1606 |
+
"step": 456
|
| 1607 |
+
},
|
| 1608 |
+
{
|
| 1609 |
+
"epoch": 1.9489361702127659,
|
| 1610 |
+
"grad_norm": 0.1916320025920868,
|
| 1611 |
+
"learning_rate": 2.9217370284987434e-05,
|
| 1612 |
+
"loss": 0.7598567605018616,
|
| 1613 |
+
"step": 458
|
| 1614 |
+
},
|
| 1615 |
+
{
|
| 1616 |
+
"epoch": 1.9574468085106385,
|
| 1617 |
+
"grad_norm": 0.2646377384662628,
|
| 1618 |
+
"learning_rate": 2.9336527609024075e-05,
|
| 1619 |
+
"loss": 1.0349591970443726,
|
| 1620 |
+
"step": 460
|
| 1621 |
+
},
|
| 1622 |
+
{
|
| 1623 |
+
"epoch": 1.9659574468085106,
|
| 1624 |
+
"grad_norm": 0.19794800877571106,
|
| 1625 |
+
"learning_rate": 2.9446090422445016e-05,
|
| 1626 |
+
"loss": 0.7465431094169617,
|
| 1627 |
+
"step": 462
|
| 1628 |
+
},
|
| 1629 |
+
{
|
| 1630 |
+
"epoch": 1.974468085106383,
|
| 1631 |
+
"grad_norm": 0.11537999659776688,
|
| 1632 |
+
"learning_rate": 2.9545971752249376e-05,
|
| 1633 |
+
"loss": 0.8450900316238403,
|
| 1634 |
+
"step": 464
|
| 1635 |
+
},
|
| 1636 |
+
{
|
| 1637 |
+
"epoch": 1.9829787234042553,
|
| 1638 |
+
"grad_norm": 0.16437967121601105,
|
| 1639 |
+
"learning_rate": 2.9636092310778195e-05,
|
| 1640 |
+
"loss": 0.8825825452804565,
|
| 1641 |
+
"step": 466
|
| 1642 |
+
},
|
| 1643 |
+
{
|
| 1644 |
+
"epoch": 1.9914893617021276,
|
| 1645 |
+
"grad_norm": 0.1353980153799057,
|
| 1646 |
+
"learning_rate": 2.9716380558654445e-05,
|
| 1647 |
+
"loss": 0.6045427918434143,
|
| 1648 |
+
"step": 468
|
| 1649 |
+
},
|
| 1650 |
+
{
|
| 1651 |
+
"epoch": 2.0,
|
| 1652 |
+
"grad_norm": 0.12124238908290863,
|
| 1653 |
+
"learning_rate": 2.9786772761572338e-05,
|
| 1654 |
+
"loss": 0.6623026728630066,
|
| 1655 |
+
"step": 470
|
| 1656 |
+
},
|
| 1657 |
+
{
|
| 1658 |
+
"epoch": 2.008510638297872,
|
| 1659 |
+
"grad_norm": 0.24585317075252533,
|
| 1660 |
+
"learning_rate": 2.9847213040890793e-05,
|
| 1661 |
+
"loss": 0.36443179845809937,
|
| 1662 |
+
"step": 472
|
| 1663 |
+
},
|
| 1664 |
+
{
|
| 1665 |
+
"epoch": 2.0170212765957447,
|
| 1666 |
+
"grad_norm": 0.13654032349586487,
|
| 1667 |
+
"learning_rate": 2.989765341799095e-05,
|
| 1668 |
+
"loss": 0.75254225730896,
|
| 1669 |
+
"step": 474
|
| 1670 |
+
},
|
| 1671 |
+
{
|
| 1672 |
+
"epoch": 2.025531914893617,
|
| 1673 |
+
"grad_norm": 0.5691254138946533,
|
| 1674 |
+
"learning_rate": 2.9938053852362484e-05,
|
| 1675 |
+
"loss": 0.47092172503471375,
|
| 1676 |
+
"step": 476
|
| 1677 |
+
},
|
| 1678 |
+
{
|
| 1679 |
+
"epoch": 2.0340425531914894,
|
| 1680 |
+
"grad_norm": 0.1691976934671402,
|
| 1681 |
+
"learning_rate": 2.99683822733885e-05,
|
| 1682 |
+
"loss": 0.6583607196807861,
|
| 1683 |
+
"step": 478
|
| 1684 |
+
},
|
| 1685 |
+
{
|
| 1686 |
+
"epoch": 2.0425531914893615,
|
| 1687 |
+
"grad_norm": 0.16407643258571625,
|
| 1688 |
+
"learning_rate": 2.9988614605803806e-05,
|
| 1689 |
+
"loss": 0.5634033679962158,
|
| 1690 |
+
"step": 480
|
| 1691 |
+
},
|
| 1692 |
+
{
|
| 1693 |
+
"epoch": 2.051063829787234,
|
| 1694 |
+
"grad_norm": 0.22440628707408905,
|
| 1695 |
+
"learning_rate": 2.9998734788806287e-05,
|
| 1696 |
+
"loss": 0.4582347571849823,
|
| 1697 |
+
"step": 482
|
| 1698 |
+
},
|
| 1699 |
+
{
|
| 1700 |
+
"epoch": 2.0595744680851062,
|
| 1701 |
+
"grad_norm": 0.07732467353343964,
|
| 1702 |
+
"learning_rate": 2.9998734788806287e-05,
|
| 1703 |
+
"loss": 0.24273234605789185,
|
| 1704 |
+
"step": 484
|
| 1705 |
+
},
|
| 1706 |
+
{
|
| 1707 |
+
"epoch": 2.068085106382979,
|
| 1708 |
+
"grad_norm": 0.46668562293052673,
|
| 1709 |
+
"learning_rate": 2.9988614605803806e-05,
|
| 1710 |
+
"loss": 0.6905072331428528,
|
| 1711 |
+
"step": 486
|
| 1712 |
+
},
|
| 1713 |
+
{
|
| 1714 |
+
"epoch": 2.076595744680851,
|
| 1715 |
+
"grad_norm": 0.14304345846176147,
|
| 1716 |
+
"learning_rate": 2.99683822733885e-05,
|
| 1717 |
+
"loss": 0.4559966027736664,
|
| 1718 |
+
"step": 488
|
| 1719 |
+
},
|
| 1720 |
+
{
|
| 1721 |
+
"epoch": 2.0851063829787235,
|
| 1722 |
+
"grad_norm": 0.370118111371994,
|
| 1723 |
+
"learning_rate": 2.9938053852362484e-05,
|
| 1724 |
+
"loss": 0.5135046243667603,
|
| 1725 |
+
"step": 490
|
| 1726 |
+
},
|
| 1727 |
+
{
|
| 1728 |
+
"epoch": 2.0936170212765957,
|
| 1729 |
+
"grad_norm": 0.15926745533943176,
|
| 1730 |
+
"learning_rate": 2.989765341799095e-05,
|
| 1731 |
+
"loss": 0.7977150678634644,
|
| 1732 |
+
"step": 492
|
| 1733 |
+
},
|
| 1734 |
+
{
|
| 1735 |
+
"epoch": 2.1021276595744682,
|
| 1736 |
+
"grad_norm": 0.13238710165023804,
|
| 1737 |
+
"learning_rate": 2.9847213040890793e-05,
|
| 1738 |
+
"loss": 0.6057368516921997,
|
| 1739 |
+
"step": 494
|
| 1740 |
+
},
|
| 1741 |
+
{
|
| 1742 |
+
"epoch": 2.1106382978723404,
|
| 1743 |
+
"grad_norm": 0.18792684376239777,
|
| 1744 |
+
"learning_rate": 2.9786772761572338e-05,
|
| 1745 |
+
"loss": 0.7654038071632385,
|
| 1746 |
+
"step": 496
|
| 1747 |
+
},
|
| 1748 |
+
{
|
| 1749 |
+
"epoch": 2.119148936170213,
|
| 1750 |
+
"grad_norm": 0.12919172644615173,
|
| 1751 |
+
"learning_rate": 2.9716380558654445e-05,
|
| 1752 |
+
"loss": 0.8083907961845398,
|
| 1753 |
+
"step": 498
|
| 1754 |
+
},
|
| 1755 |
+
{
|
| 1756 |
+
"epoch": 2.127659574468085,
|
| 1757 |
+
"grad_norm": 0.21281176805496216,
|
| 1758 |
+
"learning_rate": 2.9636092310778195e-05,
|
| 1759 |
+
"loss": 0.5940195322036743,
|
| 1760 |
+
"step": 500
|
| 1761 |
+
},
|
| 1762 |
+
{
|
| 1763 |
+
"epoch": 2.1361702127659576,
|
| 1764 |
+
"grad_norm": 0.1665232926607132,
|
| 1765 |
+
"learning_rate": 2.9545971752249383e-05,
|
| 1766 |
+
"loss": 0.5825145244598389,
|
| 1767 |
+
"step": 502
|
| 1768 |
+
},
|
| 1769 |
+
{
|
| 1770 |
+
"epoch": 2.1446808510638298,
|
| 1771 |
+
"grad_norm": 0.11076656728982925,
|
| 1772 |
+
"learning_rate": 2.9446090422445016e-05,
|
| 1773 |
+
"loss": 0.5060111284255981,
|
| 1774 |
+
"step": 504
|
| 1775 |
+
},
|
| 1776 |
+
{
|
| 1777 |
+
"epoch": 2.153191489361702,
|
| 1778 |
+
"grad_norm": 0.123874731361866,
|
| 1779 |
+
"learning_rate": 2.933652760902408e-05,
|
| 1780 |
+
"loss": 0.5895789265632629,
|
| 1781 |
+
"step": 506
|
| 1782 |
+
},
|
| 1783 |
+
{
|
| 1784 |
+
"epoch": 2.1617021276595745,
|
| 1785 |
+
"grad_norm": 0.24894492328166962,
|
| 1786 |
+
"learning_rate": 2.9217370284987434e-05,
|
| 1787 |
+
"loss": 0.3788684010505676,
|
| 1788 |
+
"step": 508
|
| 1789 |
+
},
|
| 1790 |
+
{
|
| 1791 |
+
"epoch": 2.1702127659574466,
|
| 1792 |
+
"grad_norm": 0.1470797210931778,
|
| 1793 |
+
"learning_rate": 2.908871303963712e-05,
|
| 1794 |
+
"loss": 0.3065789043903351,
|
| 1795 |
+
"step": 510
|
| 1796 |
+
},
|
| 1797 |
+
{
|
| 1798 |
+
"epoch": 2.178723404255319,
|
| 1799 |
+
"grad_norm": 0.2271808236837387,
|
| 1800 |
+
"learning_rate": 2.8950658003489534e-05,
|
| 1801 |
+
"loss": 0.3498597741127014,
|
| 1802 |
+
"step": 512
|
| 1803 |
+
},
|
| 1804 |
+
{
|
| 1805 |
+
"epoch": 2.1872340425531913,
|
| 1806 |
+
"grad_norm": 0.2549133896827698,
|
| 1807 |
+
"learning_rate": 2.8803314767202387e-05,
|
| 1808 |
+
"loss": 0.3588785231113434,
|
| 1809 |
+
"step": 514
|
| 1810 |
+
},
|
| 1811 |
+
{
|
| 1812 |
+
"epoch": 2.195744680851064,
|
| 1813 |
+
"grad_norm": 0.27323317527770996,
|
| 1814 |
+
"learning_rate": 2.864680029457952e-05,
|
| 1815 |
+
"loss": 0.4839470088481903,
|
| 1816 |
+
"step": 516
|
| 1817 |
+
},
|
| 1818 |
+
{
|
| 1819 |
+
"epoch": 2.204255319148936,
|
| 1820 |
+
"grad_norm": 0.7197582721710205,
|
| 1821 |
+
"learning_rate": 2.8481238829722946e-05,
|
| 1822 |
+
"loss": 0.6455433368682861,
|
| 1823 |
+
"step": 518
|
| 1824 |
+
},
|
| 1825 |
+
{
|
| 1826 |
+
"epoch": 2.2127659574468086,
|
| 1827 |
+
"grad_norm": 0.16234466433525085,
|
| 1828 |
+
"learning_rate": 2.8306761798405533e-05,
|
| 1829 |
+
"loss": 0.5413359999656677,
|
| 1830 |
+
"step": 520
|
| 1831 |
+
},
|
| 1832 |
+
{
|
| 1833 |
+
"epoch": 2.2212765957446807,
|
| 1834 |
+
"grad_norm": 0.21601392328739166,
|
| 1835 |
+
"learning_rate": 2.812350770374273e-05,
|
| 1836 |
+
"loss": 0.33399829268455505,
|
| 1837 |
+
"step": 522
|
| 1838 |
+
},
|
| 1839 |
+
{
|
| 1840 |
+
"epoch": 2.2297872340425533,
|
| 1841 |
+
"grad_norm": 0.3286589980125427,
|
| 1842 |
+
"learning_rate": 2.793162201624631e-05,
|
| 1843 |
+
"loss": 0.4370644688606262,
|
| 1844 |
+
"step": 524
|
| 1845 |
+
},
|
| 1846 |
+
{
|
| 1847 |
+
"epoch": 2.2382978723404254,
|
| 1848 |
+
"grad_norm": 0.28274786472320557,
|
| 1849 |
+
"learning_rate": 2.7731257058347098e-05,
|
| 1850 |
+
"loss": 0.6098963618278503,
|
| 1851 |
+
"step": 526
|
| 1852 |
+
},
|
| 1853 |
+
{
|
| 1854 |
+
"epoch": 2.246808510638298,
|
| 1855 |
+
"grad_norm": 0.1321384608745575,
|
| 1856 |
+
"learning_rate": 2.752257188347862e-05,
|
| 1857 |
+
"loss": 0.6518822908401489,
|
| 1858 |
+
"step": 528
|
| 1859 |
+
},
|
| 1860 |
+
{
|
| 1861 |
+
"epoch": 2.25531914893617,
|
| 1862 |
+
"grad_norm": 0.4378323256969452,
|
| 1863 |
+
"learning_rate": 2.7305732149817512e-05,
|
| 1864 |
+
"loss": 0.6883822679519653,
|
| 1865 |
+
"step": 530
|
| 1866 |
+
},
|
| 1867 |
+
{
|
| 1868 |
+
"epoch": 2.2638297872340427,
|
| 1869 |
+
"grad_norm": 0.12180285900831223,
|
| 1870 |
+
"learning_rate": 2.708090998878098e-05,
|
| 1871 |
+
"loss": 0.5799202919006348,
|
| 1872 |
+
"step": 532
|
| 1873 |
+
},
|
| 1874 |
+
{
|
| 1875 |
+
"epoch": 2.272340425531915,
|
| 1876 |
+
"grad_norm": 0.2532312572002411,
|
| 1877 |
+
"learning_rate": 2.68482838683857e-05,
|
| 1878 |
+
"loss": 0.30189117789268494,
|
| 1879 |
+
"step": 534
|
| 1880 |
+
},
|
| 1881 |
+
{
|
| 1882 |
+
"epoch": 2.2808510638297874,
|
| 1883 |
+
"grad_norm": 0.1414760947227478,
|
| 1884 |
+
"learning_rate": 2.6608038451576528e-05,
|
| 1885 |
+
"loss": 0.5066512823104858,
|
| 1886 |
+
"step": 536
|
| 1887 |
+
},
|
| 1888 |
+
{
|
| 1889 |
+
"epoch": 2.2893617021276595,
|
| 1890 |
+
"grad_norm": 0.15154339373111725,
|
| 1891 |
+
"learning_rate": 2.6360364449637686e-05,
|
| 1892 |
+
"loss": 0.7329890131950378,
|
| 1893 |
+
"step": 538
|
| 1894 |
+
},
|
| 1895 |
+
{
|
| 1896 |
+
"epoch": 2.297872340425532,
|
| 1897 |
+
"grad_norm": 0.438917338848114,
|
| 1898 |
+
"learning_rate": 2.6105458470802563e-05,
|
| 1899 |
+
"loss": 0.23619456589221954,
|
| 1900 |
+
"step": 540
|
| 1901 |
+
},
|
| 1902 |
+
{
|
| 1903 |
+
"epoch": 2.3063829787234043,
|
| 1904 |
+
"grad_norm": 0.10420854389667511,
|
| 1905 |
+
"learning_rate": 2.5843522864182397e-05,
|
| 1906 |
+
"loss": 0.2426261454820633,
|
| 1907 |
+
"step": 542
|
| 1908 |
+
},
|
| 1909 |
+
{
|
| 1910 |
+
"epoch": 2.3148936170212764,
|
| 1911 |
+
"grad_norm": 0.3014877736568451,
|
| 1912 |
+
"learning_rate": 2.557476555913786e-05,
|
| 1913 |
+
"loss": 0.4293208420276642,
|
| 1914 |
+
"step": 544
|
| 1915 |
+
},
|
| 1916 |
+
{
|
| 1917 |
+
"epoch": 2.323404255319149,
|
| 1918 |
+
"grad_norm": 0.16749997437000275,
|
| 1919 |
+
"learning_rate": 2.52993999002208e-05,
|
| 1920 |
+
"loss": 0.317562460899353,
|
| 1921 |
+
"step": 546
|
| 1922 |
+
},
|
| 1923 |
+
{
|
| 1924 |
+
"epoch": 2.331914893617021,
|
| 1925 |
+
"grad_norm": 0.5269374847412109,
|
| 1926 |
+
"learning_rate": 2.501764447781743e-05,
|
| 1927 |
+
"loss": 0.7331305742263794,
|
| 1928 |
+
"step": 548
|
| 1929 |
+
},
|
| 1930 |
+
{
|
| 1931 |
+
"epoch": 2.3404255319148937,
|
| 1932 |
+
"grad_norm": 0.5243010520935059,
|
| 1933 |
+
"learning_rate": 2.4729722954627106e-05,
|
| 1934 |
+
"loss": 0.4494149088859558,
|
| 1935 |
+
"step": 550
|
| 1936 |
+
},
|
| 1937 |
+
{
|
| 1938 |
+
"epoch": 2.348936170212766,
|
| 1939 |
+
"grad_norm": 0.16172371804714203,
|
| 1940 |
+
"learning_rate": 2.4435863888114814e-05,
|
| 1941 |
+
"loss": 0.5373607873916626,
|
| 1942 |
+
"step": 552
|
| 1943 |
+
},
|
| 1944 |
+
{
|
| 1945 |
+
"epoch": 2.3574468085106384,
|
| 1946 |
+
"grad_norm": 0.13132323324680328,
|
| 1947 |
+
"learning_rate": 2.413630054907798e-05,
|
| 1948 |
+
"loss": 0.7187270522117615,
|
| 1949 |
+
"step": 554
|
| 1950 |
+
},
|
| 1951 |
+
{
|
| 1952 |
+
"epoch": 2.3659574468085105,
|
| 1953 |
+
"grad_norm": 0.16762499511241913,
|
| 1954 |
+
"learning_rate": 2.383127073647171e-05,
|
| 1955 |
+
"loss": 0.5384994745254517,
|
| 1956 |
+
"step": 556
|
| 1957 |
+
},
|
| 1958 |
+
{
|
| 1959 |
+
"epoch": 2.374468085106383,
|
| 1960 |
+
"grad_norm": 0.19120921194553375,
|
| 1961 |
+
"learning_rate": 2.3521016588639598e-05,
|
| 1962 |
+
"loss": 0.5281667709350586,
|
| 1963 |
+
"step": 558
|
| 1964 |
+
},
|
| 1965 |
+
{
|
| 1966 |
+
"epoch": 2.382978723404255,
|
| 1967 |
+
"grad_norm": 0.12356223165988922,
|
| 1968 |
+
"learning_rate": 2.32057843910998e-05,
|
| 1969 |
+
"loss": 0.47801631689071655,
|
| 1970 |
+
"step": 560
|
| 1971 |
+
},
|
| 1972 |
+
{
|
| 1973 |
+
"epoch": 2.391489361702128,
|
| 1974 |
+
"grad_norm": 0.11622758209705353,
|
| 1975 |
+
"learning_rate": 2.2885824381039024e-05,
|
| 1976 |
+
"loss": 0.5657482147216797,
|
| 1977 |
+
"step": 562
|
| 1978 |
+
},
|
| 1979 |
+
{
|
| 1980 |
+
"epoch": 2.4,
|
| 1981 |
+
"grad_norm": 0.18093258142471313,
|
| 1982 |
+
"learning_rate": 2.2561390548669552e-05,
|
| 1983 |
+
"loss": 0.43637847900390625,
|
| 1984 |
+
"step": 564
|
| 1985 |
+
},
|
| 1986 |
+
{
|
| 1987 |
+
"epoch": 2.4085106382978725,
|
| 1988 |
+
"grad_norm": 0.1480812132358551,
|
| 1989 |
+
"learning_rate": 2.2232740435607067e-05,
|
| 1990 |
+
"loss": 0.4490112364292145,
|
| 1991 |
+
"step": 566
|
| 1992 |
+
},
|
| 1993 |
+
{
|
| 1994 |
+
"epoch": 2.4170212765957446,
|
| 1995 |
+
"grad_norm": 0.3488391935825348,
|
| 1996 |
+
"learning_rate": 2.1900134930429403e-05,
|
| 1997 |
+
"loss": 0.5125418901443481,
|
| 1998 |
+
"step": 568
|
| 1999 |
+
},
|
| 2000 |
+
{
|
| 2001 |
+
"epoch": 2.425531914893617,
|
| 2002 |
+
"grad_norm": 0.20989084243774414,
|
| 2003 |
+
"learning_rate": 2.1563838061578264e-05,
|
| 2004 |
+
"loss": 0.4947648346424103,
|
| 2005 |
+
"step": 570
|
| 2006 |
+
},
|
| 2007 |
+
{
|
| 2008 |
+
"epoch": 2.4340425531914893,
|
| 2009 |
+
"grad_norm": 0.1344413161277771,
|
| 2010 |
+
"learning_rate": 2.122411678776855e-05,
|
| 2011 |
+
"loss": 0.40764039754867554,
|
| 2012 |
+
"step": 572
|
| 2013 |
+
},
|
| 2014 |
+
{
|
| 2015 |
+
"epoch": 2.4425531914893615,
|
| 2016 |
+
"grad_norm": 0.5959489345550537,
|
| 2017 |
+
"learning_rate": 2.0881240786071588e-05,
|
| 2018 |
+
"loss": 0.402820885181427,
|
| 2019 |
+
"step": 574
|
| 2020 |
+
},
|
| 2021 |
+
{
|
| 2022 |
+
"epoch": 2.451063829787234,
|
| 2023 |
+
"grad_norm": 0.17302733659744263,
|
| 2024 |
+
"learning_rate": 2.0535482237840398e-05,
|
| 2025 |
+
"loss": 0.5862278342247009,
|
| 2026 |
+
"step": 576
|
| 2027 |
+
},
|
| 2028 |
+
{
|
| 2029 |
+
"epoch": 2.4595744680851066,
|
| 2030 |
+
"grad_norm": 0.18545182049274445,
|
| 2031 |
+
"learning_rate": 2.018711561264715e-05,
|
| 2032 |
+
"loss": 0.5663528442382812,
|
| 2033 |
+
"step": 578
|
| 2034 |
+
},
|
| 2035 |
+
{
|
| 2036 |
+
"epoch": 2.4680851063829787,
|
| 2037 |
+
"grad_norm": 0.1751205325126648,
|
| 2038 |
+
"learning_rate": 1.9836417450403978e-05,
|
| 2039 |
+
"loss": 0.3827342689037323,
|
| 2040 |
+
"step": 580
|
| 2041 |
+
},
|
| 2042 |
+
{
|
| 2043 |
+
"epoch": 2.476595744680851,
|
| 2044 |
+
"grad_norm": 0.25646570324897766,
|
| 2045 |
+
"learning_rate": 1.948366614184062e-05,
|
| 2046 |
+
"loss": 0.5597113966941833,
|
| 2047 |
+
"step": 582
|
| 2048 |
+
},
|
| 2049 |
+
{
|
| 2050 |
+
"epoch": 2.4851063829787234,
|
| 2051 |
+
"grad_norm": 0.1912815123796463,
|
| 2052 |
+
"learning_rate": 1.9129141707512514e-05,
|
| 2053 |
+
"loss": 0.6160271763801575,
|
| 2054 |
+
"step": 584
|
| 2055 |
+
},
|
| 2056 |
+
{
|
| 2057 |
+
"epoch": 2.4936170212765956,
|
| 2058 |
+
"grad_norm": 0.3505466878414154,
|
| 2059 |
+
"learning_rate": 1.877312557551536e-05,
|
| 2060 |
+
"loss": 0.5502729415893555,
|
| 2061 |
+
"step": 586
|
| 2062 |
+
},
|
| 2063 |
+
{
|
| 2064 |
+
"epoch": 2.502127659574468,
|
| 2065 |
+
"grad_norm": 0.17846280336380005,
|
| 2066 |
+
"learning_rate": 1.841590035808227e-05,
|
| 2067 |
+
"loss": 0.7185637354850769,
|
| 2068 |
+
"step": 588
|
| 2069 |
+
},
|
| 2070 |
+
{
|
| 2071 |
+
"epoch": 2.5106382978723403,
|
| 2072 |
+
"grad_norm": 0.15607386827468872,
|
| 2073 |
+
"learning_rate": 1.8057749627240822e-05,
|
| 2074 |
+
"loss": 0.6139054894447327,
|
| 2075 |
+
"step": 590
|
| 2076 |
+
},
|
| 2077 |
+
{
|
| 2078 |
+
"epoch": 2.519148936170213,
|
| 2079 |
+
"grad_norm": 0.13966147601604462,
|
| 2080 |
+
"learning_rate": 1.7698957689708436e-05,
|
| 2081 |
+
"loss": 0.7389253973960876,
|
| 2082 |
+
"step": 592
|
| 2083 |
+
},
|
| 2084 |
+
{
|
| 2085 |
+
"epoch": 2.527659574468085,
|
| 2086 |
+
"grad_norm": 0.14507059752941132,
|
| 2087 |
+
"learning_rate": 1.7339809361204255e-05,
|
| 2088 |
+
"loss": 0.35956406593322754,
|
| 2089 |
+
"step": 594
|
| 2090 |
+
},
|
| 2091 |
+
{
|
| 2092 |
+
"epoch": 2.5361702127659576,
|
| 2093 |
+
"grad_norm": 0.15395186841487885,
|
| 2094 |
+
"learning_rate": 1.6980589740357287e-05,
|
| 2095 |
+
"loss": 0.5801402926445007,
|
| 2096 |
+
"step": 596
|
| 2097 |
+
},
|
| 2098 |
+
{
|
| 2099 |
+
"epoch": 2.5446808510638297,
|
| 2100 |
+
"grad_norm": 0.13444769382476807,
|
| 2101 |
+
"learning_rate": 1.6621583982389714e-05,
|
| 2102 |
+
"loss": 0.4474773108959198,
|
| 2103 |
+
"step": 598
|
| 2104 |
+
},
|
| 2105 |
+
{
|
| 2106 |
+
"epoch": 2.5531914893617023,
|
| 2107 |
+
"grad_norm": 0.21395254135131836,
|
| 2108 |
+
"learning_rate": 1.626307707275533e-05,
|
| 2109 |
+
"loss": 0.5679066777229309,
|
| 2110 |
+
"step": 600
|
| 2111 |
+
},
|
| 2112 |
+
{
|
| 2113 |
+
"epoch": 2.5617021276595744,
|
| 2114 |
+
"grad_norm": 0.1135779544711113,
|
| 2115 |
+
"learning_rate": 1.59053536009129e-05,
|
| 2116 |
+
"loss": 0.5999655723571777,
|
| 2117 |
+
"step": 602
|
| 2118 |
+
},
|
| 2119 |
+
{
|
| 2120 |
+
"epoch": 2.570212765957447,
|
| 2121 |
+
"grad_norm": 0.11653319001197815,
|
| 2122 |
+
"learning_rate": 1.5548697534413653e-05,
|
| 2123 |
+
"loss": 0.577793300151825,
|
| 2124 |
+
"step": 604
|
| 2125 |
+
},
|
| 2126 |
+
{
|
| 2127 |
+
"epoch": 2.578723404255319,
|
| 2128 |
+
"grad_norm": 0.1222231388092041,
|
| 2129 |
+
"learning_rate": 1.5193391993482573e-05,
|
| 2130 |
+
"loss": 0.6178088188171387,
|
| 2131 |
+
"step": 606
|
| 2132 |
+
},
|
| 2133 |
+
{
|
| 2134 |
+
"epoch": 2.5872340425531917,
|
| 2135 |
+
"grad_norm": 0.1294461488723755,
|
| 2136 |
+
"learning_rate": 1.483971902627239e-05,
|
| 2137 |
+
"loss": 0.2757226824760437,
|
| 2138 |
+
"step": 608
|
| 2139 |
+
},
|
| 2140 |
+
{
|
| 2141 |
+
"epoch": 2.595744680851064,
|
| 2142 |
+
"grad_norm": 0.12525388598442078,
|
| 2143 |
+
"learning_rate": 1.4487959384968272e-05,
|
| 2144 |
+
"loss": 0.5488746762275696,
|
| 2145 |
+
"step": 610
|
| 2146 |
+
},
|
| 2147 |
+
{
|
| 2148 |
+
"epoch": 2.604255319148936,
|
| 2149 |
+
"grad_norm": 0.3998476564884186,
|
| 2150 |
+
"learning_rate": 1.4138392302921813e-05,
|
| 2151 |
+
"loss": 0.6341690421104431,
|
| 2152 |
+
"step": 612
|
| 2153 |
+
},
|
| 2154 |
+
{
|
| 2155 |
+
"epoch": 2.6127659574468085,
|
| 2156 |
+
"grad_norm": 0.1306917667388916,
|
| 2157 |
+
"learning_rate": 1.3791295272990178e-05,
|
| 2158 |
+
"loss": 0.6712806224822998,
|
| 2159 |
+
"step": 614
|
| 2160 |
+
},
|
| 2161 |
+
{
|
| 2162 |
+
"epoch": 2.621276595744681,
|
| 2163 |
+
"grad_norm": 0.08778780698776245,
|
| 2164 |
+
"learning_rate": 1.344694382725719e-05,
|
| 2165 |
+
"loss": 0.45013314485549927,
|
| 2166 |
+
"step": 616
|
| 2167 |
+
},
|
| 2168 |
+
{
|
| 2169 |
+
"epoch": 2.629787234042553,
|
| 2170 |
+
"grad_norm": 0.2586289048194885,
|
| 2171 |
+
"learning_rate": 1.3105611318310828e-05,
|
| 2172 |
+
"loss": 0.6572415828704834,
|
| 2173 |
+
"step": 618
|
| 2174 |
+
},
|
| 2175 |
+
{
|
| 2176 |
+
"epoch": 2.6382978723404253,
|
| 2177 |
+
"grad_norm": 0.10759896785020828,
|
| 2178 |
+
"learning_rate": 1.2767568702250834e-05,
|
| 2179 |
+
"loss": 0.41325774788856506,
|
| 2180 |
+
"step": 620
|
| 2181 |
+
},
|
| 2182 |
+
{
|
| 2183 |
+
"epoch": 2.646808510638298,
|
| 2184 |
+
"grad_norm": 0.21708400547504425,
|
| 2185 |
+
"learning_rate": 1.2433084323598806e-05,
|
| 2186 |
+
"loss": 0.4483058750629425,
|
| 2187 |
+
"step": 622
|
| 2188 |
+
},
|
| 2189 |
+
{
|
| 2190 |
+
"epoch": 2.65531914893617,
|
| 2191 |
+
"grad_norm": 0.17001259326934814,
|
| 2192 |
+
"learning_rate": 1.2102423702281114e-05,
|
| 2193 |
+
"loss": 0.6922531127929688,
|
| 2194 |
+
"step": 624
|
| 2195 |
+
},
|
| 2196 |
+
{
|
| 2197 |
+
"epoch": 2.6638297872340426,
|
| 2198 |
+
"grad_norm": 0.21257923543453217,
|
| 2199 |
+
"learning_rate": 1.1775849322854515e-05,
|
| 2200 |
+
"loss": 0.5280181169509888,
|
| 2201 |
+
"step": 626
|
| 2202 |
+
},
|
| 2203 |
+
{
|
| 2204 |
+
"epoch": 2.6723404255319148,
|
| 2205 |
+
"grad_norm": 0.18666359782218933,
|
| 2206 |
+
"learning_rate": 1.1453620426140796e-05,
|
| 2207 |
+
"loss": 0.5663700699806213,
|
| 2208 |
+
"step": 628
|
| 2209 |
+
},
|
| 2210 |
+
{
|
| 2211 |
+
"epoch": 2.6808510638297873,
|
| 2212 |
+
"grad_norm": 1.1582063436508179,
|
| 2213 |
+
"learning_rate": 1.1135992803436701e-05,
|
| 2214 |
+
"loss": 0.5217815637588501,
|
| 2215 |
+
"step": 630
|
| 2216 |
+
},
|
| 2217 |
+
{
|
| 2218 |
+
"epoch": 2.6893617021276595,
|
| 2219 |
+
"grad_norm": 0.15095171332359314,
|
| 2220 |
+
"learning_rate": 1.0823218593462006e-05,
|
| 2221 |
+
"loss": 0.5002037882804871,
|
| 2222 |
+
"step": 632
|
| 2223 |
+
},
|
| 2224 |
+
{
|
| 2225 |
+
"epoch": 2.697872340425532,
|
| 2226 |
+
"grad_norm": 0.258025199174881,
|
| 2227 |
+
"learning_rate": 1.0515546082207089e-05,
|
| 2228 |
+
"loss": 0.7550774812698364,
|
| 2229 |
+
"step": 634
|
| 2230 |
+
},
|
| 2231 |
+
{
|
| 2232 |
+
"epoch": 2.706382978723404,
|
| 2233 |
+
"grad_norm": 0.2747920751571655,
|
| 2234 |
+
"learning_rate": 1.0213219505839e-05,
|
| 2235 |
+
"loss": 0.7289509773254395,
|
| 2236 |
+
"step": 636
|
| 2237 |
+
},
|
| 2238 |
+
{
|
| 2239 |
+
"epoch": 2.7148936170212767,
|
| 2240 |
+
"grad_norm": 0.10981704294681549,
|
| 2241 |
+
"learning_rate": 9.916478856822011e-06,
|
| 2242 |
+
"loss": 0.4343630075454712,
|
| 2243 |
+
"step": 638
|
| 2244 |
+
},
|
| 2245 |
+
{
|
| 2246 |
+
"epoch": 2.723404255319149,
|
| 2247 |
+
"grad_norm": 0.10845521837472916,
|
| 2248 |
+
"learning_rate": 9.625559693407416e-06,
|
| 2249 |
+
"loss": 0.8249025940895081,
|
| 2250 |
+
"step": 640
|
| 2251 |
+
},
|
| 2252 |
+
{
|
| 2253 |
+
"epoch": 2.731914893617021,
|
| 2254 |
+
"grad_norm": 0.15325450897216797,
|
| 2255 |
+
"learning_rate": 9.34069295264279e-06,
|
| 2256 |
+
"loss": 0.7887688875198364,
|
| 2257 |
+
"step": 642
|
| 2258 |
+
},
|
| 2259 |
+
{
|
| 2260 |
+
"epoch": 2.7404255319148936,
|
| 2261 |
+
"grad_norm": 0.12251801788806915,
|
| 2262 |
+
"learning_rate": 9.062104767049962e-06,
|
| 2263 |
+
"loss": 0.8136211037635803,
|
| 2264 |
+
"step": 644
|
| 2265 |
+
},
|
| 2266 |
+
{
|
| 2267 |
+
"epoch": 2.748936170212766,
|
| 2268 |
+
"grad_norm": 0.12305980175733566,
|
| 2269 |
+
"learning_rate": 8.790016285116773e-06,
|
| 2270 |
+
"loss": 0.3323878347873688,
|
| 2271 |
+
"step": 646
|
| 2272 |
+
},
|
| 2273 |
+
{
|
| 2274 |
+
"epoch": 2.7574468085106383,
|
| 2275 |
+
"grad_norm": 0.16256316006183624,
|
| 2276 |
+
"learning_rate": 8.5246434957453e-06,
|
| 2277 |
+
"loss": 0.31487664580345154,
|
| 2278 |
+
"step": 648
|
| 2279 |
+
},
|
| 2280 |
+
{
|
| 2281 |
+
"epoch": 2.7659574468085104,
|
| 2282 |
+
"grad_norm": 0.29724588990211487,
|
| 2283 |
+
"learning_rate": 8.266197056795886e-06,
|
| 2284 |
+
"loss": 0.43204954266548157,
|
| 2285 |
+
"step": 650
|
| 2286 |
+
},
|
| 2287 |
+
{
|
| 2288 |
+
"epoch": 2.774468085106383,
|
| 2289 |
+
"grad_norm": 0.21929951012134552,
|
| 2290 |
+
"learning_rate": 8.014882127862926e-06,
|
| 2291 |
+
"loss": 0.562320351600647,
|
| 2292 |
+
"step": 652
|
| 2293 |
+
},
|
| 2294 |
+
{
|
| 2295 |
+
"epoch": 2.7829787234042556,
|
| 2296 |
+
"grad_norm": 0.11705265194177628,
|
| 2297 |
+
"learning_rate": 7.77089820741542e-06,
|
| 2298 |
+
"loss": 0.5608207583427429,
|
| 2299 |
+
"step": 654
|
| 2300 |
+
},
|
| 2301 |
+
{
|
| 2302 |
+
"epoch": 2.7914893617021277,
|
| 2303 |
+
"grad_norm": 0.14389561116695404,
|
| 2304 |
+
"learning_rate": 7.534438974431356e-06,
|
| 2305 |
+
"loss": 0.44889208674430847,
|
| 2306 |
+
"step": 656
|
| 2307 |
+
},
|
| 2308 |
+
{
|
| 2309 |
+
"epoch": 2.8,
|
| 2310 |
+
"grad_norm": 0.10500220209360123,
|
| 2311 |
+
"learning_rate": 7.305692134651748e-06,
|
| 2312 |
+
"loss": 0.5233709216117859,
|
| 2313 |
+
"step": 658
|
| 2314 |
+
},
|
| 2315 |
+
{
|
| 2316 |
+
"epoch": 2.8085106382978724,
|
| 2317 |
+
"grad_norm": 0.11123310774564743,
|
| 2318 |
+
"learning_rate": 7.0848392715763e-06,
|
| 2319 |
+
"loss": 0.41444164514541626,
|
| 2320 |
+
"step": 660
|
| 2321 |
+
},
|
| 2322 |
+
{
|
| 2323 |
+
"epoch": 2.8170212765957445,
|
| 2324 |
+
"grad_norm": 0.14375989139080048,
|
| 2325 |
+
"learning_rate": 6.872055702319048e-06,
|
| 2326 |
+
"loss": 0.2203376591205597,
|
| 2327 |
+
"step": 662
|
| 2328 |
+
},
|
| 2329 |
+
{
|
| 2330 |
+
"epoch": 2.825531914893617,
|
| 2331 |
+
"grad_norm": 2.4339959621429443,
|
| 2332 |
+
"learning_rate": 6.66751033843842e-06,
|
| 2333 |
+
"loss": 0.4634183943271637,
|
| 2334 |
+
"step": 664
|
| 2335 |
+
},
|
| 2336 |
+
{
|
| 2337 |
+
"epoch": 2.8340425531914892,
|
| 2338 |
+
"grad_norm": 0.16652415692806244,
|
| 2339 |
+
"learning_rate": 6.471365551852014e-06,
|
| 2340 |
+
"loss": 0.36938074231147766,
|
| 2341 |
+
"step": 666
|
| 2342 |
+
},
|
| 2343 |
+
{
|
| 2344 |
+
"epoch": 2.842553191489362,
|
| 2345 |
+
"grad_norm": 0.13066215813159943,
|
| 2346 |
+
"learning_rate": 6.283777045942801e-06,
|
| 2347 |
+
"loss": 0.5424007177352905,
|
| 2348 |
+
"step": 668
|
| 2349 |
+
},
|
| 2350 |
+
{
|
| 2351 |
+
"epoch": 2.851063829787234,
|
| 2352 |
+
"grad_norm": 0.1719757467508316,
|
| 2353 |
+
"learning_rate": 6.104893731958872e-06,
|
| 2354 |
+
"loss": 0.7605326175689697,
|
| 2355 |
+
"step": 670
|
| 2356 |
+
},
|
| 2357 |
+
{
|
| 2358 |
+
"epoch": 2.8595744680851065,
|
| 2359 |
+
"grad_norm": 0.15954963862895966,
|
| 2360 |
+
"learning_rate": 5.934857610804912e-06,
|
| 2361 |
+
"loss": 0.4137082099914551,
|
| 2362 |
+
"step": 672
|
| 2363 |
+
},
|
| 2364 |
+
{
|
| 2365 |
+
"epoch": 2.8680851063829786,
|
| 2366 |
+
"grad_norm": 0.182533860206604,
|
| 2367 |
+
"learning_rate": 5.773803660319231e-06,
|
| 2368 |
+
"loss": 0.5575495362281799,
|
| 2369 |
+
"step": 674
|
| 2370 |
+
},
|
| 2371 |
+
{
|
| 2372 |
+
"epoch": 2.876595744680851,
|
| 2373 |
+
"grad_norm": 0.13435368239879608,
|
| 2374 |
+
"learning_rate": 5.6218597281258834e-06,
|
| 2375 |
+
"loss": 0.3841201961040497,
|
| 2376 |
+
"step": 676
|
| 2377 |
+
},
|
| 2378 |
+
{
|
| 2379 |
+
"epoch": 2.8851063829787233,
|
| 2380 |
+
"grad_norm": 0.09731018543243408,
|
| 2381 |
+
"learning_rate": 5.479146430146783e-06,
|
| 2382 |
+
"loss": 0.3572618365287781,
|
| 2383 |
+
"step": 678
|
| 2384 |
+
},
|
| 2385 |
+
{
|
| 2386 |
+
"epoch": 2.8936170212765955,
|
| 2387 |
+
"grad_norm": 0.12130768597126007,
|
| 2388 |
+
"learning_rate": 5.3457770548545805e-06,
|
| 2389 |
+
"loss": 0.4105460047721863,
|
| 2390 |
+
"step": 680
|
| 2391 |
+
},
|
| 2392 |
+
{
|
| 2393 |
+
"epoch": 2.902127659574468,
|
| 2394 |
+
"grad_norm": 0.4408089518547058,
|
| 2395 |
+
"learning_rate": 5.22185747334215e-06,
|
| 2396 |
+
"loss": 0.5799260139465332,
|
| 2397 |
+
"step": 682
|
| 2398 |
+
},
|
| 2399 |
+
{
|
| 2400 |
+
"epoch": 2.9106382978723406,
|
| 2401 |
+
"grad_norm": 0.12350846827030182,
|
| 2402 |
+
"learning_rate": 5.107486055280145e-06,
|
| 2403 |
+
"loss": 0.4056027829647064,
|
| 2404 |
+
"step": 684
|
| 2405 |
+
},
|
| 2406 |
+
{
|
| 2407 |
+
"epoch": 2.9191489361702128,
|
| 2408 |
+
"grad_norm": 3.8421390056610107,
|
| 2409 |
+
"learning_rate": 5.002753590829352e-06,
|
| 2410 |
+
"loss": 0.23622764647006989,
|
| 2411 |
+
"step": 686
|
| 2412 |
+
},
|
| 2413 |
+
{
|
| 2414 |
+
"epoch": 2.927659574468085,
|
| 2415 |
+
"grad_norm": 0.163557767868042,
|
| 2416 |
+
"learning_rate": 4.9077432185697e-06,
|
| 2417 |
+
"loss": 0.33212676644325256,
|
| 2418 |
+
"step": 688
|
| 2419 |
+
},
|
| 2420 |
+
{
|
| 2421 |
+
"epoch": 2.9361702127659575,
|
| 2422 |
+
"grad_norm": 0.143082395195961,
|
| 2423 |
+
"learning_rate": 4.822530359503391e-06,
|
| 2424 |
+
"loss": 0.7329955697059631,
|
| 2425 |
+
"step": 690
|
| 2426 |
+
},
|
| 2427 |
+
{
|
| 2428 |
+
"epoch": 2.94468085106383,
|
| 2429 |
+
"grad_norm": 0.2611314058303833,
|
| 2430 |
+
"learning_rate": 4.747182657184251e-06,
|
| 2431 |
+
"loss": 0.43970412015914917,
|
| 2432 |
+
"step": 692
|
| 2433 |
+
},
|
| 2434 |
+
{
|
| 2435 |
+
"epoch": 2.953191489361702,
|
| 2436 |
+
"grad_norm": 0.12711837887763977,
|
| 2437 |
+
"learning_rate": 4.681759924021033e-06,
|
| 2438 |
+
"loss": 0.642443835735321,
|
| 2439 |
+
"step": 694
|
| 2440 |
+
},
|
| 2441 |
+
{
|
| 2442 |
+
"epoch": 2.9617021276595743,
|
| 2443 |
+
"grad_norm": 0.30099472403526306,
|
| 2444 |
+
"learning_rate": 4.626314093797213e-06,
|
| 2445 |
+
"loss": 0.35701537132263184,
|
| 2446 |
+
"step": 696
|
| 2447 |
+
},
|
| 2448 |
+
{
|
| 2449 |
+
"epoch": 2.970212765957447,
|
| 2450 |
+
"grad_norm": 0.13871702551841736,
|
| 2451 |
+
"learning_rate": 4.580889180444988e-06,
|
| 2452 |
+
"loss": 0.48086193203926086,
|
| 2453 |
+
"step": 698
|
| 2454 |
+
},
|
| 2455 |
+
{
|
| 2456 |
+
"epoch": 2.978723404255319,
|
| 2457 |
+
"grad_norm": 0.1269788146018982,
|
| 2458 |
+
"learning_rate": 4.5455212431061985e-06,
|
| 2459 |
+
"loss": 0.4837539792060852,
|
| 2460 |
+
"step": 700
|
| 2461 |
+
},
|
| 2462 |
+
{
|
| 2463 |
+
"epoch": 2.9872340425531916,
|
| 2464 |
+
"grad_norm": 0.31502285599708557,
|
| 2465 |
+
"learning_rate": 4.520238357507899e-06,
|
| 2466 |
+
"loss": 0.5840956568717957,
|
| 2467 |
+
"step": 702
|
| 2468 |
+
},
|
| 2469 |
+
{
|
| 2470 |
+
"epoch": 2.9957446808510637,
|
| 2471 |
+
"grad_norm": 0.1223224624991417,
|
| 2472 |
+
"learning_rate": 4.505060593675342e-06,
|
| 2473 |
+
"loss": 0.34119483828544617,
|
| 2474 |
+
"step": 704
|
| 2475 |
+
},
|
| 2476 |
+
{
|
| 2477 |
+
"epoch": 3.0,
|
| 2478 |
+
"step": 705,
|
| 2479 |
+
"total_flos": 2.502111532985352e+18,
|
| 2480 |
+
"train_loss": 0.8120331417161523,
|
| 2481 |
+
"train_runtime": 7663.1544,
|
| 2482 |
+
"train_samples_per_second": 5.888,
|
| 2483 |
+
"train_steps_per_second": 0.092
|
| 2484 |
+
}
|
| 2485 |
+
],
|
| 2486 |
+
"logging_steps": 2,
|
| 2487 |
+
"max_steps": 705,
|
| 2488 |
+
"num_input_tokens_seen": 0,
|
| 2489 |
+
"num_train_epochs": 3,
|
| 2490 |
+
"save_steps": 99999,
|
| 2491 |
+
"stateful_callbacks": {
|
| 2492 |
+
"TrainerControl": {
|
| 2493 |
+
"args": {
|
| 2494 |
+
"should_epoch_stop": false,
|
| 2495 |
+
"should_evaluate": false,
|
| 2496 |
+
"should_log": false,
|
| 2497 |
+
"should_save": true,
|
| 2498 |
+
"should_training_stop": true
|
| 2499 |
+
},
|
| 2500 |
+
"attributes": {}
|
| 2501 |
+
}
|
| 2502 |
+
},
|
| 2503 |
+
"total_flos": 2.502111532985352e+18,
|
| 2504 |
+
"train_batch_size": 2,
|
| 2505 |
+
"trial_name": null,
|
| 2506 |
+
"trial_params": null
|
| 2507 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e767b048628318f19dd4cf6d4d277e3cbc3c815321b52f9ef82922f3853cacd5
|
| 3 |
+
size 5649
|
training_loss.png
ADDED
|