Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +72 -0
- added_tokens.json +28 -0
- all_results.json +12 -0
- chat_template.jinja +120 -0
- config.json +67 -0
- eval_results.json +7 -0
- generation_config.json +13 -0
- merges.txt +0 -0
- model-00001-of-00004.safetensors +3 -0
- model-00002-of-00004.safetensors +3 -0
- model-00003-of-00004.safetensors +3 -0
- model-00004-of-00004.safetensors +3 -0
- model.safetensors.index.json +758 -0
- preprocessor_config.json +39 -0
- runs/Jan20_18-52-58_gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn/events.out.tfevents.1768943156.gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn.1113.0 +3 -0
- runs/Jan20_18-52-58_gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn/events.out.tfevents.1768955825.gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn.1113.1 +3 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +241 -0
- train_results.json +8 -0
- trainer_log.jsonl +370 -0
- trainer_state.json +2633 -0
- training_args.bin +3 -0
- training_eval_loss.png +0 -0
- training_loss.png +0 -0
- video_preprocessor_config.json +41 -0
- vocab.json +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
|
README.md
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
library_name: transformers
|
| 3 |
+
license: other
|
| 4 |
+
base_model: Qwen/Qwen3-VL-8B-Instruct
|
| 5 |
+
tags:
|
| 6 |
+
- llama-factory
|
| 7 |
+
- full
|
| 8 |
+
- generated_from_trainer
|
| 9 |
+
model-index:
|
| 10 |
+
- name: gen_reward_sft
|
| 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 |
+
# gen_reward_sft
|
| 18 |
+
|
| 19 |
+
This model is a fine-tuned version of [Qwen/Qwen3-VL-8B-Instruct](https://huggingface.co/Qwen/Qwen3-VL-8B-Instruct) on the gen_reward_sft dataset.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5180
|
| 22 |
+
|
| 23 |
+
## Model description
|
| 24 |
+
|
| 25 |
+
More information needed
|
| 26 |
+
|
| 27 |
+
## Intended uses & limitations
|
| 28 |
+
|
| 29 |
+
More information needed
|
| 30 |
+
|
| 31 |
+
## Training and evaluation data
|
| 32 |
+
|
| 33 |
+
More information needed
|
| 34 |
+
|
| 35 |
+
## Training procedure
|
| 36 |
+
|
| 37 |
+
### Training hyperparameters
|
| 38 |
+
|
| 39 |
+
The following hyperparameters were used during training:
|
| 40 |
+
- learning_rate: 1e-05
|
| 41 |
+
- train_batch_size: 5
|
| 42 |
+
- eval_batch_size: 2
|
| 43 |
+
- seed: 42
|
| 44 |
+
- distributed_type: multi-GPU
|
| 45 |
+
- num_devices: 8
|
| 46 |
+
- gradient_accumulation_steps: 2
|
| 47 |
+
- total_train_batch_size: 80
|
| 48 |
+
- total_eval_batch_size: 16
|
| 49 |
+
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 50 |
+
- lr_scheduler_type: cosine
|
| 51 |
+
- lr_scheduler_warmup_ratio: 0.1
|
| 52 |
+
- num_epochs: 1.0
|
| 53 |
+
|
| 54 |
+
### Training results
|
| 55 |
+
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss |
|
| 57 |
+
|:-------------:|:------:|:----:|:---------------:|
|
| 58 |
+
| 0.6131 | 0.1380 | 500 | 0.6089 |
|
| 59 |
+
| 0.5714 | 0.2760 | 1000 | 0.5768 |
|
| 60 |
+
| 0.5524 | 0.4140 | 1500 | 0.5562 |
|
| 61 |
+
| 0.537 | 0.5520 | 2000 | 0.5407 |
|
| 62 |
+
| 0.5282 | 0.6899 | 2500 | 0.5283 |
|
| 63 |
+
| 0.5155 | 0.8279 | 3000 | 0.5207 |
|
| 64 |
+
| 0.5106 | 0.9659 | 3500 | 0.5181 |
|
| 65 |
+
|
| 66 |
+
|
| 67 |
+
### Framework versions
|
| 68 |
+
|
| 69 |
+
- Transformers 4.57.3
|
| 70 |
+
- Pytorch 2.7.1+cu128
|
| 71 |
+
- Datasets 4.0.0
|
| 72 |
+
- Tokenizers 0.22.2
|
added_tokens.json
ADDED
|
@@ -0,0 +1,28 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</think>": 151668,
|
| 3 |
+
"</tool_call>": 151658,
|
| 4 |
+
"</tool_response>": 151666,
|
| 5 |
+
"<think>": 151667,
|
| 6 |
+
"<tool_call>": 151657,
|
| 7 |
+
"<tool_response>": 151665,
|
| 8 |
+
"<|box_end|>": 151649,
|
| 9 |
+
"<|box_start|>": 151648,
|
| 10 |
+
"<|endoftext|>": 151643,
|
| 11 |
+
"<|file_sep|>": 151664,
|
| 12 |
+
"<|fim_middle|>": 151660,
|
| 13 |
+
"<|fim_pad|>": 151662,
|
| 14 |
+
"<|fim_prefix|>": 151659,
|
| 15 |
+
"<|fim_suffix|>": 151661,
|
| 16 |
+
"<|im_end|>": 151645,
|
| 17 |
+
"<|im_start|>": 151644,
|
| 18 |
+
"<|image_pad|>": 151655,
|
| 19 |
+
"<|object_ref_end|>": 151647,
|
| 20 |
+
"<|object_ref_start|>": 151646,
|
| 21 |
+
"<|quad_end|>": 151651,
|
| 22 |
+
"<|quad_start|>": 151650,
|
| 23 |
+
"<|repo_name|>": 151663,
|
| 24 |
+
"<|video_pad|>": 151656,
|
| 25 |
+
"<|vision_end|>": 151653,
|
| 26 |
+
"<|vision_pad|>": 151654,
|
| 27 |
+
"<|vision_start|>": 151652
|
| 28 |
+
}
|
all_results.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.5180304050445557,
|
| 4 |
+
"eval_runtime": 49.912,
|
| 5 |
+
"eval_samples_per_second": 58.663,
|
| 6 |
+
"eval_steps_per_second": 3.666,
|
| 7 |
+
"total_flos": 1884305306419200.0,
|
| 8 |
+
"train_loss": 0.5639046454929622,
|
| 9 |
+
"train_runtime": 12600.7671,
|
| 10 |
+
"train_samples_per_second": 23.004,
|
| 11 |
+
"train_steps_per_second": 0.288
|
| 12 |
+
}
|
chat_template.jinja
ADDED
|
@@ -0,0 +1,120 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{%- if tools %}
|
| 2 |
+
{{- '<|im_start|>system\n' }}
|
| 3 |
+
{%- if messages[0].role == 'system' %}
|
| 4 |
+
{%- if messages[0].content is string %}
|
| 5 |
+
{{- messages[0].content }}
|
| 6 |
+
{%- else %}
|
| 7 |
+
{%- for content in messages[0].content %}
|
| 8 |
+
{%- if 'text' in content %}
|
| 9 |
+
{{- content.text }}
|
| 10 |
+
{%- endif %}
|
| 11 |
+
{%- endfor %}
|
| 12 |
+
{%- endif %}
|
| 13 |
+
{{- '\n\n' }}
|
| 14 |
+
{%- endif %}
|
| 15 |
+
{{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
|
| 16 |
+
{%- for tool in tools %}
|
| 17 |
+
{{- "\n" }}
|
| 18 |
+
{{- tool | tojson }}
|
| 19 |
+
{%- endfor %}
|
| 20 |
+
{{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
|
| 21 |
+
{%- else %}
|
| 22 |
+
{%- if messages[0].role == 'system' %}
|
| 23 |
+
{{- '<|im_start|>system\n' }}
|
| 24 |
+
{%- if messages[0].content is string %}
|
| 25 |
+
{{- messages[0].content }}
|
| 26 |
+
{%- else %}
|
| 27 |
+
{%- for content in messages[0].content %}
|
| 28 |
+
{%- if 'text' in content %}
|
| 29 |
+
{{- content.text }}
|
| 30 |
+
{%- endif %}
|
| 31 |
+
{%- endfor %}
|
| 32 |
+
{%- endif %}
|
| 33 |
+
{{- '<|im_end|>\n' }}
|
| 34 |
+
{%- endif %}
|
| 35 |
+
{%- endif %}
|
| 36 |
+
{%- set image_count = namespace(value=0) %}
|
| 37 |
+
{%- set video_count = namespace(value=0) %}
|
| 38 |
+
{%- for message in messages %}
|
| 39 |
+
{%- if message.role == "user" %}
|
| 40 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 41 |
+
{%- if message.content is string %}
|
| 42 |
+
{{- message.content }}
|
| 43 |
+
{%- else %}
|
| 44 |
+
{%- for content in message.content %}
|
| 45 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 46 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 47 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 48 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 49 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 50 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 51 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 52 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 53 |
+
{%- elif 'text' in content %}
|
| 54 |
+
{{- content.text }}
|
| 55 |
+
{%- endif %}
|
| 56 |
+
{%- endfor %}
|
| 57 |
+
{%- endif %}
|
| 58 |
+
{{- '<|im_end|>\n' }}
|
| 59 |
+
{%- elif message.role == "assistant" %}
|
| 60 |
+
{{- '<|im_start|>' + message.role + '\n' }}
|
| 61 |
+
{%- if message.content is string %}
|
| 62 |
+
{{- message.content }}
|
| 63 |
+
{%- else %}
|
| 64 |
+
{%- for content_item in message.content %}
|
| 65 |
+
{%- if 'text' in content_item %}
|
| 66 |
+
{{- content_item.text }}
|
| 67 |
+
{%- endif %}
|
| 68 |
+
{%- endfor %}
|
| 69 |
+
{%- endif %}
|
| 70 |
+
{%- if message.tool_calls %}
|
| 71 |
+
{%- for tool_call in message.tool_calls %}
|
| 72 |
+
{%- if (loop.first and message.content) or (not loop.first) %}
|
| 73 |
+
{{- '\n' }}
|
| 74 |
+
{%- endif %}
|
| 75 |
+
{%- if tool_call.function %}
|
| 76 |
+
{%- set tool_call = tool_call.function %}
|
| 77 |
+
{%- endif %}
|
| 78 |
+
{{- '<tool_call>\n{"name": "' }}
|
| 79 |
+
{{- tool_call.name }}
|
| 80 |
+
{{- '", "arguments": ' }}
|
| 81 |
+
{%- if tool_call.arguments is string %}
|
| 82 |
+
{{- tool_call.arguments }}
|
| 83 |
+
{%- else %}
|
| 84 |
+
{{- tool_call.arguments | tojson }}
|
| 85 |
+
{%- endif %}
|
| 86 |
+
{{- '}\n</tool_call>' }}
|
| 87 |
+
{%- endfor %}
|
| 88 |
+
{%- endif %}
|
| 89 |
+
{{- '<|im_end|>\n' }}
|
| 90 |
+
{%- elif message.role == "tool" %}
|
| 91 |
+
{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
|
| 92 |
+
{{- '<|im_start|>user' }}
|
| 93 |
+
{%- endif %}
|
| 94 |
+
{{- '\n<tool_response>\n' }}
|
| 95 |
+
{%- if message.content is string %}
|
| 96 |
+
{{- message.content }}
|
| 97 |
+
{%- else %}
|
| 98 |
+
{%- for content in message.content %}
|
| 99 |
+
{%- if content.type == 'image' or 'image' in content or 'image_url' in content %}
|
| 100 |
+
{%- set image_count.value = image_count.value + 1 %}
|
| 101 |
+
{%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
|
| 102 |
+
<|vision_start|><|image_pad|><|vision_end|>
|
| 103 |
+
{%- elif content.type == 'video' or 'video' in content %}
|
| 104 |
+
{%- set video_count.value = video_count.value + 1 %}
|
| 105 |
+
{%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
|
| 106 |
+
<|vision_start|><|video_pad|><|vision_end|>
|
| 107 |
+
{%- elif 'text' in content %}
|
| 108 |
+
{{- content.text }}
|
| 109 |
+
{%- endif %}
|
| 110 |
+
{%- endfor %}
|
| 111 |
+
{%- endif %}
|
| 112 |
+
{{- '\n</tool_response>' }}
|
| 113 |
+
{%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
|
| 114 |
+
{{- '<|im_end|>\n' }}
|
| 115 |
+
{%- endif %}
|
| 116 |
+
{%- endif %}
|
| 117 |
+
{%- endfor %}
|
| 118 |
+
{%- if add_generation_prompt %}
|
| 119 |
+
{{- '<|im_start|>assistant\n' }}
|
| 120 |
+
{%- endif %}
|
config.json
ADDED
|
@@ -0,0 +1,67 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"architectures": [
|
| 3 |
+
"Qwen3VLForConditionalGeneration"
|
| 4 |
+
],
|
| 5 |
+
"dtype": "bfloat16",
|
| 6 |
+
"eos_token_id": 151645,
|
| 7 |
+
"hidden_size": 4096,
|
| 8 |
+
"image_token_id": 151655,
|
| 9 |
+
"model_type": "qwen3_vl",
|
| 10 |
+
"pad_token_id": 151643,
|
| 11 |
+
"text_config": {
|
| 12 |
+
"attention_bias": false,
|
| 13 |
+
"attention_dropout": 0.0,
|
| 14 |
+
"bos_token_id": 151643,
|
| 15 |
+
"dtype": "bfloat16",
|
| 16 |
+
"eos_token_id": 151645,
|
| 17 |
+
"head_dim": 128,
|
| 18 |
+
"hidden_act": "silu",
|
| 19 |
+
"hidden_size": 4096,
|
| 20 |
+
"initializer_range": 0.02,
|
| 21 |
+
"intermediate_size": 12288,
|
| 22 |
+
"max_position_embeddings": 262144,
|
| 23 |
+
"model_type": "qwen3_vl_text",
|
| 24 |
+
"num_attention_heads": 32,
|
| 25 |
+
"num_hidden_layers": 36,
|
| 26 |
+
"num_key_value_heads": 8,
|
| 27 |
+
"rms_norm_eps": 1e-06,
|
| 28 |
+
"rope_scaling": {
|
| 29 |
+
"mrope_interleaved": true,
|
| 30 |
+
"mrope_section": [
|
| 31 |
+
24,
|
| 32 |
+
20,
|
| 33 |
+
20
|
| 34 |
+
],
|
| 35 |
+
"rope_type": "default"
|
| 36 |
+
},
|
| 37 |
+
"rope_theta": 5000000,
|
| 38 |
+
"use_cache": false,
|
| 39 |
+
"vocab_size": 151936
|
| 40 |
+
},
|
| 41 |
+
"tie_word_embeddings": false,
|
| 42 |
+
"transformers_version": "4.57.3",
|
| 43 |
+
"use_cache": false,
|
| 44 |
+
"video_token_id": 151656,
|
| 45 |
+
"vision_config": {
|
| 46 |
+
"deepstack_visual_indexes": [
|
| 47 |
+
8,
|
| 48 |
+
16,
|
| 49 |
+
24
|
| 50 |
+
],
|
| 51 |
+
"depth": 27,
|
| 52 |
+
"hidden_act": "gelu_pytorch_tanh",
|
| 53 |
+
"hidden_size": 1152,
|
| 54 |
+
"in_channels": 3,
|
| 55 |
+
"initializer_range": 0.02,
|
| 56 |
+
"intermediate_size": 4304,
|
| 57 |
+
"model_type": "qwen3_vl",
|
| 58 |
+
"num_heads": 16,
|
| 59 |
+
"num_position_embeddings": 2304,
|
| 60 |
+
"out_hidden_size": 4096,
|
| 61 |
+
"patch_size": 16,
|
| 62 |
+
"spatial_merge_size": 2,
|
| 63 |
+
"temporal_patch_size": 2
|
| 64 |
+
},
|
| 65 |
+
"vision_end_token_id": 151653,
|
| 66 |
+
"vision_start_token_id": 151652
|
| 67 |
+
}
|
eval_results.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"eval_loss": 0.5180304050445557,
|
| 4 |
+
"eval_runtime": 49.912,
|
| 5 |
+
"eval_samples_per_second": 58.663,
|
| 6 |
+
"eval_steps_per_second": 3.666
|
| 7 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,13 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_sample": true,
|
| 3 |
+
"eos_token_id": [
|
| 4 |
+
151645,
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"temperature": 0.7,
|
| 10 |
+
"top_k": 20,
|
| 11 |
+
"top_p": 0.8,
|
| 12 |
+
"transformers_version": "4.57.3"
|
| 13 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54be9cc1947ef73b13a25f211baa38048537636a9f99e93b1250d01c8e2ad514
|
| 3 |
+
size 4998056552
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee93089657e9adf73058daffd0135497249e239e50386530892b0481cc3e720f
|
| 3 |
+
size 4915962464
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b35cd9417aae7b42148441b23cd3d47fc602c6c63c245641520038d4c3416425
|
| 3 |
+
size 4915962496
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ee39b524df9c6d1c33f635fd29d72d8ed1547f2e6ba7b3fe84c24f9ffc466501
|
| 3 |
+
size 2704357976
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,758 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_parameters": 770288,
|
| 4 |
+
"total_size": 17534247392
|
| 5 |
+
},
|
| 6 |
+
"weight_map": {
|
| 7 |
+
"lm_head.weight": "model-00004-of-00004.safetensors",
|
| 8 |
+
"model.language_model.embed_tokens.weight": "model-00001-of-00004.safetensors",
|
| 9 |
+
"model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 10 |
+
"model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 11 |
+
"model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 12 |
+
"model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 13 |
+
"model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 14 |
+
"model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 15 |
+
"model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 16 |
+
"model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 17 |
+
"model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 18 |
+
"model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 19 |
+
"model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 20 |
+
"model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 21 |
+
"model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 22 |
+
"model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 23 |
+
"model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 24 |
+
"model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 25 |
+
"model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 26 |
+
"model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 27 |
+
"model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 28 |
+
"model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 29 |
+
"model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 30 |
+
"model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 31 |
+
"model.language_model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 32 |
+
"model.language_model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 33 |
+
"model.language_model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 34 |
+
"model.language_model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 35 |
+
"model.language_model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 36 |
+
"model.language_model.layers.10.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 37 |
+
"model.language_model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 38 |
+
"model.language_model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 39 |
+
"model.language_model.layers.10.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 40 |
+
"model.language_model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 41 |
+
"model.language_model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 42 |
+
"model.language_model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 43 |
+
"model.language_model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 44 |
+
"model.language_model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 45 |
+
"model.language_model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 46 |
+
"model.language_model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 47 |
+
"model.language_model.layers.11.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 48 |
+
"model.language_model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 49 |
+
"model.language_model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 50 |
+
"model.language_model.layers.11.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 51 |
+
"model.language_model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 52 |
+
"model.language_model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 53 |
+
"model.language_model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 54 |
+
"model.language_model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 55 |
+
"model.language_model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 56 |
+
"model.language_model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 57 |
+
"model.language_model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 58 |
+
"model.language_model.layers.12.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 59 |
+
"model.language_model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 60 |
+
"model.language_model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 61 |
+
"model.language_model.layers.12.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 62 |
+
"model.language_model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 63 |
+
"model.language_model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 64 |
+
"model.language_model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 65 |
+
"model.language_model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 66 |
+
"model.language_model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 67 |
+
"model.language_model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 68 |
+
"model.language_model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 69 |
+
"model.language_model.layers.13.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 70 |
+
"model.language_model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 71 |
+
"model.language_model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 72 |
+
"model.language_model.layers.13.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 73 |
+
"model.language_model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 74 |
+
"model.language_model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 75 |
+
"model.language_model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 76 |
+
"model.language_model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 77 |
+
"model.language_model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 78 |
+
"model.language_model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 79 |
+
"model.language_model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 80 |
+
"model.language_model.layers.14.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 81 |
+
"model.language_model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 82 |
+
"model.language_model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 83 |
+
"model.language_model.layers.14.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 84 |
+
"model.language_model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 85 |
+
"model.language_model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 86 |
+
"model.language_model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 87 |
+
"model.language_model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 88 |
+
"model.language_model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 89 |
+
"model.language_model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 90 |
+
"model.language_model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 91 |
+
"model.language_model.layers.15.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 92 |
+
"model.language_model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 93 |
+
"model.language_model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 94 |
+
"model.language_model.layers.15.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 95 |
+
"model.language_model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 96 |
+
"model.language_model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 97 |
+
"model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 98 |
+
"model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 99 |
+
"model.language_model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 100 |
+
"model.language_model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 101 |
+
"model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 102 |
+
"model.language_model.layers.16.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 103 |
+
"model.language_model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 104 |
+
"model.language_model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 105 |
+
"model.language_model.layers.16.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 106 |
+
"model.language_model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 107 |
+
"model.language_model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 108 |
+
"model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 109 |
+
"model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 110 |
+
"model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 111 |
+
"model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 112 |
+
"model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 113 |
+
"model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 114 |
+
"model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 115 |
+
"model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 116 |
+
"model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 117 |
+
"model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 118 |
+
"model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 119 |
+
"model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 120 |
+
"model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 121 |
+
"model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 122 |
+
"model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 123 |
+
"model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 124 |
+
"model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 125 |
+
"model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 126 |
+
"model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 127 |
+
"model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 128 |
+
"model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 129 |
+
"model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 130 |
+
"model.language_model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 131 |
+
"model.language_model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 132 |
+
"model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 133 |
+
"model.language_model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 134 |
+
"model.language_model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 135 |
+
"model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 136 |
+
"model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 137 |
+
"model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 138 |
+
"model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 139 |
+
"model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 140 |
+
"model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 141 |
+
"model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 142 |
+
"model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 143 |
+
"model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 144 |
+
"model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 145 |
+
"model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 146 |
+
"model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 147 |
+
"model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 148 |
+
"model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 149 |
+
"model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 150 |
+
"model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 151 |
+
"model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 152 |
+
"model.language_model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 153 |
+
"model.language_model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 154 |
+
"model.language_model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 155 |
+
"model.language_model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 156 |
+
"model.language_model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 157 |
+
"model.language_model.layers.20.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 158 |
+
"model.language_model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 159 |
+
"model.language_model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 160 |
+
"model.language_model.layers.20.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 161 |
+
"model.language_model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 162 |
+
"model.language_model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 163 |
+
"model.language_model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 164 |
+
"model.language_model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 165 |
+
"model.language_model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 166 |
+
"model.language_model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 167 |
+
"model.language_model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 168 |
+
"model.language_model.layers.21.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 169 |
+
"model.language_model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 170 |
+
"model.language_model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 171 |
+
"model.language_model.layers.21.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 172 |
+
"model.language_model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 173 |
+
"model.language_model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 174 |
+
"model.language_model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 175 |
+
"model.language_model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 176 |
+
"model.language_model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 177 |
+
"model.language_model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 178 |
+
"model.language_model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 179 |
+
"model.language_model.layers.22.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 180 |
+
"model.language_model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 181 |
+
"model.language_model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 182 |
+
"model.language_model.layers.22.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 183 |
+
"model.language_model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 184 |
+
"model.language_model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 185 |
+
"model.language_model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 186 |
+
"model.language_model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 187 |
+
"model.language_model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 188 |
+
"model.language_model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 189 |
+
"model.language_model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 190 |
+
"model.language_model.layers.23.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 191 |
+
"model.language_model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 192 |
+
"model.language_model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 193 |
+
"model.language_model.layers.23.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 194 |
+
"model.language_model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 195 |
+
"model.language_model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 196 |
+
"model.language_model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 197 |
+
"model.language_model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 198 |
+
"model.language_model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 199 |
+
"model.language_model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 200 |
+
"model.language_model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 201 |
+
"model.language_model.layers.24.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 202 |
+
"model.language_model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 203 |
+
"model.language_model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 204 |
+
"model.language_model.layers.24.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 205 |
+
"model.language_model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 206 |
+
"model.language_model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 207 |
+
"model.language_model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 208 |
+
"model.language_model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 209 |
+
"model.language_model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 210 |
+
"model.language_model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 211 |
+
"model.language_model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 212 |
+
"model.language_model.layers.25.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 213 |
+
"model.language_model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 214 |
+
"model.language_model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 215 |
+
"model.language_model.layers.25.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 216 |
+
"model.language_model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 217 |
+
"model.language_model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 218 |
+
"model.language_model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 219 |
+
"model.language_model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 220 |
+
"model.language_model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 221 |
+
"model.language_model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 222 |
+
"model.language_model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 223 |
+
"model.language_model.layers.26.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 224 |
+
"model.language_model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 225 |
+
"model.language_model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 226 |
+
"model.language_model.layers.26.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 227 |
+
"model.language_model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 228 |
+
"model.language_model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 229 |
+
"model.language_model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 230 |
+
"model.language_model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 231 |
+
"model.language_model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 232 |
+
"model.language_model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 233 |
+
"model.language_model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 234 |
+
"model.language_model.layers.27.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 235 |
+
"model.language_model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 236 |
+
"model.language_model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 237 |
+
"model.language_model.layers.27.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 238 |
+
"model.language_model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 239 |
+
"model.language_model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 240 |
+
"model.language_model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 241 |
+
"model.language_model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 242 |
+
"model.language_model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 243 |
+
"model.language_model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 244 |
+
"model.language_model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 245 |
+
"model.language_model.layers.28.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 246 |
+
"model.language_model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 247 |
+
"model.language_model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 248 |
+
"model.language_model.layers.28.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 249 |
+
"model.language_model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 250 |
+
"model.language_model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 251 |
+
"model.language_model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 252 |
+
"model.language_model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 253 |
+
"model.language_model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 254 |
+
"model.language_model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 255 |
+
"model.language_model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 256 |
+
"model.language_model.layers.29.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 257 |
+
"model.language_model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 258 |
+
"model.language_model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 259 |
+
"model.language_model.layers.29.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 260 |
+
"model.language_model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 261 |
+
"model.language_model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 262 |
+
"model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 263 |
+
"model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 264 |
+
"model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 265 |
+
"model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 266 |
+
"model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 267 |
+
"model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 268 |
+
"model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 269 |
+
"model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 270 |
+
"model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 271 |
+
"model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 272 |
+
"model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 273 |
+
"model.language_model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 274 |
+
"model.language_model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 275 |
+
"model.language_model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 276 |
+
"model.language_model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 277 |
+
"model.language_model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 278 |
+
"model.language_model.layers.30.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 279 |
+
"model.language_model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 280 |
+
"model.language_model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 281 |
+
"model.language_model.layers.30.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 282 |
+
"model.language_model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 283 |
+
"model.language_model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 284 |
+
"model.language_model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 285 |
+
"model.language_model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
|
| 286 |
+
"model.language_model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
|
| 287 |
+
"model.language_model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
|
| 288 |
+
"model.language_model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
|
| 289 |
+
"model.language_model.layers.31.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 290 |
+
"model.language_model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 291 |
+
"model.language_model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 292 |
+
"model.language_model.layers.31.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 293 |
+
"model.language_model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 294 |
+
"model.language_model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 295 |
+
"model.language_model.layers.32.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 296 |
+
"model.language_model.layers.32.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 297 |
+
"model.language_model.layers.32.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 298 |
+
"model.language_model.layers.32.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 299 |
+
"model.language_model.layers.32.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 300 |
+
"model.language_model.layers.32.self_attn.k_norm.weight": "model-00003-of-00004.safetensors",
|
| 301 |
+
"model.language_model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
|
| 302 |
+
"model.language_model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
|
| 303 |
+
"model.language_model.layers.32.self_attn.q_norm.weight": "model-00003-of-00004.safetensors",
|
| 304 |
+
"model.language_model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
|
| 305 |
+
"model.language_model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
|
| 306 |
+
"model.language_model.layers.33.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 307 |
+
"model.language_model.layers.33.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 308 |
+
"model.language_model.layers.33.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 309 |
+
"model.language_model.layers.33.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 310 |
+
"model.language_model.layers.33.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 311 |
+
"model.language_model.layers.33.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 312 |
+
"model.language_model.layers.33.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 313 |
+
"model.language_model.layers.33.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 314 |
+
"model.language_model.layers.33.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 315 |
+
"model.language_model.layers.33.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 316 |
+
"model.language_model.layers.33.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 317 |
+
"model.language_model.layers.34.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 318 |
+
"model.language_model.layers.34.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 319 |
+
"model.language_model.layers.34.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 320 |
+
"model.language_model.layers.34.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 321 |
+
"model.language_model.layers.34.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 322 |
+
"model.language_model.layers.34.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 323 |
+
"model.language_model.layers.34.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 324 |
+
"model.language_model.layers.34.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 325 |
+
"model.language_model.layers.34.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 326 |
+
"model.language_model.layers.34.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 327 |
+
"model.language_model.layers.34.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 328 |
+
"model.language_model.layers.35.input_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 329 |
+
"model.language_model.layers.35.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
|
| 330 |
+
"model.language_model.layers.35.mlp.gate_proj.weight": "model-00004-of-00004.safetensors",
|
| 331 |
+
"model.language_model.layers.35.mlp.up_proj.weight": "model-00004-of-00004.safetensors",
|
| 332 |
+
"model.language_model.layers.35.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
|
| 333 |
+
"model.language_model.layers.35.self_attn.k_norm.weight": "model-00004-of-00004.safetensors",
|
| 334 |
+
"model.language_model.layers.35.self_attn.k_proj.weight": "model-00004-of-00004.safetensors",
|
| 335 |
+
"model.language_model.layers.35.self_attn.o_proj.weight": "model-00004-of-00004.safetensors",
|
| 336 |
+
"model.language_model.layers.35.self_attn.q_norm.weight": "model-00004-of-00004.safetensors",
|
| 337 |
+
"model.language_model.layers.35.self_attn.q_proj.weight": "model-00004-of-00004.safetensors",
|
| 338 |
+
"model.language_model.layers.35.self_attn.v_proj.weight": "model-00004-of-00004.safetensors",
|
| 339 |
+
"model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 340 |
+
"model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 341 |
+
"model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 342 |
+
"model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 343 |
+
"model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 344 |
+
"model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 345 |
+
"model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 346 |
+
"model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 347 |
+
"model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 348 |
+
"model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 349 |
+
"model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 350 |
+
"model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 351 |
+
"model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
|
| 352 |
+
"model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 353 |
+
"model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 354 |
+
"model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
|
| 355 |
+
"model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 356 |
+
"model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 357 |
+
"model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 358 |
+
"model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 359 |
+
"model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 360 |
+
"model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 361 |
+
"model.language_model.layers.6.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 362 |
+
"model.language_model.layers.6.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 363 |
+
"model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
|
| 364 |
+
"model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
|
| 365 |
+
"model.language_model.layers.6.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 366 |
+
"model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00004.safetensors",
|
| 367 |
+
"model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
|
| 368 |
+
"model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
|
| 369 |
+
"model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00004.safetensors",
|
| 370 |
+
"model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
|
| 371 |
+
"model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
|
| 372 |
+
"model.language_model.layers.7.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 373 |
+
"model.language_model.layers.7.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 374 |
+
"model.language_model.layers.7.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 375 |
+
"model.language_model.layers.7.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 376 |
+
"model.language_model.layers.7.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 377 |
+
"model.language_model.layers.7.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 378 |
+
"model.language_model.layers.7.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 379 |
+
"model.language_model.layers.7.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 380 |
+
"model.language_model.layers.7.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 381 |
+
"model.language_model.layers.7.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 382 |
+
"model.language_model.layers.7.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 383 |
+
"model.language_model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 384 |
+
"model.language_model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 385 |
+
"model.language_model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 386 |
+
"model.language_model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 387 |
+
"model.language_model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 388 |
+
"model.language_model.layers.8.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 389 |
+
"model.language_model.layers.8.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 390 |
+
"model.language_model.layers.8.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 391 |
+
"model.language_model.layers.8.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 392 |
+
"model.language_model.layers.8.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 393 |
+
"model.language_model.layers.8.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 394 |
+
"model.language_model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 395 |
+
"model.language_model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
|
| 396 |
+
"model.language_model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
|
| 397 |
+
"model.language_model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
|
| 398 |
+
"model.language_model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
|
| 399 |
+
"model.language_model.layers.9.self_attn.k_norm.weight": "model-00002-of-00004.safetensors",
|
| 400 |
+
"model.language_model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
|
| 401 |
+
"model.language_model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
|
| 402 |
+
"model.language_model.layers.9.self_attn.q_norm.weight": "model-00002-of-00004.safetensors",
|
| 403 |
+
"model.language_model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
|
| 404 |
+
"model.language_model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
|
| 405 |
+
"model.language_model.norm.weight": "model-00004-of-00004.safetensors",
|
| 406 |
+
"model.visual.blocks.0.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 407 |
+
"model.visual.blocks.0.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 408 |
+
"model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 409 |
+
"model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 410 |
+
"model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 411 |
+
"model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 412 |
+
"model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 413 |
+
"model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 414 |
+
"model.visual.blocks.0.norm1.bias": "model-00001-of-00004.safetensors",
|
| 415 |
+
"model.visual.blocks.0.norm1.weight": "model-00001-of-00004.safetensors",
|
| 416 |
+
"model.visual.blocks.0.norm2.bias": "model-00001-of-00004.safetensors",
|
| 417 |
+
"model.visual.blocks.0.norm2.weight": "model-00001-of-00004.safetensors",
|
| 418 |
+
"model.visual.blocks.1.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 419 |
+
"model.visual.blocks.1.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 420 |
+
"model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 421 |
+
"model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 422 |
+
"model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 423 |
+
"model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 424 |
+
"model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 425 |
+
"model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 426 |
+
"model.visual.blocks.1.norm1.bias": "model-00001-of-00004.safetensors",
|
| 427 |
+
"model.visual.blocks.1.norm1.weight": "model-00001-of-00004.safetensors",
|
| 428 |
+
"model.visual.blocks.1.norm2.bias": "model-00001-of-00004.safetensors",
|
| 429 |
+
"model.visual.blocks.1.norm2.weight": "model-00001-of-00004.safetensors",
|
| 430 |
+
"model.visual.blocks.10.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 431 |
+
"model.visual.blocks.10.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 432 |
+
"model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 433 |
+
"model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 434 |
+
"model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 435 |
+
"model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 436 |
+
"model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 437 |
+
"model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 438 |
+
"model.visual.blocks.10.norm1.bias": "model-00001-of-00004.safetensors",
|
| 439 |
+
"model.visual.blocks.10.norm1.weight": "model-00001-of-00004.safetensors",
|
| 440 |
+
"model.visual.blocks.10.norm2.bias": "model-00001-of-00004.safetensors",
|
| 441 |
+
"model.visual.blocks.10.norm2.weight": "model-00001-of-00004.safetensors",
|
| 442 |
+
"model.visual.blocks.11.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 443 |
+
"model.visual.blocks.11.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 444 |
+
"model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 445 |
+
"model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 446 |
+
"model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 447 |
+
"model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 448 |
+
"model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 449 |
+
"model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 450 |
+
"model.visual.blocks.11.norm1.bias": "model-00001-of-00004.safetensors",
|
| 451 |
+
"model.visual.blocks.11.norm1.weight": "model-00001-of-00004.safetensors",
|
| 452 |
+
"model.visual.blocks.11.norm2.bias": "model-00001-of-00004.safetensors",
|
| 453 |
+
"model.visual.blocks.11.norm2.weight": "model-00001-of-00004.safetensors",
|
| 454 |
+
"model.visual.blocks.12.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 455 |
+
"model.visual.blocks.12.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 456 |
+
"model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 457 |
+
"model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 458 |
+
"model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 459 |
+
"model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 460 |
+
"model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 461 |
+
"model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 462 |
+
"model.visual.blocks.12.norm1.bias": "model-00001-of-00004.safetensors",
|
| 463 |
+
"model.visual.blocks.12.norm1.weight": "model-00001-of-00004.safetensors",
|
| 464 |
+
"model.visual.blocks.12.norm2.bias": "model-00001-of-00004.safetensors",
|
| 465 |
+
"model.visual.blocks.12.norm2.weight": "model-00001-of-00004.safetensors",
|
| 466 |
+
"model.visual.blocks.13.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 467 |
+
"model.visual.blocks.13.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 468 |
+
"model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 469 |
+
"model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 470 |
+
"model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 471 |
+
"model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 472 |
+
"model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 473 |
+
"model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 474 |
+
"model.visual.blocks.13.norm1.bias": "model-00001-of-00004.safetensors",
|
| 475 |
+
"model.visual.blocks.13.norm1.weight": "model-00001-of-00004.safetensors",
|
| 476 |
+
"model.visual.blocks.13.norm2.bias": "model-00001-of-00004.safetensors",
|
| 477 |
+
"model.visual.blocks.13.norm2.weight": "model-00001-of-00004.safetensors",
|
| 478 |
+
"model.visual.blocks.14.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 479 |
+
"model.visual.blocks.14.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 480 |
+
"model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 481 |
+
"model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 482 |
+
"model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 483 |
+
"model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 484 |
+
"model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 485 |
+
"model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 486 |
+
"model.visual.blocks.14.norm1.bias": "model-00001-of-00004.safetensors",
|
| 487 |
+
"model.visual.blocks.14.norm1.weight": "model-00001-of-00004.safetensors",
|
| 488 |
+
"model.visual.blocks.14.norm2.bias": "model-00001-of-00004.safetensors",
|
| 489 |
+
"model.visual.blocks.14.norm2.weight": "model-00001-of-00004.safetensors",
|
| 490 |
+
"model.visual.blocks.15.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 491 |
+
"model.visual.blocks.15.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 492 |
+
"model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 493 |
+
"model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 494 |
+
"model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 495 |
+
"model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 496 |
+
"model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 497 |
+
"model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 498 |
+
"model.visual.blocks.15.norm1.bias": "model-00001-of-00004.safetensors",
|
| 499 |
+
"model.visual.blocks.15.norm1.weight": "model-00001-of-00004.safetensors",
|
| 500 |
+
"model.visual.blocks.15.norm2.bias": "model-00001-of-00004.safetensors",
|
| 501 |
+
"model.visual.blocks.15.norm2.weight": "model-00001-of-00004.safetensors",
|
| 502 |
+
"model.visual.blocks.16.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 503 |
+
"model.visual.blocks.16.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 504 |
+
"model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 505 |
+
"model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 506 |
+
"model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 507 |
+
"model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 508 |
+
"model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 509 |
+
"model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 510 |
+
"model.visual.blocks.16.norm1.bias": "model-00001-of-00004.safetensors",
|
| 511 |
+
"model.visual.blocks.16.norm1.weight": "model-00001-of-00004.safetensors",
|
| 512 |
+
"model.visual.blocks.16.norm2.bias": "model-00001-of-00004.safetensors",
|
| 513 |
+
"model.visual.blocks.16.norm2.weight": "model-00001-of-00004.safetensors",
|
| 514 |
+
"model.visual.blocks.17.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 515 |
+
"model.visual.blocks.17.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 516 |
+
"model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 517 |
+
"model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 518 |
+
"model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 519 |
+
"model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 520 |
+
"model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 521 |
+
"model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 522 |
+
"model.visual.blocks.17.norm1.bias": "model-00001-of-00004.safetensors",
|
| 523 |
+
"model.visual.blocks.17.norm1.weight": "model-00001-of-00004.safetensors",
|
| 524 |
+
"model.visual.blocks.17.norm2.bias": "model-00001-of-00004.safetensors",
|
| 525 |
+
"model.visual.blocks.17.norm2.weight": "model-00001-of-00004.safetensors",
|
| 526 |
+
"model.visual.blocks.18.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 527 |
+
"model.visual.blocks.18.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 528 |
+
"model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 529 |
+
"model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 530 |
+
"model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 531 |
+
"model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 532 |
+
"model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 533 |
+
"model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 534 |
+
"model.visual.blocks.18.norm1.bias": "model-00001-of-00004.safetensors",
|
| 535 |
+
"model.visual.blocks.18.norm1.weight": "model-00001-of-00004.safetensors",
|
| 536 |
+
"model.visual.blocks.18.norm2.bias": "model-00001-of-00004.safetensors",
|
| 537 |
+
"model.visual.blocks.18.norm2.weight": "model-00001-of-00004.safetensors",
|
| 538 |
+
"model.visual.blocks.19.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 539 |
+
"model.visual.blocks.19.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 540 |
+
"model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 541 |
+
"model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 542 |
+
"model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 543 |
+
"model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 544 |
+
"model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 545 |
+
"model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 546 |
+
"model.visual.blocks.19.norm1.bias": "model-00001-of-00004.safetensors",
|
| 547 |
+
"model.visual.blocks.19.norm1.weight": "model-00001-of-00004.safetensors",
|
| 548 |
+
"model.visual.blocks.19.norm2.bias": "model-00001-of-00004.safetensors",
|
| 549 |
+
"model.visual.blocks.19.norm2.weight": "model-00001-of-00004.safetensors",
|
| 550 |
+
"model.visual.blocks.2.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 551 |
+
"model.visual.blocks.2.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 552 |
+
"model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 553 |
+
"model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 554 |
+
"model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 555 |
+
"model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 556 |
+
"model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 557 |
+
"model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 558 |
+
"model.visual.blocks.2.norm1.bias": "model-00001-of-00004.safetensors",
|
| 559 |
+
"model.visual.blocks.2.norm1.weight": "model-00001-of-00004.safetensors",
|
| 560 |
+
"model.visual.blocks.2.norm2.bias": "model-00001-of-00004.safetensors",
|
| 561 |
+
"model.visual.blocks.2.norm2.weight": "model-00001-of-00004.safetensors",
|
| 562 |
+
"model.visual.blocks.20.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 563 |
+
"model.visual.blocks.20.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 564 |
+
"model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 565 |
+
"model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 566 |
+
"model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 567 |
+
"model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 568 |
+
"model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 569 |
+
"model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 570 |
+
"model.visual.blocks.20.norm1.bias": "model-00001-of-00004.safetensors",
|
| 571 |
+
"model.visual.blocks.20.norm1.weight": "model-00001-of-00004.safetensors",
|
| 572 |
+
"model.visual.blocks.20.norm2.bias": "model-00001-of-00004.safetensors",
|
| 573 |
+
"model.visual.blocks.20.norm2.weight": "model-00001-of-00004.safetensors",
|
| 574 |
+
"model.visual.blocks.21.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 575 |
+
"model.visual.blocks.21.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 576 |
+
"model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 577 |
+
"model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 578 |
+
"model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 579 |
+
"model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 580 |
+
"model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 581 |
+
"model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 582 |
+
"model.visual.blocks.21.norm1.bias": "model-00001-of-00004.safetensors",
|
| 583 |
+
"model.visual.blocks.21.norm1.weight": "model-00001-of-00004.safetensors",
|
| 584 |
+
"model.visual.blocks.21.norm2.bias": "model-00001-of-00004.safetensors",
|
| 585 |
+
"model.visual.blocks.21.norm2.weight": "model-00001-of-00004.safetensors",
|
| 586 |
+
"model.visual.blocks.22.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 587 |
+
"model.visual.blocks.22.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 588 |
+
"model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 589 |
+
"model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 590 |
+
"model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 591 |
+
"model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 592 |
+
"model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 593 |
+
"model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 594 |
+
"model.visual.blocks.22.norm1.bias": "model-00001-of-00004.safetensors",
|
| 595 |
+
"model.visual.blocks.22.norm1.weight": "model-00001-of-00004.safetensors",
|
| 596 |
+
"model.visual.blocks.22.norm2.bias": "model-00001-of-00004.safetensors",
|
| 597 |
+
"model.visual.blocks.22.norm2.weight": "model-00001-of-00004.safetensors",
|
| 598 |
+
"model.visual.blocks.23.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 599 |
+
"model.visual.blocks.23.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 600 |
+
"model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 601 |
+
"model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 602 |
+
"model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 603 |
+
"model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 604 |
+
"model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 605 |
+
"model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 606 |
+
"model.visual.blocks.23.norm1.bias": "model-00001-of-00004.safetensors",
|
| 607 |
+
"model.visual.blocks.23.norm1.weight": "model-00001-of-00004.safetensors",
|
| 608 |
+
"model.visual.blocks.23.norm2.bias": "model-00001-of-00004.safetensors",
|
| 609 |
+
"model.visual.blocks.23.norm2.weight": "model-00001-of-00004.safetensors",
|
| 610 |
+
"model.visual.blocks.24.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 611 |
+
"model.visual.blocks.24.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 612 |
+
"model.visual.blocks.24.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 613 |
+
"model.visual.blocks.24.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 614 |
+
"model.visual.blocks.24.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 615 |
+
"model.visual.blocks.24.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 616 |
+
"model.visual.blocks.24.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 617 |
+
"model.visual.blocks.24.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 618 |
+
"model.visual.blocks.24.norm1.bias": "model-00001-of-00004.safetensors",
|
| 619 |
+
"model.visual.blocks.24.norm1.weight": "model-00001-of-00004.safetensors",
|
| 620 |
+
"model.visual.blocks.24.norm2.bias": "model-00001-of-00004.safetensors",
|
| 621 |
+
"model.visual.blocks.24.norm2.weight": "model-00001-of-00004.safetensors",
|
| 622 |
+
"model.visual.blocks.25.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 623 |
+
"model.visual.blocks.25.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 624 |
+
"model.visual.blocks.25.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 625 |
+
"model.visual.blocks.25.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 626 |
+
"model.visual.blocks.25.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 627 |
+
"model.visual.blocks.25.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 628 |
+
"model.visual.blocks.25.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 629 |
+
"model.visual.blocks.25.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 630 |
+
"model.visual.blocks.25.norm1.bias": "model-00001-of-00004.safetensors",
|
| 631 |
+
"model.visual.blocks.25.norm1.weight": "model-00001-of-00004.safetensors",
|
| 632 |
+
"model.visual.blocks.25.norm2.bias": "model-00001-of-00004.safetensors",
|
| 633 |
+
"model.visual.blocks.25.norm2.weight": "model-00001-of-00004.safetensors",
|
| 634 |
+
"model.visual.blocks.26.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 635 |
+
"model.visual.blocks.26.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 636 |
+
"model.visual.blocks.26.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 637 |
+
"model.visual.blocks.26.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 638 |
+
"model.visual.blocks.26.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 639 |
+
"model.visual.blocks.26.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 640 |
+
"model.visual.blocks.26.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 641 |
+
"model.visual.blocks.26.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 642 |
+
"model.visual.blocks.26.norm1.bias": "model-00001-of-00004.safetensors",
|
| 643 |
+
"model.visual.blocks.26.norm1.weight": "model-00001-of-00004.safetensors",
|
| 644 |
+
"model.visual.blocks.26.norm2.bias": "model-00001-of-00004.safetensors",
|
| 645 |
+
"model.visual.blocks.26.norm2.weight": "model-00001-of-00004.safetensors",
|
| 646 |
+
"model.visual.blocks.3.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 647 |
+
"model.visual.blocks.3.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 648 |
+
"model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 649 |
+
"model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 650 |
+
"model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 651 |
+
"model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 652 |
+
"model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 653 |
+
"model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 654 |
+
"model.visual.blocks.3.norm1.bias": "model-00001-of-00004.safetensors",
|
| 655 |
+
"model.visual.blocks.3.norm1.weight": "model-00001-of-00004.safetensors",
|
| 656 |
+
"model.visual.blocks.3.norm2.bias": "model-00001-of-00004.safetensors",
|
| 657 |
+
"model.visual.blocks.3.norm2.weight": "model-00001-of-00004.safetensors",
|
| 658 |
+
"model.visual.blocks.4.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 659 |
+
"model.visual.blocks.4.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 660 |
+
"model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 661 |
+
"model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 662 |
+
"model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 663 |
+
"model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 664 |
+
"model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 665 |
+
"model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 666 |
+
"model.visual.blocks.4.norm1.bias": "model-00001-of-00004.safetensors",
|
| 667 |
+
"model.visual.blocks.4.norm1.weight": "model-00001-of-00004.safetensors",
|
| 668 |
+
"model.visual.blocks.4.norm2.bias": "model-00001-of-00004.safetensors",
|
| 669 |
+
"model.visual.blocks.4.norm2.weight": "model-00001-of-00004.safetensors",
|
| 670 |
+
"model.visual.blocks.5.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 671 |
+
"model.visual.blocks.5.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 672 |
+
"model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 673 |
+
"model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 674 |
+
"model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 675 |
+
"model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 676 |
+
"model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 677 |
+
"model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 678 |
+
"model.visual.blocks.5.norm1.bias": "model-00001-of-00004.safetensors",
|
| 679 |
+
"model.visual.blocks.5.norm1.weight": "model-00001-of-00004.safetensors",
|
| 680 |
+
"model.visual.blocks.5.norm2.bias": "model-00001-of-00004.safetensors",
|
| 681 |
+
"model.visual.blocks.5.norm2.weight": "model-00001-of-00004.safetensors",
|
| 682 |
+
"model.visual.blocks.6.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 683 |
+
"model.visual.blocks.6.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 684 |
+
"model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 685 |
+
"model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 686 |
+
"model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 687 |
+
"model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 688 |
+
"model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 689 |
+
"model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 690 |
+
"model.visual.blocks.6.norm1.bias": "model-00001-of-00004.safetensors",
|
| 691 |
+
"model.visual.blocks.6.norm1.weight": "model-00001-of-00004.safetensors",
|
| 692 |
+
"model.visual.blocks.6.norm2.bias": "model-00001-of-00004.safetensors",
|
| 693 |
+
"model.visual.blocks.6.norm2.weight": "model-00001-of-00004.safetensors",
|
| 694 |
+
"model.visual.blocks.7.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 695 |
+
"model.visual.blocks.7.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 696 |
+
"model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 697 |
+
"model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 698 |
+
"model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 699 |
+
"model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 700 |
+
"model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 701 |
+
"model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 702 |
+
"model.visual.blocks.7.norm1.bias": "model-00001-of-00004.safetensors",
|
| 703 |
+
"model.visual.blocks.7.norm1.weight": "model-00001-of-00004.safetensors",
|
| 704 |
+
"model.visual.blocks.7.norm2.bias": "model-00001-of-00004.safetensors",
|
| 705 |
+
"model.visual.blocks.7.norm2.weight": "model-00001-of-00004.safetensors",
|
| 706 |
+
"model.visual.blocks.8.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 707 |
+
"model.visual.blocks.8.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 708 |
+
"model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 709 |
+
"model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 710 |
+
"model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 711 |
+
"model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 712 |
+
"model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 713 |
+
"model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 714 |
+
"model.visual.blocks.8.norm1.bias": "model-00001-of-00004.safetensors",
|
| 715 |
+
"model.visual.blocks.8.norm1.weight": "model-00001-of-00004.safetensors",
|
| 716 |
+
"model.visual.blocks.8.norm2.bias": "model-00001-of-00004.safetensors",
|
| 717 |
+
"model.visual.blocks.8.norm2.weight": "model-00001-of-00004.safetensors",
|
| 718 |
+
"model.visual.blocks.9.attn.proj.bias": "model-00001-of-00004.safetensors",
|
| 719 |
+
"model.visual.blocks.9.attn.proj.weight": "model-00001-of-00004.safetensors",
|
| 720 |
+
"model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
|
| 721 |
+
"model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
|
| 722 |
+
"model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 723 |
+
"model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 724 |
+
"model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 725 |
+
"model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 726 |
+
"model.visual.blocks.9.norm1.bias": "model-00001-of-00004.safetensors",
|
| 727 |
+
"model.visual.blocks.9.norm1.weight": "model-00001-of-00004.safetensors",
|
| 728 |
+
"model.visual.blocks.9.norm2.bias": "model-00001-of-00004.safetensors",
|
| 729 |
+
"model.visual.blocks.9.norm2.weight": "model-00001-of-00004.safetensors",
|
| 730 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 731 |
+
"model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 732 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 733 |
+
"model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 734 |
+
"model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00004.safetensors",
|
| 735 |
+
"model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00004.safetensors",
|
| 736 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 737 |
+
"model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 738 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 739 |
+
"model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 740 |
+
"model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00004.safetensors",
|
| 741 |
+
"model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00004.safetensors",
|
| 742 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 743 |
+
"model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 744 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 745 |
+
"model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 746 |
+
"model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00004.safetensors",
|
| 747 |
+
"model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00004.safetensors",
|
| 748 |
+
"model.visual.merger.linear_fc1.bias": "model-00001-of-00004.safetensors",
|
| 749 |
+
"model.visual.merger.linear_fc1.weight": "model-00001-of-00004.safetensors",
|
| 750 |
+
"model.visual.merger.linear_fc2.bias": "model-00001-of-00004.safetensors",
|
| 751 |
+
"model.visual.merger.linear_fc2.weight": "model-00001-of-00004.safetensors",
|
| 752 |
+
"model.visual.merger.norm.bias": "model-00001-of-00004.safetensors",
|
| 753 |
+
"model.visual.merger.norm.weight": "model-00001-of-00004.safetensors",
|
| 754 |
+
"model.visual.patch_embed.proj.bias": "model-00001-of-00004.safetensors",
|
| 755 |
+
"model.visual.patch_embed.proj.weight": "model-00001-of-00004.safetensors",
|
| 756 |
+
"model.visual.pos_embed.weight": "model-00001-of-00004.safetensors"
|
| 757 |
+
}
|
| 758 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,39 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"disable_grouping": null,
|
| 7 |
+
"do_center_crop": null,
|
| 8 |
+
"do_convert_rgb": true,
|
| 9 |
+
"do_normalize": true,
|
| 10 |
+
"do_pad": null,
|
| 11 |
+
"do_rescale": true,
|
| 12 |
+
"do_resize": true,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_processor_type": "Qwen2VLImageProcessorFast",
|
| 19 |
+
"image_std": [
|
| 20 |
+
0.5,
|
| 21 |
+
0.5,
|
| 22 |
+
0.5
|
| 23 |
+
],
|
| 24 |
+
"input_data_format": null,
|
| 25 |
+
"max_pixels": null,
|
| 26 |
+
"merge_size": 2,
|
| 27 |
+
"min_pixels": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_tensors": null,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 16777216,
|
| 36 |
+
"shortest_edge": 65536
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2
|
| 39 |
+
}
|
runs/Jan20_18-52-58_gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn/events.out.tfevents.1768943156.gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn.1113.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d2cac814f69d2098e89df2653d8496d3c86f3116a3c2220ccf1b6572b9cd861
|
| 3 |
+
size 85230
|
runs/Jan20_18-52-58_gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn/events.out.tfevents.1768955825.gpu-lg-cmc-h-h200-0441.host.h.pjlab.org.cn.1113.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bdf78f7250c6f54a9c18a7ded33386810450bce63e84861bff8cf2373227dd79
|
| 3 |
+
size 359
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
|
| 3 |
+
size 11422654
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,241 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
},
|
| 181 |
+
"151665": {
|
| 182 |
+
"content": "<tool_response>",
|
| 183 |
+
"lstrip": false,
|
| 184 |
+
"normalized": false,
|
| 185 |
+
"rstrip": false,
|
| 186 |
+
"single_word": false,
|
| 187 |
+
"special": false
|
| 188 |
+
},
|
| 189 |
+
"151666": {
|
| 190 |
+
"content": "</tool_response>",
|
| 191 |
+
"lstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"rstrip": false,
|
| 194 |
+
"single_word": false,
|
| 195 |
+
"special": false
|
| 196 |
+
},
|
| 197 |
+
"151667": {
|
| 198 |
+
"content": "<think>",
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"normalized": false,
|
| 201 |
+
"rstrip": false,
|
| 202 |
+
"single_word": false,
|
| 203 |
+
"special": false
|
| 204 |
+
},
|
| 205 |
+
"151668": {
|
| 206 |
+
"content": "</think>",
|
| 207 |
+
"lstrip": false,
|
| 208 |
+
"normalized": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"single_word": false,
|
| 211 |
+
"special": false
|
| 212 |
+
}
|
| 213 |
+
},
|
| 214 |
+
"additional_special_tokens": [
|
| 215 |
+
"<|im_start|>",
|
| 216 |
+
"<|im_end|>",
|
| 217 |
+
"<|object_ref_start|>",
|
| 218 |
+
"<|object_ref_end|>",
|
| 219 |
+
"<|box_start|>",
|
| 220 |
+
"<|box_end|>",
|
| 221 |
+
"<|quad_start|>",
|
| 222 |
+
"<|quad_end|>",
|
| 223 |
+
"<|vision_start|>",
|
| 224 |
+
"<|vision_end|>",
|
| 225 |
+
"<|vision_pad|>",
|
| 226 |
+
"<|image_pad|>",
|
| 227 |
+
"<|video_pad|>"
|
| 228 |
+
],
|
| 229 |
+
"bos_token": null,
|
| 230 |
+
"clean_up_tokenization_spaces": false,
|
| 231 |
+
"eos_token": "<|im_end|>",
|
| 232 |
+
"errors": "replace",
|
| 233 |
+
"extra_special_tokens": {},
|
| 234 |
+
"model_max_length": 262144,
|
| 235 |
+
"pad_token": "<|endoftext|>",
|
| 236 |
+
"padding_side": "right",
|
| 237 |
+
"processor_class": "Qwen3VLProcessor",
|
| 238 |
+
"split_special_tokens": false,
|
| 239 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 240 |
+
"unk_token": null
|
| 241 |
+
}
|
train_results.json
ADDED
|
@@ -0,0 +1,8 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"epoch": 1.0,
|
| 3 |
+
"total_flos": 1884305306419200.0,
|
| 4 |
+
"train_loss": 0.5639046454929622,
|
| 5 |
+
"train_runtime": 12600.7671,
|
| 6 |
+
"train_samples_per_second": 23.004,
|
| 7 |
+
"train_steps_per_second": 0.288
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,370 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 3624, "loss": 1.2489, "lr": 2.4793388429752067e-07, "epoch": 0.0027597626604112047, "percentage": 0.28, "elapsed_time": "0:00:41", "remaining_time": "4:12:42"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 3624, "loss": 1.23, "lr": 5.234159779614326e-07, "epoch": 0.005519525320822409, "percentage": 0.55, "elapsed_time": "0:01:14", "remaining_time": "3:43:56"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 3624, "loss": 1.134, "lr": 7.988980716253444e-07, "epoch": 0.008279287981233613, "percentage": 0.83, "elapsed_time": "0:01:47", "remaining_time": "3:34:13"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 3624, "loss": 0.993, "lr": 1.0743801652892562e-06, "epoch": 0.011039050641644819, "percentage": 1.1, "elapsed_time": "0:02:20", "remaining_time": "3:29:34"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 3624, "loss": 0.8782, "lr": 1.3498622589531682e-06, "epoch": 0.013798813302056023, "percentage": 1.38, "elapsed_time": "0:02:53", "remaining_time": "3:26:21"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 3624, "loss": 0.8004, "lr": 1.62534435261708e-06, "epoch": 0.016558575962467226, "percentage": 1.66, "elapsed_time": "0:03:25", "remaining_time": "3:23:28"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 3624, "loss": 0.7618, "lr": 1.900826446280992e-06, "epoch": 0.019318338622878434, "percentage": 1.93, "elapsed_time": "0:03:58", "remaining_time": "3:22:03"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 3624, "loss": 0.7363, "lr": 2.1763085399449038e-06, "epoch": 0.022078101283289638, "percentage": 2.21, "elapsed_time": "0:04:30", "remaining_time": "3:20:02"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 3624, "loss": 0.7218, "lr": 2.4517906336088157e-06, "epoch": 0.02483786394370084, "percentage": 2.48, "elapsed_time": "0:05:03", "remaining_time": "3:18:26"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 3624, "loss": 0.7039, "lr": 2.7272727272727272e-06, "epoch": 0.027597626604112045, "percentage": 2.76, "elapsed_time": "0:05:35", "remaining_time": "3:17:08"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 3624, "loss": 0.7016, "lr": 3.002754820936639e-06, "epoch": 0.030357389264523253, "percentage": 3.04, "elapsed_time": "0:06:07", "remaining_time": "3:15:36"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 3624, "loss": 0.6911, "lr": 3.278236914600551e-06, "epoch": 0.03311715192493445, "percentage": 3.31, "elapsed_time": "0:06:39", "remaining_time": "3:14:38"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 3624, "loss": 0.6837, "lr": 3.553719008264463e-06, "epoch": 0.035876914585345664, "percentage": 3.59, "elapsed_time": "0:07:13", "remaining_time": "3:14:00"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 3624, "loss": 0.6733, "lr": 3.8292011019283746e-06, "epoch": 0.03863667724575687, "percentage": 3.86, "elapsed_time": "0:07:46", "remaining_time": "3:13:30"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 3624, "loss": 0.6663, "lr": 4.104683195592287e-06, "epoch": 0.04139643990616807, "percentage": 4.14, "elapsed_time": "0:08:18", "remaining_time": "3:12:35"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 3624, "loss": 0.6672, "lr": 4.3801652892561984e-06, "epoch": 0.044156202566579275, "percentage": 4.42, "elapsed_time": "0:08:51", "remaining_time": "3:11:41"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 3624, "loss": 0.6604, "lr": 4.655647382920111e-06, "epoch": 0.04691596522699048, "percentage": 4.69, "elapsed_time": "0:09:24", "remaining_time": "3:11:12"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 3624, "loss": 0.654, "lr": 4.931129476584022e-06, "epoch": 0.04967572788740168, "percentage": 4.97, "elapsed_time": "0:09:56", "remaining_time": "3:10:20"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 3624, "loss": 0.653, "lr": 5.206611570247935e-06, "epoch": 0.05243549054781289, "percentage": 5.24, "elapsed_time": "0:10:28", "remaining_time": "3:09:20"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 3624, "loss": 0.6508, "lr": 5.482093663911846e-06, "epoch": 0.05519525320822409, "percentage": 5.52, "elapsed_time": "0:11:01", "remaining_time": "3:08:49"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 3624, "loss": 0.6498, "lr": 5.7575757575757586e-06, "epoch": 0.057955015868635294, "percentage": 5.79, "elapsed_time": "0:11:54", "remaining_time": "3:13:35"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 3624, "loss": 0.6453, "lr": 6.03305785123967e-06, "epoch": 0.060714778529046505, "percentage": 6.07, "elapsed_time": "0:12:28", "remaining_time": "3:12:54"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 3624, "loss": 0.6414, "lr": 6.3085399449035824e-06, "epoch": 0.06347454118945771, "percentage": 6.35, "elapsed_time": "0:13:00", "remaining_time": "3:11:58"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 3624, "loss": 0.6345, "lr": 6.584022038567494e-06, "epoch": 0.0662343038498689, "percentage": 6.62, "elapsed_time": "0:13:32", "remaining_time": "3:11:01"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 3624, "loss": 0.6386, "lr": 6.859504132231406e-06, "epoch": 0.06899406651028012, "percentage": 6.9, "elapsed_time": "0:14:05", "remaining_time": "3:10:10"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 3624, "loss": 0.6403, "lr": 7.134986225895317e-06, "epoch": 0.07175382917069133, "percentage": 7.17, "elapsed_time": "0:14:38", "remaining_time": "3:09:27"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 3624, "loss": 0.6361, "lr": 7.410468319559229e-06, "epoch": 0.07451359183110252, "percentage": 7.45, "elapsed_time": "0:15:11", "remaining_time": "3:08:41"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 3624, "loss": 0.6348, "lr": 7.685950413223142e-06, "epoch": 0.07727335449151373, "percentage": 7.73, "elapsed_time": "0:15:43", "remaining_time": "3:07:53"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 3624, "loss": 0.6263, "lr": 7.961432506887054e-06, "epoch": 0.08003311715192493, "percentage": 8.0, "elapsed_time": "0:16:16", "remaining_time": "3:07:04"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 3624, "loss": 0.6294, "lr": 8.236914600550965e-06, "epoch": 0.08279287981233614, "percentage": 8.28, "elapsed_time": "0:16:48", "remaining_time": "3:06:18"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 3624, "loss": 0.6268, "lr": 8.512396694214877e-06, "epoch": 0.08555264247274734, "percentage": 8.55, "elapsed_time": "0:17:20", "remaining_time": "3:05:28"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 3624, "loss": 0.6247, "lr": 8.787878787878788e-06, "epoch": 0.08831240513315855, "percentage": 8.83, "elapsed_time": "0:17:53", "remaining_time": "3:04:46"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 3624, "loss": 0.619, "lr": 9.063360881542702e-06, "epoch": 0.09107216779356975, "percentage": 9.11, "elapsed_time": "0:18:28", "remaining_time": "3:04:24"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 3624, "loss": 0.6262, "lr": 9.338842975206613e-06, "epoch": 0.09383193045398096, "percentage": 9.38, "elapsed_time": "0:19:01", "remaining_time": "3:03:45"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 3624, "loss": 0.6241, "lr": 9.614325068870525e-06, "epoch": 0.09659169311439217, "percentage": 9.66, "elapsed_time": "0:19:36", "remaining_time": "3:03:22"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 3624, "loss": 0.6247, "lr": 9.889807162534436e-06, "epoch": 0.09935145577480337, "percentage": 9.93, "elapsed_time": "0:20:09", "remaining_time": "3:02:43"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 3624, "loss": 0.6223, "lr": 9.999916470583429e-06, "epoch": 0.10211121843521458, "percentage": 10.21, "elapsed_time": "0:20:41", "remaining_time": "3:01:56"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 3624, "loss": 0.6172, "lr": 9.999406023144514e-06, "epoch": 0.10487098109562577, "percentage": 10.49, "elapsed_time": "0:21:13", "remaining_time": "3:01:08"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 3624, "loss": 0.6178, "lr": 9.998431580815314e-06, "epoch": 0.10763074375603698, "percentage": 10.76, "elapsed_time": "0:21:46", "remaining_time": "3:00:30"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 3624, "loss": 0.6187, "lr": 9.996993234033826e-06, "epoch": 0.11039050641644818, "percentage": 11.04, "elapsed_time": "0:22:18", "remaining_time": "2:59:46"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 3624, "loss": 0.6195, "lr": 9.995091116293022e-06, "epoch": 0.11315026907685939, "percentage": 11.31, "elapsed_time": "0:23:10", "remaining_time": "3:01:42"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 3624, "loss": 0.6162, "lr": 9.992725404128452e-06, "epoch": 0.11591003173727059, "percentage": 11.59, "elapsed_time": "0:23:42", "remaining_time": "3:00:47"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 3624, "loss": 0.6075, "lr": 9.989896317101873e-06, "epoch": 0.1186697943976818, "percentage": 11.87, "elapsed_time": "0:24:14", "remaining_time": "3:00:05"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 3624, "loss": 0.6157, "lr": 9.986604117780861e-06, "epoch": 0.12142955705809301, "percentage": 12.14, "elapsed_time": "0:24:47", "remaining_time": "2:59:21"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 3624, "loss": 0.6147, "lr": 9.982849111714445e-06, "epoch": 0.1241893197185042, "percentage": 12.42, "elapsed_time": "0:25:18", "remaining_time": "2:58:31"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 3624, "loss": 0.6089, "lr": 9.978631647404755e-06, "epoch": 0.12694908237891542, "percentage": 12.69, "elapsed_time": "0:25:51", "remaining_time": "2:57:50"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 3624, "loss": 0.6132, "lr": 9.973952116274664e-06, "epoch": 0.12970884503932661, "percentage": 12.97, "elapsed_time": "0:26:23", "remaining_time": "2:57:09"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 3624, "loss": 0.6077, "lr": 9.968810952631473e-06, "epoch": 0.1324686076997378, "percentage": 13.25, "elapsed_time": "0:26:56", "remaining_time": "2:56:26"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 3624, "loss": 0.6116, "lr": 9.9632086336266e-06, "epoch": 0.13522837036014904, "percentage": 13.52, "elapsed_time": "0:27:27", "remaining_time": "2:55:35"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 3624, "loss": 0.6131, "lr": 9.957145679211288e-06, "epoch": 0.13798813302056023, "percentage": 13.8, "elapsed_time": "0:28:00", "remaining_time": "2:54:56"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 3624, "eval_loss": 0.6089209318161011, "epoch": 0.13798813302056023, "percentage": 13.8, "elapsed_time": "0:28:49", "remaining_time": "3:00:08"}
|
| 52 |
+
{"current_steps": 510, "total_steps": 3624, "loss": 0.606, "lr": 9.95062265208836e-06, "epoch": 0.14074789568097143, "percentage": 14.07, "elapsed_time": "0:29:22", "remaining_time": "2:59:23"}
|
| 53 |
+
{"current_steps": 520, "total_steps": 3624, "loss": 0.6071, "lr": 9.943640157659984e-06, "epoch": 0.14350765834138265, "percentage": 14.35, "elapsed_time": "0:29:56", "remaining_time": "2:58:44"}
|
| 54 |
+
{"current_steps": 530, "total_steps": 3624, "loss": 0.6021, "lr": 9.936198843971493e-06, "epoch": 0.14626742100179385, "percentage": 14.62, "elapsed_time": "0:30:29", "remaining_time": "2:57:59"}
|
| 55 |
+
{"current_steps": 540, "total_steps": 3624, "loss": 0.5981, "lr": 9.928299401651236e-06, "epoch": 0.14902718366220505, "percentage": 14.9, "elapsed_time": "0:31:01", "remaining_time": "2:57:13"}
|
| 56 |
+
{"current_steps": 550, "total_steps": 3624, "loss": 0.6005, "lr": 9.919942563846482e-06, "epoch": 0.15178694632261625, "percentage": 15.18, "elapsed_time": "0:31:34", "remaining_time": "2:56:27"}
|
| 57 |
+
{"current_steps": 560, "total_steps": 3624, "loss": 0.6046, "lr": 9.911129106155375e-06, "epoch": 0.15454670898302747, "percentage": 15.45, "elapsed_time": "0:32:06", "remaining_time": "2:55:38"}
|
| 58 |
+
{"current_steps": 570, "total_steps": 3624, "loss": 0.6053, "lr": 9.901859846554955e-06, "epoch": 0.15730647164343867, "percentage": 15.73, "elapsed_time": "0:32:38", "remaining_time": "2:54:54"}
|
| 59 |
+
{"current_steps": 580, "total_steps": 3624, "loss": 0.5984, "lr": 9.892135645325238e-06, "epoch": 0.16006623430384986, "percentage": 16.0, "elapsed_time": "0:33:11", "remaining_time": "2:54:11"}
|
| 60 |
+
{"current_steps": 590, "total_steps": 3624, "loss": 0.5978, "lr": 9.881957404969373e-06, "epoch": 0.16282599696426106, "percentage": 16.28, "elapsed_time": "0:33:44", "remaining_time": "2:53:31"}
|
| 61 |
+
{"current_steps": 600, "total_steps": 3624, "loss": 0.6094, "lr": 9.871326070129885e-06, "epoch": 0.16558575962467229, "percentage": 16.56, "elapsed_time": "0:34:17", "remaining_time": "2:52:50"}
|
| 62 |
+
{"current_steps": 610, "total_steps": 3624, "loss": 0.5974, "lr": 9.860242627500994e-06, "epoch": 0.16834552228508348, "percentage": 16.83, "elapsed_time": "0:35:10", "remaining_time": "2:53:45"}
|
| 63 |
+
{"current_steps": 620, "total_steps": 3624, "loss": 0.598, "lr": 9.848708105737049e-06, "epoch": 0.17110528494549468, "percentage": 17.11, "elapsed_time": "0:35:42", "remaining_time": "2:53:01"}
|
| 64 |
+
{"current_steps": 630, "total_steps": 3624, "loss": 0.5988, "lr": 9.836723575357056e-06, "epoch": 0.1738650476059059, "percentage": 17.38, "elapsed_time": "0:36:14", "remaining_time": "2:52:14"}
|
| 65 |
+
{"current_steps": 640, "total_steps": 3624, "loss": 0.5957, "lr": 9.824290148645322e-06, "epoch": 0.1766248102663171, "percentage": 17.66, "elapsed_time": "0:36:46", "remaining_time": "2:51:27"}
|
| 66 |
+
{"current_steps": 650, "total_steps": 3624, "loss": 0.591, "lr": 9.811408979548219e-06, "epoch": 0.1793845729267283, "percentage": 17.94, "elapsed_time": "0:37:19", "remaining_time": "2:50:46"}
|
| 67 |
+
{"current_steps": 660, "total_steps": 3624, "loss": 0.5948, "lr": 9.7980812635671e-06, "epoch": 0.1821443355871395, "percentage": 18.21, "elapsed_time": "0:37:52", "remaining_time": "2:50:05"}
|
| 68 |
+
{"current_steps": 670, "total_steps": 3624, "loss": 0.5954, "lr": 9.784308237647329e-06, "epoch": 0.18490409824755072, "percentage": 18.49, "elapsed_time": "0:38:24", "remaining_time": "2:49:21"}
|
| 69 |
+
{"current_steps": 680, "total_steps": 3624, "loss": 0.596, "lr": 9.770091180063489e-06, "epoch": 0.18766386090796192, "percentage": 18.76, "elapsed_time": "0:38:57", "remaining_time": "2:48:40"}
|
| 70 |
+
{"current_steps": 690, "total_steps": 3624, "loss": 0.5871, "lr": 9.755431410300743e-06, "epoch": 0.1904236235683731, "percentage": 19.04, "elapsed_time": "0:39:30", "remaining_time": "2:47:57"}
|
| 71 |
+
{"current_steps": 700, "total_steps": 3624, "loss": 0.5948, "lr": 9.740330288932379e-06, "epoch": 0.19318338622878434, "percentage": 19.32, "elapsed_time": "0:40:03", "remaining_time": "2:47:18"}
|
| 72 |
+
{"current_steps": 710, "total_steps": 3624, "loss": 0.5898, "lr": 9.724789217493514e-06, "epoch": 0.19594314888919553, "percentage": 19.59, "elapsed_time": "0:40:37", "remaining_time": "2:46:45"}
|
| 73 |
+
{"current_steps": 720, "total_steps": 3624, "loss": 0.5925, "lr": 9.708809638351048e-06, "epoch": 0.19870291154960673, "percentage": 19.87, "elapsed_time": "0:41:12", "remaining_time": "2:46:13"}
|
| 74 |
+
{"current_steps": 730, "total_steps": 3624, "loss": 0.5917, "lr": 9.692393034569776e-06, "epoch": 0.20146267421001793, "percentage": 20.14, "elapsed_time": "0:41:45", "remaining_time": "2:45:31"}
|
| 75 |
+
{"current_steps": 740, "total_steps": 3624, "loss": 0.5911, "lr": 9.675540929774751e-06, "epoch": 0.20422243687042915, "percentage": 20.42, "elapsed_time": "0:42:17", "remaining_time": "2:44:50"}
|
| 76 |
+
{"current_steps": 750, "total_steps": 3624, "loss": 0.5862, "lr": 9.658254888009877e-06, "epoch": 0.20698219953084035, "percentage": 20.7, "elapsed_time": "0:42:50", "remaining_time": "2:44:10"}
|
| 77 |
+
{"current_steps": 760, "total_steps": 3624, "loss": 0.5871, "lr": 9.64053651359275e-06, "epoch": 0.20974196219125155, "percentage": 20.97, "elapsed_time": "0:43:26", "remaining_time": "2:43:42"}
|
| 78 |
+
{"current_steps": 770, "total_steps": 3624, "loss": 0.5851, "lr": 9.622387450965758e-06, "epoch": 0.21250172485166274, "percentage": 21.25, "elapsed_time": "0:43:58", "remaining_time": "2:42:59"}
|
| 79 |
+
{"current_steps": 780, "total_steps": 3624, "loss": 0.5937, "lr": 9.603809384543472e-06, "epoch": 0.21526148751207397, "percentage": 21.52, "elapsed_time": "0:44:30", "remaining_time": "2:42:18"}
|
| 80 |
+
{"current_steps": 790, "total_steps": 3624, "loss": 0.5834, "lr": 9.584804038556297e-06, "epoch": 0.21802125017248516, "percentage": 21.8, "elapsed_time": "0:45:03", "remaining_time": "2:41:37"}
|
| 81 |
+
{"current_steps": 800, "total_steps": 3624, "loss": 0.5903, "lr": 9.56537317689046e-06, "epoch": 0.22078101283289636, "percentage": 22.08, "elapsed_time": "0:45:34", "remaining_time": "2:40:52"}
|
| 82 |
+
{"current_steps": 810, "total_steps": 3624, "loss": 0.5872, "lr": 9.5455186029243e-06, "epoch": 0.2235407754933076, "percentage": 22.35, "elapsed_time": "0:46:26", "remaining_time": "2:41:20"}
|
| 83 |
+
{"current_steps": 820, "total_steps": 3624, "loss": 0.5888, "lr": 9.525242159360897e-06, "epoch": 0.22630053815371878, "percentage": 22.63, "elapsed_time": "0:46:59", "remaining_time": "2:40:39"}
|
| 84 |
+
{"current_steps": 830, "total_steps": 3624, "loss": 0.5822, "lr": 9.504545728057046e-06, "epoch": 0.22906030081412998, "percentage": 22.9, "elapsed_time": "0:47:32", "remaining_time": "2:40:00"}
|
| 85 |
+
{"current_steps": 840, "total_steps": 3624, "loss": 0.5847, "lr": 9.483431229848607e-06, "epoch": 0.23182006347454118, "percentage": 23.18, "elapsed_time": "0:48:04", "remaining_time": "2:39:20"}
|
| 86 |
+
{"current_steps": 850, "total_steps": 3624, "loss": 0.5763, "lr": 9.461900624372233e-06, "epoch": 0.2345798261349524, "percentage": 23.45, "elapsed_time": "0:48:38", "remaining_time": "2:38:43"}
|
| 87 |
+
{"current_steps": 860, "total_steps": 3624, "loss": 0.5815, "lr": 9.439955909883493e-06, "epoch": 0.2373395887953636, "percentage": 23.73, "elapsed_time": "0:49:11", "remaining_time": "2:38:04"}
|
| 88 |
+
{"current_steps": 870, "total_steps": 3624, "loss": 0.5838, "lr": 9.417599123071417e-06, "epoch": 0.2400993514557748, "percentage": 24.01, "elapsed_time": "0:49:44", "remaining_time": "2:37:26"}
|
| 89 |
+
{"current_steps": 880, "total_steps": 3624, "loss": 0.5785, "lr": 9.39483233886946e-06, "epoch": 0.24285911411618602, "percentage": 24.28, "elapsed_time": "0:50:15", "remaining_time": "2:36:43"}
|
| 90 |
+
{"current_steps": 890, "total_steps": 3624, "loss": 0.5742, "lr": 9.371657670262947e-06, "epoch": 0.24561887677659722, "percentage": 24.56, "elapsed_time": "0:50:48", "remaining_time": "2:36:04"}
|
| 91 |
+
{"current_steps": 900, "total_steps": 3624, "loss": 0.5763, "lr": 9.348077268092951e-06, "epoch": 0.2483786394370084, "percentage": 24.83, "elapsed_time": "0:51:20", "remaining_time": "2:35:23"}
|
| 92 |
+
{"current_steps": 910, "total_steps": 3624, "loss": 0.5777, "lr": 9.324093320856679e-06, "epoch": 0.2511384020974196, "percentage": 25.11, "elapsed_time": "0:51:53", "remaining_time": "2:34:45"}
|
| 93 |
+
{"current_steps": 920, "total_steps": 3624, "loss": 0.5781, "lr": 9.299708054504355e-06, "epoch": 0.25389816475783084, "percentage": 25.39, "elapsed_time": "0:52:26", "remaining_time": "2:34:06"}
|
| 94 |
+
{"current_steps": 930, "total_steps": 3624, "loss": 0.5813, "lr": 9.274923732232635e-06, "epoch": 0.256657927418242, "percentage": 25.66, "elapsed_time": "0:52:58", "remaining_time": "2:33:26"}
|
| 95 |
+
{"current_steps": 940, "total_steps": 3624, "loss": 0.576, "lr": 9.249742654274554e-06, "epoch": 0.25941769007865323, "percentage": 25.94, "elapsed_time": "0:53:32", "remaining_time": "2:32:53"}
|
| 96 |
+
{"current_steps": 950, "total_steps": 3624, "loss": 0.5756, "lr": 9.224167157686044e-06, "epoch": 0.26217745273906445, "percentage": 26.21, "elapsed_time": "0:54:05", "remaining_time": "2:32:14"}
|
| 97 |
+
{"current_steps": 960, "total_steps": 3624, "loss": 0.5718, "lr": 9.198199616129033e-06, "epoch": 0.2649372153994756, "percentage": 26.49, "elapsed_time": "0:54:37", "remaining_time": "2:31:35"}
|
| 98 |
+
{"current_steps": 970, "total_steps": 3624, "loss": 0.5722, "lr": 9.171842439651143e-06, "epoch": 0.26769697805988685, "percentage": 26.77, "elapsed_time": "0:55:09", "remaining_time": "2:30:55"}
|
| 99 |
+
{"current_steps": 980, "total_steps": 3624, "loss": 0.577, "lr": 9.145098074462012e-06, "epoch": 0.27045674072029807, "percentage": 27.04, "elapsed_time": "0:55:43", "remaining_time": "2:30:20"}
|
| 100 |
+
{"current_steps": 990, "total_steps": 3624, "loss": 0.5738, "lr": 9.117969002706267e-06, "epoch": 0.27321650338070924, "percentage": 27.32, "elapsed_time": "0:56:15", "remaining_time": "2:29:40"}
|
| 101 |
+
{"current_steps": 1000, "total_steps": 3624, "loss": 0.5714, "lr": 9.090457742233152e-06, "epoch": 0.27597626604112047, "percentage": 27.59, "elapsed_time": "0:56:47", "remaining_time": "2:29:01"}
|
| 102 |
+
{"current_steps": 1000, "total_steps": 3624, "eval_loss": 0.5767696499824524, "epoch": 0.27597626604112047, "percentage": 27.59, "elapsed_time": "0:57:36", "remaining_time": "2:31:09"}
|
| 103 |
+
{"current_steps": 1010, "total_steps": 3624, "loss": 0.5746, "lr": 9.062566846362843e-06, "epoch": 0.2787360287015317, "percentage": 27.87, "elapsed_time": "0:58:28", "remaining_time": "2:31:21"}
|
| 104 |
+
{"current_steps": 1020, "total_steps": 3624, "loss": 0.5731, "lr": 9.034298903649485e-06, "epoch": 0.28149579136194286, "percentage": 28.15, "elapsed_time": "0:59:01", "remaining_time": "2:30:41"}
|
| 105 |
+
{"current_steps": 1030, "total_steps": 3624, "loss": 0.574, "lr": 9.005656537640942e-06, "epoch": 0.2842555540223541, "percentage": 28.42, "elapsed_time": "0:59:34", "remaining_time": "2:30:01"}
|
| 106 |
+
{"current_steps": 1040, "total_steps": 3624, "loss": 0.5725, "lr": 8.976642406635295e-06, "epoch": 0.2870153166827653, "percentage": 28.7, "elapsed_time": "1:00:07", "remaining_time": "2:29:22"}
|
| 107 |
+
{"current_steps": 1050, "total_steps": 3624, "loss": 0.5737, "lr": 8.947259203434147e-06, "epoch": 0.2897750793431765, "percentage": 28.97, "elapsed_time": "1:00:39", "remaining_time": "2:28:42"}
|
| 108 |
+
{"current_steps": 1060, "total_steps": 3624, "loss": 0.5723, "lr": 8.917509655092691e-06, "epoch": 0.2925348420035877, "percentage": 29.25, "elapsed_time": "1:01:13", "remaining_time": "2:28:05"}
|
| 109 |
+
{"current_steps": 1070, "total_steps": 3624, "loss": 0.566, "lr": 8.887396522666608e-06, "epoch": 0.29529460466399887, "percentage": 29.53, "elapsed_time": "1:01:46", "remaining_time": "2:27:26"}
|
| 110 |
+
{"current_steps": 1080, "total_steps": 3624, "loss": 0.5683, "lr": 8.85692260095582e-06, "epoch": 0.2980543673244101, "percentage": 29.8, "elapsed_time": "1:02:18", "remaining_time": "2:26:45"}
|
| 111 |
+
{"current_steps": 1090, "total_steps": 3624, "loss": 0.5661, "lr": 8.826090718245112e-06, "epoch": 0.3008141299848213, "percentage": 30.08, "elapsed_time": "1:02:50", "remaining_time": "2:26:06"}
|
| 112 |
+
{"current_steps": 1100, "total_steps": 3624, "loss": 0.5717, "lr": 8.794903736041622e-06, "epoch": 0.3035738926452325, "percentage": 30.35, "elapsed_time": "1:03:26", "remaining_time": "2:25:33"}
|
| 113 |
+
{"current_steps": 1110, "total_steps": 3624, "loss": 0.5658, "lr": 8.763364548809279e-06, "epoch": 0.3063336553056437, "percentage": 30.63, "elapsed_time": "1:04:00", "remaining_time": "2:24:59"}
|
| 114 |
+
{"current_steps": 1120, "total_steps": 3624, "loss": 0.5679, "lr": 8.731476083700154e-06, "epoch": 0.30909341796605494, "percentage": 30.91, "elapsed_time": "1:04:34", "remaining_time": "2:24:21"}
|
| 115 |
+
{"current_steps": 1130, "total_steps": 3624, "loss": 0.5684, "lr": 8.699241300282806e-06, "epoch": 0.3118531806264661, "percentage": 31.18, "elapsed_time": "1:05:07", "remaining_time": "2:23:44"}
|
| 116 |
+
{"current_steps": 1140, "total_steps": 3624, "loss": 0.5621, "lr": 8.666663190267596e-06, "epoch": 0.31461294328687733, "percentage": 31.46, "elapsed_time": "1:05:40", "remaining_time": "2:23:05"}
|
| 117 |
+
{"current_steps": 1150, "total_steps": 3624, "loss": 0.569, "lr": 8.633744777229029e-06, "epoch": 0.31737270594728856, "percentage": 31.73, "elapsed_time": "1:06:12", "remaining_time": "2:22:25"}
|
| 118 |
+
{"current_steps": 1160, "total_steps": 3624, "loss": 0.5678, "lr": 8.600489116325128e-06, "epoch": 0.3201324686076997, "percentage": 32.01, "elapsed_time": "1:06:44", "remaining_time": "2:21:45"}
|
| 119 |
+
{"current_steps": 1170, "total_steps": 3624, "loss": 0.5696, "lr": 8.566899294013901e-06, "epoch": 0.32289223126811095, "percentage": 32.28, "elapsed_time": "1:07:16", "remaining_time": "2:21:07"}
|
| 120 |
+
{"current_steps": 1180, "total_steps": 3624, "loss": 0.5655, "lr": 8.53297842776687e-06, "epoch": 0.3256519939285221, "percentage": 32.56, "elapsed_time": "1:07:50", "remaining_time": "2:20:30"}
|
| 121 |
+
{"current_steps": 1190, "total_steps": 3624, "loss": 0.5653, "lr": 8.498729665779751e-06, "epoch": 0.32841175658893335, "percentage": 32.84, "elapsed_time": "1:08:22", "remaining_time": "2:19:51"}
|
| 122 |
+
{"current_steps": 1200, "total_steps": 3624, "loss": 0.5665, "lr": 8.464156186680262e-06, "epoch": 0.33117151924934457, "percentage": 33.11, "elapsed_time": "1:08:56", "remaining_time": "2:19:15"}
|
| 123 |
+
{"current_steps": 1210, "total_steps": 3624, "loss": 0.5633, "lr": 8.429261199233114e-06, "epoch": 0.33393128190975574, "percentage": 33.39, "elapsed_time": "1:09:49", "remaining_time": "2:19:18"}
|
| 124 |
+
{"current_steps": 1220, "total_steps": 3624, "loss": 0.5648, "lr": 8.394047942042215e-06, "epoch": 0.33669104457016696, "percentage": 33.66, "elapsed_time": "1:10:21", "remaining_time": "2:18:38"}
|
| 125 |
+
{"current_steps": 1230, "total_steps": 3624, "loss": 0.5628, "lr": 8.358519683250087e-06, "epoch": 0.3394508072305782, "percentage": 33.94, "elapsed_time": "1:10:53", "remaining_time": "2:17:59"}
|
| 126 |
+
{"current_steps": 1240, "total_steps": 3624, "loss": 0.5665, "lr": 8.322679720234553e-06, "epoch": 0.34221056989098936, "percentage": 34.22, "elapsed_time": "1:11:27", "remaining_time": "2:17:23"}
|
| 127 |
+
{"current_steps": 1250, "total_steps": 3624, "loss": 0.5615, "lr": 8.286531379302703e-06, "epoch": 0.3449703325514006, "percentage": 34.49, "elapsed_time": "1:12:02", "remaining_time": "2:16:48"}
|
| 128 |
+
{"current_steps": 1260, "total_steps": 3624, "loss": 0.5626, "lr": 8.25007801538218e-06, "epoch": 0.3477300952118118, "percentage": 34.77, "elapsed_time": "1:12:40", "remaining_time": "2:16:20"}
|
| 129 |
+
{"current_steps": 1270, "total_steps": 3624, "loss": 0.5645, "lr": 8.21332301170982e-06, "epoch": 0.350489857872223, "percentage": 35.04, "elapsed_time": "1:13:12", "remaining_time": "2:15:42"}
|
| 130 |
+
{"current_steps": 1280, "total_steps": 3624, "loss": 0.5622, "lr": 8.17626977951764e-06, "epoch": 0.3532496205326342, "percentage": 35.32, "elapsed_time": "1:13:44", "remaining_time": "2:15:03"}
|
| 131 |
+
{"current_steps": 1290, "total_steps": 3624, "loss": 0.5581, "lr": 8.138921757716245e-06, "epoch": 0.3560093831930454, "percentage": 35.6, "elapsed_time": "1:14:17", "remaining_time": "2:14:24"}
|
| 132 |
+
{"current_steps": 1300, "total_steps": 3624, "loss": 0.5618, "lr": 8.101282412575673e-06, "epoch": 0.3587691458534566, "percentage": 35.87, "elapsed_time": "1:14:50", "remaining_time": "2:13:47"}
|
| 133 |
+
{"current_steps": 1310, "total_steps": 3624, "loss": 0.5555, "lr": 8.063355237403672e-06, "epoch": 0.3615289085138678, "percentage": 36.15, "elapsed_time": "1:15:22", "remaining_time": "2:13:08"}
|
| 134 |
+
{"current_steps": 1320, "total_steps": 3624, "loss": 0.5588, "lr": 8.0251437522215e-06, "epoch": 0.364288671174279, "percentage": 36.42, "elapsed_time": "1:15:58", "remaining_time": "2:12:35"}
|
| 135 |
+
{"current_steps": 1330, "total_steps": 3624, "loss": 0.5638, "lr": 7.986651503437233e-06, "epoch": 0.3670484338346902, "percentage": 36.7, "elapsed_time": "1:16:29", "remaining_time": "2:11:56"}
|
| 136 |
+
{"current_steps": 1340, "total_steps": 3624, "loss": 0.561, "lr": 7.947882063516612e-06, "epoch": 0.36980819649510144, "percentage": 36.98, "elapsed_time": "1:17:01", "remaining_time": "2:11:17"}
|
| 137 |
+
{"current_steps": 1350, "total_steps": 3624, "loss": 0.558, "lr": 7.908839030651488e-06, "epoch": 0.3725679591555126, "percentage": 37.25, "elapsed_time": "1:17:34", "remaining_time": "2:10:40"}
|
| 138 |
+
{"current_steps": 1360, "total_steps": 3624, "loss": 0.5587, "lr": 7.869526028425878e-06, "epoch": 0.37532772181592383, "percentage": 37.53, "elapsed_time": "1:18:07", "remaining_time": "2:10:02"}
|
| 139 |
+
{"current_steps": 1370, "total_steps": 3624, "loss": 0.5584, "lr": 7.829946705479654e-06, "epoch": 0.37808748447633506, "percentage": 37.8, "elapsed_time": "1:18:40", "remaining_time": "2:09:26"}
|
| 140 |
+
{"current_steps": 1380, "total_steps": 3624, "loss": 0.5576, "lr": 7.790104735169915e-06, "epoch": 0.3808472471367462, "percentage": 38.08, "elapsed_time": "1:19:12", "remaining_time": "2:08:48"}
|
| 141 |
+
{"current_steps": 1390, "total_steps": 3624, "loss": 0.5558, "lr": 7.750003815230062e-06, "epoch": 0.38360700979715745, "percentage": 38.36, "elapsed_time": "1:19:44", "remaining_time": "2:08:09"}
|
| 142 |
+
{"current_steps": 1400, "total_steps": 3624, "loss": 0.5611, "lr": 7.70964766742662e-06, "epoch": 0.3863667724575687, "percentage": 38.63, "elapsed_time": "1:20:16", "remaining_time": "2:07:31"}
|
| 143 |
+
{"current_steps": 1410, "total_steps": 3624, "loss": 0.5559, "lr": 7.669040037213795e-06, "epoch": 0.38912653511797984, "percentage": 38.91, "elapsed_time": "1:21:07", "remaining_time": "2:07:23"}
|
| 144 |
+
{"current_steps": 1420, "total_steps": 3624, "loss": 0.5601, "lr": 7.628184693385896e-06, "epoch": 0.39188629777839107, "percentage": 39.18, "elapsed_time": "1:21:40", "remaining_time": "2:06:45"}
|
| 145 |
+
{"current_steps": 1430, "total_steps": 3624, "loss": 0.5555, "lr": 7.587085427727523e-06, "epoch": 0.39464606043880224, "percentage": 39.46, "elapsed_time": "1:22:13", "remaining_time": "2:06:08"}
|
| 146 |
+
{"current_steps": 1440, "total_steps": 3624, "loss": 0.554, "lr": 7.54574605466166e-06, "epoch": 0.39740582309921346, "percentage": 39.74, "elapsed_time": "1:22:46", "remaining_time": "2:05:32"}
|
| 147 |
+
{"current_steps": 1450, "total_steps": 3624, "loss": 0.5576, "lr": 7.504170410895668e-06, "epoch": 0.4001655857596247, "percentage": 40.01, "elapsed_time": "1:23:18", "remaining_time": "2:04:54"}
|
| 148 |
+
{"current_steps": 1460, "total_steps": 3624, "loss": 0.5531, "lr": 7.462362355065189e-06, "epoch": 0.40292534842003586, "percentage": 40.29, "elapsed_time": "1:23:50", "remaining_time": "2:04:16"}
|
| 149 |
+
{"current_steps": 1470, "total_steps": 3624, "loss": 0.5536, "lr": 7.420325767376026e-06, "epoch": 0.4056851110804471, "percentage": 40.56, "elapsed_time": "1:24:23", "remaining_time": "2:03:39"}
|
| 150 |
+
{"current_steps": 1480, "total_steps": 3624, "loss": 0.5512, "lr": 7.378064549244031e-06, "epoch": 0.4084448737408583, "percentage": 40.84, "elapsed_time": "1:24:55", "remaining_time": "2:03:01"}
|
| 151 |
+
{"current_steps": 1490, "total_steps": 3624, "loss": 0.5601, "lr": 7.335582622933e-06, "epoch": 0.4112046364012695, "percentage": 41.11, "elapsed_time": "1:25:27", "remaining_time": "2:02:23"}
|
| 152 |
+
{"current_steps": 1500, "total_steps": 3624, "loss": 0.5524, "lr": 7.292883931190667e-06, "epoch": 0.4139643990616807, "percentage": 41.39, "elapsed_time": "1:26:00", "remaining_time": "2:01:47"}
|
| 153 |
+
{"current_steps": 1500, "total_steps": 3624, "eval_loss": 0.5561984777450562, "epoch": 0.4139643990616807, "percentage": 41.39, "elapsed_time": "1:26:50", "remaining_time": "2:02:57"}
|
| 154 |
+
{"current_steps": 1510, "total_steps": 3624, "loss": 0.5542, "lr": 7.249972436882756e-06, "epoch": 0.4167241617220919, "percentage": 41.67, "elapsed_time": "1:27:22", "remaining_time": "2:02:19"}
|
| 155 |
+
{"current_steps": 1520, "total_steps": 3624, "loss": 0.5524, "lr": 7.206852122625203e-06, "epoch": 0.4194839243825031, "percentage": 41.94, "elapsed_time": "1:27:55", "remaining_time": "2:01:41"}
|
| 156 |
+
{"current_steps": 1530, "total_steps": 3624, "loss": 0.5542, "lr": 7.163526990414522e-06, "epoch": 0.4222436870429143, "percentage": 42.22, "elapsed_time": "1:28:28", "remaining_time": "2:01:05"}
|
| 157 |
+
{"current_steps": 1540, "total_steps": 3624, "loss": 0.5525, "lr": 7.120001061256387e-06, "epoch": 0.4250034497033255, "percentage": 42.49, "elapsed_time": "1:29:01", "remaining_time": "2:00:28"}
|
| 158 |
+
{"current_steps": 1550, "total_steps": 3624, "loss": 0.5541, "lr": 7.076278374792429e-06, "epoch": 0.4277632123637367, "percentage": 42.77, "elapsed_time": "1:29:34", "remaining_time": "1:59:50"}
|
| 159 |
+
{"current_steps": 1560, "total_steps": 3624, "loss": 0.5553, "lr": 7.032362988925332e-06, "epoch": 0.43052297502414794, "percentage": 43.05, "elapsed_time": "1:30:06", "remaining_time": "1:59:13"}
|
| 160 |
+
{"current_steps": 1570, "total_steps": 3624, "loss": 0.5489, "lr": 6.9882589794422105e-06, "epoch": 0.4332827376845591, "percentage": 43.32, "elapsed_time": "1:30:39", "remaining_time": "1:58:36"}
|
| 161 |
+
{"current_steps": 1580, "total_steps": 3624, "loss": 0.5494, "lr": 6.943970439636336e-06, "epoch": 0.43604250034497033, "percentage": 43.6, "elapsed_time": "1:31:12", "remaining_time": "1:57:59"}
|
| 162 |
+
{"current_steps": 1590, "total_steps": 3624, "loss": 0.5484, "lr": 6.899501479927242e-06, "epoch": 0.43880226300538155, "percentage": 43.87, "elapsed_time": "1:31:45", "remaining_time": "1:57:22"}
|
| 163 |
+
{"current_steps": 1600, "total_steps": 3624, "loss": 0.5453, "lr": 6.8548562274792325e-06, "epoch": 0.4415620256657927, "percentage": 44.15, "elapsed_time": "1:32:17", "remaining_time": "1:56:45"}
|
| 164 |
+
{"current_steps": 1610, "total_steps": 3624, "loss": 0.5482, "lr": 6.81003882581834e-06, "epoch": 0.44432178832620395, "percentage": 44.43, "elapsed_time": "1:33:09", "remaining_time": "1:56:32"}
|
| 165 |
+
{"current_steps": 1620, "total_steps": 3624, "loss": 0.5487, "lr": 6.765053434447769e-06, "epoch": 0.4470815509866152, "percentage": 44.7, "elapsed_time": "1:33:41", "remaining_time": "1:55:54"}
|
| 166 |
+
{"current_steps": 1630, "total_steps": 3624, "loss": 0.5505, "lr": 6.7199042284618484e-06, "epoch": 0.44984131364702634, "percentage": 44.98, "elapsed_time": "1:34:15", "remaining_time": "1:55:17"}
|
| 167 |
+
{"current_steps": 1640, "total_steps": 3624, "loss": 0.5493, "lr": 6.674595398158541e-06, "epoch": 0.45260107630743757, "percentage": 45.25, "elapsed_time": "1:34:47", "remaining_time": "1:54:39"}
|
| 168 |
+
{"current_steps": 1650, "total_steps": 3624, "loss": 0.5444, "lr": 6.629131148650543e-06, "epoch": 0.4553608389678488, "percentage": 45.53, "elapsed_time": "1:35:20", "remaining_time": "1:54:03"}
|
| 169 |
+
{"current_steps": 1660, "total_steps": 3624, "loss": 0.5496, "lr": 6.583515699475009e-06, "epoch": 0.45812060162825996, "percentage": 45.81, "elapsed_time": "1:35:55", "remaining_time": "1:53:29"}
|
| 170 |
+
{"current_steps": 1670, "total_steps": 3624, "loss": 0.5487, "lr": 6.537753284201935e-06, "epoch": 0.4608803642886712, "percentage": 46.08, "elapsed_time": "1:36:28", "remaining_time": "1:52:52"}
|
| 171 |
+
{"current_steps": 1680, "total_steps": 3624, "loss": 0.5477, "lr": 6.491848150041242e-06, "epoch": 0.46364012694908235, "percentage": 46.36, "elapsed_time": "1:37:00", "remaining_time": "1:52:15"}
|
| 172 |
+
{"current_steps": 1690, "total_steps": 3624, "loss": 0.5519, "lr": 6.4458045574485875e-06, "epoch": 0.4663998896094936, "percentage": 46.63, "elapsed_time": "1:37:33", "remaining_time": "1:51:39"}
|
| 173 |
+
{"current_steps": 1700, "total_steps": 3624, "loss": 0.5439, "lr": 6.399626779729959e-06, "epoch": 0.4691596522699048, "percentage": 46.91, "elapsed_time": "1:38:06", "remaining_time": "1:51:02"}
|
| 174 |
+
{"current_steps": 1710, "total_steps": 3624, "loss": 0.5465, "lr": 6.353319102645069e-06, "epoch": 0.471919414930316, "percentage": 47.19, "elapsed_time": "1:38:39", "remaining_time": "1:50:25"}
|
| 175 |
+
{"current_steps": 1720, "total_steps": 3624, "loss": 0.547, "lr": 6.306885824009585e-06, "epoch": 0.4746791775907272, "percentage": 47.46, "elapsed_time": "1:39:12", "remaining_time": "1:49:49"}
|
| 176 |
+
{"current_steps": 1730, "total_steps": 3624, "loss": 0.5495, "lr": 6.260331253296259e-06, "epoch": 0.4774389402511384, "percentage": 47.74, "elapsed_time": "1:39:45", "remaining_time": "1:49:12"}
|
| 177 |
+
{"current_steps": 1740, "total_steps": 3624, "loss": 0.5481, "lr": 6.213659711234958e-06, "epoch": 0.4801987029115496, "percentage": 48.01, "elapsed_time": "1:40:17", "remaining_time": "1:48:35"}
|
| 178 |
+
{"current_steps": 1750, "total_steps": 3624, "loss": 0.5468, "lr": 6.1668755294116655e-06, "epoch": 0.4829584655719608, "percentage": 48.29, "elapsed_time": "1:40:49", "remaining_time": "1:47:58"}
|
| 179 |
+
{"current_steps": 1760, "total_steps": 3624, "loss": 0.5438, "lr": 6.119983049866456e-06, "epoch": 0.48571822823237204, "percentage": 48.57, "elapsed_time": "1:41:22", "remaining_time": "1:47:22"}
|
| 180 |
+
{"current_steps": 1770, "total_steps": 3624, "loss": 0.5478, "lr": 6.072986624690516e-06, "epoch": 0.4884779908927832, "percentage": 48.84, "elapsed_time": "1:41:55", "remaining_time": "1:46:45"}
|
| 181 |
+
{"current_steps": 1780, "total_steps": 3624, "loss": 0.5415, "lr": 6.025890615622233e-06, "epoch": 0.49123775355319443, "percentage": 49.12, "elapsed_time": "1:42:27", "remaining_time": "1:46:08"}
|
| 182 |
+
{"current_steps": 1790, "total_steps": 3624, "loss": 0.5411, "lr": 5.97869939364237e-06, "epoch": 0.4939975162136056, "percentage": 49.39, "elapsed_time": "1:43:00", "remaining_time": "1:45:32"}
|
| 183 |
+
{"current_steps": 1800, "total_steps": 3624, "loss": 0.5453, "lr": 5.9314173385683986e-06, "epoch": 0.4967572788740168, "percentage": 49.67, "elapsed_time": "1:43:33", "remaining_time": "1:44:55"}
|
| 184 |
+
{"current_steps": 1810, "total_steps": 3624, "loss": 0.5384, "lr": 5.884048838648017e-06, "epoch": 0.49951704153442805, "percentage": 49.94, "elapsed_time": "1:44:24", "remaining_time": "1:44:37"}
|
| 185 |
+
{"current_steps": 1820, "total_steps": 3624, "loss": 0.5456, "lr": 5.836598290151866e-06, "epoch": 0.5022768041948392, "percentage": 50.22, "elapsed_time": "1:44:57", "remaining_time": "1:44:02"}
|
| 186 |
+
{"current_steps": 1830, "total_steps": 3624, "loss": 0.5426, "lr": 5.789070096965514e-06, "epoch": 0.5050365668552504, "percentage": 50.5, "elapsed_time": "1:45:29", "remaining_time": "1:43:24"}
|
| 187 |
+
{"current_steps": 1840, "total_steps": 3624, "loss": 0.5434, "lr": 5.741468670180737e-06, "epoch": 0.5077963295156617, "percentage": 50.77, "elapsed_time": "1:46:02", "remaining_time": "1:42:48"}
|
| 188 |
+
{"current_steps": 1850, "total_steps": 3624, "loss": 0.5441, "lr": 5.6937984276861195e-06, "epoch": 0.5105560921760729, "percentage": 51.05, "elapsed_time": "1:46:34", "remaining_time": "1:42:11"}
|
| 189 |
+
{"current_steps": 1860, "total_steps": 3624, "loss": 0.5413, "lr": 5.646063793757028e-06, "epoch": 0.513315854836484, "percentage": 51.32, "elapsed_time": "1:47:06", "remaining_time": "1:41:34"}
|
| 190 |
+
{"current_steps": 1870, "total_steps": 3624, "loss": 0.5457, "lr": 5.598269198645008e-06, "epoch": 0.5160756174968952, "percentage": 51.6, "elapsed_time": "1:47:39", "remaining_time": "1:40:58"}
|
| 191 |
+
{"current_steps": 1880, "total_steps": 3624, "loss": 0.5452, "lr": 5.550419078166594e-06, "epoch": 0.5188353801573065, "percentage": 51.88, "elapsed_time": "1:48:12", "remaining_time": "1:40:22"}
|
| 192 |
+
{"current_steps": 1890, "total_steps": 3624, "loss": 0.5467, "lr": 5.502517873291632e-06, "epoch": 0.5215951428177177, "percentage": 52.15, "elapsed_time": "1:48:45", "remaining_time": "1:39:46"}
|
| 193 |
+
{"current_steps": 1900, "total_steps": 3624, "loss": 0.5413, "lr": 5.454570029731115e-06, "epoch": 0.5243549054781289, "percentage": 52.43, "elapsed_time": "1:49:17", "remaining_time": "1:39:10"}
|
| 194 |
+
{"current_steps": 1910, "total_steps": 3624, "loss": 0.5411, "lr": 5.406579997524567e-06, "epoch": 0.5271146681385401, "percentage": 52.7, "elapsed_time": "1:49:49", "remaining_time": "1:38:32"}
|
| 195 |
+
{"current_steps": 1920, "total_steps": 3624, "loss": 0.539, "lr": 5.358552230627044e-06, "epoch": 0.5298744307989512, "percentage": 52.98, "elapsed_time": "1:50:21", "remaining_time": "1:37:56"}
|
| 196 |
+
{"current_steps": 1930, "total_steps": 3624, "loss": 0.5429, "lr": 5.310491186495757e-06, "epoch": 0.5326341934593625, "percentage": 53.26, "elapsed_time": "1:50:53", "remaining_time": "1:37:19"}
|
| 197 |
+
{"current_steps": 1940, "total_steps": 3624, "loss": 0.5384, "lr": 5.262401325676378e-06, "epoch": 0.5353939561197737, "percentage": 53.53, "elapsed_time": "1:51:26", "remaining_time": "1:36:44"}
|
| 198 |
+
{"current_steps": 1950, "total_steps": 3624, "loss": 0.5362, "lr": 5.214287111389057e-06, "epoch": 0.5381537187801849, "percentage": 53.81, "elapsed_time": "1:51:59", "remaining_time": "1:36:08"}
|
| 199 |
+
{"current_steps": 1960, "total_steps": 3624, "loss": 0.5378, "lr": 5.166153009114188e-06, "epoch": 0.5409134814405961, "percentage": 54.08, "elapsed_time": "1:52:32", "remaining_time": "1:35:32"}
|
| 200 |
+
{"current_steps": 1970, "total_steps": 3624, "loss": 0.5399, "lr": 5.1180034861779685e-06, "epoch": 0.5436732441010073, "percentage": 54.36, "elapsed_time": "1:53:05", "remaining_time": "1:34:57"}
|
| 201 |
+
{"current_steps": 1980, "total_steps": 3624, "loss": 0.5412, "lr": 5.069843011337789e-06, "epoch": 0.5464330067614185, "percentage": 54.64, "elapsed_time": "1:53:37", "remaining_time": "1:34:20"}
|
| 202 |
+
{"current_steps": 1990, "total_steps": 3624, "loss": 0.5415, "lr": 5.0216760543674855e-06, "epoch": 0.5491927694218297, "percentage": 54.91, "elapsed_time": "1:54:09", "remaining_time": "1:33:44"}
|
| 203 |
+
{"current_steps": 2000, "total_steps": 3624, "loss": 0.537, "lr": 4.973507085642502e-06, "epoch": 0.5519525320822409, "percentage": 55.19, "elapsed_time": "1:54:41", "remaining_time": "1:33:07"}
|
| 204 |
+
{"current_steps": 2000, "total_steps": 3624, "eval_loss": 0.540687620639801, "epoch": 0.5519525320822409, "percentage": 55.19, "elapsed_time": "1:55:30", "remaining_time": "1:33:47"}
|
| 205 |
+
{"current_steps": 2010, "total_steps": 3624, "loss": 0.5406, "lr": 4.92534057572499e-06, "epoch": 0.5547122947426522, "percentage": 55.46, "elapsed_time": "1:56:23", "remaining_time": "1:33:28"}
|
| 206 |
+
{"current_steps": 2020, "total_steps": 3624, "loss": 0.5385, "lr": 4.8771809949489056e-06, "epoch": 0.5574720574030634, "percentage": 55.74, "elapsed_time": "1:56:56", "remaining_time": "1:32:51"}
|
| 207 |
+
{"current_steps": 2030, "total_steps": 3624, "loss": 0.542, "lr": 4.829032813005103e-06, "epoch": 0.5602318200634745, "percentage": 56.02, "elapsed_time": "1:57:29", "remaining_time": "1:32:15"}
|
| 208 |
+
{"current_steps": 2040, "total_steps": 3624, "loss": 0.5365, "lr": 4.780900498526515e-06, "epoch": 0.5629915827238857, "percentage": 56.29, "elapsed_time": "1:58:02", "remaining_time": "1:31:39"}
|
| 209 |
+
{"current_steps": 2050, "total_steps": 3624, "loss": 0.5353, "lr": 4.732788518673418e-06, "epoch": 0.5657513453842969, "percentage": 56.57, "elapsed_time": "1:58:35", "remaining_time": "1:31:03"}
|
| 210 |
+
{"current_steps": 2060, "total_steps": 3624, "loss": 0.5317, "lr": 4.684701338718825e-06, "epoch": 0.5685111080447082, "percentage": 56.84, "elapsed_time": "1:59:07", "remaining_time": "1:30:26"}
|
| 211 |
+
{"current_steps": 2070, "total_steps": 3624, "loss": 0.5371, "lr": 4.636643421634075e-06, "epoch": 0.5712708707051194, "percentage": 57.12, "elapsed_time": "1:59:41", "remaining_time": "1:29:51"}
|
| 212 |
+
{"current_steps": 2080, "total_steps": 3624, "loss": 0.5365, "lr": 4.588619227674619e-06, "epoch": 0.5740306333655306, "percentage": 57.4, "elapsed_time": "2:00:14", "remaining_time": "1:29:15"}
|
| 213 |
+
{"current_steps": 2090, "total_steps": 3624, "loss": 0.5334, "lr": 4.540633213966064e-06, "epoch": 0.5767903960259417, "percentage": 57.67, "elapsed_time": "2:00:46", "remaining_time": "1:28:38"}
|
| 214 |
+
{"current_steps": 2100, "total_steps": 3624, "loss": 0.5341, "lr": 4.492689834090508e-06, "epoch": 0.579550158686353, "percentage": 57.95, "elapsed_time": "2:01:19", "remaining_time": "1:28:02"}
|
| 215 |
+
{"current_steps": 2110, "total_steps": 3624, "loss": 0.5306, "lr": 4.444793537673204e-06, "epoch": 0.5823099213467642, "percentage": 58.22, "elapsed_time": "2:01:51", "remaining_time": "1:27:26"}
|
| 216 |
+
{"current_steps": 2120, "total_steps": 3624, "loss": 0.5379, "lr": 4.396948769969587e-06, "epoch": 0.5850696840071754, "percentage": 58.5, "elapsed_time": "2:02:23", "remaining_time": "1:26:49"}
|
| 217 |
+
{"current_steps": 2130, "total_steps": 3624, "loss": 0.5348, "lr": 4.3491599714527115e-06, "epoch": 0.5878294466675866, "percentage": 58.77, "elapsed_time": "2:02:56", "remaining_time": "1:26:13"}
|
| 218 |
+
{"current_steps": 2140, "total_steps": 3624, "loss": 0.5323, "lr": 4.301431577401136e-06, "epoch": 0.5905892093279977, "percentage": 59.05, "elapsed_time": "2:03:27", "remaining_time": "1:25:36"}
|
| 219 |
+
{"current_steps": 2150, "total_steps": 3624, "loss": 0.5389, "lr": 4.253768017487275e-06, "epoch": 0.593348971988409, "percentage": 59.33, "elapsed_time": "2:04:01", "remaining_time": "1:25:01"}
|
| 220 |
+
{"current_steps": 2160, "total_steps": 3624, "loss": 0.5343, "lr": 4.206173715366289e-06, "epoch": 0.5961087346488202, "percentage": 59.6, "elapsed_time": "2:04:36", "remaining_time": "1:24:27"}
|
| 221 |
+
{"current_steps": 2170, "total_steps": 3624, "loss": 0.5352, "lr": 4.1586530882655226e-06, "epoch": 0.5988684973092314, "percentage": 59.88, "elapsed_time": "2:05:10", "remaining_time": "1:23:52"}
|
| 222 |
+
{"current_steps": 2180, "total_steps": 3624, "loss": 0.534, "lr": 4.111210546574545e-06, "epoch": 0.6016282599696426, "percentage": 60.15, "elapsed_time": "2:05:44", "remaining_time": "1:23:17"}
|
| 223 |
+
{"current_steps": 2190, "total_steps": 3624, "loss": 0.5298, "lr": 4.063850493435808e-06, "epoch": 0.6043880226300539, "percentage": 60.43, "elapsed_time": "2:06:17", "remaining_time": "1:22:41"}
|
| 224 |
+
{"current_steps": 2200, "total_steps": 3624, "loss": 0.5338, "lr": 4.0165773243360105e-06, "epoch": 0.607147785290465, "percentage": 60.71, "elapsed_time": "2:06:49", "remaining_time": "1:22:05"}
|
| 225 |
+
{"current_steps": 2210, "total_steps": 3624, "loss": 0.5306, "lr": 3.96939542669814e-06, "epoch": 0.6099075479508762, "percentage": 60.98, "elapsed_time": "2:07:41", "remaining_time": "1:21:41"}
|
| 226 |
+
{"current_steps": 2220, "total_steps": 3624, "loss": 0.5306, "lr": 3.922309179474279e-06, "epoch": 0.6126673106112874, "percentage": 61.26, "elapsed_time": "2:08:13", "remaining_time": "1:21:05"}
|
| 227 |
+
{"current_steps": 2230, "total_steps": 3624, "loss": 0.5348, "lr": 3.875322952739196e-06, "epoch": 0.6154270732716987, "percentage": 61.53, "elapsed_time": "2:08:46", "remaining_time": "1:20:30"}
|
| 228 |
+
{"current_steps": 2240, "total_steps": 3624, "loss": 0.5343, "lr": 3.828441107284755e-06, "epoch": 0.6181868359321099, "percentage": 61.81, "elapsed_time": "2:09:21", "remaining_time": "1:19:55"}
|
| 229 |
+
{"current_steps": 2250, "total_steps": 3624, "loss": 0.523, "lr": 3.7816679942151945e-06, "epoch": 0.620946598592521, "percentage": 62.09, "elapsed_time": "2:09:55", "remaining_time": "1:19:20"}
|
| 230 |
+
{"current_steps": 2260, "total_steps": 3624, "loss": 0.5279, "lr": 3.7350079545433014e-06, "epoch": 0.6237063612529322, "percentage": 62.36, "elapsed_time": "2:10:28", "remaining_time": "1:18:44"}
|
| 231 |
+
{"current_steps": 2270, "total_steps": 3624, "loss": 0.5293, "lr": 3.6884653187875193e-06, "epoch": 0.6264661239133434, "percentage": 62.64, "elapsed_time": "2:11:03", "remaining_time": "1:18:10"}
|
| 232 |
+
{"current_steps": 2280, "total_steps": 3624, "loss": 0.5256, "lr": 3.642044406570031e-06, "epoch": 0.6292258865737547, "percentage": 62.91, "elapsed_time": "2:11:38", "remaining_time": "1:17:35"}
|
| 233 |
+
{"current_steps": 2290, "total_steps": 3624, "loss": 0.5328, "lr": 3.595749526215862e-06, "epoch": 0.6319856492341659, "percentage": 63.19, "elapsed_time": "2:12:11", "remaining_time": "1:17:00"}
|
| 234 |
+
{"current_steps": 2300, "total_steps": 3624, "loss": 0.5336, "lr": 3.549584974353018e-06, "epoch": 0.6347454118945771, "percentage": 63.47, "elapsed_time": "2:12:43", "remaining_time": "1:16:24"}
|
| 235 |
+
{"current_steps": 2310, "total_steps": 3624, "loss": 0.5318, "lr": 3.5035550355137156e-06, "epoch": 0.6375051745549882, "percentage": 63.74, "elapsed_time": "2:13:15", "remaining_time": "1:15:48"}
|
| 236 |
+
{"current_steps": 2320, "total_steps": 3624, "loss": 0.5346, "lr": 3.457663981736739e-06, "epoch": 0.6402649372153995, "percentage": 64.02, "elapsed_time": "2:13:48", "remaining_time": "1:15:12"}
|
| 237 |
+
{"current_steps": 2330, "total_steps": 3624, "loss": 0.5318, "lr": 3.411916072170946e-06, "epoch": 0.6430246998758107, "percentage": 64.29, "elapsed_time": "2:14:23", "remaining_time": "1:14:38"}
|
| 238 |
+
{"current_steps": 2340, "total_steps": 3624, "loss": 0.5306, "lr": 3.3663155526799827e-06, "epoch": 0.6457844625362219, "percentage": 64.57, "elapsed_time": "2:14:57", "remaining_time": "1:14:03"}
|
| 239 |
+
{"current_steps": 2350, "total_steps": 3624, "loss": 0.5291, "lr": 3.3208666554482216e-06, "epoch": 0.6485442251966331, "percentage": 64.85, "elapsed_time": "2:15:30", "remaining_time": "1:13:27"}
|
| 240 |
+
{"current_steps": 2360, "total_steps": 3624, "loss": 0.5229, "lr": 3.275573598587969e-06, "epoch": 0.6513039878570442, "percentage": 65.12, "elapsed_time": "2:16:02", "remaining_time": "1:12:51"}
|
| 241 |
+
{"current_steps": 2370, "total_steps": 3624, "loss": 0.527, "lr": 3.230440585747991e-06, "epoch": 0.6540637505174555, "percentage": 65.4, "elapsed_time": "2:16:35", "remaining_time": "1:12:16"}
|
| 242 |
+
{"current_steps": 2380, "total_steps": 3624, "loss": 0.5261, "lr": 3.185471805723365e-06, "epoch": 0.6568235131778667, "percentage": 65.67, "elapsed_time": "2:17:06", "remaining_time": "1:11:39"}
|
| 243 |
+
{"current_steps": 2390, "total_steps": 3624, "loss": 0.5308, "lr": 3.140671432066719e-06, "epoch": 0.6595832758382779, "percentage": 65.95, "elapsed_time": "2:17:39", "remaining_time": "1:11:04"}
|
| 244 |
+
{"current_steps": 2400, "total_steps": 3624, "loss": 0.5294, "lr": 3.096043622700888e-06, "epoch": 0.6623430384986891, "percentage": 66.23, "elapsed_time": "2:18:11", "remaining_time": "1:10:28"}
|
| 245 |
+
{"current_steps": 2410, "total_steps": 3624, "loss": 0.5283, "lr": 3.0515925195330148e-06, "epoch": 0.6651028011591004, "percentage": 66.5, "elapsed_time": "2:19:03", "remaining_time": "1:10:02"}
|
| 246 |
+
{"current_steps": 2420, "total_steps": 3624, "loss": 0.5275, "lr": 3.0073222480701354e-06, "epoch": 0.6678625638195115, "percentage": 66.78, "elapsed_time": "2:19:36", "remaining_time": "1:09:27"}
|
| 247 |
+
{"current_steps": 2430, "total_steps": 3624, "loss": 0.5235, "lr": 2.9632369170362977e-06, "epoch": 0.6706223264799227, "percentage": 67.05, "elapsed_time": "2:20:08", "remaining_time": "1:08:51"}
|
| 248 |
+
{"current_steps": 2440, "total_steps": 3624, "loss": 0.5271, "lr": 2.9193406179912297e-06, "epoch": 0.6733820891403339, "percentage": 67.33, "elapsed_time": "2:20:40", "remaining_time": "1:08:15"}
|
| 249 |
+
{"current_steps": 2450, "total_steps": 3624, "loss": 0.522, "lr": 2.875637424950595e-06, "epoch": 0.6761418518007452, "percentage": 67.6, "elapsed_time": "2:21:13", "remaining_time": "1:07:40"}
|
| 250 |
+
{"current_steps": 2460, "total_steps": 3624, "loss": 0.5221, "lr": 2.832131394007891e-06, "epoch": 0.6789016144611564, "percentage": 67.88, "elapsed_time": "2:21:45", "remaining_time": "1:07:04"}
|
| 251 |
+
{"current_steps": 2470, "total_steps": 3624, "loss": 0.5289, "lr": 2.788826562958e-06, "epoch": 0.6816613771215675, "percentage": 68.16, "elapsed_time": "2:22:18", "remaining_time": "1:06:29"}
|
| 252 |
+
{"current_steps": 2480, "total_steps": 3624, "loss": 0.5241, "lr": 2.745726950922444e-06, "epoch": 0.6844211397819787, "percentage": 68.43, "elapsed_time": "2:22:51", "remaining_time": "1:05:54"}
|
| 253 |
+
{"current_steps": 2490, "total_steps": 3624, "loss": 0.5298, "lr": 2.7028365579763606e-06, "epoch": 0.6871809024423899, "percentage": 68.71, "elapsed_time": "2:23:24", "remaining_time": "1:05:18"}
|
| 254 |
+
{"current_steps": 2500, "total_steps": 3624, "loss": 0.5282, "lr": 2.6601593647772696e-06, "epoch": 0.6899406651028012, "percentage": 68.98, "elapsed_time": "2:23:57", "remaining_time": "1:04:43"}
|
| 255 |
+
{"current_steps": 2500, "total_steps": 3624, "eval_loss": 0.5283246636390686, "epoch": 0.6899406651028012, "percentage": 68.98, "elapsed_time": "2:24:48", "remaining_time": "1:05:06"}
|
| 256 |
+
{"current_steps": 2510, "total_steps": 3624, "loss": 0.5253, "lr": 2.6176993321956185e-06, "epoch": 0.6927004277632124, "percentage": 69.26, "elapsed_time": "2:25:21", "remaining_time": "1:04:30"}
|
| 257 |
+
{"current_steps": 2520, "total_steps": 3624, "loss": 0.5229, "lr": 2.5754604009471786e-06, "epoch": 0.6954601904236236, "percentage": 69.54, "elapsed_time": "2:25:53", "remaining_time": "1:03:54"}
|
| 258 |
+
{"current_steps": 2530, "total_steps": 3624, "loss": 0.5247, "lr": 2.533446491227305e-06, "epoch": 0.6982199530840347, "percentage": 69.81, "elapsed_time": "2:26:26", "remaining_time": "1:03:19"}
|
| 259 |
+
{"current_steps": 2540, "total_steps": 3624, "loss": 0.5218, "lr": 2.491661502347106e-06, "epoch": 0.700979715744446, "percentage": 70.09, "elapsed_time": "2:26:59", "remaining_time": "1:02:43"}
|
| 260 |
+
{"current_steps": 2550, "total_steps": 3624, "loss": 0.5238, "lr": 2.4501093123715395e-06, "epoch": 0.7037394784048572, "percentage": 70.36, "elapsed_time": "2:27:32", "remaining_time": "1:02:08"}
|
| 261 |
+
{"current_steps": 2560, "total_steps": 3624, "loss": 0.5234, "lr": 2.408793777759504e-06, "epoch": 0.7064992410652684, "percentage": 70.64, "elapsed_time": "2:28:04", "remaining_time": "1:01:32"}
|
| 262 |
+
{"current_steps": 2570, "total_steps": 3624, "loss": 0.5247, "lr": 2.3677187330059084e-06, "epoch": 0.7092590037256796, "percentage": 70.92, "elapsed_time": "2:28:41", "remaining_time": "1:00:58"}
|
| 263 |
+
{"current_steps": 2580, "total_steps": 3624, "loss": 0.5194, "lr": 2.3268879902857978e-06, "epoch": 0.7120187663860909, "percentage": 71.19, "elapsed_time": "2:29:16", "remaining_time": "1:00:24"}
|
| 264 |
+
{"current_steps": 2590, "total_steps": 3624, "loss": 0.5236, "lr": 2.2863053391005462e-06, "epoch": 0.714778529046502, "percentage": 71.47, "elapsed_time": "2:29:48", "remaining_time": "0:59:48"}
|
| 265 |
+
{"current_steps": 2600, "total_steps": 3624, "loss": 0.5179, "lr": 2.245974545926152e-06, "epoch": 0.7175382917069132, "percentage": 71.74, "elapsed_time": "2:30:20", "remaining_time": "0:59:12"}
|
| 266 |
+
{"current_steps": 2610, "total_steps": 3624, "loss": 0.5224, "lr": 2.205899353863665e-06, "epoch": 0.7202980543673244, "percentage": 72.02, "elapsed_time": "2:31:13", "remaining_time": "0:58:45"}
|
| 267 |
+
{"current_steps": 2620, "total_steps": 3624, "loss": 0.5254, "lr": 2.166083482291801e-06, "epoch": 0.7230578170277356, "percentage": 72.3, "elapsed_time": "2:31:45", "remaining_time": "0:58:09"}
|
| 268 |
+
{"current_steps": 2630, "total_steps": 3624, "loss": 0.5214, "lr": 2.1265306265217382e-06, "epoch": 0.7258175796881469, "percentage": 72.57, "elapsed_time": "2:32:19", "remaining_time": "0:57:34"}
|
| 269 |
+
{"current_steps": 2640, "total_steps": 3624, "loss": 0.5298, "lr": 2.0872444574541574e-06, "epoch": 0.728577342348558, "percentage": 72.85, "elapsed_time": "2:32:52", "remaining_time": "0:56:59"}
|
| 270 |
+
{"current_steps": 2650, "total_steps": 3624, "loss": 0.5209, "lr": 2.048228621238547e-06, "epoch": 0.7313371050089692, "percentage": 73.12, "elapsed_time": "2:33:25", "remaining_time": "0:56:23"}
|
| 271 |
+
{"current_steps": 2660, "total_steps": 3624, "loss": 0.5248, "lr": 2.0094867389347982e-06, "epoch": 0.7340968676693804, "percentage": 73.4, "elapsed_time": "2:33:58", "remaining_time": "0:55:47"}
|
| 272 |
+
{"current_steps": 2670, "total_steps": 3624, "loss": 0.5227, "lr": 1.971022406177142e-06, "epoch": 0.7368566303297917, "percentage": 73.68, "elapsed_time": "2:34:31", "remaining_time": "0:55:12"}
|
| 273 |
+
{"current_steps": 2680, "total_steps": 3624, "loss": 0.522, "lr": 1.932839192840436e-06, "epoch": 0.7396163929902029, "percentage": 73.95, "elapsed_time": "2:35:04", "remaining_time": "0:54:37"}
|
| 274 |
+
{"current_steps": 2690, "total_steps": 3624, "loss": 0.5223, "lr": 1.8949406427088407e-06, "epoch": 0.7423761556506141, "percentage": 74.23, "elapsed_time": "2:35:37", "remaining_time": "0:54:01"}
|
| 275 |
+
{"current_steps": 2700, "total_steps": 3624, "loss": 0.5241, "lr": 1.8573302731469255e-06, "epoch": 0.7451359183110252, "percentage": 74.5, "elapsed_time": "2:36:10", "remaining_time": "0:53:26"}
|
| 276 |
+
{"current_steps": 2710, "total_steps": 3624, "loss": 0.5264, "lr": 1.820011574773221e-06, "epoch": 0.7478956809714364, "percentage": 74.78, "elapsed_time": "2:36:42", "remaining_time": "0:52:51"}
|
| 277 |
+
{"current_steps": 2720, "total_steps": 3624, "loss": 0.5181, "lr": 1.7829880111362486e-06, "epoch": 0.7506554436318477, "percentage": 75.06, "elapsed_time": "2:37:13", "remaining_time": "0:52:15"}
|
| 278 |
+
{"current_steps": 2730, "total_steps": 3624, "loss": 0.5292, "lr": 1.746263018393079e-06, "epoch": 0.7534152062922589, "percentage": 75.33, "elapsed_time": "2:37:47", "remaining_time": "0:51:40"}
|
| 279 |
+
{"current_steps": 2740, "total_steps": 3624, "loss": 0.5219, "lr": 1.7098400049904163e-06, "epoch": 0.7561749689526701, "percentage": 75.61, "elapsed_time": "2:38:19", "remaining_time": "0:51:04"}
|
| 280 |
+
{"current_steps": 2750, "total_steps": 3624, "loss": 0.5259, "lr": 1.6737223513482591e-06, "epoch": 0.7589347316130812, "percentage": 75.88, "elapsed_time": "2:38:52", "remaining_time": "0:50:29"}
|
| 281 |
+
{"current_steps": 2760, "total_steps": 3624, "loss": 0.5171, "lr": 1.6379134095461673e-06, "epoch": 0.7616944942734925, "percentage": 76.16, "elapsed_time": "2:39:24", "remaining_time": "0:49:53"}
|
| 282 |
+
{"current_steps": 2770, "total_steps": 3624, "loss": 0.521, "lr": 1.6024165030121542e-06, "epoch": 0.7644542569339037, "percentage": 76.43, "elapsed_time": "2:39:56", "remaining_time": "0:49:18"}
|
| 283 |
+
{"current_steps": 2780, "total_steps": 3624, "loss": 0.5149, "lr": 1.567234926214236e-06, "epoch": 0.7672140195943149, "percentage": 76.71, "elapsed_time": "2:40:28", "remaining_time": "0:48:43"}
|
| 284 |
+
{"current_steps": 2790, "total_steps": 3624, "loss": 0.5217, "lr": 1.5323719443546785e-06, "epoch": 0.7699737822547261, "percentage": 76.99, "elapsed_time": "2:41:01", "remaining_time": "0:48:08"}
|
| 285 |
+
{"current_steps": 2800, "total_steps": 3624, "loss": 0.5174, "lr": 1.4978307930669483e-06, "epoch": 0.7727335449151373, "percentage": 77.26, "elapsed_time": "2:41:34", "remaining_time": "0:47:32"}
|
| 286 |
+
{"current_steps": 2810, "total_steps": 3624, "loss": 0.5262, "lr": 1.4636146781154164e-06, "epoch": 0.7754933075755485, "percentage": 77.54, "elapsed_time": "2:42:26", "remaining_time": "0:47:03"}
|
| 287 |
+
{"current_steps": 2820, "total_steps": 3624, "loss": 0.5258, "lr": 1.4297267750978277e-06, "epoch": 0.7782530702359597, "percentage": 77.81, "elapsed_time": "2:42:59", "remaining_time": "0:46:28"}
|
| 288 |
+
{"current_steps": 2830, "total_steps": 3624, "loss": 0.5233, "lr": 1.3961702291505791e-06, "epoch": 0.7810128328963709, "percentage": 78.09, "elapsed_time": "2:43:31", "remaining_time": "0:45:52"}
|
| 289 |
+
{"current_steps": 2840, "total_steps": 3624, "loss": 0.5153, "lr": 1.3629481546568163e-06, "epoch": 0.7837725955567821, "percentage": 78.37, "elapsed_time": "2:44:03", "remaining_time": "0:45:17"}
|
| 290 |
+
{"current_steps": 2850, "total_steps": 3624, "loss": 0.5169, "lr": 1.3300636349573882e-06, "epoch": 0.7865323582171934, "percentage": 78.64, "elapsed_time": "2:44:35", "remaining_time": "0:44:42"}
|
| 291 |
+
{"current_steps": 2860, "total_steps": 3624, "loss": 0.5211, "lr": 1.2975197220646807e-06, "epoch": 0.7892921208776045, "percentage": 78.92, "elapsed_time": "2:45:08", "remaining_time": "0:44:06"}
|
| 292 |
+
{"current_steps": 2870, "total_steps": 3624, "loss": 0.5169, "lr": 1.2653194363793642e-06, "epoch": 0.7920518835380157, "percentage": 79.19, "elapsed_time": "2:45:40", "remaining_time": "0:43:31"}
|
| 293 |
+
{"current_steps": 2880, "total_steps": 3624, "loss": 0.5167, "lr": 1.2334657664100614e-06, "epoch": 0.7948116461984269, "percentage": 79.47, "elapsed_time": "2:46:12", "remaining_time": "0:42:56"}
|
| 294 |
+
{"current_steps": 2890, "total_steps": 3624, "loss": 0.5207, "lr": 1.2019616684959934e-06, "epoch": 0.7975714088588381, "percentage": 79.75, "elapsed_time": "2:46:45", "remaining_time": "0:42:21"}
|
| 295 |
+
{"current_steps": 2900, "total_steps": 3624, "loss": 0.5176, "lr": 1.1708100665325967e-06, "epoch": 0.8003311715192494, "percentage": 80.02, "elapsed_time": "2:47:17", "remaining_time": "0:41:45"}
|
| 296 |
+
{"current_steps": 2910, "total_steps": 3624, "loss": 0.5147, "lr": 1.1400138517001564e-06, "epoch": 0.8030909341796606, "percentage": 80.3, "elapsed_time": "2:47:49", "remaining_time": "0:41:10"}
|
| 297 |
+
{"current_steps": 2920, "total_steps": 3624, "loss": 0.5212, "lr": 1.1095758821954788e-06, "epoch": 0.8058506968400717, "percentage": 80.57, "elapsed_time": "2:48:22", "remaining_time": "0:40:35"}
|
| 298 |
+
{"current_steps": 2930, "total_steps": 3624, "loss": 0.5154, "lr": 1.0794989829666197e-06, "epoch": 0.8086104595004829, "percentage": 80.85, "elapsed_time": "2:48:55", "remaining_time": "0:40:00"}
|
| 299 |
+
{"current_steps": 2940, "total_steps": 3624, "loss": 0.516, "lr": 1.049785945450697e-06, "epoch": 0.8113702221608942, "percentage": 81.13, "elapsed_time": "2:49:28", "remaining_time": "0:39:25"}
|
| 300 |
+
{"current_steps": 2950, "total_steps": 3624, "loss": 0.5197, "lr": 1.0204395273148277e-06, "epoch": 0.8141299848213054, "percentage": 81.4, "elapsed_time": "2:50:00", "remaining_time": "0:38:50"}
|
| 301 |
+
{"current_steps": 2960, "total_steps": 3624, "loss": 0.5232, "lr": 9.914624522001792e-07, "epoch": 0.8168897474817166, "percentage": 81.68, "elapsed_time": "2:50:33", "remaining_time": "0:38:15"}
|
| 302 |
+
{"current_steps": 2970, "total_steps": 3624, "loss": 0.5139, "lr": 9.628574094691945e-07, "epoch": 0.8196495101421277, "percentage": 81.95, "elapsed_time": "2:51:05", "remaining_time": "0:37:40"}
|
| 303 |
+
{"current_steps": 2980, "total_steps": 3624, "loss": 0.52, "lr": 9.346270539559882e-07, "epoch": 0.822409272802539, "percentage": 82.23, "elapsed_time": "2:51:38", "remaining_time": "0:37:05"}
|
| 304 |
+
{"current_steps": 2990, "total_steps": 3624, "loss": 0.518, "lr": 9.067740057199514e-07, "epoch": 0.8251690354629502, "percentage": 82.51, "elapsed_time": "2:52:10", "remaining_time": "0:36:30"}
|
| 305 |
+
{"current_steps": 3000, "total_steps": 3624, "loss": 0.5155, "lr": 8.793008498025879e-07, "epoch": 0.8279287981233614, "percentage": 82.78, "elapsed_time": "2:52:43", "remaining_time": "0:35:55"}
|
| 306 |
+
{"current_steps": 3000, "total_steps": 3624, "eval_loss": 0.5207065939903259, "epoch": 0.8279287981233614, "percentage": 82.78, "elapsed_time": "2:53:32", "remaining_time": "0:36:05"}
|
| 307 |
+
{"current_steps": 3010, "total_steps": 3624, "loss": 0.5131, "lr": 8.522101359875934e-07, "epoch": 0.8306885607837726, "percentage": 83.06, "elapsed_time": "2:54:25", "remaining_time": "0:35:34"}
|
| 308 |
+
{"current_steps": 3020, "total_steps": 3624, "loss": 0.5125, "lr": 8.255043785642108e-07, "epoch": 0.8334483234441838, "percentage": 83.33, "elapsed_time": "2:54:56", "remaining_time": "0:34:59"}
|
| 309 |
+
{"current_steps": 3030, "total_steps": 3624, "loss": 0.5234, "lr": 7.991860560938786e-07, "epoch": 0.836208086104595, "percentage": 83.61, "elapsed_time": "2:55:29", "remaining_time": "0:34:24"}
|
| 310 |
+
{"current_steps": 3040, "total_steps": 3624, "loss": 0.5176, "lr": 7.732576111801982e-07, "epoch": 0.8389678487650062, "percentage": 83.89, "elapsed_time": "2:56:01", "remaining_time": "0:33:48"}
|
| 311 |
+
{"current_steps": 3050, "total_steps": 3624, "loss": 0.5223, "lr": 7.477214502422281e-07, "epoch": 0.8417276114254174, "percentage": 84.16, "elapsed_time": "2:56:33", "remaining_time": "0:33:13"}
|
| 312 |
+
{"current_steps": 3060, "total_steps": 3624, "loss": 0.5219, "lr": 7.225799432911557e-07, "epoch": 0.8444873740858286, "percentage": 84.44, "elapsed_time": "2:57:06", "remaining_time": "0:32:38"}
|
| 313 |
+
{"current_steps": 3070, "total_steps": 3624, "loss": 0.516, "lr": 6.978354237103264e-07, "epoch": 0.8472471367462399, "percentage": 84.71, "elapsed_time": "2:57:40", "remaining_time": "0:32:03"}
|
| 314 |
+
{"current_steps": 3080, "total_steps": 3624, "loss": 0.5185, "lr": 6.734901880386896e-07, "epoch": 0.850006899406651, "percentage": 84.99, "elapsed_time": "2:58:13", "remaining_time": "0:31:28"}
|
| 315 |
+
{"current_steps": 3090, "total_steps": 3624, "loss": 0.5122, "lr": 6.495464957576508e-07, "epoch": 0.8527666620670622, "percentage": 85.26, "elapsed_time": "2:58:48", "remaining_time": "0:30:54"}
|
| 316 |
+
{"current_steps": 3100, "total_steps": 3624, "loss": 0.5158, "lr": 6.260065690813754e-07, "epoch": 0.8555264247274734, "percentage": 85.54, "elapsed_time": "2:59:20", "remaining_time": "0:30:18"}
|
| 317 |
+
{"current_steps": 3110, "total_steps": 3624, "loss": 0.5201, "lr": 6.028725927505369e-07, "epoch": 0.8582861873878846, "percentage": 85.82, "elapsed_time": "2:59:52", "remaining_time": "0:29:43"}
|
| 318 |
+
{"current_steps": 3120, "total_steps": 3624, "loss": 0.5189, "lr": 5.801467138295597e-07, "epoch": 0.8610459500482959, "percentage": 86.09, "elapsed_time": "3:00:25", "remaining_time": "0:29:08"}
|
| 319 |
+
{"current_steps": 3130, "total_steps": 3624, "loss": 0.515, "lr": 5.578310415073451e-07, "epoch": 0.8638057127087071, "percentage": 86.37, "elapsed_time": "3:00:59", "remaining_time": "0:28:33"}
|
| 320 |
+
{"current_steps": 3140, "total_steps": 3624, "loss": 0.5151, "lr": 5.359276469015179e-07, "epoch": 0.8665654753691182, "percentage": 86.64, "elapsed_time": "3:01:31", "remaining_time": "0:27:58"}
|
| 321 |
+
{"current_steps": 3150, "total_steps": 3624, "loss": 0.5223, "lr": 5.14438562866208e-07, "epoch": 0.8693252380295294, "percentage": 86.92, "elapsed_time": "3:02:03", "remaining_time": "0:27:23"}
|
| 322 |
+
{"current_steps": 3160, "total_steps": 3624, "loss": 0.5144, "lr": 4.933657838033795e-07, "epoch": 0.8720850006899407, "percentage": 87.2, "elapsed_time": "3:02:35", "remaining_time": "0:26:48"}
|
| 323 |
+
{"current_steps": 3170, "total_steps": 3624, "loss": 0.5165, "lr": 4.7271126547772773e-07, "epoch": 0.8748447633503519, "percentage": 87.47, "elapsed_time": "3:03:08", "remaining_time": "0:26:13"}
|
| 324 |
+
{"current_steps": 3180, "total_steps": 3624, "loss": 0.5157, "lr": 4.524769248351718e-07, "epoch": 0.8776045260107631, "percentage": 87.75, "elapsed_time": "3:03:40", "remaining_time": "0:25:38"}
|
| 325 |
+
{"current_steps": 3190, "total_steps": 3624, "loss": 0.5167, "lr": 4.3266463982493566e-07, "epoch": 0.8803642886711743, "percentage": 88.02, "elapsed_time": "3:04:13", "remaining_time": "0:25:03"}
|
| 326 |
+
{"current_steps": 3200, "total_steps": 3624, "loss": 0.5229, "lr": 4.132762492252601e-07, "epoch": 0.8831240513315854, "percentage": 88.3, "elapsed_time": "3:04:46", "remaining_time": "0:24:28"}
|
| 327 |
+
{"current_steps": 3210, "total_steps": 3624, "loss": 0.5168, "lr": 3.943135524727448e-07, "epoch": 0.8858838139919967, "percentage": 88.58, "elapsed_time": "3:05:38", "remaining_time": "0:23:56"}
|
| 328 |
+
{"current_steps": 3220, "total_steps": 3624, "loss": 0.52, "lr": 3.757783094953382e-07, "epoch": 0.8886435766524079, "percentage": 88.85, "elapsed_time": "3:06:11", "remaining_time": "0:23:21"}
|
| 329 |
+
{"current_steps": 3230, "total_steps": 3624, "loss": 0.514, "lr": 3.5767224054900687e-07, "epoch": 0.8914033393128191, "percentage": 89.13, "elapsed_time": "3:06:44", "remaining_time": "0:22:46"}
|
| 330 |
+
{"current_steps": 3240, "total_steps": 3624, "loss": 0.5153, "lr": 3.3999702605807203e-07, "epoch": 0.8941631019732303, "percentage": 89.4, "elapsed_time": "3:07:16", "remaining_time": "0:22:11"}
|
| 331 |
+
{"current_steps": 3250, "total_steps": 3624, "loss": 0.5179, "lr": 3.227543064592514e-07, "epoch": 0.8969228646336415, "percentage": 89.68, "elapsed_time": "3:07:49", "remaining_time": "0:21:36"}
|
| 332 |
+
{"current_steps": 3260, "total_steps": 3624, "loss": 0.5187, "lr": 3.059456820494111e-07, "epoch": 0.8996826272940527, "percentage": 89.96, "elapsed_time": "3:08:22", "remaining_time": "0:21:02"}
|
| 333 |
+
{"current_steps": 3270, "total_steps": 3624, "loss": 0.5188, "lr": 2.8957271283704067e-07, "epoch": 0.9024423899544639, "percentage": 90.23, "elapsed_time": "3:08:55", "remaining_time": "0:20:27"}
|
| 334 |
+
{"current_steps": 3280, "total_steps": 3624, "loss": 0.5161, "lr": 2.736369183974685e-07, "epoch": 0.9052021526148751, "percentage": 90.51, "elapsed_time": "3:09:27", "remaining_time": "0:19:52"}
|
| 335 |
+
{"current_steps": 3290, "total_steps": 3624, "loss": 0.515, "lr": 2.5813977773183175e-07, "epoch": 0.9079619152752864, "percentage": 90.78, "elapsed_time": "3:09:59", "remaining_time": "0:19:17"}
|
| 336 |
+
{"current_steps": 3300, "total_steps": 3624, "loss": 0.5198, "lr": 2.430827291298099e-07, "epoch": 0.9107216779356976, "percentage": 91.06, "elapsed_time": "3:10:33", "remaining_time": "0:18:42"}
|
| 337 |
+
{"current_steps": 3310, "total_steps": 3624, "loss": 0.5221, "lr": 2.2846717003613462e-07, "epoch": 0.9134814405961087, "percentage": 91.34, "elapsed_time": "3:11:05", "remaining_time": "0:18:07"}
|
| 338 |
+
{"current_steps": 3320, "total_steps": 3624, "loss": 0.5154, "lr": 2.1429445692089712e-07, "epoch": 0.9162412032565199, "percentage": 91.61, "elapsed_time": "3:11:39", "remaining_time": "0:17:33"}
|
| 339 |
+
{"current_steps": 3330, "total_steps": 3624, "loss": 0.5159, "lr": 2.0056590515365016e-07, "epoch": 0.9190009659169311, "percentage": 91.89, "elapsed_time": "3:12:14", "remaining_time": "0:16:58"}
|
| 340 |
+
{"current_steps": 3340, "total_steps": 3624, "loss": 0.518, "lr": 1.8728278888132944e-07, "epoch": 0.9217607285773424, "percentage": 92.16, "elapsed_time": "3:12:47", "remaining_time": "0:16:23"}
|
| 341 |
+
{"current_steps": 3350, "total_steps": 3624, "loss": 0.5189, "lr": 1.744463409100039e-07, "epoch": 0.9245204912377536, "percentage": 92.44, "elapsed_time": "3:13:19", "remaining_time": "0:15:48"}
|
| 342 |
+
{"current_steps": 3360, "total_steps": 3624, "loss": 0.5099, "lr": 1.620577525904532e-07, "epoch": 0.9272802538981647, "percentage": 92.72, "elapsed_time": "3:13:51", "remaining_time": "0:15:13"}
|
| 343 |
+
{"current_steps": 3370, "total_steps": 3624, "loss": 0.5154, "lr": 1.501181737076035e-07, "epoch": 0.9300400165585759, "percentage": 92.99, "elapsed_time": "3:14:24", "remaining_time": "0:14:39"}
|
| 344 |
+
{"current_steps": 3380, "total_steps": 3624, "loss": 0.5108, "lr": 1.3862871237381004e-07, "epoch": 0.9327997792189872, "percentage": 93.27, "elapsed_time": "3:14:56", "remaining_time": "0:14:04"}
|
| 345 |
+
{"current_steps": 3390, "total_steps": 3624, "loss": 0.5136, "lr": 1.2759043492601986e-07, "epoch": 0.9355595418793984, "percentage": 93.54, "elapsed_time": "3:15:28", "remaining_time": "0:13:29"}
|
| 346 |
+
{"current_steps": 3400, "total_steps": 3624, "loss": 0.5192, "lr": 1.1700436582680108e-07, "epoch": 0.9383193045398096, "percentage": 93.82, "elapsed_time": "3:16:01", "remaining_time": "0:12:54"}
|
| 347 |
+
{"current_steps": 3410, "total_steps": 3624, "loss": 0.5116, "lr": 1.068714875692628e-07, "epoch": 0.9410790672002208, "percentage": 94.09, "elapsed_time": "3:16:53", "remaining_time": "0:12:21"}
|
| 348 |
+
{"current_steps": 3420, "total_steps": 3624, "loss": 0.5125, "lr": 9.719274058587247e-08, "epoch": 0.943838829860632, "percentage": 94.37, "elapsed_time": "3:17:25", "remaining_time": "0:11:46"}
|
| 349 |
+
{"current_steps": 3430, "total_steps": 3624, "loss": 0.5156, "lr": 8.796902316117018e-08, "epoch": 0.9465985925210432, "percentage": 94.65, "elapsed_time": "3:17:58", "remaining_time": "0:11:11"}
|
| 350 |
+
{"current_steps": 3440, "total_steps": 3624, "loss": 0.5141, "lr": 7.920119134840199e-08, "epoch": 0.9493583551814544, "percentage": 94.92, "elapsed_time": "3:18:31", "remaining_time": "0:10:37"}
|
| 351 |
+
{"current_steps": 3450, "total_steps": 3624, "loss": 0.5131, "lr": 7.08900588900685e-08, "epoch": 0.9521181178418656, "percentage": 95.2, "elapsed_time": "3:19:03", "remaining_time": "0:10:02"}
|
| 352 |
+
{"current_steps": 3460, "total_steps": 3624, "loss": 0.5193, "lr": 6.303639714240196e-08, "epoch": 0.9548778805022768, "percentage": 95.47, "elapsed_time": "3:19:35", "remaining_time": "0:09:27"}
|
| 353 |
+
{"current_steps": 3470, "total_steps": 3624, "loss": 0.515, "lr": 5.564093500377732e-08, "epoch": 0.957637643162688, "percentage": 95.75, "elapsed_time": "3:20:07", "remaining_time": "0:08:52"}
|
| 354 |
+
{"current_steps": 3480, "total_steps": 3624, "loss": 0.5135, "lr": 4.870435884705982e-08, "epoch": 0.9603974058230992, "percentage": 96.03, "elapsed_time": "3:20:40", "remaining_time": "0:08:18"}
|
| 355 |
+
{"current_steps": 3490, "total_steps": 3624, "loss": 0.5165, "lr": 4.22273124559075e-08, "epoch": 0.9631571684835104, "percentage": 96.3, "elapsed_time": "3:21:13", "remaining_time": "0:07:43"}
|
| 356 |
+
{"current_steps": 3500, "total_steps": 3624, "loss": 0.5106, "lr": 3.621039696501794e-08, "epoch": 0.9659169311439216, "percentage": 96.58, "elapsed_time": "3:21:47", "remaining_time": "0:07:08"}
|
| 357 |
+
{"current_steps": 3500, "total_steps": 3624, "eval_loss": 0.5180693864822388, "epoch": 0.9659169311439216, "percentage": 96.58, "elapsed_time": "3:22:36", "remaining_time": "0:07:10"}
|
| 358 |
+
{"current_steps": 3510, "total_steps": 3624, "loss": 0.517, "lr": 3.065417080433841e-08, "epoch": 0.9686766938043329, "percentage": 96.85, "elapsed_time": "3:23:08", "remaining_time": "0:06:35"}
|
| 359 |
+
{"current_steps": 3520, "total_steps": 3624, "loss": 0.5142, "lr": 2.555914964723849e-08, "epoch": 0.9714364564647441, "percentage": 97.13, "elapsed_time": "3:23:42", "remaining_time": "0:06:01"}
|
| 360 |
+
{"current_steps": 3530, "total_steps": 3624, "loss": 0.5198, "lr": 2.0925806362648847e-08, "epoch": 0.9741962191251552, "percentage": 97.41, "elapsed_time": "3:24:14", "remaining_time": "0:05:26"}
|
| 361 |
+
{"current_steps": 3540, "total_steps": 3624, "loss": 0.5125, "lr": 1.6754570971176944e-08, "epoch": 0.9769559817855664, "percentage": 97.68, "elapsed_time": "3:24:47", "remaining_time": "0:04:51"}
|
| 362 |
+
{"current_steps": 3550, "total_steps": 3624, "loss": 0.5192, "lr": 1.3045830605192266e-08, "epoch": 0.9797157444459776, "percentage": 97.96, "elapsed_time": "3:25:19", "remaining_time": "0:04:16"}
|
| 363 |
+
{"current_steps": 3560, "total_steps": 3624, "loss": 0.5205, "lr": 9.799929472902315e-09, "epoch": 0.9824755071063889, "percentage": 98.23, "elapsed_time": "3:25:52", "remaining_time": "0:03:42"}
|
| 364 |
+
{"current_steps": 3570, "total_steps": 3624, "loss": 0.5169, "lr": 7.017168826401466e-09, "epoch": 0.9852352697668001, "percentage": 98.51, "elapsed_time": "3:26:27", "remaining_time": "0:03:07"}
|
| 365 |
+
{"current_steps": 3580, "total_steps": 3624, "loss": 0.5095, "lr": 4.697806933715021e-09, "epoch": 0.9879950324272112, "percentage": 98.79, "elapsed_time": "3:26:59", "remaining_time": "0:02:32"}
|
| 366 |
+
{"current_steps": 3590, "total_steps": 3624, "loss": 0.5175, "lr": 2.8420590548294825e-09, "epoch": 0.9907547950876224, "percentage": 99.06, "elapsed_time": "3:27:32", "remaining_time": "0:01:57"}
|
| 367 |
+
{"current_steps": 3600, "total_steps": 3624, "loss": 0.519, "lr": 1.450097421710206e-09, "epoch": 0.9935145577480337, "percentage": 99.34, "elapsed_time": "3:28:04", "remaining_time": "0:01:23"}
|
| 368 |
+
{"current_steps": 3610, "total_steps": 3624, "loss": 0.5135, "lr": 5.220512223219621e-10, "epoch": 0.9962743204084449, "percentage": 99.61, "elapsed_time": "3:28:57", "remaining_time": "0:00:48"}
|
| 369 |
+
{"current_steps": 3620, "total_steps": 3624, "loss": 0.5151, "lr": 5.8006588636305704e-11, "epoch": 0.9990340830688561, "percentage": 99.89, "elapsed_time": "3:29:29", "remaining_time": "0:00:13"}
|
| 370 |
+
{"current_steps": 3624, "total_steps": 3624, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "3:30:00", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,2633 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"best_global_step": null,
|
| 3 |
+
"best_metric": null,
|
| 4 |
+
"best_model_checkpoint": null,
|
| 5 |
+
"epoch": 1.0,
|
| 6 |
+
"eval_steps": 500,
|
| 7 |
+
"global_step": 3624,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.0027597626604112047,
|
| 14 |
+
"grad_norm": 9.687899712924036,
|
| 15 |
+
"learning_rate": 2.4793388429752067e-07,
|
| 16 |
+
"loss": 1.2489,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.005519525320822409,
|
| 21 |
+
"grad_norm": 7.993583387794843,
|
| 22 |
+
"learning_rate": 5.234159779614326e-07,
|
| 23 |
+
"loss": 1.23,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.008279287981233613,
|
| 28 |
+
"grad_norm": 4.419911118410825,
|
| 29 |
+
"learning_rate": 7.988980716253444e-07,
|
| 30 |
+
"loss": 1.134,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.011039050641644819,
|
| 35 |
+
"grad_norm": 3.0732247545437965,
|
| 36 |
+
"learning_rate": 1.0743801652892562e-06,
|
| 37 |
+
"loss": 0.993,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.013798813302056023,
|
| 42 |
+
"grad_norm": 2.005789581836949,
|
| 43 |
+
"learning_rate": 1.3498622589531682e-06,
|
| 44 |
+
"loss": 0.8782,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.016558575962467226,
|
| 49 |
+
"grad_norm": 1.3028620164242184,
|
| 50 |
+
"learning_rate": 1.62534435261708e-06,
|
| 51 |
+
"loss": 0.8004,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.019318338622878434,
|
| 56 |
+
"grad_norm": 1.2871645472343145,
|
| 57 |
+
"learning_rate": 1.900826446280992e-06,
|
| 58 |
+
"loss": 0.7618,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.022078101283289638,
|
| 63 |
+
"grad_norm": 2.0977280137118854,
|
| 64 |
+
"learning_rate": 2.1763085399449038e-06,
|
| 65 |
+
"loss": 0.7363,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.02483786394370084,
|
| 70 |
+
"grad_norm": 1.235679470482907,
|
| 71 |
+
"learning_rate": 2.4517906336088157e-06,
|
| 72 |
+
"loss": 0.7218,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.027597626604112045,
|
| 77 |
+
"grad_norm": 1.2008847267657137,
|
| 78 |
+
"learning_rate": 2.7272727272727272e-06,
|
| 79 |
+
"loss": 0.7039,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.030357389264523253,
|
| 84 |
+
"grad_norm": 1.2865692124934534,
|
| 85 |
+
"learning_rate": 3.002754820936639e-06,
|
| 86 |
+
"loss": 0.7016,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.03311715192493445,
|
| 91 |
+
"grad_norm": 1.225519692241417,
|
| 92 |
+
"learning_rate": 3.278236914600551e-06,
|
| 93 |
+
"loss": 0.6911,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.035876914585345664,
|
| 98 |
+
"grad_norm": 1.1074744380119828,
|
| 99 |
+
"learning_rate": 3.553719008264463e-06,
|
| 100 |
+
"loss": 0.6837,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.03863667724575687,
|
| 105 |
+
"grad_norm": 1.2255853901709166,
|
| 106 |
+
"learning_rate": 3.8292011019283746e-06,
|
| 107 |
+
"loss": 0.6733,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.04139643990616807,
|
| 112 |
+
"grad_norm": 1.2160790653325682,
|
| 113 |
+
"learning_rate": 4.104683195592287e-06,
|
| 114 |
+
"loss": 0.6663,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.044156202566579275,
|
| 119 |
+
"grad_norm": 1.2160126107257938,
|
| 120 |
+
"learning_rate": 4.3801652892561984e-06,
|
| 121 |
+
"loss": 0.6672,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.04691596522699048,
|
| 126 |
+
"grad_norm": 1.3030345619512333,
|
| 127 |
+
"learning_rate": 4.655647382920111e-06,
|
| 128 |
+
"loss": 0.6604,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.04967572788740168,
|
| 133 |
+
"grad_norm": 1.1675762652939756,
|
| 134 |
+
"learning_rate": 4.931129476584022e-06,
|
| 135 |
+
"loss": 0.654,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.05243549054781289,
|
| 140 |
+
"grad_norm": 1.3421701645033057,
|
| 141 |
+
"learning_rate": 5.206611570247935e-06,
|
| 142 |
+
"loss": 0.653,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.05519525320822409,
|
| 147 |
+
"grad_norm": 1.1987056035659454,
|
| 148 |
+
"learning_rate": 5.482093663911846e-06,
|
| 149 |
+
"loss": 0.6508,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.057955015868635294,
|
| 154 |
+
"grad_norm": 1.3869845490974586,
|
| 155 |
+
"learning_rate": 5.7575757575757586e-06,
|
| 156 |
+
"loss": 0.6498,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.060714778529046505,
|
| 161 |
+
"grad_norm": 1.116588718762935,
|
| 162 |
+
"learning_rate": 6.03305785123967e-06,
|
| 163 |
+
"loss": 0.6453,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.06347454118945771,
|
| 168 |
+
"grad_norm": 1.0960389471025322,
|
| 169 |
+
"learning_rate": 6.3085399449035824e-06,
|
| 170 |
+
"loss": 0.6414,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.0662343038498689,
|
| 175 |
+
"grad_norm": 1.2133969264114732,
|
| 176 |
+
"learning_rate": 6.584022038567494e-06,
|
| 177 |
+
"loss": 0.6345,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.06899406651028012,
|
| 182 |
+
"grad_norm": 1.2700545101041685,
|
| 183 |
+
"learning_rate": 6.859504132231406e-06,
|
| 184 |
+
"loss": 0.6386,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.07175382917069133,
|
| 189 |
+
"grad_norm": 1.2174406212987252,
|
| 190 |
+
"learning_rate": 7.134986225895317e-06,
|
| 191 |
+
"loss": 0.6403,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.07451359183110252,
|
| 196 |
+
"grad_norm": 1.1500811137175568,
|
| 197 |
+
"learning_rate": 7.410468319559229e-06,
|
| 198 |
+
"loss": 0.6361,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.07727335449151373,
|
| 203 |
+
"grad_norm": 1.2075741428461082,
|
| 204 |
+
"learning_rate": 7.685950413223142e-06,
|
| 205 |
+
"loss": 0.6348,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.08003311715192493,
|
| 210 |
+
"grad_norm": 1.6661536273928046,
|
| 211 |
+
"learning_rate": 7.961432506887054e-06,
|
| 212 |
+
"loss": 0.6263,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.08279287981233614,
|
| 217 |
+
"grad_norm": 1.2692327811914956,
|
| 218 |
+
"learning_rate": 8.236914600550965e-06,
|
| 219 |
+
"loss": 0.6294,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.08555264247274734,
|
| 224 |
+
"grad_norm": 1.3688551805953726,
|
| 225 |
+
"learning_rate": 8.512396694214877e-06,
|
| 226 |
+
"loss": 0.6268,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.08831240513315855,
|
| 231 |
+
"grad_norm": 1.3470949176246652,
|
| 232 |
+
"learning_rate": 8.787878787878788e-06,
|
| 233 |
+
"loss": 0.6247,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.09107216779356975,
|
| 238 |
+
"grad_norm": 1.136787185698281,
|
| 239 |
+
"learning_rate": 9.063360881542702e-06,
|
| 240 |
+
"loss": 0.619,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.09383193045398096,
|
| 245 |
+
"grad_norm": 1.1593643608420736,
|
| 246 |
+
"learning_rate": 9.338842975206613e-06,
|
| 247 |
+
"loss": 0.6262,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.09659169311439217,
|
| 252 |
+
"grad_norm": 1.1708021309308343,
|
| 253 |
+
"learning_rate": 9.614325068870525e-06,
|
| 254 |
+
"loss": 0.6241,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.09935145577480337,
|
| 259 |
+
"grad_norm": 1.1394208261112413,
|
| 260 |
+
"learning_rate": 9.889807162534436e-06,
|
| 261 |
+
"loss": 0.6247,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.10211121843521458,
|
| 266 |
+
"grad_norm": 1.243982861233763,
|
| 267 |
+
"learning_rate": 9.999916470583429e-06,
|
| 268 |
+
"loss": 0.6223,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.10487098109562577,
|
| 273 |
+
"grad_norm": 1.0950836157642558,
|
| 274 |
+
"learning_rate": 9.999406023144514e-06,
|
| 275 |
+
"loss": 0.6172,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.10763074375603698,
|
| 280 |
+
"grad_norm": 1.1223718246628647,
|
| 281 |
+
"learning_rate": 9.998431580815314e-06,
|
| 282 |
+
"loss": 0.6178,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.11039050641644818,
|
| 287 |
+
"grad_norm": 1.2801215739716154,
|
| 288 |
+
"learning_rate": 9.996993234033826e-06,
|
| 289 |
+
"loss": 0.6187,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.11315026907685939,
|
| 294 |
+
"grad_norm": 1.1553035959732303,
|
| 295 |
+
"learning_rate": 9.995091116293022e-06,
|
| 296 |
+
"loss": 0.6195,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.11591003173727059,
|
| 301 |
+
"grad_norm": 1.163353982074495,
|
| 302 |
+
"learning_rate": 9.992725404128452e-06,
|
| 303 |
+
"loss": 0.6162,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.1186697943976818,
|
| 308 |
+
"grad_norm": 1.0553152985762932,
|
| 309 |
+
"learning_rate": 9.989896317101873e-06,
|
| 310 |
+
"loss": 0.6075,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.12142955705809301,
|
| 315 |
+
"grad_norm": 1.061674081293769,
|
| 316 |
+
"learning_rate": 9.986604117780861e-06,
|
| 317 |
+
"loss": 0.6157,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.1241893197185042,
|
| 322 |
+
"grad_norm": 1.0865591957408132,
|
| 323 |
+
"learning_rate": 9.982849111714445e-06,
|
| 324 |
+
"loss": 0.6147,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.12694908237891542,
|
| 329 |
+
"grad_norm": 1.039091554305776,
|
| 330 |
+
"learning_rate": 9.978631647404755e-06,
|
| 331 |
+
"loss": 0.6089,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.12970884503932661,
|
| 336 |
+
"grad_norm": 1.1565672987905995,
|
| 337 |
+
"learning_rate": 9.973952116274664e-06,
|
| 338 |
+
"loss": 0.6132,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.1324686076997378,
|
| 343 |
+
"grad_norm": 1.141107303982074,
|
| 344 |
+
"learning_rate": 9.968810952631473e-06,
|
| 345 |
+
"loss": 0.6077,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.13522837036014904,
|
| 350 |
+
"grad_norm": 1.1858850784459474,
|
| 351 |
+
"learning_rate": 9.9632086336266e-06,
|
| 352 |
+
"loss": 0.6116,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.13798813302056023,
|
| 357 |
+
"grad_norm": 1.0965450940865213,
|
| 358 |
+
"learning_rate": 9.957145679211288e-06,
|
| 359 |
+
"loss": 0.6131,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.13798813302056023,
|
| 364 |
+
"eval_loss": 0.6089209318161011,
|
| 365 |
+
"eval_runtime": 49.9455,
|
| 366 |
+
"eval_samples_per_second": 58.624,
|
| 367 |
+
"eval_steps_per_second": 3.664,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.14074789568097143,
|
| 372 |
+
"grad_norm": 1.076032821296556,
|
| 373 |
+
"learning_rate": 9.95062265208836e-06,
|
| 374 |
+
"loss": 0.606,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.14350765834138265,
|
| 379 |
+
"grad_norm": 1.0371790631769926,
|
| 380 |
+
"learning_rate": 9.943640157659984e-06,
|
| 381 |
+
"loss": 0.6071,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.14626742100179385,
|
| 386 |
+
"grad_norm": 1.0166966431904405,
|
| 387 |
+
"learning_rate": 9.936198843971493e-06,
|
| 388 |
+
"loss": 0.6021,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.14902718366220505,
|
| 393 |
+
"grad_norm": 1.3219793417334544,
|
| 394 |
+
"learning_rate": 9.928299401651236e-06,
|
| 395 |
+
"loss": 0.5981,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.15178694632261625,
|
| 400 |
+
"grad_norm": 1.0389071117117548,
|
| 401 |
+
"learning_rate": 9.919942563846482e-06,
|
| 402 |
+
"loss": 0.6005,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.15454670898302747,
|
| 407 |
+
"grad_norm": 1.0246893171620508,
|
| 408 |
+
"learning_rate": 9.911129106155375e-06,
|
| 409 |
+
"loss": 0.6046,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.15730647164343867,
|
| 414 |
+
"grad_norm": 1.0445099757660354,
|
| 415 |
+
"learning_rate": 9.901859846554955e-06,
|
| 416 |
+
"loss": 0.6053,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.16006623430384986,
|
| 421 |
+
"grad_norm": 1.064106651611097,
|
| 422 |
+
"learning_rate": 9.892135645325238e-06,
|
| 423 |
+
"loss": 0.5984,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.16282599696426106,
|
| 428 |
+
"grad_norm": 1.0462870772071302,
|
| 429 |
+
"learning_rate": 9.881957404969373e-06,
|
| 430 |
+
"loss": 0.5978,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.16558575962467229,
|
| 435 |
+
"grad_norm": 1.0000683469984344,
|
| 436 |
+
"learning_rate": 9.871326070129885e-06,
|
| 437 |
+
"loss": 0.6094,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.16834552228508348,
|
| 442 |
+
"grad_norm": 0.9977951236432633,
|
| 443 |
+
"learning_rate": 9.860242627500994e-06,
|
| 444 |
+
"loss": 0.5974,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.17110528494549468,
|
| 449 |
+
"grad_norm": 4.8609383522246405,
|
| 450 |
+
"learning_rate": 9.848708105737049e-06,
|
| 451 |
+
"loss": 0.598,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.1738650476059059,
|
| 456 |
+
"grad_norm": 1.0005981539720457,
|
| 457 |
+
"learning_rate": 9.836723575357056e-06,
|
| 458 |
+
"loss": 0.5988,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.1766248102663171,
|
| 463 |
+
"grad_norm": 1.0638070414980612,
|
| 464 |
+
"learning_rate": 9.824290148645322e-06,
|
| 465 |
+
"loss": 0.5957,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.1793845729267283,
|
| 470 |
+
"grad_norm": 1.0406376026434327,
|
| 471 |
+
"learning_rate": 9.811408979548219e-06,
|
| 472 |
+
"loss": 0.591,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.1821443355871395,
|
| 477 |
+
"grad_norm": 1.07624118905585,
|
| 478 |
+
"learning_rate": 9.7980812635671e-06,
|
| 479 |
+
"loss": 0.5948,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.18490409824755072,
|
| 484 |
+
"grad_norm": 1.049133255644815,
|
| 485 |
+
"learning_rate": 9.784308237647329e-06,
|
| 486 |
+
"loss": 0.5954,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.18766386090796192,
|
| 491 |
+
"grad_norm": 1.0143310556909468,
|
| 492 |
+
"learning_rate": 9.770091180063489e-06,
|
| 493 |
+
"loss": 0.596,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.1904236235683731,
|
| 498 |
+
"grad_norm": 1.0508407539599804,
|
| 499 |
+
"learning_rate": 9.755431410300743e-06,
|
| 500 |
+
"loss": 0.5871,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.19318338622878434,
|
| 505 |
+
"grad_norm": 1.2937338319267142,
|
| 506 |
+
"learning_rate": 9.740330288932379e-06,
|
| 507 |
+
"loss": 0.5948,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.19594314888919553,
|
| 512 |
+
"grad_norm": 1.0318704519944248,
|
| 513 |
+
"learning_rate": 9.724789217493514e-06,
|
| 514 |
+
"loss": 0.5898,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.19870291154960673,
|
| 519 |
+
"grad_norm": 0.9605096481233693,
|
| 520 |
+
"learning_rate": 9.708809638351048e-06,
|
| 521 |
+
"loss": 0.5925,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.20146267421001793,
|
| 526 |
+
"grad_norm": 1.0371369229103382,
|
| 527 |
+
"learning_rate": 9.692393034569776e-06,
|
| 528 |
+
"loss": 0.5917,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.20422243687042915,
|
| 533 |
+
"grad_norm": 0.97367889824368,
|
| 534 |
+
"learning_rate": 9.675540929774751e-06,
|
| 535 |
+
"loss": 0.5911,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.20698219953084035,
|
| 540 |
+
"grad_norm": 0.9914313419740074,
|
| 541 |
+
"learning_rate": 9.658254888009877e-06,
|
| 542 |
+
"loss": 0.5862,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.20974196219125155,
|
| 547 |
+
"grad_norm": 0.9822682480321101,
|
| 548 |
+
"learning_rate": 9.64053651359275e-06,
|
| 549 |
+
"loss": 0.5871,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.21250172485166274,
|
| 554 |
+
"grad_norm": 1.001214024547401,
|
| 555 |
+
"learning_rate": 9.622387450965758e-06,
|
| 556 |
+
"loss": 0.5851,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.21526148751207397,
|
| 561 |
+
"grad_norm": 0.9608822251160972,
|
| 562 |
+
"learning_rate": 9.603809384543472e-06,
|
| 563 |
+
"loss": 0.5937,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.21802125017248516,
|
| 568 |
+
"grad_norm": 1.003270353697929,
|
| 569 |
+
"learning_rate": 9.584804038556297e-06,
|
| 570 |
+
"loss": 0.5834,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.22078101283289636,
|
| 575 |
+
"grad_norm": 1.0623920143347612,
|
| 576 |
+
"learning_rate": 9.56537317689046e-06,
|
| 577 |
+
"loss": 0.5903,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.2235407754933076,
|
| 582 |
+
"grad_norm": 0.9490080408477698,
|
| 583 |
+
"learning_rate": 9.5455186029243e-06,
|
| 584 |
+
"loss": 0.5872,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.22630053815371878,
|
| 589 |
+
"grad_norm": 0.944874262643946,
|
| 590 |
+
"learning_rate": 9.525242159360897e-06,
|
| 591 |
+
"loss": 0.5888,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.22906030081412998,
|
| 596 |
+
"grad_norm": 0.9755675580087483,
|
| 597 |
+
"learning_rate": 9.504545728057046e-06,
|
| 598 |
+
"loss": 0.5822,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.23182006347454118,
|
| 603 |
+
"grad_norm": 0.9892178439036814,
|
| 604 |
+
"learning_rate": 9.483431229848607e-06,
|
| 605 |
+
"loss": 0.5847,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.2345798261349524,
|
| 610 |
+
"grad_norm": 1.3473013721931224,
|
| 611 |
+
"learning_rate": 9.461900624372233e-06,
|
| 612 |
+
"loss": 0.5763,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.2373395887953636,
|
| 617 |
+
"grad_norm": 1.1368854612150283,
|
| 618 |
+
"learning_rate": 9.439955909883493e-06,
|
| 619 |
+
"loss": 0.5815,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.2400993514557748,
|
| 624 |
+
"grad_norm": 1.0103375787124518,
|
| 625 |
+
"learning_rate": 9.417599123071417e-06,
|
| 626 |
+
"loss": 0.5838,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.24285911411618602,
|
| 631 |
+
"grad_norm": 1.0432433126635938,
|
| 632 |
+
"learning_rate": 9.39483233886946e-06,
|
| 633 |
+
"loss": 0.5785,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.24561887677659722,
|
| 638 |
+
"grad_norm": 1.1847765522018567,
|
| 639 |
+
"learning_rate": 9.371657670262947e-06,
|
| 640 |
+
"loss": 0.5742,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.2483786394370084,
|
| 645 |
+
"grad_norm": 0.9243729444752771,
|
| 646 |
+
"learning_rate": 9.348077268092951e-06,
|
| 647 |
+
"loss": 0.5763,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.2511384020974196,
|
| 652 |
+
"grad_norm": 1.3733927460707915,
|
| 653 |
+
"learning_rate": 9.324093320856679e-06,
|
| 654 |
+
"loss": 0.5777,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.25389816475783084,
|
| 659 |
+
"grad_norm": 1.098267274159629,
|
| 660 |
+
"learning_rate": 9.299708054504355e-06,
|
| 661 |
+
"loss": 0.5781,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.256657927418242,
|
| 666 |
+
"grad_norm": 0.940463162328034,
|
| 667 |
+
"learning_rate": 9.274923732232635e-06,
|
| 668 |
+
"loss": 0.5813,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.25941769007865323,
|
| 673 |
+
"grad_norm": 0.936901862695869,
|
| 674 |
+
"learning_rate": 9.249742654274554e-06,
|
| 675 |
+
"loss": 0.576,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.26217745273906445,
|
| 680 |
+
"grad_norm": 0.9160606268594537,
|
| 681 |
+
"learning_rate": 9.224167157686044e-06,
|
| 682 |
+
"loss": 0.5756,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.2649372153994756,
|
| 687 |
+
"grad_norm": 0.902157881662283,
|
| 688 |
+
"learning_rate": 9.198199616129033e-06,
|
| 689 |
+
"loss": 0.5718,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.26769697805988685,
|
| 694 |
+
"grad_norm": 0.9251021746256725,
|
| 695 |
+
"learning_rate": 9.171842439651143e-06,
|
| 696 |
+
"loss": 0.5722,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.27045674072029807,
|
| 701 |
+
"grad_norm": 0.9049498340659763,
|
| 702 |
+
"learning_rate": 9.145098074462012e-06,
|
| 703 |
+
"loss": 0.577,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.27321650338070924,
|
| 708 |
+
"grad_norm": 1.0139196145776603,
|
| 709 |
+
"learning_rate": 9.117969002706267e-06,
|
| 710 |
+
"loss": 0.5738,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.27597626604112047,
|
| 715 |
+
"grad_norm": 0.9648188962102778,
|
| 716 |
+
"learning_rate": 9.090457742233152e-06,
|
| 717 |
+
"loss": 0.5714,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.27597626604112047,
|
| 722 |
+
"eval_loss": 0.5767696499824524,
|
| 723 |
+
"eval_runtime": 48.8421,
|
| 724 |
+
"eval_samples_per_second": 59.948,
|
| 725 |
+
"eval_steps_per_second": 3.747,
|
| 726 |
+
"step": 1000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.2787360287015317,
|
| 730 |
+
"grad_norm": 0.994421928125615,
|
| 731 |
+
"learning_rate": 9.062566846362843e-06,
|
| 732 |
+
"loss": 0.5746,
|
| 733 |
+
"step": 1010
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.28149579136194286,
|
| 737 |
+
"grad_norm": 0.9627083740767366,
|
| 738 |
+
"learning_rate": 9.034298903649485e-06,
|
| 739 |
+
"loss": 0.5731,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.2842555540223541,
|
| 744 |
+
"grad_norm": 0.9143645503640928,
|
| 745 |
+
"learning_rate": 9.005656537640942e-06,
|
| 746 |
+
"loss": 0.574,
|
| 747 |
+
"step": 1030
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.2870153166827653,
|
| 751 |
+
"grad_norm": 1.0384970550188914,
|
| 752 |
+
"learning_rate": 8.976642406635295e-06,
|
| 753 |
+
"loss": 0.5725,
|
| 754 |
+
"step": 1040
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.2897750793431765,
|
| 758 |
+
"grad_norm": 0.9669853254759909,
|
| 759 |
+
"learning_rate": 8.947259203434147e-06,
|
| 760 |
+
"loss": 0.5737,
|
| 761 |
+
"step": 1050
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.2925348420035877,
|
| 765 |
+
"grad_norm": 0.965075042317439,
|
| 766 |
+
"learning_rate": 8.917509655092691e-06,
|
| 767 |
+
"loss": 0.5723,
|
| 768 |
+
"step": 1060
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.29529460466399887,
|
| 772 |
+
"grad_norm": 0.9720003134521186,
|
| 773 |
+
"learning_rate": 8.887396522666608e-06,
|
| 774 |
+
"loss": 0.566,
|
| 775 |
+
"step": 1070
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.2980543673244101,
|
| 779 |
+
"grad_norm": 1.0399992404707865,
|
| 780 |
+
"learning_rate": 8.85692260095582e-06,
|
| 781 |
+
"loss": 0.5683,
|
| 782 |
+
"step": 1080
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.3008141299848213,
|
| 786 |
+
"grad_norm": 1.0679186267160017,
|
| 787 |
+
"learning_rate": 8.826090718245112e-06,
|
| 788 |
+
"loss": 0.5661,
|
| 789 |
+
"step": 1090
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.3035738926452325,
|
| 793 |
+
"grad_norm": 0.9643258915292706,
|
| 794 |
+
"learning_rate": 8.794903736041622e-06,
|
| 795 |
+
"loss": 0.5717,
|
| 796 |
+
"step": 1100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.3063336553056437,
|
| 800 |
+
"grad_norm": 0.9136180676106652,
|
| 801 |
+
"learning_rate": 8.763364548809279e-06,
|
| 802 |
+
"loss": 0.5658,
|
| 803 |
+
"step": 1110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.30909341796605494,
|
| 807 |
+
"grad_norm": 0.9512590668833296,
|
| 808 |
+
"learning_rate": 8.731476083700154e-06,
|
| 809 |
+
"loss": 0.5679,
|
| 810 |
+
"step": 1120
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.3118531806264661,
|
| 814 |
+
"grad_norm": 0.8874320591828697,
|
| 815 |
+
"learning_rate": 8.699241300282806e-06,
|
| 816 |
+
"loss": 0.5684,
|
| 817 |
+
"step": 1130
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.31461294328687733,
|
| 821 |
+
"grad_norm": 0.8922502034099749,
|
| 822 |
+
"learning_rate": 8.666663190267596e-06,
|
| 823 |
+
"loss": 0.5621,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.31737270594728856,
|
| 828 |
+
"grad_norm": 1.6201987068583557,
|
| 829 |
+
"learning_rate": 8.633744777229029e-06,
|
| 830 |
+
"loss": 0.569,
|
| 831 |
+
"step": 1150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.3201324686076997,
|
| 835 |
+
"grad_norm": 0.9202299543891491,
|
| 836 |
+
"learning_rate": 8.600489116325128e-06,
|
| 837 |
+
"loss": 0.5678,
|
| 838 |
+
"step": 1160
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.32289223126811095,
|
| 842 |
+
"grad_norm": 1.007642513849446,
|
| 843 |
+
"learning_rate": 8.566899294013901e-06,
|
| 844 |
+
"loss": 0.5696,
|
| 845 |
+
"step": 1170
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.3256519939285221,
|
| 849 |
+
"grad_norm": 0.9837333100849195,
|
| 850 |
+
"learning_rate": 8.53297842776687e-06,
|
| 851 |
+
"loss": 0.5655,
|
| 852 |
+
"step": 1180
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.32841175658893335,
|
| 856 |
+
"grad_norm": 0.9874781114751451,
|
| 857 |
+
"learning_rate": 8.498729665779751e-06,
|
| 858 |
+
"loss": 0.5653,
|
| 859 |
+
"step": 1190
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.33117151924934457,
|
| 863 |
+
"grad_norm": 0.9230978368811615,
|
| 864 |
+
"learning_rate": 8.464156186680262e-06,
|
| 865 |
+
"loss": 0.5665,
|
| 866 |
+
"step": 1200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.33393128190975574,
|
| 870 |
+
"grad_norm": 0.8844537320977038,
|
| 871 |
+
"learning_rate": 8.429261199233114e-06,
|
| 872 |
+
"loss": 0.5633,
|
| 873 |
+
"step": 1210
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.33669104457016696,
|
| 877 |
+
"grad_norm": 0.8743072862956215,
|
| 878 |
+
"learning_rate": 8.394047942042215e-06,
|
| 879 |
+
"loss": 0.5648,
|
| 880 |
+
"step": 1220
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.3394508072305782,
|
| 884 |
+
"grad_norm": 0.9571103987457272,
|
| 885 |
+
"learning_rate": 8.358519683250087e-06,
|
| 886 |
+
"loss": 0.5628,
|
| 887 |
+
"step": 1230
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.34221056989098936,
|
| 891 |
+
"grad_norm": 0.9109271244972179,
|
| 892 |
+
"learning_rate": 8.322679720234553e-06,
|
| 893 |
+
"loss": 0.5665,
|
| 894 |
+
"step": 1240
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.3449703325514006,
|
| 898 |
+
"grad_norm": 0.9812446794213074,
|
| 899 |
+
"learning_rate": 8.286531379302703e-06,
|
| 900 |
+
"loss": 0.5615,
|
| 901 |
+
"step": 1250
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.3477300952118118,
|
| 905 |
+
"grad_norm": 0.9841621501852277,
|
| 906 |
+
"learning_rate": 8.25007801538218e-06,
|
| 907 |
+
"loss": 0.5626,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.350489857872223,
|
| 912 |
+
"grad_norm": 0.9203538923510197,
|
| 913 |
+
"learning_rate": 8.21332301170982e-06,
|
| 914 |
+
"loss": 0.5645,
|
| 915 |
+
"step": 1270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.3532496205326342,
|
| 919 |
+
"grad_norm": 1.0479420531686792,
|
| 920 |
+
"learning_rate": 8.17626977951764e-06,
|
| 921 |
+
"loss": 0.5622,
|
| 922 |
+
"step": 1280
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.3560093831930454,
|
| 926 |
+
"grad_norm": 0.9787960431652523,
|
| 927 |
+
"learning_rate": 8.138921757716245e-06,
|
| 928 |
+
"loss": 0.5581,
|
| 929 |
+
"step": 1290
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.3587691458534566,
|
| 933 |
+
"grad_norm": 0.9530332373900086,
|
| 934 |
+
"learning_rate": 8.101282412575673e-06,
|
| 935 |
+
"loss": 0.5618,
|
| 936 |
+
"step": 1300
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.3615289085138678,
|
| 940 |
+
"grad_norm": 1.0048234119883286,
|
| 941 |
+
"learning_rate": 8.063355237403672e-06,
|
| 942 |
+
"loss": 0.5555,
|
| 943 |
+
"step": 1310
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.364288671174279,
|
| 947 |
+
"grad_norm": 0.9557255183834055,
|
| 948 |
+
"learning_rate": 8.0251437522215e-06,
|
| 949 |
+
"loss": 0.5588,
|
| 950 |
+
"step": 1320
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.3670484338346902,
|
| 954 |
+
"grad_norm": 0.8586667700859966,
|
| 955 |
+
"learning_rate": 7.986651503437233e-06,
|
| 956 |
+
"loss": 0.5638,
|
| 957 |
+
"step": 1330
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.36980819649510144,
|
| 961 |
+
"grad_norm": 0.910151087145653,
|
| 962 |
+
"learning_rate": 7.947882063516612e-06,
|
| 963 |
+
"loss": 0.561,
|
| 964 |
+
"step": 1340
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.3725679591555126,
|
| 968 |
+
"grad_norm": 1.055588127662,
|
| 969 |
+
"learning_rate": 7.908839030651488e-06,
|
| 970 |
+
"loss": 0.558,
|
| 971 |
+
"step": 1350
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.37532772181592383,
|
| 975 |
+
"grad_norm": 0.9158993525267682,
|
| 976 |
+
"learning_rate": 7.869526028425878e-06,
|
| 977 |
+
"loss": 0.5587,
|
| 978 |
+
"step": 1360
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.37808748447633506,
|
| 982 |
+
"grad_norm": 0.9374100988045402,
|
| 983 |
+
"learning_rate": 7.829946705479654e-06,
|
| 984 |
+
"loss": 0.5584,
|
| 985 |
+
"step": 1370
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.3808472471367462,
|
| 989 |
+
"grad_norm": 0.9220438433292831,
|
| 990 |
+
"learning_rate": 7.790104735169915e-06,
|
| 991 |
+
"loss": 0.5576,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.38360700979715745,
|
| 996 |
+
"grad_norm": 0.987945504497949,
|
| 997 |
+
"learning_rate": 7.750003815230062e-06,
|
| 998 |
+
"loss": 0.5558,
|
| 999 |
+
"step": 1390
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.3863667724575687,
|
| 1003 |
+
"grad_norm": 0.9218901797189658,
|
| 1004 |
+
"learning_rate": 7.70964766742662e-06,
|
| 1005 |
+
"loss": 0.5611,
|
| 1006 |
+
"step": 1400
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.38912653511797984,
|
| 1010 |
+
"grad_norm": 0.964522451572826,
|
| 1011 |
+
"learning_rate": 7.669040037213795e-06,
|
| 1012 |
+
"loss": 0.5559,
|
| 1013 |
+
"step": 1410
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.39188629777839107,
|
| 1017 |
+
"grad_norm": 0.8962914985254243,
|
| 1018 |
+
"learning_rate": 7.628184693385896e-06,
|
| 1019 |
+
"loss": 0.5601,
|
| 1020 |
+
"step": 1420
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.39464606043880224,
|
| 1024 |
+
"grad_norm": 1.0900746038682583,
|
| 1025 |
+
"learning_rate": 7.587085427727523e-06,
|
| 1026 |
+
"loss": 0.5555,
|
| 1027 |
+
"step": 1430
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.39740582309921346,
|
| 1031 |
+
"grad_norm": 0.8919597256872009,
|
| 1032 |
+
"learning_rate": 7.54574605466166e-06,
|
| 1033 |
+
"loss": 0.554,
|
| 1034 |
+
"step": 1440
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.4001655857596247,
|
| 1038 |
+
"grad_norm": 0.937111912961035,
|
| 1039 |
+
"learning_rate": 7.504170410895668e-06,
|
| 1040 |
+
"loss": 0.5576,
|
| 1041 |
+
"step": 1450
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.40292534842003586,
|
| 1045 |
+
"grad_norm": 0.9458249661943667,
|
| 1046 |
+
"learning_rate": 7.462362355065189e-06,
|
| 1047 |
+
"loss": 0.5531,
|
| 1048 |
+
"step": 1460
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.4056851110804471,
|
| 1052 |
+
"grad_norm": 0.9326011700869207,
|
| 1053 |
+
"learning_rate": 7.420325767376026e-06,
|
| 1054 |
+
"loss": 0.5536,
|
| 1055 |
+
"step": 1470
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.4084448737408583,
|
| 1059 |
+
"grad_norm": 1.0186083692765828,
|
| 1060 |
+
"learning_rate": 7.378064549244031e-06,
|
| 1061 |
+
"loss": 0.5512,
|
| 1062 |
+
"step": 1480
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.4112046364012695,
|
| 1066 |
+
"grad_norm": 1.2256145317450289,
|
| 1067 |
+
"learning_rate": 7.335582622933e-06,
|
| 1068 |
+
"loss": 0.5601,
|
| 1069 |
+
"step": 1490
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.4139643990616807,
|
| 1073 |
+
"grad_norm": 0.8742188645170639,
|
| 1074 |
+
"learning_rate": 7.292883931190667e-06,
|
| 1075 |
+
"loss": 0.5524,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.4139643990616807,
|
| 1080 |
+
"eval_loss": 0.5561984777450562,
|
| 1081 |
+
"eval_runtime": 49.4336,
|
| 1082 |
+
"eval_samples_per_second": 59.231,
|
| 1083 |
+
"eval_steps_per_second": 3.702,
|
| 1084 |
+
"step": 1500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.4167241617220919,
|
| 1088 |
+
"grad_norm": 1.2121655526375013,
|
| 1089 |
+
"learning_rate": 7.249972436882756e-06,
|
| 1090 |
+
"loss": 0.5542,
|
| 1091 |
+
"step": 1510
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.4194839243825031,
|
| 1095 |
+
"grad_norm": 0.9357492214275386,
|
| 1096 |
+
"learning_rate": 7.206852122625203e-06,
|
| 1097 |
+
"loss": 0.5524,
|
| 1098 |
+
"step": 1520
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.4222436870429143,
|
| 1102 |
+
"grad_norm": 0.9433912153799177,
|
| 1103 |
+
"learning_rate": 7.163526990414522e-06,
|
| 1104 |
+
"loss": 0.5542,
|
| 1105 |
+
"step": 1530
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.4250034497033255,
|
| 1109 |
+
"grad_norm": 1.1073143594605637,
|
| 1110 |
+
"learning_rate": 7.120001061256387e-06,
|
| 1111 |
+
"loss": 0.5525,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.4277632123637367,
|
| 1116 |
+
"grad_norm": 0.9302028752309601,
|
| 1117 |
+
"learning_rate": 7.076278374792429e-06,
|
| 1118 |
+
"loss": 0.5541,
|
| 1119 |
+
"step": 1550
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.43052297502414794,
|
| 1123 |
+
"grad_norm": 0.9606456277899846,
|
| 1124 |
+
"learning_rate": 7.032362988925332e-06,
|
| 1125 |
+
"loss": 0.5553,
|
| 1126 |
+
"step": 1560
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.4332827376845591,
|
| 1130 |
+
"grad_norm": 0.9251439989697735,
|
| 1131 |
+
"learning_rate": 6.9882589794422105e-06,
|
| 1132 |
+
"loss": 0.5489,
|
| 1133 |
+
"step": 1570
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.43604250034497033,
|
| 1137 |
+
"grad_norm": 0.9323884014701264,
|
| 1138 |
+
"learning_rate": 6.943970439636336e-06,
|
| 1139 |
+
"loss": 0.5494,
|
| 1140 |
+
"step": 1580
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.43880226300538155,
|
| 1144 |
+
"grad_norm": 1.3158449326861952,
|
| 1145 |
+
"learning_rate": 6.899501479927242e-06,
|
| 1146 |
+
"loss": 0.5484,
|
| 1147 |
+
"step": 1590
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.4415620256657927,
|
| 1151 |
+
"grad_norm": 0.8775790961507058,
|
| 1152 |
+
"learning_rate": 6.8548562274792325e-06,
|
| 1153 |
+
"loss": 0.5453,
|
| 1154 |
+
"step": 1600
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.44432178832620395,
|
| 1158 |
+
"grad_norm": 0.9478549256736298,
|
| 1159 |
+
"learning_rate": 6.81003882581834e-06,
|
| 1160 |
+
"loss": 0.5482,
|
| 1161 |
+
"step": 1610
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.4470815509866152,
|
| 1165 |
+
"grad_norm": 0.9723342894189143,
|
| 1166 |
+
"learning_rate": 6.765053434447769e-06,
|
| 1167 |
+
"loss": 0.5487,
|
| 1168 |
+
"step": 1620
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.44984131364702634,
|
| 1172 |
+
"grad_norm": 0.974749959194784,
|
| 1173 |
+
"learning_rate": 6.7199042284618484e-06,
|
| 1174 |
+
"loss": 0.5505,
|
| 1175 |
+
"step": 1630
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.45260107630743757,
|
| 1179 |
+
"grad_norm": 0.9255671399322642,
|
| 1180 |
+
"learning_rate": 6.674595398158541e-06,
|
| 1181 |
+
"loss": 0.5493,
|
| 1182 |
+
"step": 1640
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.4553608389678488,
|
| 1186 |
+
"grad_norm": 0.9465763497145431,
|
| 1187 |
+
"learning_rate": 6.629131148650543e-06,
|
| 1188 |
+
"loss": 0.5444,
|
| 1189 |
+
"step": 1650
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.45812060162825996,
|
| 1193 |
+
"grad_norm": 0.9292686081943923,
|
| 1194 |
+
"learning_rate": 6.583515699475009e-06,
|
| 1195 |
+
"loss": 0.5496,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.4608803642886712,
|
| 1200 |
+
"grad_norm": 1.108323416936679,
|
| 1201 |
+
"learning_rate": 6.537753284201935e-06,
|
| 1202 |
+
"loss": 0.5487,
|
| 1203 |
+
"step": 1670
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.46364012694908235,
|
| 1207 |
+
"grad_norm": 0.9042384031621171,
|
| 1208 |
+
"learning_rate": 6.491848150041242e-06,
|
| 1209 |
+
"loss": 0.5477,
|
| 1210 |
+
"step": 1680
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.4663998896094936,
|
| 1214 |
+
"grad_norm": 0.850329034972769,
|
| 1215 |
+
"learning_rate": 6.4458045574485875e-06,
|
| 1216 |
+
"loss": 0.5519,
|
| 1217 |
+
"step": 1690
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.4691596522699048,
|
| 1221 |
+
"grad_norm": 0.9490531745735549,
|
| 1222 |
+
"learning_rate": 6.399626779729959e-06,
|
| 1223 |
+
"loss": 0.5439,
|
| 1224 |
+
"step": 1700
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.471919414930316,
|
| 1228 |
+
"grad_norm": 0.9352622534171564,
|
| 1229 |
+
"learning_rate": 6.353319102645069e-06,
|
| 1230 |
+
"loss": 0.5465,
|
| 1231 |
+
"step": 1710
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.4746791775907272,
|
| 1235 |
+
"grad_norm": 0.9191680266246547,
|
| 1236 |
+
"learning_rate": 6.306885824009585e-06,
|
| 1237 |
+
"loss": 0.547,
|
| 1238 |
+
"step": 1720
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.4774389402511384,
|
| 1242 |
+
"grad_norm": 0.8597116149610817,
|
| 1243 |
+
"learning_rate": 6.260331253296259e-06,
|
| 1244 |
+
"loss": 0.5495,
|
| 1245 |
+
"step": 1730
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.4801987029115496,
|
| 1249 |
+
"grad_norm": 0.929502998942292,
|
| 1250 |
+
"learning_rate": 6.213659711234958e-06,
|
| 1251 |
+
"loss": 0.5481,
|
| 1252 |
+
"step": 1740
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.4829584655719608,
|
| 1256 |
+
"grad_norm": 0.9675046561306946,
|
| 1257 |
+
"learning_rate": 6.1668755294116655e-06,
|
| 1258 |
+
"loss": 0.5468,
|
| 1259 |
+
"step": 1750
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.48571822823237204,
|
| 1263 |
+
"grad_norm": 0.9073333178919157,
|
| 1264 |
+
"learning_rate": 6.119983049866456e-06,
|
| 1265 |
+
"loss": 0.5438,
|
| 1266 |
+
"step": 1760
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.4884779908927832,
|
| 1270 |
+
"grad_norm": 0.9109565773453232,
|
| 1271 |
+
"learning_rate": 6.072986624690516e-06,
|
| 1272 |
+
"loss": 0.5478,
|
| 1273 |
+
"step": 1770
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.49123775355319443,
|
| 1277 |
+
"grad_norm": 0.8955027642684514,
|
| 1278 |
+
"learning_rate": 6.025890615622233e-06,
|
| 1279 |
+
"loss": 0.5415,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.4939975162136056,
|
| 1284 |
+
"grad_norm": 0.8648546291027864,
|
| 1285 |
+
"learning_rate": 5.97869939364237e-06,
|
| 1286 |
+
"loss": 0.5411,
|
| 1287 |
+
"step": 1790
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.4967572788740168,
|
| 1291 |
+
"grad_norm": 0.9523614008291538,
|
| 1292 |
+
"learning_rate": 5.9314173385683986e-06,
|
| 1293 |
+
"loss": 0.5453,
|
| 1294 |
+
"step": 1800
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.49951704153442805,
|
| 1298 |
+
"grad_norm": 0.9383064266388607,
|
| 1299 |
+
"learning_rate": 5.884048838648017e-06,
|
| 1300 |
+
"loss": 0.5384,
|
| 1301 |
+
"step": 1810
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.5022768041948392,
|
| 1305 |
+
"grad_norm": 0.9021624786717238,
|
| 1306 |
+
"learning_rate": 5.836598290151866e-06,
|
| 1307 |
+
"loss": 0.5456,
|
| 1308 |
+
"step": 1820
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.5050365668552504,
|
| 1312 |
+
"grad_norm": 0.9088357380698893,
|
| 1313 |
+
"learning_rate": 5.789070096965514e-06,
|
| 1314 |
+
"loss": 0.5426,
|
| 1315 |
+
"step": 1830
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.5077963295156617,
|
| 1319 |
+
"grad_norm": 0.922862032580903,
|
| 1320 |
+
"learning_rate": 5.741468670180737e-06,
|
| 1321 |
+
"loss": 0.5434,
|
| 1322 |
+
"step": 1840
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.5105560921760729,
|
| 1326 |
+
"grad_norm": 1.4926573419318607,
|
| 1327 |
+
"learning_rate": 5.6937984276861195e-06,
|
| 1328 |
+
"loss": 0.5441,
|
| 1329 |
+
"step": 1850
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.513315854836484,
|
| 1333 |
+
"grad_norm": 0.8580464247033338,
|
| 1334 |
+
"learning_rate": 5.646063793757028e-06,
|
| 1335 |
+
"loss": 0.5413,
|
| 1336 |
+
"step": 1860
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.5160756174968952,
|
| 1340 |
+
"grad_norm": 0.8836024449571962,
|
| 1341 |
+
"learning_rate": 5.598269198645008e-06,
|
| 1342 |
+
"loss": 0.5457,
|
| 1343 |
+
"step": 1870
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.5188353801573065,
|
| 1347 |
+
"grad_norm": 0.8951578721801148,
|
| 1348 |
+
"learning_rate": 5.550419078166594e-06,
|
| 1349 |
+
"loss": 0.5452,
|
| 1350 |
+
"step": 1880
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.5215951428177177,
|
| 1354 |
+
"grad_norm": 0.9955192132312739,
|
| 1355 |
+
"learning_rate": 5.502517873291632e-06,
|
| 1356 |
+
"loss": 0.5467,
|
| 1357 |
+
"step": 1890
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.5243549054781289,
|
| 1361 |
+
"grad_norm": 1.1988654703686727,
|
| 1362 |
+
"learning_rate": 5.454570029731115e-06,
|
| 1363 |
+
"loss": 0.5413,
|
| 1364 |
+
"step": 1900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.5271146681385401,
|
| 1368 |
+
"grad_norm": 0.8839237136665734,
|
| 1369 |
+
"learning_rate": 5.406579997524567e-06,
|
| 1370 |
+
"loss": 0.5411,
|
| 1371 |
+
"step": 1910
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.5298744307989512,
|
| 1375 |
+
"grad_norm": 0.9047836025418462,
|
| 1376 |
+
"learning_rate": 5.358552230627044e-06,
|
| 1377 |
+
"loss": 0.539,
|
| 1378 |
+
"step": 1920
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.5326341934593625,
|
| 1382 |
+
"grad_norm": 0.875356281556686,
|
| 1383 |
+
"learning_rate": 5.310491186495757e-06,
|
| 1384 |
+
"loss": 0.5429,
|
| 1385 |
+
"step": 1930
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.5353939561197737,
|
| 1389 |
+
"grad_norm": 0.9167892739496736,
|
| 1390 |
+
"learning_rate": 5.262401325676378e-06,
|
| 1391 |
+
"loss": 0.5384,
|
| 1392 |
+
"step": 1940
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.5381537187801849,
|
| 1396 |
+
"grad_norm": 0.9525976300842104,
|
| 1397 |
+
"learning_rate": 5.214287111389057e-06,
|
| 1398 |
+
"loss": 0.5362,
|
| 1399 |
+
"step": 1950
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.5409134814405961,
|
| 1403 |
+
"grad_norm": 0.885862636010332,
|
| 1404 |
+
"learning_rate": 5.166153009114188e-06,
|
| 1405 |
+
"loss": 0.5378,
|
| 1406 |
+
"step": 1960
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.5436732441010073,
|
| 1410 |
+
"grad_norm": 0.9013246458040829,
|
| 1411 |
+
"learning_rate": 5.1180034861779685e-06,
|
| 1412 |
+
"loss": 0.5399,
|
| 1413 |
+
"step": 1970
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.5464330067614185,
|
| 1417 |
+
"grad_norm": 0.9017690594117211,
|
| 1418 |
+
"learning_rate": 5.069843011337789e-06,
|
| 1419 |
+
"loss": 0.5412,
|
| 1420 |
+
"step": 1980
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.5491927694218297,
|
| 1424 |
+
"grad_norm": 0.9063217665862804,
|
| 1425 |
+
"learning_rate": 5.0216760543674855e-06,
|
| 1426 |
+
"loss": 0.5415,
|
| 1427 |
+
"step": 1990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.5519525320822409,
|
| 1431 |
+
"grad_norm": 0.8411472472974292,
|
| 1432 |
+
"learning_rate": 4.973507085642502e-06,
|
| 1433 |
+
"loss": 0.537,
|
| 1434 |
+
"step": 2000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.5519525320822409,
|
| 1438 |
+
"eval_loss": 0.540687620639801,
|
| 1439 |
+
"eval_runtime": 48.7225,
|
| 1440 |
+
"eval_samples_per_second": 60.095,
|
| 1441 |
+
"eval_steps_per_second": 3.756,
|
| 1442 |
+
"step": 2000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.5547122947426522,
|
| 1446 |
+
"grad_norm": 0.8884146283634436,
|
| 1447 |
+
"learning_rate": 4.92534057572499e-06,
|
| 1448 |
+
"loss": 0.5406,
|
| 1449 |
+
"step": 2010
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.5574720574030634,
|
| 1453 |
+
"grad_norm": 0.8914897264034541,
|
| 1454 |
+
"learning_rate": 4.8771809949489056e-06,
|
| 1455 |
+
"loss": 0.5385,
|
| 1456 |
+
"step": 2020
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.5602318200634745,
|
| 1460 |
+
"grad_norm": 0.936304320970765,
|
| 1461 |
+
"learning_rate": 4.829032813005103e-06,
|
| 1462 |
+
"loss": 0.542,
|
| 1463 |
+
"step": 2030
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.5629915827238857,
|
| 1467 |
+
"grad_norm": 0.9310122808691009,
|
| 1468 |
+
"learning_rate": 4.780900498526515e-06,
|
| 1469 |
+
"loss": 0.5365,
|
| 1470 |
+
"step": 2040
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.5657513453842969,
|
| 1474 |
+
"grad_norm": 0.9518666584186597,
|
| 1475 |
+
"learning_rate": 4.732788518673418e-06,
|
| 1476 |
+
"loss": 0.5353,
|
| 1477 |
+
"step": 2050
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.5685111080447082,
|
| 1481 |
+
"grad_norm": 0.9510071761987918,
|
| 1482 |
+
"learning_rate": 4.684701338718825e-06,
|
| 1483 |
+
"loss": 0.5317,
|
| 1484 |
+
"step": 2060
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.5712708707051194,
|
| 1488 |
+
"grad_norm": 0.9432991523879628,
|
| 1489 |
+
"learning_rate": 4.636643421634075e-06,
|
| 1490 |
+
"loss": 0.5371,
|
| 1491 |
+
"step": 2070
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.5740306333655306,
|
| 1495 |
+
"grad_norm": 0.8853811386420297,
|
| 1496 |
+
"learning_rate": 4.588619227674619e-06,
|
| 1497 |
+
"loss": 0.5365,
|
| 1498 |
+
"step": 2080
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.5767903960259417,
|
| 1502 |
+
"grad_norm": 0.9290294341366813,
|
| 1503 |
+
"learning_rate": 4.540633213966064e-06,
|
| 1504 |
+
"loss": 0.5334,
|
| 1505 |
+
"step": 2090
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.579550158686353,
|
| 1509 |
+
"grad_norm": 0.9327668087903835,
|
| 1510 |
+
"learning_rate": 4.492689834090508e-06,
|
| 1511 |
+
"loss": 0.5341,
|
| 1512 |
+
"step": 2100
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.5823099213467642,
|
| 1516 |
+
"grad_norm": 1.3176571259191412,
|
| 1517 |
+
"learning_rate": 4.444793537673204e-06,
|
| 1518 |
+
"loss": 0.5306,
|
| 1519 |
+
"step": 2110
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.5850696840071754,
|
| 1523 |
+
"grad_norm": 0.9485574547153368,
|
| 1524 |
+
"learning_rate": 4.396948769969587e-06,
|
| 1525 |
+
"loss": 0.5379,
|
| 1526 |
+
"step": 2120
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.5878294466675866,
|
| 1530 |
+
"grad_norm": 0.951959101524703,
|
| 1531 |
+
"learning_rate": 4.3491599714527115e-06,
|
| 1532 |
+
"loss": 0.5348,
|
| 1533 |
+
"step": 2130
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.5905892093279977,
|
| 1537 |
+
"grad_norm": 0.8736078038744113,
|
| 1538 |
+
"learning_rate": 4.301431577401136e-06,
|
| 1539 |
+
"loss": 0.5323,
|
| 1540 |
+
"step": 2140
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.593348971988409,
|
| 1544 |
+
"grad_norm": 0.8979881907613325,
|
| 1545 |
+
"learning_rate": 4.253768017487275e-06,
|
| 1546 |
+
"loss": 0.5389,
|
| 1547 |
+
"step": 2150
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.5961087346488202,
|
| 1551 |
+
"grad_norm": 0.9371779488004714,
|
| 1552 |
+
"learning_rate": 4.206173715366289e-06,
|
| 1553 |
+
"loss": 0.5343,
|
| 1554 |
+
"step": 2160
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.5988684973092314,
|
| 1558 |
+
"grad_norm": 0.9563875289878281,
|
| 1559 |
+
"learning_rate": 4.1586530882655226e-06,
|
| 1560 |
+
"loss": 0.5352,
|
| 1561 |
+
"step": 2170
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.6016282599696426,
|
| 1565 |
+
"grad_norm": 0.9747450112581771,
|
| 1566 |
+
"learning_rate": 4.111210546574545e-06,
|
| 1567 |
+
"loss": 0.534,
|
| 1568 |
+
"step": 2180
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.6043880226300539,
|
| 1572 |
+
"grad_norm": 0.9351891869474309,
|
| 1573 |
+
"learning_rate": 4.063850493435808e-06,
|
| 1574 |
+
"loss": 0.5298,
|
| 1575 |
+
"step": 2190
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.607147785290465,
|
| 1579 |
+
"grad_norm": 0.8980425451702817,
|
| 1580 |
+
"learning_rate": 4.0165773243360105e-06,
|
| 1581 |
+
"loss": 0.5338,
|
| 1582 |
+
"step": 2200
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.6099075479508762,
|
| 1586 |
+
"grad_norm": 0.9224682367333663,
|
| 1587 |
+
"learning_rate": 3.96939542669814e-06,
|
| 1588 |
+
"loss": 0.5306,
|
| 1589 |
+
"step": 2210
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.6126673106112874,
|
| 1593 |
+
"grad_norm": 0.8491438680952316,
|
| 1594 |
+
"learning_rate": 3.922309179474279e-06,
|
| 1595 |
+
"loss": 0.5306,
|
| 1596 |
+
"step": 2220
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.6154270732716987,
|
| 1600 |
+
"grad_norm": 0.9550543136397366,
|
| 1601 |
+
"learning_rate": 3.875322952739196e-06,
|
| 1602 |
+
"loss": 0.5348,
|
| 1603 |
+
"step": 2230
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.6181868359321099,
|
| 1607 |
+
"grad_norm": 0.8390020003541692,
|
| 1608 |
+
"learning_rate": 3.828441107284755e-06,
|
| 1609 |
+
"loss": 0.5343,
|
| 1610 |
+
"step": 2240
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.620946598592521,
|
| 1614 |
+
"grad_norm": 0.892945059961568,
|
| 1615 |
+
"learning_rate": 3.7816679942151945e-06,
|
| 1616 |
+
"loss": 0.523,
|
| 1617 |
+
"step": 2250
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.6237063612529322,
|
| 1621 |
+
"grad_norm": 0.9210249115479134,
|
| 1622 |
+
"learning_rate": 3.7350079545433014e-06,
|
| 1623 |
+
"loss": 0.5279,
|
| 1624 |
+
"step": 2260
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.6264661239133434,
|
| 1628 |
+
"grad_norm": 0.9570746572961814,
|
| 1629 |
+
"learning_rate": 3.6884653187875193e-06,
|
| 1630 |
+
"loss": 0.5293,
|
| 1631 |
+
"step": 2270
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.6292258865737547,
|
| 1635 |
+
"grad_norm": 0.8534492122472642,
|
| 1636 |
+
"learning_rate": 3.642044406570031e-06,
|
| 1637 |
+
"loss": 0.5256,
|
| 1638 |
+
"step": 2280
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.6319856492341659,
|
| 1642 |
+
"grad_norm": 0.8732168431838571,
|
| 1643 |
+
"learning_rate": 3.595749526215862e-06,
|
| 1644 |
+
"loss": 0.5328,
|
| 1645 |
+
"step": 2290
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 0.6347454118945771,
|
| 1649 |
+
"grad_norm": 0.8962727112777485,
|
| 1650 |
+
"learning_rate": 3.549584974353018e-06,
|
| 1651 |
+
"loss": 0.5336,
|
| 1652 |
+
"step": 2300
|
| 1653 |
+
},
|
| 1654 |
+
{
|
| 1655 |
+
"epoch": 0.6375051745549882,
|
| 1656 |
+
"grad_norm": 0.8730073595406601,
|
| 1657 |
+
"learning_rate": 3.5035550355137156e-06,
|
| 1658 |
+
"loss": 0.5318,
|
| 1659 |
+
"step": 2310
|
| 1660 |
+
},
|
| 1661 |
+
{
|
| 1662 |
+
"epoch": 0.6402649372153995,
|
| 1663 |
+
"grad_norm": 0.9162256052176202,
|
| 1664 |
+
"learning_rate": 3.457663981736739e-06,
|
| 1665 |
+
"loss": 0.5346,
|
| 1666 |
+
"step": 2320
|
| 1667 |
+
},
|
| 1668 |
+
{
|
| 1669 |
+
"epoch": 0.6430246998758107,
|
| 1670 |
+
"grad_norm": 0.8555722066919174,
|
| 1671 |
+
"learning_rate": 3.411916072170946e-06,
|
| 1672 |
+
"loss": 0.5318,
|
| 1673 |
+
"step": 2330
|
| 1674 |
+
},
|
| 1675 |
+
{
|
| 1676 |
+
"epoch": 0.6457844625362219,
|
| 1677 |
+
"grad_norm": 0.8407652045731654,
|
| 1678 |
+
"learning_rate": 3.3663155526799827e-06,
|
| 1679 |
+
"loss": 0.5306,
|
| 1680 |
+
"step": 2340
|
| 1681 |
+
},
|
| 1682 |
+
{
|
| 1683 |
+
"epoch": 0.6485442251966331,
|
| 1684 |
+
"grad_norm": 0.876217339145573,
|
| 1685 |
+
"learning_rate": 3.3208666554482216e-06,
|
| 1686 |
+
"loss": 0.5291,
|
| 1687 |
+
"step": 2350
|
| 1688 |
+
},
|
| 1689 |
+
{
|
| 1690 |
+
"epoch": 0.6513039878570442,
|
| 1691 |
+
"grad_norm": 0.897083649993733,
|
| 1692 |
+
"learning_rate": 3.275573598587969e-06,
|
| 1693 |
+
"loss": 0.5229,
|
| 1694 |
+
"step": 2360
|
| 1695 |
+
},
|
| 1696 |
+
{
|
| 1697 |
+
"epoch": 0.6540637505174555,
|
| 1698 |
+
"grad_norm": 0.7995897085360415,
|
| 1699 |
+
"learning_rate": 3.230440585747991e-06,
|
| 1700 |
+
"loss": 0.527,
|
| 1701 |
+
"step": 2370
|
| 1702 |
+
},
|
| 1703 |
+
{
|
| 1704 |
+
"epoch": 0.6568235131778667,
|
| 1705 |
+
"grad_norm": 0.9014903537041772,
|
| 1706 |
+
"learning_rate": 3.185471805723365e-06,
|
| 1707 |
+
"loss": 0.5261,
|
| 1708 |
+
"step": 2380
|
| 1709 |
+
},
|
| 1710 |
+
{
|
| 1711 |
+
"epoch": 0.6595832758382779,
|
| 1712 |
+
"grad_norm": 0.856492997294296,
|
| 1713 |
+
"learning_rate": 3.140671432066719e-06,
|
| 1714 |
+
"loss": 0.5308,
|
| 1715 |
+
"step": 2390
|
| 1716 |
+
},
|
| 1717 |
+
{
|
| 1718 |
+
"epoch": 0.6623430384986891,
|
| 1719 |
+
"grad_norm": 0.888225217505466,
|
| 1720 |
+
"learning_rate": 3.096043622700888e-06,
|
| 1721 |
+
"loss": 0.5294,
|
| 1722 |
+
"step": 2400
|
| 1723 |
+
},
|
| 1724 |
+
{
|
| 1725 |
+
"epoch": 0.6651028011591004,
|
| 1726 |
+
"grad_norm": 0.9531940854665482,
|
| 1727 |
+
"learning_rate": 3.0515925195330148e-06,
|
| 1728 |
+
"loss": 0.5283,
|
| 1729 |
+
"step": 2410
|
| 1730 |
+
},
|
| 1731 |
+
{
|
| 1732 |
+
"epoch": 0.6678625638195115,
|
| 1733 |
+
"grad_norm": 1.2539256252009454,
|
| 1734 |
+
"learning_rate": 3.0073222480701354e-06,
|
| 1735 |
+
"loss": 0.5275,
|
| 1736 |
+
"step": 2420
|
| 1737 |
+
},
|
| 1738 |
+
{
|
| 1739 |
+
"epoch": 0.6706223264799227,
|
| 1740 |
+
"grad_norm": 0.9137548818626098,
|
| 1741 |
+
"learning_rate": 2.9632369170362977e-06,
|
| 1742 |
+
"loss": 0.5235,
|
| 1743 |
+
"step": 2430
|
| 1744 |
+
},
|
| 1745 |
+
{
|
| 1746 |
+
"epoch": 0.6733820891403339,
|
| 1747 |
+
"grad_norm": 1.6494495739553416,
|
| 1748 |
+
"learning_rate": 2.9193406179912297e-06,
|
| 1749 |
+
"loss": 0.5271,
|
| 1750 |
+
"step": 2440
|
| 1751 |
+
},
|
| 1752 |
+
{
|
| 1753 |
+
"epoch": 0.6761418518007452,
|
| 1754 |
+
"grad_norm": 0.8590622849369576,
|
| 1755 |
+
"learning_rate": 2.875637424950595e-06,
|
| 1756 |
+
"loss": 0.522,
|
| 1757 |
+
"step": 2450
|
| 1758 |
+
},
|
| 1759 |
+
{
|
| 1760 |
+
"epoch": 0.6789016144611564,
|
| 1761 |
+
"grad_norm": 0.9186749142898574,
|
| 1762 |
+
"learning_rate": 2.832131394007891e-06,
|
| 1763 |
+
"loss": 0.5221,
|
| 1764 |
+
"step": 2460
|
| 1765 |
+
},
|
| 1766 |
+
{
|
| 1767 |
+
"epoch": 0.6816613771215675,
|
| 1768 |
+
"grad_norm": 0.9090102002494171,
|
| 1769 |
+
"learning_rate": 2.788826562958e-06,
|
| 1770 |
+
"loss": 0.5289,
|
| 1771 |
+
"step": 2470
|
| 1772 |
+
},
|
| 1773 |
+
{
|
| 1774 |
+
"epoch": 0.6844211397819787,
|
| 1775 |
+
"grad_norm": 1.0599147672457048,
|
| 1776 |
+
"learning_rate": 2.745726950922444e-06,
|
| 1777 |
+
"loss": 0.5241,
|
| 1778 |
+
"step": 2480
|
| 1779 |
+
},
|
| 1780 |
+
{
|
| 1781 |
+
"epoch": 0.6871809024423899,
|
| 1782 |
+
"grad_norm": 0.8881000835172156,
|
| 1783 |
+
"learning_rate": 2.7028365579763606e-06,
|
| 1784 |
+
"loss": 0.5298,
|
| 1785 |
+
"step": 2490
|
| 1786 |
+
},
|
| 1787 |
+
{
|
| 1788 |
+
"epoch": 0.6899406651028012,
|
| 1789 |
+
"grad_norm": 0.8992940208666876,
|
| 1790 |
+
"learning_rate": 2.6601593647772696e-06,
|
| 1791 |
+
"loss": 0.5282,
|
| 1792 |
+
"step": 2500
|
| 1793 |
+
},
|
| 1794 |
+
{
|
| 1795 |
+
"epoch": 0.6899406651028012,
|
| 1796 |
+
"eval_loss": 0.5283246636390686,
|
| 1797 |
+
"eval_runtime": 51.449,
|
| 1798 |
+
"eval_samples_per_second": 56.911,
|
| 1799 |
+
"eval_steps_per_second": 3.557,
|
| 1800 |
+
"step": 2500
|
| 1801 |
+
},
|
| 1802 |
+
{
|
| 1803 |
+
"epoch": 0.6927004277632124,
|
| 1804 |
+
"grad_norm": 0.9769386150489252,
|
| 1805 |
+
"learning_rate": 2.6176993321956185e-06,
|
| 1806 |
+
"loss": 0.5253,
|
| 1807 |
+
"step": 2510
|
| 1808 |
+
},
|
| 1809 |
+
{
|
| 1810 |
+
"epoch": 0.6954601904236236,
|
| 1811 |
+
"grad_norm": 0.9191890198831723,
|
| 1812 |
+
"learning_rate": 2.5754604009471786e-06,
|
| 1813 |
+
"loss": 0.5229,
|
| 1814 |
+
"step": 2520
|
| 1815 |
+
},
|
| 1816 |
+
{
|
| 1817 |
+
"epoch": 0.6982199530840347,
|
| 1818 |
+
"grad_norm": 0.8879005162140707,
|
| 1819 |
+
"learning_rate": 2.533446491227305e-06,
|
| 1820 |
+
"loss": 0.5247,
|
| 1821 |
+
"step": 2530
|
| 1822 |
+
},
|
| 1823 |
+
{
|
| 1824 |
+
"epoch": 0.700979715744446,
|
| 1825 |
+
"grad_norm": 0.9109715281747162,
|
| 1826 |
+
"learning_rate": 2.491661502347106e-06,
|
| 1827 |
+
"loss": 0.5218,
|
| 1828 |
+
"step": 2540
|
| 1829 |
+
},
|
| 1830 |
+
{
|
| 1831 |
+
"epoch": 0.7037394784048572,
|
| 1832 |
+
"grad_norm": 0.8969876737597425,
|
| 1833 |
+
"learning_rate": 2.4501093123715395e-06,
|
| 1834 |
+
"loss": 0.5238,
|
| 1835 |
+
"step": 2550
|
| 1836 |
+
},
|
| 1837 |
+
{
|
| 1838 |
+
"epoch": 0.7064992410652684,
|
| 1839 |
+
"grad_norm": 0.9123939456680997,
|
| 1840 |
+
"learning_rate": 2.408793777759504e-06,
|
| 1841 |
+
"loss": 0.5234,
|
| 1842 |
+
"step": 2560
|
| 1843 |
+
},
|
| 1844 |
+
{
|
| 1845 |
+
"epoch": 0.7092590037256796,
|
| 1846 |
+
"grad_norm": 0.8767338790553574,
|
| 1847 |
+
"learning_rate": 2.3677187330059084e-06,
|
| 1848 |
+
"loss": 0.5247,
|
| 1849 |
+
"step": 2570
|
| 1850 |
+
},
|
| 1851 |
+
{
|
| 1852 |
+
"epoch": 0.7120187663860909,
|
| 1853 |
+
"grad_norm": 0.9605486388857951,
|
| 1854 |
+
"learning_rate": 2.3268879902857978e-06,
|
| 1855 |
+
"loss": 0.5194,
|
| 1856 |
+
"step": 2580
|
| 1857 |
+
},
|
| 1858 |
+
{
|
| 1859 |
+
"epoch": 0.714778529046502,
|
| 1860 |
+
"grad_norm": 0.9895359728969572,
|
| 1861 |
+
"learning_rate": 2.2863053391005462e-06,
|
| 1862 |
+
"loss": 0.5236,
|
| 1863 |
+
"step": 2590
|
| 1864 |
+
},
|
| 1865 |
+
{
|
| 1866 |
+
"epoch": 0.7175382917069132,
|
| 1867 |
+
"grad_norm": 0.957733912839131,
|
| 1868 |
+
"learning_rate": 2.245974545926152e-06,
|
| 1869 |
+
"loss": 0.5179,
|
| 1870 |
+
"step": 2600
|
| 1871 |
+
},
|
| 1872 |
+
{
|
| 1873 |
+
"epoch": 0.7202980543673244,
|
| 1874 |
+
"grad_norm": 0.9601154451397089,
|
| 1875 |
+
"learning_rate": 2.205899353863665e-06,
|
| 1876 |
+
"loss": 0.5224,
|
| 1877 |
+
"step": 2610
|
| 1878 |
+
},
|
| 1879 |
+
{
|
| 1880 |
+
"epoch": 0.7230578170277356,
|
| 1881 |
+
"grad_norm": 0.9084441231449814,
|
| 1882 |
+
"learning_rate": 2.166083482291801e-06,
|
| 1883 |
+
"loss": 0.5254,
|
| 1884 |
+
"step": 2620
|
| 1885 |
+
},
|
| 1886 |
+
{
|
| 1887 |
+
"epoch": 0.7258175796881469,
|
| 1888 |
+
"grad_norm": 1.0841389588139543,
|
| 1889 |
+
"learning_rate": 2.1265306265217382e-06,
|
| 1890 |
+
"loss": 0.5214,
|
| 1891 |
+
"step": 2630
|
| 1892 |
+
},
|
| 1893 |
+
{
|
| 1894 |
+
"epoch": 0.728577342348558,
|
| 1895 |
+
"grad_norm": 1.451146075094232,
|
| 1896 |
+
"learning_rate": 2.0872444574541574e-06,
|
| 1897 |
+
"loss": 0.5298,
|
| 1898 |
+
"step": 2640
|
| 1899 |
+
},
|
| 1900 |
+
{
|
| 1901 |
+
"epoch": 0.7313371050089692,
|
| 1902 |
+
"grad_norm": 0.9009140743152368,
|
| 1903 |
+
"learning_rate": 2.048228621238547e-06,
|
| 1904 |
+
"loss": 0.5209,
|
| 1905 |
+
"step": 2650
|
| 1906 |
+
},
|
| 1907 |
+
{
|
| 1908 |
+
"epoch": 0.7340968676693804,
|
| 1909 |
+
"grad_norm": 0.8967623610111647,
|
| 1910 |
+
"learning_rate": 2.0094867389347982e-06,
|
| 1911 |
+
"loss": 0.5248,
|
| 1912 |
+
"step": 2660
|
| 1913 |
+
},
|
| 1914 |
+
{
|
| 1915 |
+
"epoch": 0.7368566303297917,
|
| 1916 |
+
"grad_norm": 0.9029822617189499,
|
| 1917 |
+
"learning_rate": 1.971022406177142e-06,
|
| 1918 |
+
"loss": 0.5227,
|
| 1919 |
+
"step": 2670
|
| 1920 |
+
},
|
| 1921 |
+
{
|
| 1922 |
+
"epoch": 0.7396163929902029,
|
| 1923 |
+
"grad_norm": 0.9009675358712146,
|
| 1924 |
+
"learning_rate": 1.932839192840436e-06,
|
| 1925 |
+
"loss": 0.522,
|
| 1926 |
+
"step": 2680
|
| 1927 |
+
},
|
| 1928 |
+
{
|
| 1929 |
+
"epoch": 0.7423761556506141,
|
| 1930 |
+
"grad_norm": 0.8816707412986489,
|
| 1931 |
+
"learning_rate": 1.8949406427088407e-06,
|
| 1932 |
+
"loss": 0.5223,
|
| 1933 |
+
"step": 2690
|
| 1934 |
+
},
|
| 1935 |
+
{
|
| 1936 |
+
"epoch": 0.7451359183110252,
|
| 1937 |
+
"grad_norm": 0.8605202814409114,
|
| 1938 |
+
"learning_rate": 1.8573302731469255e-06,
|
| 1939 |
+
"loss": 0.5241,
|
| 1940 |
+
"step": 2700
|
| 1941 |
+
},
|
| 1942 |
+
{
|
| 1943 |
+
"epoch": 0.7478956809714364,
|
| 1944 |
+
"grad_norm": 0.9612849756128029,
|
| 1945 |
+
"learning_rate": 1.820011574773221e-06,
|
| 1946 |
+
"loss": 0.5264,
|
| 1947 |
+
"step": 2710
|
| 1948 |
+
},
|
| 1949 |
+
{
|
| 1950 |
+
"epoch": 0.7506554436318477,
|
| 1951 |
+
"grad_norm": 0.8793842539758803,
|
| 1952 |
+
"learning_rate": 1.7829880111362486e-06,
|
| 1953 |
+
"loss": 0.5181,
|
| 1954 |
+
"step": 2720
|
| 1955 |
+
},
|
| 1956 |
+
{
|
| 1957 |
+
"epoch": 0.7534152062922589,
|
| 1958 |
+
"grad_norm": 1.2081068952668312,
|
| 1959 |
+
"learning_rate": 1.746263018393079e-06,
|
| 1960 |
+
"loss": 0.5292,
|
| 1961 |
+
"step": 2730
|
| 1962 |
+
},
|
| 1963 |
+
{
|
| 1964 |
+
"epoch": 0.7561749689526701,
|
| 1965 |
+
"grad_norm": 0.8860653822887559,
|
| 1966 |
+
"learning_rate": 1.7098400049904163e-06,
|
| 1967 |
+
"loss": 0.5219,
|
| 1968 |
+
"step": 2740
|
| 1969 |
+
},
|
| 1970 |
+
{
|
| 1971 |
+
"epoch": 0.7589347316130812,
|
| 1972 |
+
"grad_norm": 0.8901286343549357,
|
| 1973 |
+
"learning_rate": 1.6737223513482591e-06,
|
| 1974 |
+
"loss": 0.5259,
|
| 1975 |
+
"step": 2750
|
| 1976 |
+
},
|
| 1977 |
+
{
|
| 1978 |
+
"epoch": 0.7616944942734925,
|
| 1979 |
+
"grad_norm": 0.9081512876330592,
|
| 1980 |
+
"learning_rate": 1.6379134095461673e-06,
|
| 1981 |
+
"loss": 0.5171,
|
| 1982 |
+
"step": 2760
|
| 1983 |
+
},
|
| 1984 |
+
{
|
| 1985 |
+
"epoch": 0.7644542569339037,
|
| 1986 |
+
"grad_norm": 0.854771397996212,
|
| 1987 |
+
"learning_rate": 1.6024165030121542e-06,
|
| 1988 |
+
"loss": 0.521,
|
| 1989 |
+
"step": 2770
|
| 1990 |
+
},
|
| 1991 |
+
{
|
| 1992 |
+
"epoch": 0.7672140195943149,
|
| 1993 |
+
"grad_norm": 0.9522518174715512,
|
| 1994 |
+
"learning_rate": 1.567234926214236e-06,
|
| 1995 |
+
"loss": 0.5149,
|
| 1996 |
+
"step": 2780
|
| 1997 |
+
},
|
| 1998 |
+
{
|
| 1999 |
+
"epoch": 0.7699737822547261,
|
| 2000 |
+
"grad_norm": 0.855171965732468,
|
| 2001 |
+
"learning_rate": 1.5323719443546785e-06,
|
| 2002 |
+
"loss": 0.5217,
|
| 2003 |
+
"step": 2790
|
| 2004 |
+
},
|
| 2005 |
+
{
|
| 2006 |
+
"epoch": 0.7727335449151373,
|
| 2007 |
+
"grad_norm": 0.846551026714045,
|
| 2008 |
+
"learning_rate": 1.4978307930669483e-06,
|
| 2009 |
+
"loss": 0.5174,
|
| 2010 |
+
"step": 2800
|
| 2011 |
+
},
|
| 2012 |
+
{
|
| 2013 |
+
"epoch": 0.7754933075755485,
|
| 2014 |
+
"grad_norm": 0.9109328397942944,
|
| 2015 |
+
"learning_rate": 1.4636146781154164e-06,
|
| 2016 |
+
"loss": 0.5262,
|
| 2017 |
+
"step": 2810
|
| 2018 |
+
},
|
| 2019 |
+
{
|
| 2020 |
+
"epoch": 0.7782530702359597,
|
| 2021 |
+
"grad_norm": 0.8916543609749644,
|
| 2022 |
+
"learning_rate": 1.4297267750978277e-06,
|
| 2023 |
+
"loss": 0.5258,
|
| 2024 |
+
"step": 2820
|
| 2025 |
+
},
|
| 2026 |
+
{
|
| 2027 |
+
"epoch": 0.7810128328963709,
|
| 2028 |
+
"grad_norm": 0.839376705554234,
|
| 2029 |
+
"learning_rate": 1.3961702291505791e-06,
|
| 2030 |
+
"loss": 0.5233,
|
| 2031 |
+
"step": 2830
|
| 2032 |
+
},
|
| 2033 |
+
{
|
| 2034 |
+
"epoch": 0.7837725955567821,
|
| 2035 |
+
"grad_norm": 0.9530767315659909,
|
| 2036 |
+
"learning_rate": 1.3629481546568163e-06,
|
| 2037 |
+
"loss": 0.5153,
|
| 2038 |
+
"step": 2840
|
| 2039 |
+
},
|
| 2040 |
+
{
|
| 2041 |
+
"epoch": 0.7865323582171934,
|
| 2042 |
+
"grad_norm": 0.9433520691735623,
|
| 2043 |
+
"learning_rate": 1.3300636349573882e-06,
|
| 2044 |
+
"loss": 0.5169,
|
| 2045 |
+
"step": 2850
|
| 2046 |
+
},
|
| 2047 |
+
{
|
| 2048 |
+
"epoch": 0.7892921208776045,
|
| 2049 |
+
"grad_norm": 0.8633774616839734,
|
| 2050 |
+
"learning_rate": 1.2975197220646807e-06,
|
| 2051 |
+
"loss": 0.5211,
|
| 2052 |
+
"step": 2860
|
| 2053 |
+
},
|
| 2054 |
+
{
|
| 2055 |
+
"epoch": 0.7920518835380157,
|
| 2056 |
+
"grad_norm": 0.8830161483028809,
|
| 2057 |
+
"learning_rate": 1.2653194363793642e-06,
|
| 2058 |
+
"loss": 0.5169,
|
| 2059 |
+
"step": 2870
|
| 2060 |
+
},
|
| 2061 |
+
{
|
| 2062 |
+
"epoch": 0.7948116461984269,
|
| 2063 |
+
"grad_norm": 0.905868276953366,
|
| 2064 |
+
"learning_rate": 1.2334657664100614e-06,
|
| 2065 |
+
"loss": 0.5167,
|
| 2066 |
+
"step": 2880
|
| 2067 |
+
},
|
| 2068 |
+
{
|
| 2069 |
+
"epoch": 0.7975714088588381,
|
| 2070 |
+
"grad_norm": 0.8402578283356454,
|
| 2071 |
+
"learning_rate": 1.2019616684959934e-06,
|
| 2072 |
+
"loss": 0.5207,
|
| 2073 |
+
"step": 2890
|
| 2074 |
+
},
|
| 2075 |
+
{
|
| 2076 |
+
"epoch": 0.8003311715192494,
|
| 2077 |
+
"grad_norm": 1.0070145612320756,
|
| 2078 |
+
"learning_rate": 1.1708100665325967e-06,
|
| 2079 |
+
"loss": 0.5176,
|
| 2080 |
+
"step": 2900
|
| 2081 |
+
},
|
| 2082 |
+
{
|
| 2083 |
+
"epoch": 0.8030909341796606,
|
| 2084 |
+
"grad_norm": 0.8631246623697408,
|
| 2085 |
+
"learning_rate": 1.1400138517001564e-06,
|
| 2086 |
+
"loss": 0.5147,
|
| 2087 |
+
"step": 2910
|
| 2088 |
+
},
|
| 2089 |
+
{
|
| 2090 |
+
"epoch": 0.8058506968400717,
|
| 2091 |
+
"grad_norm": 0.8746596064396687,
|
| 2092 |
+
"learning_rate": 1.1095758821954788e-06,
|
| 2093 |
+
"loss": 0.5212,
|
| 2094 |
+
"step": 2920
|
| 2095 |
+
},
|
| 2096 |
+
{
|
| 2097 |
+
"epoch": 0.8086104595004829,
|
| 2098 |
+
"grad_norm": 0.8440888494194767,
|
| 2099 |
+
"learning_rate": 1.0794989829666197e-06,
|
| 2100 |
+
"loss": 0.5154,
|
| 2101 |
+
"step": 2930
|
| 2102 |
+
},
|
| 2103 |
+
{
|
| 2104 |
+
"epoch": 0.8113702221608942,
|
| 2105 |
+
"grad_norm": 0.8369885923181033,
|
| 2106 |
+
"learning_rate": 1.049785945450697e-06,
|
| 2107 |
+
"loss": 0.516,
|
| 2108 |
+
"step": 2940
|
| 2109 |
+
},
|
| 2110 |
+
{
|
| 2111 |
+
"epoch": 0.8141299848213054,
|
| 2112 |
+
"grad_norm": 1.5997002594596106,
|
| 2113 |
+
"learning_rate": 1.0204395273148277e-06,
|
| 2114 |
+
"loss": 0.5197,
|
| 2115 |
+
"step": 2950
|
| 2116 |
+
},
|
| 2117 |
+
{
|
| 2118 |
+
"epoch": 0.8168897474817166,
|
| 2119 |
+
"grad_norm": 0.8873807689235719,
|
| 2120 |
+
"learning_rate": 9.914624522001792e-07,
|
| 2121 |
+
"loss": 0.5232,
|
| 2122 |
+
"step": 2960
|
| 2123 |
+
},
|
| 2124 |
+
{
|
| 2125 |
+
"epoch": 0.8196495101421277,
|
| 2126 |
+
"grad_norm": 0.8697811520680214,
|
| 2127 |
+
"learning_rate": 9.628574094691945e-07,
|
| 2128 |
+
"loss": 0.5139,
|
| 2129 |
+
"step": 2970
|
| 2130 |
+
},
|
| 2131 |
+
{
|
| 2132 |
+
"epoch": 0.822409272802539,
|
| 2133 |
+
"grad_norm": 0.8378502425029508,
|
| 2134 |
+
"learning_rate": 9.346270539559882e-07,
|
| 2135 |
+
"loss": 0.52,
|
| 2136 |
+
"step": 2980
|
| 2137 |
+
},
|
| 2138 |
+
{
|
| 2139 |
+
"epoch": 0.8251690354629502,
|
| 2140 |
+
"grad_norm": 0.8849196731646373,
|
| 2141 |
+
"learning_rate": 9.067740057199514e-07,
|
| 2142 |
+
"loss": 0.518,
|
| 2143 |
+
"step": 2990
|
| 2144 |
+
},
|
| 2145 |
+
{
|
| 2146 |
+
"epoch": 0.8279287981233614,
|
| 2147 |
+
"grad_norm": 0.8664792504731555,
|
| 2148 |
+
"learning_rate": 8.793008498025879e-07,
|
| 2149 |
+
"loss": 0.5155,
|
| 2150 |
+
"step": 3000
|
| 2151 |
+
},
|
| 2152 |
+
{
|
| 2153 |
+
"epoch": 0.8279287981233614,
|
| 2154 |
+
"eval_loss": 0.5207065939903259,
|
| 2155 |
+
"eval_runtime": 49.1882,
|
| 2156 |
+
"eval_samples_per_second": 59.526,
|
| 2157 |
+
"eval_steps_per_second": 3.72,
|
| 2158 |
+
"step": 3000
|
| 2159 |
+
},
|
| 2160 |
+
{
|
| 2161 |
+
"epoch": 0.8306885607837726,
|
| 2162 |
+
"grad_norm": 0.8700644465815897,
|
| 2163 |
+
"learning_rate": 8.522101359875934e-07,
|
| 2164 |
+
"loss": 0.5131,
|
| 2165 |
+
"step": 3010
|
| 2166 |
+
},
|
| 2167 |
+
{
|
| 2168 |
+
"epoch": 0.8334483234441838,
|
| 2169 |
+
"grad_norm": 0.9097989981675693,
|
| 2170 |
+
"learning_rate": 8.255043785642108e-07,
|
| 2171 |
+
"loss": 0.5125,
|
| 2172 |
+
"step": 3020
|
| 2173 |
+
},
|
| 2174 |
+
{
|
| 2175 |
+
"epoch": 0.836208086104595,
|
| 2176 |
+
"grad_norm": 0.8631047164247316,
|
| 2177 |
+
"learning_rate": 7.991860560938786e-07,
|
| 2178 |
+
"loss": 0.5234,
|
| 2179 |
+
"step": 3030
|
| 2180 |
+
},
|
| 2181 |
+
{
|
| 2182 |
+
"epoch": 0.8389678487650062,
|
| 2183 |
+
"grad_norm": 1.2358190890284166,
|
| 2184 |
+
"learning_rate": 7.732576111801982e-07,
|
| 2185 |
+
"loss": 0.5176,
|
| 2186 |
+
"step": 3040
|
| 2187 |
+
},
|
| 2188 |
+
{
|
| 2189 |
+
"epoch": 0.8417276114254174,
|
| 2190 |
+
"grad_norm": 0.8514248482095018,
|
| 2191 |
+
"learning_rate": 7.477214502422281e-07,
|
| 2192 |
+
"loss": 0.5223,
|
| 2193 |
+
"step": 3050
|
| 2194 |
+
},
|
| 2195 |
+
{
|
| 2196 |
+
"epoch": 0.8444873740858286,
|
| 2197 |
+
"grad_norm": 0.8563129413552018,
|
| 2198 |
+
"learning_rate": 7.225799432911557e-07,
|
| 2199 |
+
"loss": 0.5219,
|
| 2200 |
+
"step": 3060
|
| 2201 |
+
},
|
| 2202 |
+
{
|
| 2203 |
+
"epoch": 0.8472471367462399,
|
| 2204 |
+
"grad_norm": 1.6151093899813862,
|
| 2205 |
+
"learning_rate": 6.978354237103264e-07,
|
| 2206 |
+
"loss": 0.516,
|
| 2207 |
+
"step": 3070
|
| 2208 |
+
},
|
| 2209 |
+
{
|
| 2210 |
+
"epoch": 0.850006899406651,
|
| 2211 |
+
"grad_norm": 2.00845392683435,
|
| 2212 |
+
"learning_rate": 6.734901880386896e-07,
|
| 2213 |
+
"loss": 0.5185,
|
| 2214 |
+
"step": 3080
|
| 2215 |
+
},
|
| 2216 |
+
{
|
| 2217 |
+
"epoch": 0.8527666620670622,
|
| 2218 |
+
"grad_norm": 1.1862873972091095,
|
| 2219 |
+
"learning_rate": 6.495464957576508e-07,
|
| 2220 |
+
"loss": 0.5122,
|
| 2221 |
+
"step": 3090
|
| 2222 |
+
},
|
| 2223 |
+
{
|
| 2224 |
+
"epoch": 0.8555264247274734,
|
| 2225 |
+
"grad_norm": 0.8470639388291085,
|
| 2226 |
+
"learning_rate": 6.260065690813754e-07,
|
| 2227 |
+
"loss": 0.5158,
|
| 2228 |
+
"step": 3100
|
| 2229 |
+
},
|
| 2230 |
+
{
|
| 2231 |
+
"epoch": 0.8582861873878846,
|
| 2232 |
+
"grad_norm": 0.9219107715988072,
|
| 2233 |
+
"learning_rate": 6.028725927505369e-07,
|
| 2234 |
+
"loss": 0.5201,
|
| 2235 |
+
"step": 3110
|
| 2236 |
+
},
|
| 2237 |
+
{
|
| 2238 |
+
"epoch": 0.8610459500482959,
|
| 2239 |
+
"grad_norm": 0.8827729120692012,
|
| 2240 |
+
"learning_rate": 5.801467138295597e-07,
|
| 2241 |
+
"loss": 0.5189,
|
| 2242 |
+
"step": 3120
|
| 2243 |
+
},
|
| 2244 |
+
{
|
| 2245 |
+
"epoch": 0.8638057127087071,
|
| 2246 |
+
"grad_norm": 0.8610445224310359,
|
| 2247 |
+
"learning_rate": 5.578310415073451e-07,
|
| 2248 |
+
"loss": 0.515,
|
| 2249 |
+
"step": 3130
|
| 2250 |
+
},
|
| 2251 |
+
{
|
| 2252 |
+
"epoch": 0.8665654753691182,
|
| 2253 |
+
"grad_norm": 0.870963273635567,
|
| 2254 |
+
"learning_rate": 5.359276469015179e-07,
|
| 2255 |
+
"loss": 0.5151,
|
| 2256 |
+
"step": 3140
|
| 2257 |
+
},
|
| 2258 |
+
{
|
| 2259 |
+
"epoch": 0.8693252380295294,
|
| 2260 |
+
"grad_norm": 0.8396590023282043,
|
| 2261 |
+
"learning_rate": 5.14438562866208e-07,
|
| 2262 |
+
"loss": 0.5223,
|
| 2263 |
+
"step": 3150
|
| 2264 |
+
},
|
| 2265 |
+
{
|
| 2266 |
+
"epoch": 0.8720850006899407,
|
| 2267 |
+
"grad_norm": 0.8992961235238134,
|
| 2268 |
+
"learning_rate": 4.933657838033795e-07,
|
| 2269 |
+
"loss": 0.5144,
|
| 2270 |
+
"step": 3160
|
| 2271 |
+
},
|
| 2272 |
+
{
|
| 2273 |
+
"epoch": 0.8748447633503519,
|
| 2274 |
+
"grad_norm": 0.9038948906592709,
|
| 2275 |
+
"learning_rate": 4.7271126547772773e-07,
|
| 2276 |
+
"loss": 0.5165,
|
| 2277 |
+
"step": 3170
|
| 2278 |
+
},
|
| 2279 |
+
{
|
| 2280 |
+
"epoch": 0.8776045260107631,
|
| 2281 |
+
"grad_norm": 0.8686028788473747,
|
| 2282 |
+
"learning_rate": 4.524769248351718e-07,
|
| 2283 |
+
"loss": 0.5157,
|
| 2284 |
+
"step": 3180
|
| 2285 |
+
},
|
| 2286 |
+
{
|
| 2287 |
+
"epoch": 0.8803642886711743,
|
| 2288 |
+
"grad_norm": 0.8744713706157983,
|
| 2289 |
+
"learning_rate": 4.3266463982493566e-07,
|
| 2290 |
+
"loss": 0.5167,
|
| 2291 |
+
"step": 3190
|
| 2292 |
+
},
|
| 2293 |
+
{
|
| 2294 |
+
"epoch": 0.8831240513315854,
|
| 2295 |
+
"grad_norm": 0.8953682081464681,
|
| 2296 |
+
"learning_rate": 4.132762492252601e-07,
|
| 2297 |
+
"loss": 0.5229,
|
| 2298 |
+
"step": 3200
|
| 2299 |
+
},
|
| 2300 |
+
{
|
| 2301 |
+
"epoch": 0.8858838139919967,
|
| 2302 |
+
"grad_norm": 1.0500886926956579,
|
| 2303 |
+
"learning_rate": 3.943135524727448e-07,
|
| 2304 |
+
"loss": 0.5168,
|
| 2305 |
+
"step": 3210
|
| 2306 |
+
},
|
| 2307 |
+
{
|
| 2308 |
+
"epoch": 0.8886435766524079,
|
| 2309 |
+
"grad_norm": 0.8891911066911182,
|
| 2310 |
+
"learning_rate": 3.757783094953382e-07,
|
| 2311 |
+
"loss": 0.52,
|
| 2312 |
+
"step": 3220
|
| 2313 |
+
},
|
| 2314 |
+
{
|
| 2315 |
+
"epoch": 0.8914033393128191,
|
| 2316 |
+
"grad_norm": 0.8469428073562058,
|
| 2317 |
+
"learning_rate": 3.5767224054900687e-07,
|
| 2318 |
+
"loss": 0.514,
|
| 2319 |
+
"step": 3230
|
| 2320 |
+
},
|
| 2321 |
+
{
|
| 2322 |
+
"epoch": 0.8941631019732303,
|
| 2323 |
+
"grad_norm": 0.8985979256834127,
|
| 2324 |
+
"learning_rate": 3.3999702605807203e-07,
|
| 2325 |
+
"loss": 0.5153,
|
| 2326 |
+
"step": 3240
|
| 2327 |
+
},
|
| 2328 |
+
{
|
| 2329 |
+
"epoch": 0.8969228646336415,
|
| 2330 |
+
"grad_norm": 0.8740663379412131,
|
| 2331 |
+
"learning_rate": 3.227543064592514e-07,
|
| 2332 |
+
"loss": 0.5179,
|
| 2333 |
+
"step": 3250
|
| 2334 |
+
},
|
| 2335 |
+
{
|
| 2336 |
+
"epoch": 0.8996826272940527,
|
| 2337 |
+
"grad_norm": 0.9253549886032714,
|
| 2338 |
+
"learning_rate": 3.059456820494111e-07,
|
| 2339 |
+
"loss": 0.5187,
|
| 2340 |
+
"step": 3260
|
| 2341 |
+
},
|
| 2342 |
+
{
|
| 2343 |
+
"epoch": 0.9024423899544639,
|
| 2344 |
+
"grad_norm": 0.8657401705396123,
|
| 2345 |
+
"learning_rate": 2.8957271283704067e-07,
|
| 2346 |
+
"loss": 0.5188,
|
| 2347 |
+
"step": 3270
|
| 2348 |
+
},
|
| 2349 |
+
{
|
| 2350 |
+
"epoch": 0.9052021526148751,
|
| 2351 |
+
"grad_norm": 0.8317058461633765,
|
| 2352 |
+
"learning_rate": 2.736369183974685e-07,
|
| 2353 |
+
"loss": 0.5161,
|
| 2354 |
+
"step": 3280
|
| 2355 |
+
},
|
| 2356 |
+
{
|
| 2357 |
+
"epoch": 0.9079619152752864,
|
| 2358 |
+
"grad_norm": 0.8738336902844653,
|
| 2359 |
+
"learning_rate": 2.5813977773183175e-07,
|
| 2360 |
+
"loss": 0.515,
|
| 2361 |
+
"step": 3290
|
| 2362 |
+
},
|
| 2363 |
+
{
|
| 2364 |
+
"epoch": 0.9107216779356976,
|
| 2365 |
+
"grad_norm": 0.9137477549092036,
|
| 2366 |
+
"learning_rate": 2.430827291298099e-07,
|
| 2367 |
+
"loss": 0.5198,
|
| 2368 |
+
"step": 3300
|
| 2369 |
+
},
|
| 2370 |
+
{
|
| 2371 |
+
"epoch": 0.9134814405961087,
|
| 2372 |
+
"grad_norm": 0.8521777662643962,
|
| 2373 |
+
"learning_rate": 2.2846717003613462e-07,
|
| 2374 |
+
"loss": 0.5221,
|
| 2375 |
+
"step": 3310
|
| 2376 |
+
},
|
| 2377 |
+
{
|
| 2378 |
+
"epoch": 0.9162412032565199,
|
| 2379 |
+
"grad_norm": 1.12701228509693,
|
| 2380 |
+
"learning_rate": 2.1429445692089712e-07,
|
| 2381 |
+
"loss": 0.5154,
|
| 2382 |
+
"step": 3320
|
| 2383 |
+
},
|
| 2384 |
+
{
|
| 2385 |
+
"epoch": 0.9190009659169311,
|
| 2386 |
+
"grad_norm": 0.9027916863842183,
|
| 2387 |
+
"learning_rate": 2.0056590515365016e-07,
|
| 2388 |
+
"loss": 0.5159,
|
| 2389 |
+
"step": 3330
|
| 2390 |
+
},
|
| 2391 |
+
{
|
| 2392 |
+
"epoch": 0.9217607285773424,
|
| 2393 |
+
"grad_norm": 0.839347519350046,
|
| 2394 |
+
"learning_rate": 1.8728278888132944e-07,
|
| 2395 |
+
"loss": 0.518,
|
| 2396 |
+
"step": 3340
|
| 2397 |
+
},
|
| 2398 |
+
{
|
| 2399 |
+
"epoch": 0.9245204912377536,
|
| 2400 |
+
"grad_norm": 0.8627735870099915,
|
| 2401 |
+
"learning_rate": 1.744463409100039e-07,
|
| 2402 |
+
"loss": 0.5189,
|
| 2403 |
+
"step": 3350
|
| 2404 |
+
},
|
| 2405 |
+
{
|
| 2406 |
+
"epoch": 0.9272802538981647,
|
| 2407 |
+
"grad_norm": 0.8677279393067534,
|
| 2408 |
+
"learning_rate": 1.620577525904532e-07,
|
| 2409 |
+
"loss": 0.5099,
|
| 2410 |
+
"step": 3360
|
| 2411 |
+
},
|
| 2412 |
+
{
|
| 2413 |
+
"epoch": 0.9300400165585759,
|
| 2414 |
+
"grad_norm": 0.8705917700670992,
|
| 2415 |
+
"learning_rate": 1.501181737076035e-07,
|
| 2416 |
+
"loss": 0.5154,
|
| 2417 |
+
"step": 3370
|
| 2418 |
+
},
|
| 2419 |
+
{
|
| 2420 |
+
"epoch": 0.9327997792189872,
|
| 2421 |
+
"grad_norm": 0.9046790697526798,
|
| 2422 |
+
"learning_rate": 1.3862871237381004e-07,
|
| 2423 |
+
"loss": 0.5108,
|
| 2424 |
+
"step": 3380
|
| 2425 |
+
},
|
| 2426 |
+
{
|
| 2427 |
+
"epoch": 0.9355595418793984,
|
| 2428 |
+
"grad_norm": 0.8203655507439958,
|
| 2429 |
+
"learning_rate": 1.2759043492601986e-07,
|
| 2430 |
+
"loss": 0.5136,
|
| 2431 |
+
"step": 3390
|
| 2432 |
+
},
|
| 2433 |
+
{
|
| 2434 |
+
"epoch": 0.9383193045398096,
|
| 2435 |
+
"grad_norm": 0.8949093577414237,
|
| 2436 |
+
"learning_rate": 1.1700436582680108e-07,
|
| 2437 |
+
"loss": 0.5192,
|
| 2438 |
+
"step": 3400
|
| 2439 |
+
},
|
| 2440 |
+
{
|
| 2441 |
+
"epoch": 0.9410790672002208,
|
| 2442 |
+
"grad_norm": 0.8425742363423367,
|
| 2443 |
+
"learning_rate": 1.068714875692628e-07,
|
| 2444 |
+
"loss": 0.5116,
|
| 2445 |
+
"step": 3410
|
| 2446 |
+
},
|
| 2447 |
+
{
|
| 2448 |
+
"epoch": 0.943838829860632,
|
| 2449 |
+
"grad_norm": 0.9030687400394452,
|
| 2450 |
+
"learning_rate": 9.719274058587247e-08,
|
| 2451 |
+
"loss": 0.5125,
|
| 2452 |
+
"step": 3420
|
| 2453 |
+
},
|
| 2454 |
+
{
|
| 2455 |
+
"epoch": 0.9465985925210432,
|
| 2456 |
+
"grad_norm": 0.8753228488205499,
|
| 2457 |
+
"learning_rate": 8.796902316117018e-08,
|
| 2458 |
+
"loss": 0.5156,
|
| 2459 |
+
"step": 3430
|
| 2460 |
+
},
|
| 2461 |
+
{
|
| 2462 |
+
"epoch": 0.9493583551814544,
|
| 2463 |
+
"grad_norm": 0.8396184463940205,
|
| 2464 |
+
"learning_rate": 7.920119134840199e-08,
|
| 2465 |
+
"loss": 0.5141,
|
| 2466 |
+
"step": 3440
|
| 2467 |
+
},
|
| 2468 |
+
{
|
| 2469 |
+
"epoch": 0.9521181178418656,
|
| 2470 |
+
"grad_norm": 0.882889766020658,
|
| 2471 |
+
"learning_rate": 7.08900588900685e-08,
|
| 2472 |
+
"loss": 0.5131,
|
| 2473 |
+
"step": 3450
|
| 2474 |
+
},
|
| 2475 |
+
{
|
| 2476 |
+
"epoch": 0.9548778805022768,
|
| 2477 |
+
"grad_norm": 0.8504174898031396,
|
| 2478 |
+
"learning_rate": 6.303639714240196e-08,
|
| 2479 |
+
"loss": 0.5193,
|
| 2480 |
+
"step": 3460
|
| 2481 |
+
},
|
| 2482 |
+
{
|
| 2483 |
+
"epoch": 0.957637643162688,
|
| 2484 |
+
"grad_norm": 0.8595498992279648,
|
| 2485 |
+
"learning_rate": 5.564093500377732e-08,
|
| 2486 |
+
"loss": 0.515,
|
| 2487 |
+
"step": 3470
|
| 2488 |
+
},
|
| 2489 |
+
{
|
| 2490 |
+
"epoch": 0.9603974058230992,
|
| 2491 |
+
"grad_norm": 0.8244758548316357,
|
| 2492 |
+
"learning_rate": 4.870435884705982e-08,
|
| 2493 |
+
"loss": 0.5135,
|
| 2494 |
+
"step": 3480
|
| 2495 |
+
},
|
| 2496 |
+
{
|
| 2497 |
+
"epoch": 0.9631571684835104,
|
| 2498 |
+
"grad_norm": 0.9192549923625648,
|
| 2499 |
+
"learning_rate": 4.22273124559075e-08,
|
| 2500 |
+
"loss": 0.5165,
|
| 2501 |
+
"step": 3490
|
| 2502 |
+
},
|
| 2503 |
+
{
|
| 2504 |
+
"epoch": 0.9659169311439216,
|
| 2505 |
+
"grad_norm": 1.8467401343991516,
|
| 2506 |
+
"learning_rate": 3.621039696501794e-08,
|
| 2507 |
+
"loss": 0.5106,
|
| 2508 |
+
"step": 3500
|
| 2509 |
+
},
|
| 2510 |
+
{
|
| 2511 |
+
"epoch": 0.9659169311439216,
|
| 2512 |
+
"eval_loss": 0.5180693864822388,
|
| 2513 |
+
"eval_runtime": 48.9508,
|
| 2514 |
+
"eval_samples_per_second": 59.815,
|
| 2515 |
+
"eval_steps_per_second": 3.738,
|
| 2516 |
+
"step": 3500
|
| 2517 |
+
},
|
| 2518 |
+
{
|
| 2519 |
+
"epoch": 0.9686766938043329,
|
| 2520 |
+
"grad_norm": 0.9145993584663505,
|
| 2521 |
+
"learning_rate": 3.065417080433841e-08,
|
| 2522 |
+
"loss": 0.517,
|
| 2523 |
+
"step": 3510
|
| 2524 |
+
},
|
| 2525 |
+
{
|
| 2526 |
+
"epoch": 0.9714364564647441,
|
| 2527 |
+
"grad_norm": 0.8570121000540161,
|
| 2528 |
+
"learning_rate": 2.555914964723849e-08,
|
| 2529 |
+
"loss": 0.5142,
|
| 2530 |
+
"step": 3520
|
| 2531 |
+
},
|
| 2532 |
+
{
|
| 2533 |
+
"epoch": 0.9741962191251552,
|
| 2534 |
+
"grad_norm": 0.8678615083324009,
|
| 2535 |
+
"learning_rate": 2.0925806362648847e-08,
|
| 2536 |
+
"loss": 0.5198,
|
| 2537 |
+
"step": 3530
|
| 2538 |
+
},
|
| 2539 |
+
{
|
| 2540 |
+
"epoch": 0.9769559817855664,
|
| 2541 |
+
"grad_norm": 0.8381539016578547,
|
| 2542 |
+
"learning_rate": 1.6754570971176944e-08,
|
| 2543 |
+
"loss": 0.5125,
|
| 2544 |
+
"step": 3540
|
| 2545 |
+
},
|
| 2546 |
+
{
|
| 2547 |
+
"epoch": 0.9797157444459776,
|
| 2548 |
+
"grad_norm": 0.9056379885360033,
|
| 2549 |
+
"learning_rate": 1.3045830605192266e-08,
|
| 2550 |
+
"loss": 0.5192,
|
| 2551 |
+
"step": 3550
|
| 2552 |
+
},
|
| 2553 |
+
{
|
| 2554 |
+
"epoch": 0.9824755071063889,
|
| 2555 |
+
"grad_norm": 0.8696346972561173,
|
| 2556 |
+
"learning_rate": 9.799929472902315e-09,
|
| 2557 |
+
"loss": 0.5205,
|
| 2558 |
+
"step": 3560
|
| 2559 |
+
},
|
| 2560 |
+
{
|
| 2561 |
+
"epoch": 0.9852352697668001,
|
| 2562 |
+
"grad_norm": 3.314581793197866,
|
| 2563 |
+
"learning_rate": 7.017168826401466e-09,
|
| 2564 |
+
"loss": 0.5169,
|
| 2565 |
+
"step": 3570
|
| 2566 |
+
},
|
| 2567 |
+
{
|
| 2568 |
+
"epoch": 0.9879950324272112,
|
| 2569 |
+
"grad_norm": 0.8566695475770818,
|
| 2570 |
+
"learning_rate": 4.697806933715021e-09,
|
| 2571 |
+
"loss": 0.5095,
|
| 2572 |
+
"step": 3580
|
| 2573 |
+
},
|
| 2574 |
+
{
|
| 2575 |
+
"epoch": 0.9907547950876224,
|
| 2576 |
+
"grad_norm": 0.8718028954806468,
|
| 2577 |
+
"learning_rate": 2.8420590548294825e-09,
|
| 2578 |
+
"loss": 0.5175,
|
| 2579 |
+
"step": 3590
|
| 2580 |
+
},
|
| 2581 |
+
{
|
| 2582 |
+
"epoch": 0.9935145577480337,
|
| 2583 |
+
"grad_norm": 0.8678996243220692,
|
| 2584 |
+
"learning_rate": 1.450097421710206e-09,
|
| 2585 |
+
"loss": 0.519,
|
| 2586 |
+
"step": 3600
|
| 2587 |
+
},
|
| 2588 |
+
{
|
| 2589 |
+
"epoch": 0.9962743204084449,
|
| 2590 |
+
"grad_norm": 0.8913548884246177,
|
| 2591 |
+
"learning_rate": 5.220512223219621e-10,
|
| 2592 |
+
"loss": 0.5135,
|
| 2593 |
+
"step": 3610
|
| 2594 |
+
},
|
| 2595 |
+
{
|
| 2596 |
+
"epoch": 0.9990340830688561,
|
| 2597 |
+
"grad_norm": 0.8708615108897616,
|
| 2598 |
+
"learning_rate": 5.8006588636305704e-11,
|
| 2599 |
+
"loss": 0.5151,
|
| 2600 |
+
"step": 3620
|
| 2601 |
+
},
|
| 2602 |
+
{
|
| 2603 |
+
"epoch": 1.0,
|
| 2604 |
+
"step": 3624,
|
| 2605 |
+
"total_flos": 1884305306419200.0,
|
| 2606 |
+
"train_loss": 0.5639046454929622,
|
| 2607 |
+
"train_runtime": 12600.7671,
|
| 2608 |
+
"train_samples_per_second": 23.004,
|
| 2609 |
+
"train_steps_per_second": 0.288
|
| 2610 |
+
}
|
| 2611 |
+
],
|
| 2612 |
+
"logging_steps": 10,
|
| 2613 |
+
"max_steps": 3624,
|
| 2614 |
+
"num_input_tokens_seen": 0,
|
| 2615 |
+
"num_train_epochs": 1,
|
| 2616 |
+
"save_steps": 200,
|
| 2617 |
+
"stateful_callbacks": {
|
| 2618 |
+
"TrainerControl": {
|
| 2619 |
+
"args": {
|
| 2620 |
+
"should_epoch_stop": false,
|
| 2621 |
+
"should_evaluate": false,
|
| 2622 |
+
"should_log": false,
|
| 2623 |
+
"should_save": true,
|
| 2624 |
+
"should_training_stop": true
|
| 2625 |
+
},
|
| 2626 |
+
"attributes": {}
|
| 2627 |
+
}
|
| 2628 |
+
},
|
| 2629 |
+
"total_flos": 1884305306419200.0,
|
| 2630 |
+
"train_batch_size": 5,
|
| 2631 |
+
"trial_name": null,
|
| 2632 |
+
"trial_params": null
|
| 2633 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:97c6e4d7b115e0701ae8a27826aa5b4468697f6689d45864f19a2dc387adc3cf
|
| 3 |
+
size 8593
|
training_eval_loss.png
ADDED
|
training_loss.png
ADDED
|
video_preprocessor_config.json
ADDED
|
@@ -0,0 +1,41 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"crop_size": null,
|
| 3 |
+
"data_format": "channels_first",
|
| 4 |
+
"default_to_square": true,
|
| 5 |
+
"device": null,
|
| 6 |
+
"do_center_crop": null,
|
| 7 |
+
"do_convert_rgb": true,
|
| 8 |
+
"do_normalize": true,
|
| 9 |
+
"do_rescale": true,
|
| 10 |
+
"do_resize": true,
|
| 11 |
+
"do_sample_frames": true,
|
| 12 |
+
"fps": 2,
|
| 13 |
+
"image_mean": [
|
| 14 |
+
0.5,
|
| 15 |
+
0.5,
|
| 16 |
+
0.5
|
| 17 |
+
],
|
| 18 |
+
"image_std": [
|
| 19 |
+
0.5,
|
| 20 |
+
0.5,
|
| 21 |
+
0.5
|
| 22 |
+
],
|
| 23 |
+
"input_data_format": null,
|
| 24 |
+
"max_frames": 768,
|
| 25 |
+
"merge_size": 2,
|
| 26 |
+
"min_frames": 4,
|
| 27 |
+
"num_frames": null,
|
| 28 |
+
"pad_size": null,
|
| 29 |
+
"patch_size": 16,
|
| 30 |
+
"processor_class": "Qwen3VLProcessor",
|
| 31 |
+
"resample": 3,
|
| 32 |
+
"rescale_factor": 0.00392156862745098,
|
| 33 |
+
"return_metadata": false,
|
| 34 |
+
"size": {
|
| 35 |
+
"longest_edge": 25165824,
|
| 36 |
+
"shortest_edge": 4096
|
| 37 |
+
},
|
| 38 |
+
"temporal_patch_size": 2,
|
| 39 |
+
"video_metadata": null,
|
| 40 |
+
"video_processor_type": "Qwen3VLVideoProcessor"
|
| 41 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|