Upload folder using huggingface_hub
Browse files- .gitattributes +1 -0
- README.md +69 -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/Feb02_17-11-14_gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn/events.out.tfevents.1770056607.gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn.1569.0 +3 -0
- runs/Feb02_17-11-14_gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn/events.out.tfevents.1770071322.gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn.1569.1 +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 +234 -0
- trainer_state.json +1678 -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 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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: edit_evaluation_sft_202602030104
|
| 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 |
+
# edit_evaluation_sft_202602030104
|
| 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 instruction_following_train_v3 and the consistency_train_v3 datasets.
|
| 20 |
+
It achieves the following results on the evaluation set:
|
| 21 |
+
- Loss: 0.5041
|
| 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: 10
|
| 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: 160
|
| 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 |
+
| 0.591 | 0.2182 | 500 | 0.5827 |
|
| 59 |
+
| 0.5605 | 0.4364 | 1000 | 0.5460 |
|
| 60 |
+
| 0.5252 | 0.6546 | 1500 | 0.5199 |
|
| 61 |
+
| 0.5075 | 0.8728 | 2000 | 0.5055 |
|
| 62 |
+
|
| 63 |
+
|
| 64 |
+
### Framework versions
|
| 65 |
+
|
| 66 |
+
- Transformers 4.57.3
|
| 67 |
+
- Pytorch 2.7.1+cu128
|
| 68 |
+
- Datasets 4.0.0
|
| 69 |
+
- 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": 0.5041009783744812,
|
| 4 |
+
"eval_runtime": 65.962,
|
| 5 |
+
"eval_samples_per_second": 56.138,
|
| 6 |
+
"eval_steps_per_second": 3.517,
|
| 7 |
+
"total_flos": 2450977789313024.0,
|
| 8 |
+
"train_loss": 0.5714389552828737,
|
| 9 |
+
"train_runtime": 14627.8115,
|
| 10 |
+
"train_samples_per_second": 25.06,
|
| 11 |
+
"train_steps_per_second": 0.157
|
| 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": 0.5041009783744812,
|
| 4 |
+
"eval_runtime": 65.962,
|
| 5 |
+
"eval_samples_per_second": 56.138,
|
| 6 |
+
"eval_steps_per_second": 3.517
|
| 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:a8ff48209a7be77703b0bd04402ac6f57d59102053d3ecfdb8ab0e8eb9b107ef
|
| 3 |
+
size 4998056552
|
model-00002-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:98abf482da7482528d7973f0aba4344bf4ae24472fb11c36dde2a329e8dda5f4
|
| 3 |
+
size 4915962464
|
model-00003-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:844f6e51e5e148922b236c14373dd1ea274fafe06f96a937d2b61539561b6b51
|
| 3 |
+
size 4915962496
|
model-00004-of-00004.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:466c59a4e155ac6115e1622b4753802e5094c10b80869880aa487f58b37ee0fb
|
| 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/Feb02_17-11-14_gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn/events.out.tfevents.1770056607.gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn.1569.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0684d11a8e393053a608e13b783dd9402f6ab85f3bcdcf7609b7ee6f96b14fcb
|
| 3 |
+
size 56401
|
runs/Feb02_17-11-14_gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn/events.out.tfevents.1770071322.gpu-lg-cmc-h-h200-0426.host.h.pjlab.org.cn.1569.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f23c04662e77bc6ea92854257ace380c7827d52c60bf840e0cac67fc378d0711
|
| 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": 2450977789313024.0,
|
| 4 |
+
"train_loss": 0.5714389552828737,
|
| 5 |
+
"train_runtime": 14627.8115,
|
| 6 |
+
"train_samples_per_second": 25.06,
|
| 7 |
+
"train_steps_per_second": 0.157
|
| 8 |
+
}
|
trainer_log.jsonl
ADDED
|
@@ -0,0 +1,234 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{"current_steps": 10, "total_steps": 2292, "loss": 1.5146, "lr": 3.91304347826087e-07, "epoch": 0.004363953742090334, "percentage": 0.44, "elapsed_time": "0:01:33", "remaining_time": "5:56:04"}
|
| 2 |
+
{"current_steps": 20, "total_steps": 2292, "loss": 1.3975, "lr": 8.260869565217392e-07, "epoch": 0.008727907484180668, "percentage": 0.87, "elapsed_time": "0:02:36", "remaining_time": "4:56:39"}
|
| 3 |
+
{"current_steps": 30, "total_steps": 2292, "loss": 1.0301, "lr": 1.2608695652173913e-06, "epoch": 0.013091861226271002, "percentage": 1.31, "elapsed_time": "0:03:37", "remaining_time": "4:33:05"}
|
| 4 |
+
{"current_steps": 40, "total_steps": 2292, "loss": 0.9338, "lr": 1.6956521739130435e-06, "epoch": 0.017455814968361336, "percentage": 1.75, "elapsed_time": "0:04:39", "remaining_time": "4:22:13"}
|
| 5 |
+
{"current_steps": 50, "total_steps": 2292, "loss": 0.834, "lr": 2.130434782608696e-06, "epoch": 0.02181976871045167, "percentage": 2.18, "elapsed_time": "0:05:41", "remaining_time": "4:14:55"}
|
| 6 |
+
{"current_steps": 60, "total_steps": 2292, "loss": 0.7817, "lr": 2.5652173913043484e-06, "epoch": 0.026183722452542003, "percentage": 2.62, "elapsed_time": "0:06:42", "remaining_time": "4:09:24"}
|
| 7 |
+
{"current_steps": 70, "total_steps": 2292, "loss": 0.7423, "lr": 3e-06, "epoch": 0.030547676194632337, "percentage": 3.05, "elapsed_time": "0:07:42", "remaining_time": "4:04:48"}
|
| 8 |
+
{"current_steps": 80, "total_steps": 2292, "loss": 0.7193, "lr": 3.4347826086956526e-06, "epoch": 0.03491162993672267, "percentage": 3.49, "elapsed_time": "0:08:42", "remaining_time": "4:00:39"}
|
| 9 |
+
{"current_steps": 90, "total_steps": 2292, "loss": 0.6965, "lr": 3.869565217391304e-06, "epoch": 0.039275583678813, "percentage": 3.93, "elapsed_time": "0:09:42", "remaining_time": "3:57:32"}
|
| 10 |
+
{"current_steps": 100, "total_steps": 2292, "loss": 0.6863, "lr": 4.304347826086957e-06, "epoch": 0.04363953742090334, "percentage": 4.36, "elapsed_time": "0:10:43", "remaining_time": "3:54:58"}
|
| 11 |
+
{"current_steps": 110, "total_steps": 2292, "loss": 0.6761, "lr": 4.739130434782609e-06, "epoch": 0.04800349116299367, "percentage": 4.8, "elapsed_time": "0:11:43", "remaining_time": "3:52:41"}
|
| 12 |
+
{"current_steps": 120, "total_steps": 2292, "loss": 0.669, "lr": 5.173913043478262e-06, "epoch": 0.05236744490508401, "percentage": 5.24, "elapsed_time": "0:12:45", "remaining_time": "3:50:52"}
|
| 13 |
+
{"current_steps": 130, "total_steps": 2292, "loss": 0.6553, "lr": 5.608695652173914e-06, "epoch": 0.05673139864717434, "percentage": 5.67, "elapsed_time": "0:13:45", "remaining_time": "3:48:55"}
|
| 14 |
+
{"current_steps": 140, "total_steps": 2292, "loss": 0.6635, "lr": 6.043478260869565e-06, "epoch": 0.061095352389264675, "percentage": 6.11, "elapsed_time": "0:14:47", "remaining_time": "3:47:26"}
|
| 15 |
+
{"current_steps": 150, "total_steps": 2292, "loss": 0.6417, "lr": 6.478260869565218e-06, "epoch": 0.065459306131355, "percentage": 6.54, "elapsed_time": "0:15:49", "remaining_time": "3:45:52"}
|
| 16 |
+
{"current_steps": 160, "total_steps": 2292, "loss": 0.6427, "lr": 6.91304347826087e-06, "epoch": 0.06982325987344534, "percentage": 6.98, "elapsed_time": "0:16:50", "remaining_time": "3:44:25"}
|
| 17 |
+
{"current_steps": 170, "total_steps": 2292, "loss": 0.6442, "lr": 7.347826086956522e-06, "epoch": 0.07418721361553568, "percentage": 7.42, "elapsed_time": "0:17:51", "remaining_time": "3:42:53"}
|
| 18 |
+
{"current_steps": 180, "total_steps": 2292, "loss": 0.6369, "lr": 7.782608695652174e-06, "epoch": 0.078551167357626, "percentage": 7.85, "elapsed_time": "0:18:52", "remaining_time": "3:41:28"}
|
| 19 |
+
{"current_steps": 190, "total_steps": 2292, "loss": 0.639, "lr": 8.217391304347827e-06, "epoch": 0.08291512109971634, "percentage": 8.29, "elapsed_time": "0:19:54", "remaining_time": "3:40:09"}
|
| 20 |
+
{"current_steps": 200, "total_steps": 2292, "loss": 0.6414, "lr": 8.65217391304348e-06, "epoch": 0.08727907484180668, "percentage": 8.73, "elapsed_time": "0:20:56", "remaining_time": "3:38:57"}
|
| 21 |
+
{"current_steps": 210, "total_steps": 2292, "loss": 0.6392, "lr": 9.086956521739132e-06, "epoch": 0.09164302858389702, "percentage": 9.16, "elapsed_time": "0:22:18", "remaining_time": "3:41:10"}
|
| 22 |
+
{"current_steps": 220, "total_steps": 2292, "loss": 0.6407, "lr": 9.521739130434784e-06, "epoch": 0.09600698232598734, "percentage": 9.6, "elapsed_time": "0:23:18", "remaining_time": "3:39:31"}
|
| 23 |
+
{"current_steps": 230, "total_steps": 2292, "loss": 0.6296, "lr": 9.956521739130436e-06, "epoch": 0.10037093606807768, "percentage": 10.03, "elapsed_time": "0:24:19", "remaining_time": "3:38:03"}
|
| 24 |
+
{"current_steps": 240, "total_steps": 2292, "loss": 0.6364, "lr": 9.999529953691501e-06, "epoch": 0.10473488981016801, "percentage": 10.47, "elapsed_time": "0:25:20", "remaining_time": "3:36:39"}
|
| 25 |
+
{"current_steps": 250, "total_steps": 2292, "loss": 0.6271, "lr": 9.997905215717636e-06, "epoch": 0.10909884355225835, "percentage": 10.91, "elapsed_time": "0:26:21", "remaining_time": "3:35:19"}
|
| 26 |
+
{"current_steps": 260, "total_steps": 2292, "loss": 0.625, "lr": 9.995120360083208e-06, "epoch": 0.11346279729434867, "percentage": 11.34, "elapsed_time": "0:27:22", "remaining_time": "3:33:55"}
|
| 27 |
+
{"current_steps": 270, "total_steps": 2292, "loss": 0.6271, "lr": 9.991176033211077e-06, "epoch": 0.11782675103643901, "percentage": 11.78, "elapsed_time": "0:28:23", "remaining_time": "3:32:34"}
|
| 28 |
+
{"current_steps": 280, "total_steps": 2292, "loss": 0.62, "lr": 9.98607315066148e-06, "epoch": 0.12219070477852935, "percentage": 12.22, "elapsed_time": "0:29:25", "remaining_time": "3:31:26"}
|
| 29 |
+
{"current_steps": 290, "total_steps": 2292, "loss": 0.6234, "lr": 9.979812896919497e-06, "epoch": 0.12655465852061967, "percentage": 12.65, "elapsed_time": "0:30:26", "remaining_time": "3:30:11"}
|
| 30 |
+
{"current_steps": 300, "total_steps": 2292, "loss": 0.6228, "lr": 9.97239672512011e-06, "epoch": 0.13091861226271, "percentage": 13.09, "elapsed_time": "0:31:28", "remaining_time": "3:28:56"}
|
| 31 |
+
{"current_steps": 310, "total_steps": 2292, "loss": 0.6189, "lr": 9.963826356710913e-06, "epoch": 0.13528256600480035, "percentage": 13.53, "elapsed_time": "0:32:28", "remaining_time": "3:27:38"}
|
| 32 |
+
{"current_steps": 320, "total_steps": 2292, "loss": 0.622, "lr": 9.954103781052508e-06, "epoch": 0.13964651974689068, "percentage": 13.96, "elapsed_time": "0:33:29", "remaining_time": "3:26:23"}
|
| 33 |
+
{"current_steps": 330, "total_steps": 2292, "loss": 0.6215, "lr": 9.943231254956749e-06, "epoch": 0.14401047348898102, "percentage": 14.4, "elapsed_time": "0:34:30", "remaining_time": "3:25:12"}
|
| 34 |
+
{"current_steps": 340, "total_steps": 2292, "loss": 0.6095, "lr": 9.93121130216288e-06, "epoch": 0.14837442723107136, "percentage": 14.83, "elapsed_time": "0:35:32", "remaining_time": "3:24:03"}
|
| 35 |
+
{"current_steps": 350, "total_steps": 2292, "loss": 0.6073, "lr": 9.918046712751731e-06, "epoch": 0.1527383809731617, "percentage": 15.27, "elapsed_time": "0:36:33", "remaining_time": "3:22:49"}
|
| 36 |
+
{"current_steps": 360, "total_steps": 2292, "loss": 0.6095, "lr": 9.903740542498071e-06, "epoch": 0.157102334715252, "percentage": 15.71, "elapsed_time": "0:37:35", "remaining_time": "3:21:46"}
|
| 37 |
+
{"current_steps": 370, "total_steps": 2292, "loss": 0.6039, "lr": 9.888296112161308e-06, "epoch": 0.16146628845734234, "percentage": 16.14, "elapsed_time": "0:38:37", "remaining_time": "3:20:40"}
|
| 38 |
+
{"current_steps": 380, "total_steps": 2292, "loss": 0.6049, "lr": 9.87171700671467e-06, "epoch": 0.16583024219943268, "percentage": 16.58, "elapsed_time": "0:39:38", "remaining_time": "3:19:25"}
|
| 39 |
+
{"current_steps": 390, "total_steps": 2292, "loss": 0.6069, "lr": 9.854007074513056e-06, "epoch": 0.17019419594152302, "percentage": 17.02, "elapsed_time": "0:40:39", "remaining_time": "3:18:18"}
|
| 40 |
+
{"current_steps": 400, "total_steps": 2292, "loss": 0.6067, "lr": 9.835170426399757e-06, "epoch": 0.17455814968361336, "percentage": 17.45, "elapsed_time": "0:41:40", "remaining_time": "3:17:09"}
|
| 41 |
+
{"current_steps": 410, "total_steps": 2292, "loss": 0.6021, "lr": 9.815211434752236e-06, "epoch": 0.1789221034257037, "percentage": 17.89, "elapsed_time": "0:43:03", "remaining_time": "3:17:39"}
|
| 42 |
+
{"current_steps": 420, "total_steps": 2292, "loss": 0.6064, "lr": 9.79413473246722e-06, "epoch": 0.18328605716779403, "percentage": 18.32, "elapsed_time": "0:44:04", "remaining_time": "3:16:28"}
|
| 43 |
+
{"current_steps": 430, "total_steps": 2292, "loss": 0.5962, "lr": 9.771945211885294e-06, "epoch": 0.18765001090988437, "percentage": 18.76, "elapsed_time": "0:45:06", "remaining_time": "3:15:17"}
|
| 44 |
+
{"current_steps": 440, "total_steps": 2292, "loss": 0.6005, "lr": 9.748648023655302e-06, "epoch": 0.19201396465197468, "percentage": 19.2, "elapsed_time": "0:46:06", "remaining_time": "3:14:05"}
|
| 45 |
+
{"current_steps": 450, "total_steps": 2292, "loss": 0.5922, "lr": 9.724248575538764e-06, "epoch": 0.19637791839406502, "percentage": 19.63, "elapsed_time": "0:47:07", "remaining_time": "3:12:54"}
|
| 46 |
+
{"current_steps": 460, "total_steps": 2292, "loss": 0.5977, "lr": 9.698752531154623e-06, "epoch": 0.20074187213615535, "percentage": 20.07, "elapsed_time": "0:48:09", "remaining_time": "3:11:48"}
|
| 47 |
+
{"current_steps": 470, "total_steps": 2292, "loss": 0.5989, "lr": 9.672165808664609e-06, "epoch": 0.2051058258782457, "percentage": 20.51, "elapsed_time": "0:49:12", "remaining_time": "3:10:46"}
|
| 48 |
+
{"current_steps": 480, "total_steps": 2292, "loss": 0.5914, "lr": 9.6444945793995e-06, "epoch": 0.20946977962033603, "percentage": 20.94, "elapsed_time": "0:50:16", "remaining_time": "3:09:48"}
|
| 49 |
+
{"current_steps": 490, "total_steps": 2292, "loss": 0.5883, "lr": 9.61574526642664e-06, "epoch": 0.21383373336242636, "percentage": 21.38, "elapsed_time": "0:51:19", "remaining_time": "3:08:43"}
|
| 50 |
+
{"current_steps": 500, "total_steps": 2292, "loss": 0.591, "lr": 9.585924543058997e-06, "epoch": 0.2181976871045167, "percentage": 21.82, "elapsed_time": "0:52:18", "remaining_time": "3:07:29"}
|
| 51 |
+
{"current_steps": 500, "total_steps": 2292, "eval_loss": 0.5827435255050659, "epoch": 0.2181976871045167, "percentage": 21.82, "elapsed_time": "0:53:28", "remaining_time": "3:11:39"}
|
| 52 |
+
{"current_steps": 510, "total_steps": 2292, "loss": 0.5893, "lr": 9.555039331306164e-06, "epoch": 0.22256164084660704, "percentage": 22.25, "elapsed_time": "0:54:29", "remaining_time": "3:10:25"}
|
| 53 |
+
{"current_steps": 520, "total_steps": 2292, "loss": 0.5967, "lr": 9.523096800267602e-06, "epoch": 0.22692559458869735, "percentage": 22.69, "elapsed_time": "0:55:31", "remaining_time": "3:09:11"}
|
| 54 |
+
{"current_steps": 530, "total_steps": 2292, "loss": 0.5876, "lr": 9.490104364468557e-06, "epoch": 0.2312895483307877, "percentage": 23.12, "elapsed_time": "0:56:32", "remaining_time": "3:07:59"}
|
| 55 |
+
{"current_steps": 540, "total_steps": 2292, "loss": 0.5879, "lr": 9.456069682138981e-06, "epoch": 0.23565350207287802, "percentage": 23.56, "elapsed_time": "0:57:33", "remaining_time": "3:06:45"}
|
| 56 |
+
{"current_steps": 550, "total_steps": 2292, "loss": 0.5898, "lr": 9.421000653435908e-06, "epoch": 0.24001745581496836, "percentage": 24.0, "elapsed_time": "0:58:33", "remaining_time": "3:05:28"}
|
| 57 |
+
{"current_steps": 560, "total_steps": 2292, "loss": 0.5938, "lr": 9.38490541860966e-06, "epoch": 0.2443814095570587, "percentage": 24.43, "elapsed_time": "0:59:34", "remaining_time": "3:04:15"}
|
| 58 |
+
{"current_steps": 570, "total_steps": 2292, "loss": 0.5893, "lr": 9.347792356114324e-06, "epoch": 0.24874536329914904, "percentage": 24.87, "elapsed_time": "1:00:36", "remaining_time": "3:03:06"}
|
| 59 |
+
{"current_steps": 580, "total_steps": 2292, "loss": 0.5976, "lr": 9.30967008066294e-06, "epoch": 0.25310931704123935, "percentage": 25.31, "elapsed_time": "1:01:37", "remaining_time": "3:01:54"}
|
| 60 |
+
{"current_steps": 590, "total_steps": 2292, "loss": 0.592, "lr": 9.27054744122785e-06, "epoch": 0.2574732707833297, "percentage": 25.74, "elapsed_time": "1:02:40", "remaining_time": "3:00:48"}
|
| 61 |
+
{"current_steps": 600, "total_steps": 2292, "loss": 0.5888, "lr": 9.230433518986664e-06, "epoch": 0.26183722452542, "percentage": 26.18, "elapsed_time": "1:03:42", "remaining_time": "2:59:39"}
|
| 62 |
+
{"current_steps": 610, "total_steps": 2292, "loss": 0.5842, "lr": 9.189337625214324e-06, "epoch": 0.2662011782675104, "percentage": 26.61, "elapsed_time": "1:05:04", "remaining_time": "2:59:26"}
|
| 63 |
+
{"current_steps": 620, "total_steps": 2292, "loss": 0.582, "lr": 9.147269299121782e-06, "epoch": 0.2705651320096007, "percentage": 27.05, "elapsed_time": "1:06:07", "remaining_time": "2:58:18"}
|
| 64 |
+
{"current_steps": 630, "total_steps": 2292, "loss": 0.579, "lr": 9.104238305641731e-06, "epoch": 0.274929085751691, "percentage": 27.49, "elapsed_time": "1:07:08", "remaining_time": "2:57:08"}
|
| 65 |
+
{"current_steps": 640, "total_steps": 2292, "loss": 0.5889, "lr": 9.060254633161973e-06, "epoch": 0.27929303949378137, "percentage": 27.92, "elapsed_time": "1:08:12", "remaining_time": "2:56:04"}
|
| 66 |
+
{"current_steps": 650, "total_steps": 2292, "loss": 0.5793, "lr": 9.015328491206901e-06, "epoch": 0.2836569932358717, "percentage": 28.36, "elapsed_time": "1:09:14", "remaining_time": "2:54:56"}
|
| 67 |
+
{"current_steps": 660, "total_steps": 2292, "loss": 0.5807, "lr": 8.969470308067662e-06, "epoch": 0.28802094697796204, "percentage": 28.8, "elapsed_time": "1:10:15", "remaining_time": "2:53:43"}
|
| 68 |
+
{"current_steps": 670, "total_steps": 2292, "loss": 0.5748, "lr": 8.922690728381527e-06, "epoch": 0.29238490072005235, "percentage": 29.23, "elapsed_time": "1:11:18", "remaining_time": "2:52:37"}
|
| 69 |
+
{"current_steps": 680, "total_steps": 2292, "loss": 0.5688, "lr": 8.875000610661052e-06, "epoch": 0.2967488544621427, "percentage": 29.67, "elapsed_time": "1:12:20", "remaining_time": "2:51:30"}
|
| 70 |
+
{"current_steps": 690, "total_steps": 2292, "loss": 0.5727, "lr": 8.826411024773595e-06, "epoch": 0.30111280820423303, "percentage": 30.1, "elapsed_time": "1:13:23", "remaining_time": "2:50:23"}
|
| 71 |
+
{"current_steps": 700, "total_steps": 2292, "loss": 0.5621, "lr": 8.776933249371769e-06, "epoch": 0.3054767619463234, "percentage": 30.54, "elapsed_time": "1:14:24", "remaining_time": "2:49:14"}
|
| 72 |
+
{"current_steps": 710, "total_steps": 2292, "loss": 0.57, "lr": 8.726578769275426e-06, "epoch": 0.3098407156884137, "percentage": 30.98, "elapsed_time": "1:15:26", "remaining_time": "2:48:05"}
|
| 73 |
+
{"current_steps": 720, "total_steps": 2292, "loss": 0.5733, "lr": 8.675359272805796e-06, "epoch": 0.314204669430504, "percentage": 31.41, "elapsed_time": "1:16:27", "remaining_time": "2:46:56"}
|
| 74 |
+
{"current_steps": 730, "total_steps": 2292, "loss": 0.5617, "lr": 8.62328664907239e-06, "epoch": 0.3185686231725944, "percentage": 31.85, "elapsed_time": "1:17:29", "remaining_time": "2:45:49"}
|
| 75 |
+
{"current_steps": 740, "total_steps": 2292, "loss": 0.5748, "lr": 8.570372985213283e-06, "epoch": 0.3229325769146847, "percentage": 32.29, "elapsed_time": "1:18:29", "remaining_time": "2:44:36"}
|
| 76 |
+
{"current_steps": 750, "total_steps": 2292, "loss": 0.5765, "lr": 8.516630563589436e-06, "epoch": 0.32729653065677505, "percentage": 32.72, "elapsed_time": "1:19:29", "remaining_time": "2:43:26"}
|
| 77 |
+
{"current_steps": 760, "total_steps": 2292, "loss": 0.5717, "lr": 8.462071858933717e-06, "epoch": 0.33166048439886536, "percentage": 33.16, "elapsed_time": "1:20:29", "remaining_time": "2:42:15"}
|
| 78 |
+
{"current_steps": 770, "total_steps": 2292, "loss": 0.5728, "lr": 8.406709535455242e-06, "epoch": 0.33602443814095573, "percentage": 33.6, "elapsed_time": "1:21:32", "remaining_time": "2:41:11"}
|
| 79 |
+
{"current_steps": 780, "total_steps": 2292, "loss": 0.5621, "lr": 8.35055644389976e-06, "epoch": 0.34038839188304604, "percentage": 34.03, "elapsed_time": "1:22:33", "remaining_time": "2:40:03"}
|
| 80 |
+
{"current_steps": 790, "total_steps": 2292, "loss": 0.5676, "lr": 8.293625618566723e-06, "epoch": 0.34475234562513635, "percentage": 34.47, "elapsed_time": "1:23:35", "remaining_time": "2:38:54"}
|
| 81 |
+
{"current_steps": 800, "total_steps": 2292, "loss": 0.5657, "lr": 8.23593027428375e-06, "epoch": 0.3491162993672267, "percentage": 34.9, "elapsed_time": "1:24:35", "remaining_time": "2:37:45"}
|
| 82 |
+
{"current_steps": 810, "total_steps": 2292, "loss": 0.5739, "lr": 8.177483803339203e-06, "epoch": 0.353480253109317, "percentage": 35.34, "elapsed_time": "1:25:57", "remaining_time": "2:37:16"}
|
| 83 |
+
{"current_steps": 820, "total_steps": 2292, "loss": 0.5708, "lr": 8.118299772373546e-06, "epoch": 0.3578442068514074, "percentage": 35.78, "elapsed_time": "1:27:00", "remaining_time": "2:36:10"}
|
| 84 |
+
{"current_steps": 830, "total_steps": 2292, "loss": 0.5652, "lr": 8.05839191923025e-06, "epoch": 0.3622081605934977, "percentage": 36.21, "elapsed_time": "1:28:01", "remaining_time": "2:35:02"}
|
| 85 |
+
{"current_steps": 840, "total_steps": 2292, "loss": 0.5665, "lr": 7.997774149766962e-06, "epoch": 0.36657211433558806, "percentage": 36.65, "elapsed_time": "1:29:03", "remaining_time": "2:33:57"}
|
| 86 |
+
{"current_steps": 850, "total_steps": 2292, "loss": 0.5592, "lr": 7.936460534627648e-06, "epoch": 0.37093606807767837, "percentage": 37.09, "elapsed_time": "1:30:04", "remaining_time": "2:32:48"}
|
| 87 |
+
{"current_steps": 860, "total_steps": 2292, "loss": 0.558, "lr": 7.874465305976527e-06, "epoch": 0.37530002181976874, "percentage": 37.52, "elapsed_time": "1:31:04", "remaining_time": "2:31:39"}
|
| 88 |
+
{"current_steps": 870, "total_steps": 2292, "loss": 0.5653, "lr": 7.81180285419447e-06, "epoch": 0.37966397556185905, "percentage": 37.96, "elapsed_time": "1:32:06", "remaining_time": "2:30:32"}
|
| 89 |
+
{"current_steps": 880, "total_steps": 2292, "loss": 0.5587, "lr": 7.748487724538707e-06, "epoch": 0.38402792930394936, "percentage": 38.39, "elapsed_time": "1:33:08", "remaining_time": "2:29:26"}
|
| 90 |
+
{"current_steps": 890, "total_steps": 2292, "loss": 0.574, "lr": 7.684534613766566e-06, "epoch": 0.3883918830460397, "percentage": 38.83, "elapsed_time": "1:34:11", "remaining_time": "2:28:22"}
|
| 91 |
+
{"current_steps": 900, "total_steps": 2292, "loss": 0.5657, "lr": 7.619958366724043e-06, "epoch": 0.39275583678813003, "percentage": 39.27, "elapsed_time": "1:35:13", "remaining_time": "2:27:16"}
|
| 92 |
+
{"current_steps": 910, "total_steps": 2292, "loss": 0.5642, "lr": 7.554773972900024e-06, "epoch": 0.3971197905302204, "percentage": 39.7, "elapsed_time": "1:36:13", "remaining_time": "2:26:07"}
|
| 93 |
+
{"current_steps": 920, "total_steps": 2292, "loss": 0.5585, "lr": 7.488996562946886e-06, "epoch": 0.4014837442723107, "percentage": 40.14, "elapsed_time": "1:37:13", "remaining_time": "2:24:59"}
|
| 94 |
+
{"current_steps": 930, "total_steps": 2292, "loss": 0.5611, "lr": 7.422641405168386e-06, "epoch": 0.40584769801440107, "percentage": 40.58, "elapsed_time": "1:38:14", "remaining_time": "2:23:52"}
|
| 95 |
+
{"current_steps": 940, "total_steps": 2292, "loss": 0.5556, "lr": 7.355723901975546e-06, "epoch": 0.4102116517564914, "percentage": 41.01, "elapsed_time": "1:39:16", "remaining_time": "2:22:46"}
|
| 96 |
+
{"current_steps": 950, "total_steps": 2292, "loss": 0.5638, "lr": 7.288259586311455e-06, "epoch": 0.4145756054985817, "percentage": 41.45, "elapsed_time": "1:40:18", "remaining_time": "2:21:41"}
|
| 97 |
+
{"current_steps": 960, "total_steps": 2292, "loss": 0.554, "lr": 7.22026411804573e-06, "epoch": 0.41893955924067205, "percentage": 41.88, "elapsed_time": "1:41:19", "remaining_time": "2:20:35"}
|
| 98 |
+
{"current_steps": 970, "total_steps": 2292, "loss": 0.5574, "lr": 7.151753280339554e-06, "epoch": 0.42330351298276236, "percentage": 42.32, "elapsed_time": "1:42:24", "remaining_time": "2:19:33"}
|
| 99 |
+
{"current_steps": 980, "total_steps": 2292, "loss": 0.5613, "lr": 7.082742975982057e-06, "epoch": 0.42766746672485273, "percentage": 42.76, "elapsed_time": "1:43:24", "remaining_time": "2:18:26"}
|
| 100 |
+
{"current_steps": 990, "total_steps": 2292, "loss": 0.5549, "lr": 7.0132492236989694e-06, "epoch": 0.43203142046694304, "percentage": 43.19, "elapsed_time": "1:44:26", "remaining_time": "2:17:20"}
|
| 101 |
+
{"current_steps": 1000, "total_steps": 2292, "loss": 0.5605, "lr": 6.94328815443432e-06, "epoch": 0.4363953742090334, "percentage": 43.63, "elapsed_time": "1:45:31", "remaining_time": "2:16:20"}
|
| 102 |
+
{"current_steps": 1000, "total_steps": 2292, "eval_loss": 0.545971155166626, "epoch": 0.4363953742090334, "percentage": 43.63, "elapsed_time": "1:46:39", "remaining_time": "2:17:48"}
|
| 103 |
+
{"current_steps": 1010, "total_steps": 2292, "loss": 0.5505, "lr": 6.872876007606127e-06, "epoch": 0.4407593279511237, "percentage": 44.07, "elapsed_time": "1:48:02", "remaining_time": "2:17:08"}
|
| 104 |
+
{"current_steps": 1020, "total_steps": 2292, "loss": 0.5511, "lr": 6.802029127336884e-06, "epoch": 0.4451232816932141, "percentage": 44.5, "elapsed_time": "1:49:04", "remaining_time": "2:16:01"}
|
| 105 |
+
{"current_steps": 1030, "total_steps": 2292, "loss": 0.5479, "lr": 6.73076395865975e-06, "epoch": 0.4494872354353044, "percentage": 44.94, "elapsed_time": "1:50:06", "remaining_time": "2:14:54"}
|
| 106 |
+
{"current_steps": 1040, "total_steps": 2292, "loss": 0.5549, "lr": 6.6590970437013135e-06, "epoch": 0.4538511891773947, "percentage": 45.38, "elapsed_time": "1:51:07", "remaining_time": "2:13:46"}
|
| 107 |
+
{"current_steps": 1050, "total_steps": 2292, "loss": 0.5566, "lr": 6.587045017841828e-06, "epoch": 0.45821514291948506, "percentage": 45.81, "elapsed_time": "1:52:09", "remaining_time": "2:12:40"}
|
| 108 |
+
{"current_steps": 1060, "total_steps": 2292, "loss": 0.5519, "lr": 6.514624605853785e-06, "epoch": 0.4625790966615754, "percentage": 46.25, "elapsed_time": "1:53:10", "remaining_time": "2:11:32"}
|
| 109 |
+
{"current_steps": 1070, "total_steps": 2292, "loss": 0.5453, "lr": 6.441852618019757e-06, "epoch": 0.46694305040366574, "percentage": 46.68, "elapsed_time": "1:54:10", "remaining_time": "2:10:23"}
|
| 110 |
+
{"current_steps": 1080, "total_steps": 2292, "loss": 0.5509, "lr": 6.368745946230371e-06, "epoch": 0.47130700414575605, "percentage": 47.12, "elapsed_time": "1:55:11", "remaining_time": "2:09:15"}
|
| 111 |
+
{"current_steps": 1090, "total_steps": 2292, "loss": 0.5558, "lr": 6.295321560063358e-06, "epoch": 0.4756709578878464, "percentage": 47.56, "elapsed_time": "1:56:13", "remaining_time": "2:08:09"}
|
| 112 |
+
{"current_steps": 1100, "total_steps": 2292, "loss": 0.5496, "lr": 6.221596502844558e-06, "epoch": 0.4800349116299367, "percentage": 47.99, "elapsed_time": "1:57:14", "remaining_time": "2:07:03"}
|
| 113 |
+
{"current_steps": 1110, "total_steps": 2292, "loss": 0.5447, "lr": 6.147587887691812e-06, "epoch": 0.48439886537202703, "percentage": 48.43, "elapsed_time": "1:58:15", "remaining_time": "2:05:55"}
|
| 114 |
+
{"current_steps": 1120, "total_steps": 2292, "loss": 0.5507, "lr": 6.073312893542644e-06, "epoch": 0.4887628191141174, "percentage": 48.87, "elapsed_time": "1:59:15", "remaining_time": "2:04:48"}
|
| 115 |
+
{"current_steps": 1130, "total_steps": 2292, "loss": 0.5497, "lr": 5.998788761166689e-06, "epoch": 0.4931267728562077, "percentage": 49.3, "elapsed_time": "2:00:16", "remaining_time": "2:03:40"}
|
| 116 |
+
{"current_steps": 1140, "total_steps": 2292, "loss": 0.5521, "lr": 5.9240327891637296e-06, "epoch": 0.49749072659829807, "percentage": 49.74, "elapsed_time": "2:01:17", "remaining_time": "2:02:34"}
|
| 117 |
+
{"current_steps": 1150, "total_steps": 2292, "loss": 0.5451, "lr": 5.849062329948353e-06, "epoch": 0.5018546803403884, "percentage": 50.17, "elapsed_time": "2:02:17", "remaining_time": "2:01:26"}
|
| 118 |
+
{"current_steps": 1160, "total_steps": 2292, "loss": 0.547, "lr": 5.773894785722082e-06, "epoch": 0.5062186340824787, "percentage": 50.61, "elapsed_time": "2:03:17", "remaining_time": "2:00:19"}
|
| 119 |
+
{"current_steps": 1170, "total_steps": 2292, "loss": 0.551, "lr": 5.698547604433963e-06, "epoch": 0.5105825878245691, "percentage": 51.05, "elapsed_time": "2:04:18", "remaining_time": "1:59:12"}
|
| 120 |
+
{"current_steps": 1180, "total_steps": 2292, "loss": 0.5482, "lr": 5.623038275730543e-06, "epoch": 0.5149465415666594, "percentage": 51.48, "elapsed_time": "2:05:20", "remaining_time": "1:58:07"}
|
| 121 |
+
{"current_steps": 1190, "total_steps": 2292, "loss": 0.5378, "lr": 5.547384326896152e-06, "epoch": 0.5193104953087497, "percentage": 51.92, "elapsed_time": "2:06:22", "remaining_time": "1:57:01"}
|
| 122 |
+
{"current_steps": 1200, "total_steps": 2292, "loss": 0.5289, "lr": 5.4716033187844565e-06, "epoch": 0.52367444905084, "percentage": 52.36, "elapsed_time": "2:07:23", "remaining_time": "1:55:55"}
|
| 123 |
+
{"current_steps": 1210, "total_steps": 2292, "loss": 0.5375, "lr": 5.3957128417422196e-06, "epoch": 0.5280384027929304, "percentage": 52.79, "elapsed_time": "2:08:45", "remaining_time": "1:55:08"}
|
| 124 |
+
{"current_steps": 1220, "total_steps": 2292, "loss": 0.5484, "lr": 5.319730511526225e-06, "epoch": 0.5324023565350208, "percentage": 53.23, "elapsed_time": "2:09:47", "remaining_time": "1:54:02"}
|
| 125 |
+
{"current_steps": 1230, "total_steps": 2292, "loss": 0.5352, "lr": 5.243673965214276e-06, "epoch": 0.5367663102771111, "percentage": 53.66, "elapsed_time": "2:10:47", "remaining_time": "1:52:55"}
|
| 126 |
+
{"current_steps": 1240, "total_steps": 2292, "loss": 0.5407, "lr": 5.167560857111286e-06, "epoch": 0.5411302640192014, "percentage": 54.1, "elapsed_time": "2:11:49", "remaining_time": "1:51:50"}
|
| 127 |
+
{"current_steps": 1250, "total_steps": 2292, "loss": 0.5354, "lr": 5.091408854651327e-06, "epoch": 0.5454942177612917, "percentage": 54.54, "elapsed_time": "2:12:50", "remaining_time": "1:50:44"}
|
| 128 |
+
{"current_steps": 1260, "total_steps": 2292, "loss": 0.5425, "lr": 5.0152356342966624e-06, "epoch": 0.549858171503382, "percentage": 54.97, "elapsed_time": "2:13:52", "remaining_time": "1:49:38"}
|
| 129 |
+
{"current_steps": 1270, "total_steps": 2292, "loss": 0.5386, "lr": 4.939058877434672e-06, "epoch": 0.5542221252454724, "percentage": 55.41, "elapsed_time": "2:14:53", "remaining_time": "1:48:33"}
|
| 130 |
+
{"current_steps": 1280, "total_steps": 2292, "loss": 0.5512, "lr": 4.862896266273627e-06, "epoch": 0.5585860789875627, "percentage": 55.85, "elapsed_time": "2:15:54", "remaining_time": "1:47:26"}
|
| 131 |
+
{"current_steps": 1290, "total_steps": 2292, "loss": 0.5422, "lr": 4.786765479738293e-06, "epoch": 0.562950032729653, "percentage": 56.28, "elapsed_time": "2:16:54", "remaining_time": "1:46:20"}
|
| 132 |
+
{"current_steps": 1300, "total_steps": 2292, "loss": 0.5377, "lr": 4.7106841893662755e-06, "epoch": 0.5673139864717434, "percentage": 56.72, "elapsed_time": "2:17:54", "remaining_time": "1:45:14"}
|
| 133 |
+
{"current_steps": 1310, "total_steps": 2292, "loss": 0.5429, "lr": 4.634670055206092e-06, "epoch": 0.5716779402138338, "percentage": 57.16, "elapsed_time": "2:18:55", "remaining_time": "1:44:08"}
|
| 134 |
+
{"current_steps": 1320, "total_steps": 2292, "loss": 0.5441, "lr": 4.5587407217179094e-06, "epoch": 0.5760418939559241, "percentage": 57.59, "elapsed_time": "2:19:55", "remaining_time": "1:43:01"}
|
| 135 |
+
{"current_steps": 1330, "total_steps": 2292, "loss": 0.5372, "lr": 4.482913813677896e-06, "epoch": 0.5804058476980144, "percentage": 58.03, "elapsed_time": "2:20:55", "remaining_time": "1:41:56"}
|
| 136 |
+
{"current_steps": 1340, "total_steps": 2292, "loss": 0.5431, "lr": 4.407206932087143e-06, "epoch": 0.5847698014401047, "percentage": 58.46, "elapsed_time": "2:21:55", "remaining_time": "1:40:49"}
|
| 137 |
+
{"current_steps": 1350, "total_steps": 2292, "loss": 0.5354, "lr": 4.331637650086111e-06, "epoch": 0.589133755182195, "percentage": 58.9, "elapsed_time": "2:22:58", "remaining_time": "1:39:45"}
|
| 138 |
+
{"current_steps": 1360, "total_steps": 2292, "loss": 0.536, "lr": 4.256223508875536e-06, "epoch": 0.5934977089242854, "percentage": 59.34, "elapsed_time": "2:24:00", "remaining_time": "1:38:41"}
|
| 139 |
+
{"current_steps": 1370, "total_steps": 2292, "loss": 0.5345, "lr": 4.180982013644749e-06, "epoch": 0.5978616626663757, "percentage": 59.77, "elapsed_time": "2:25:02", "remaining_time": "1:37:36"}
|
| 140 |
+
{"current_steps": 1380, "total_steps": 2292, "loss": 0.5349, "lr": 4.105930629508369e-06, "epoch": 0.6022256164084661, "percentage": 60.21, "elapsed_time": "2:26:03", "remaining_time": "1:36:31"}
|
| 141 |
+
{"current_steps": 1390, "total_steps": 2292, "loss": 0.5338, "lr": 4.0310867774522724e-06, "epoch": 0.6065895701505564, "percentage": 60.65, "elapsed_time": "2:27:05", "remaining_time": "1:35:26"}
|
| 142 |
+
{"current_steps": 1400, "total_steps": 2292, "loss": 0.5332, "lr": 3.95646783028983e-06, "epoch": 0.6109535238926468, "percentage": 61.08, "elapsed_time": "2:28:06", "remaining_time": "1:34:22"}
|
| 143 |
+
{"current_steps": 1410, "total_steps": 2292, "loss": 0.5305, "lr": 3.882091108629311e-06, "epoch": 0.6153174776347371, "percentage": 61.52, "elapsed_time": "2:29:28", "remaining_time": "1:33:30"}
|
| 144 |
+
{"current_steps": 1420, "total_steps": 2292, "loss": 0.5333, "lr": 3.807973876853414e-06, "epoch": 0.6196814313768274, "percentage": 61.95, "elapsed_time": "2:30:30", "remaining_time": "1:32:25"}
|
| 145 |
+
{"current_steps": 1430, "total_steps": 2292, "loss": 0.5305, "lr": 3.734133339111844e-06, "epoch": 0.6240453851189177, "percentage": 62.39, "elapsed_time": "2:31:33", "remaining_time": "1:31:21"}
|
| 146 |
+
{"current_steps": 1440, "total_steps": 2292, "loss": 0.5386, "lr": 3.660586635327869e-06, "epoch": 0.628409338861008, "percentage": 62.83, "elapsed_time": "2:32:35", "remaining_time": "1:30:16"}
|
| 147 |
+
{"current_steps": 1450, "total_steps": 2292, "loss": 0.5396, "lr": 3.587350837219788e-06, "epoch": 0.6327732926030984, "percentage": 63.26, "elapsed_time": "2:33:36", "remaining_time": "1:29:12"}
|
| 148 |
+
{"current_steps": 1460, "total_steps": 2292, "loss": 0.5366, "lr": 3.5144429443382356e-06, "epoch": 0.6371372463451888, "percentage": 63.7, "elapsed_time": "2:34:37", "remaining_time": "1:28:07"}
|
| 149 |
+
{"current_steps": 1470, "total_steps": 2292, "loss": 0.5255, "lr": 3.4418798801202256e-06, "epoch": 0.6415012000872791, "percentage": 64.14, "elapsed_time": "2:35:38", "remaining_time": "1:27:02"}
|
| 150 |
+
{"current_steps": 1480, "total_steps": 2292, "loss": 0.5307, "lr": 3.3696784879608747e-06, "epoch": 0.6458651538293694, "percentage": 64.57, "elapsed_time": "2:36:39", "remaining_time": "1:25:57"}
|
| 151 |
+
{"current_steps": 1490, "total_steps": 2292, "loss": 0.5269, "lr": 3.2978555273037006e-06, "epoch": 0.6502291075714598, "percentage": 65.01, "elapsed_time": "2:37:42", "remaining_time": "1:24:53"}
|
| 152 |
+
{"current_steps": 1500, "total_steps": 2292, "loss": 0.5252, "lr": 3.2264276697504026e-06, "epoch": 0.6545930613135501, "percentage": 65.45, "elapsed_time": "2:38:44", "remaining_time": "1:23:48"}
|
| 153 |
+
{"current_steps": 1500, "total_steps": 2292, "eval_loss": 0.5199297666549683, "epoch": 0.6545930613135501, "percentage": 65.45, "elapsed_time": "2:39:54", "remaining_time": "1:24:25"}
|
| 154 |
+
{"current_steps": 1510, "total_steps": 2292, "loss": 0.5312, "lr": 3.1554114951910387e-06, "epoch": 0.6589570150556404, "percentage": 65.88, "elapsed_time": "2:40:55", "remaining_time": "1:23:20"}
|
| 155 |
+
{"current_steps": 1520, "total_steps": 2292, "loss": 0.5283, "lr": 3.0848234879554916e-06, "epoch": 0.6633209687977307, "percentage": 66.32, "elapsed_time": "2:41:56", "remaining_time": "1:22:14"}
|
| 156 |
+
{"current_steps": 1530, "total_steps": 2292, "loss": 0.5359, "lr": 3.0146800329871107e-06, "epoch": 0.667684922539821, "percentage": 66.75, "elapsed_time": "2:42:57", "remaining_time": "1:21:09"}
|
| 157 |
+
{"current_steps": 1540, "total_steps": 2292, "loss": 0.5286, "lr": 2.944997412039422e-06, "epoch": 0.6720488762819115, "percentage": 67.19, "elapsed_time": "2:43:59", "remaining_time": "1:20:04"}
|
| 158 |
+
{"current_steps": 1550, "total_steps": 2292, "loss": 0.5345, "lr": 2.8757917998968042e-06, "epoch": 0.6764128300240018, "percentage": 67.63, "elapsed_time": "2:45:00", "remaining_time": "1:18:59"}
|
| 159 |
+
{"current_steps": 1560, "total_steps": 2292, "loss": 0.5226, "lr": 2.807079260619976e-06, "epoch": 0.6807767837660921, "percentage": 68.06, "elapsed_time": "2:46:02", "remaining_time": "1:17:54"}
|
| 160 |
+
{"current_steps": 1570, "total_steps": 2292, "loss": 0.5294, "lr": 2.7388757438171953e-06, "epoch": 0.6851407375081824, "percentage": 68.5, "elapsed_time": "2:47:04", "remaining_time": "1:16:50"}
|
| 161 |
+
{"current_steps": 1580, "total_steps": 2292, "loss": 0.5243, "lr": 2.6711970809420327e-06, "epoch": 0.6895046912502727, "percentage": 68.94, "elapsed_time": "2:48:06", "remaining_time": "1:15:45"}
|
| 162 |
+
{"current_steps": 1590, "total_steps": 2292, "loss": 0.5227, "lr": 2.6040589816185534e-06, "epoch": 0.6938686449923631, "percentage": 69.37, "elapsed_time": "2:49:07", "remaining_time": "1:14:40"}
|
| 163 |
+
{"current_steps": 1600, "total_steps": 2292, "loss": 0.5336, "lr": 2.5374770299947837e-06, "epoch": 0.6982325987344534, "percentage": 69.81, "elapsed_time": "2:50:09", "remaining_time": "1:13:35"}
|
| 164 |
+
{"current_steps": 1610, "total_steps": 2292, "loss": 0.5242, "lr": 2.471466681125316e-06, "epoch": 0.7025965524765437, "percentage": 70.24, "elapsed_time": "2:51:31", "remaining_time": "1:12:39"}
|
| 165 |
+
{"current_steps": 1620, "total_steps": 2292, "loss": 0.5229, "lr": 2.4060432573838686e-06, "epoch": 0.706960506218634, "percentage": 70.68, "elapsed_time": "2:52:33", "remaining_time": "1:11:34"}
|
| 166 |
+
{"current_steps": 1630, "total_steps": 2292, "loss": 0.5238, "lr": 2.3412219449066316e-06, "epoch": 0.7113244599607245, "percentage": 71.12, "elapsed_time": "2:53:35", "remaining_time": "1:10:30"}
|
| 167 |
+
{"current_steps": 1640, "total_steps": 2292, "loss": 0.527, "lr": 2.2770177900672658e-06, "epoch": 0.7156884137028148, "percentage": 71.55, "elapsed_time": "2:54:38", "remaining_time": "1:09:25"}
|
| 168 |
+
{"current_steps": 1650, "total_steps": 2292, "loss": 0.5208, "lr": 2.213445695984318e-06, "epoch": 0.7200523674449051, "percentage": 71.99, "elapsed_time": "2:55:39", "remaining_time": "1:08:20"}
|
| 169 |
+
{"current_steps": 1660, "total_steps": 2292, "loss": 0.5268, "lr": 2.150520419061896e-06, "epoch": 0.7244163211869954, "percentage": 72.43, "elapsed_time": "2:56:39", "remaining_time": "1:07:15"}
|
| 170 |
+
{"current_steps": 1670, "total_steps": 2292, "loss": 0.5233, "lr": 2.0882565655644054e-06, "epoch": 0.7287802749290857, "percentage": 72.86, "elapsed_time": "2:57:41", "remaining_time": "1:06:10"}
|
| 171 |
+
{"current_steps": 1680, "total_steps": 2292, "loss": 0.5254, "lr": 2.026668588226133e-06, "epoch": 0.7331442286711761, "percentage": 73.3, "elapsed_time": "2:58:42", "remaining_time": "1:05:05"}
|
| 172 |
+
{"current_steps": 1690, "total_steps": 2292, "loss": 0.5224, "lr": 1.965770782896455e-06, "epoch": 0.7375081824132664, "percentage": 73.73, "elapsed_time": "2:59:42", "remaining_time": "1:04:00"}
|
| 173 |
+
{"current_steps": 1700, "total_steps": 2292, "loss": 0.515, "lr": 1.9055772852214916e-06, "epoch": 0.7418721361553567, "percentage": 74.17, "elapsed_time": "3:00:44", "remaining_time": "1:02:56"}
|
| 174 |
+
{"current_steps": 1710, "total_steps": 2292, "loss": 0.5144, "lr": 1.8461020673629172e-06, "epoch": 0.746236089897447, "percentage": 74.61, "elapsed_time": "3:01:46", "remaining_time": "1:01:51"}
|
| 175 |
+
{"current_steps": 1720, "total_steps": 2292, "loss": 0.5173, "lr": 1.7873589347547321e-06, "epoch": 0.7506000436395375, "percentage": 75.04, "elapsed_time": "3:02:48", "remaining_time": "1:00:47"}
|
| 176 |
+
{"current_steps": 1730, "total_steps": 2292, "loss": 0.5228, "lr": 1.729361522898737e-06, "epoch": 0.7549639973816278, "percentage": 75.48, "elapsed_time": "3:03:50", "remaining_time": "0:59:43"}
|
| 177 |
+
{"current_steps": 1740, "total_steps": 2292, "loss": 0.5282, "lr": 1.6721232941994526e-06, "epoch": 0.7593279511237181, "percentage": 75.92, "elapsed_time": "3:04:56", "remaining_time": "0:58:40"}
|
| 178 |
+
{"current_steps": 1750, "total_steps": 2292, "loss": 0.5208, "lr": 1.6156575348392122e-06, "epoch": 0.7636919048658084, "percentage": 76.35, "elapsed_time": "3:05:57", "remaining_time": "0:57:35"}
|
| 179 |
+
{"current_steps": 1760, "total_steps": 2292, "loss": 0.5208, "lr": 1.559977351694158e-06, "epoch": 0.7680558586078987, "percentage": 76.79, "elapsed_time": "3:06:59", "remaining_time": "0:56:31"}
|
| 180 |
+
{"current_steps": 1770, "total_steps": 2292, "loss": 0.5186, "lr": 1.5050956692918739e-06, "epoch": 0.7724198123499891, "percentage": 77.23, "elapsed_time": "3:08:01", "remaining_time": "0:55:26"}
|
| 181 |
+
{"current_steps": 1780, "total_steps": 2292, "loss": 0.5192, "lr": 1.4510252268113263e-06, "epoch": 0.7767837660920794, "percentage": 77.66, "elapsed_time": "3:09:01", "remaining_time": "0:54:22"}
|
| 182 |
+
{"current_steps": 1790, "total_steps": 2292, "loss": 0.5211, "lr": 1.3977785751258345e-06, "epoch": 0.7811477198341698, "percentage": 78.1, "elapsed_time": "3:10:02", "remaining_time": "0:53:17"}
|
| 183 |
+
{"current_steps": 1800, "total_steps": 2292, "loss": 0.5159, "lr": 1.34536807388976e-06, "epoch": 0.7855116735762601, "percentage": 78.53, "elapsed_time": "3:11:03", "remaining_time": "0:52:13"}
|
| 184 |
+
{"current_steps": 1810, "total_steps": 2292, "loss": 0.5169, "lr": 1.2938058886695643e-06, "epoch": 0.7898756273183504, "percentage": 78.97, "elapsed_time": "3:12:26", "remaining_time": "0:51:14"}
|
| 185 |
+
{"current_steps": 1820, "total_steps": 2292, "loss": 0.5246, "lr": 1.2431039881199374e-06, "epoch": 0.7942395810604408, "percentage": 79.41, "elapsed_time": "3:13:27", "remaining_time": "0:50:10"}
|
| 186 |
+
{"current_steps": 1830, "total_steps": 2292, "loss": 0.5238, "lr": 1.1932741412056187e-06, "epoch": 0.7986035348025311, "percentage": 79.84, "elapsed_time": "3:14:28", "remaining_time": "0:49:05"}
|
| 187 |
+
{"current_steps": 1840, "total_steps": 2292, "loss": 0.5202, "lr": 1.1443279144695746e-06, "epoch": 0.8029674885446214, "percentage": 80.28, "elapsed_time": "3:15:29", "remaining_time": "0:48:01"}
|
| 188 |
+
{"current_steps": 1850, "total_steps": 2292, "loss": 0.5178, "lr": 1.0962766693481686e-06, "epoch": 0.8073314422867117, "percentage": 80.72, "elapsed_time": "3:16:30", "remaining_time": "0:46:57"}
|
| 189 |
+
{"current_steps": 1860, "total_steps": 2292, "loss": 0.5142, "lr": 1.049131559533933e-06, "epoch": 0.8116953960288021, "percentage": 81.15, "elapsed_time": "3:17:33", "remaining_time": "0:45:53"}
|
| 190 |
+
{"current_steps": 1870, "total_steps": 2292, "loss": 0.5188, "lr": 1.002903528386564e-06, "epoch": 0.8160593497708925, "percentage": 81.59, "elapsed_time": "3:18:34", "remaining_time": "0:44:48"}
|
| 191 |
+
{"current_steps": 1880, "total_steps": 2292, "loss": 0.5207, "lr": 9.576033063927398e-07, "epoch": 0.8204233035129828, "percentage": 82.02, "elapsed_time": "3:19:36", "remaining_time": "0:43:44"}
|
| 192 |
+
{"current_steps": 1890, "total_steps": 2292, "loss": 0.5134, "lr": 9.132414086753578e-07, "epoch": 0.8247872572550731, "percentage": 82.46, "elapsed_time": "3:20:37", "remaining_time": "0:42:40"}
|
| 193 |
+
{"current_steps": 1900, "total_steps": 2292, "loss": 0.5144, "lr": 8.698281325527502e-07, "epoch": 0.8291512109971634, "percentage": 82.9, "elapsed_time": "3:21:38", "remaining_time": "0:41:36"}
|
| 194 |
+
{"current_steps": 1910, "total_steps": 2292, "loss": 0.5158, "lr": 8.273735551484613e-07, "epoch": 0.8335151647392538, "percentage": 83.33, "elapsed_time": "3:22:40", "remaining_time": "0:40:32"}
|
| 195 |
+
{"current_steps": 1920, "total_steps": 2292, "loss": 0.5116, "lr": 7.858875310521447e-07, "epoch": 0.8378791184813441, "percentage": 83.77, "elapsed_time": "3:23:41", "remaining_time": "0:39:27"}
|
| 196 |
+
{"current_steps": 1930, "total_steps": 2292, "loss": 0.5213, "lr": 7.45379690032102e-07, "epoch": 0.8422430722234344, "percentage": 84.21, "elapsed_time": "3:24:41", "remaining_time": "0:38:23"}
|
| 197 |
+
{"current_steps": 1940, "total_steps": 2292, "loss": 0.5126, "lr": 7.058594348000142e-07, "epoch": 0.8466070259655247, "percentage": 84.64, "elapsed_time": "3:25:41", "remaining_time": "0:37:19"}
|
| 198 |
+
{"current_steps": 1950, "total_steps": 2292, "loss": 0.5118, "lr": 6.673359388283796e-07, "epoch": 0.8509709797076151, "percentage": 85.08, "elapsed_time": "3:26:43", "remaining_time": "0:36:15"}
|
| 199 |
+
{"current_steps": 1960, "total_steps": 2292, "loss": 0.5256, "lr": 6.29818144221161e-07, "epoch": 0.8553349334497055, "percentage": 85.51, "elapsed_time": "3:27:46", "remaining_time": "0:35:11"}
|
| 200 |
+
{"current_steps": 1970, "total_steps": 2292, "loss": 0.5178, "lr": 5.933147596381295e-07, "epoch": 0.8596988871917958, "percentage": 85.95, "elapsed_time": "3:28:47", "remaining_time": "0:34:07"}
|
| 201 |
+
{"current_steps": 1980, "total_steps": 2292, "loss": 0.5106, "lr": 5.578342582734153e-07, "epoch": 0.8640628409338861, "percentage": 86.39, "elapsed_time": "3:29:50", "remaining_time": "0:33:03"}
|
| 202 |
+
{"current_steps": 1990, "total_steps": 2292, "loss": 0.515, "lr": 5.233848758886945e-07, "epoch": 0.8684267946759764, "percentage": 86.82, "elapsed_time": "3:30:50", "remaining_time": "0:31:59"}
|
| 203 |
+
{"current_steps": 2000, "total_steps": 2292, "loss": 0.5075, "lr": 4.899746089015006e-07, "epoch": 0.8727907484180668, "percentage": 87.26, "elapsed_time": "3:31:51", "remaining_time": "0:30:55"}
|
| 204 |
+
{"current_steps": 2000, "total_steps": 2292, "eval_loss": 0.5055009722709656, "epoch": 0.8727907484180668, "percentage": 87.26, "elapsed_time": "3:33:00", "remaining_time": "0:31:05"}
|
| 205 |
+
{"current_steps": 2010, "total_steps": 2292, "loss": 0.5118, "lr": 4.57611212529091e-07, "epoch": 0.8771547021601571, "percentage": 87.7, "elapsed_time": "3:34:22", "remaining_time": "0:30:04"}
|
| 206 |
+
{"current_steps": 2020, "total_steps": 2292, "loss": 0.5209, "lr": 4.263021989882965e-07, "epoch": 0.8815186559022474, "percentage": 88.13, "elapsed_time": "3:35:25", "remaining_time": "0:29:00"}
|
| 207 |
+
{"current_steps": 2030, "total_steps": 2292, "loss": 0.5172, "lr": 3.9605483575178517e-07, "epoch": 0.8858826096443377, "percentage": 88.57, "elapsed_time": "3:36:25", "remaining_time": "0:27:55"}
|
| 208 |
+
{"current_steps": 2040, "total_steps": 2292, "loss": 0.51, "lr": 3.6687614386112403e-07, "epoch": 0.8902465633864282, "percentage": 89.01, "elapsed_time": "3:37:24", "remaining_time": "0:26:51"}
|
| 209 |
+
{"current_steps": 2050, "total_steps": 2292, "loss": 0.512, "lr": 3.38772896297056e-07, "epoch": 0.8946105171285185, "percentage": 89.44, "elapsed_time": "3:38:26", "remaining_time": "0:25:47"}
|
| 210 |
+
{"current_steps": 2060, "total_steps": 2292, "loss": 0.519, "lr": 3.117516164073459e-07, "epoch": 0.8989744708706088, "percentage": 89.88, "elapsed_time": "3:39:27", "remaining_time": "0:24:42"}
|
| 211 |
+
{"current_steps": 2070, "total_steps": 2292, "loss": 0.5104, "lr": 2.858185763925764e-07, "epoch": 0.9033384246126991, "percentage": 90.31, "elapsed_time": "3:40:28", "remaining_time": "0:23:38"}
|
| 212 |
+
{"current_steps": 2080, "total_steps": 2292, "loss": 0.5136, "lr": 2.6097979585024193e-07, "epoch": 0.9077023783547894, "percentage": 90.75, "elapsed_time": "3:41:29", "remaining_time": "0:22:34"}
|
| 213 |
+
{"current_steps": 2090, "total_steps": 2292, "loss": 0.5085, "lr": 2.3724104037747553e-07, "epoch": 0.9120663320968798, "percentage": 91.19, "elapsed_time": "3:42:30", "remaining_time": "0:21:30"}
|
| 214 |
+
{"current_steps": 2100, "total_steps": 2292, "loss": 0.5159, "lr": 2.146078202327284e-07, "epoch": 0.9164302858389701, "percentage": 91.62, "elapsed_time": "3:43:30", "remaining_time": "0:20:26"}
|
| 215 |
+
{"current_steps": 2110, "total_steps": 2292, "loss": 0.5118, "lr": 1.9308538905673135e-07, "epoch": 0.9207942395810604, "percentage": 92.06, "elapsed_time": "3:44:33", "remaining_time": "0:19:22"}
|
| 216 |
+
{"current_steps": 2120, "total_steps": 2292, "loss": 0.5139, "lr": 1.7267874265301187e-07, "epoch": 0.9251581933231507, "percentage": 92.5, "elapsed_time": "3:45:34", "remaining_time": "0:18:18"}
|
| 217 |
+
{"current_steps": 2130, "total_steps": 2292, "loss": 0.5084, "lr": 1.533926178282641e-07, "epoch": 0.9295221470652411, "percentage": 92.93, "elapsed_time": "3:46:36", "remaining_time": "0:17:14"}
|
| 218 |
+
{"current_steps": 2140, "total_steps": 2292, "loss": 0.5222, "lr": 1.3523149129283987e-07, "epoch": 0.9338861008073315, "percentage": 93.37, "elapsed_time": "3:47:37", "remaining_time": "0:16:10"}
|
| 219 |
+
{"current_steps": 2150, "total_steps": 2292, "loss": 0.5069, "lr": 1.1819957862160835e-07, "epoch": 0.9382500545494218, "percentage": 93.8, "elapsed_time": "3:48:38", "remaining_time": "0:15:06"}
|
| 220 |
+
{"current_steps": 2160, "total_steps": 2292, "loss": 0.5142, "lr": 1.0230083327543661e-07, "epoch": 0.9426140082915121, "percentage": 94.24, "elapsed_time": "3:49:40", "remaining_time": "0:14:02"}
|
| 221 |
+
{"current_steps": 2170, "total_steps": 2292, "loss": 0.5155, "lr": 8.753894568350573e-08, "epoch": 0.9469779620336024, "percentage": 94.68, "elapsed_time": "3:50:41", "remaining_time": "0:12:58"}
|
| 222 |
+
{"current_steps": 2180, "total_steps": 2292, "loss": 0.5074, "lr": 7.391734238668846e-08, "epoch": 0.9513419157756928, "percentage": 95.11, "elapsed_time": "3:51:43", "remaining_time": "0:11:54"}
|
| 223 |
+
{"current_steps": 2190, "total_steps": 2292, "loss": 0.5176, "lr": 6.143918524217696e-08, "epoch": 0.9557058695177831, "percentage": 95.55, "elapsed_time": "3:52:43", "remaining_time": "0:10:50"}
|
| 224 |
+
{"current_steps": 2200, "total_steps": 2292, "loss": 0.5137, "lr": 5.01073706895483e-08, "epoch": 0.9600698232598734, "percentage": 95.99, "elapsed_time": "3:53:43", "remaining_time": "0:09:46"}
|
| 225 |
+
{"current_steps": 2210, "total_steps": 2292, "loss": 0.5142, "lr": 3.992452907844502e-08, "epoch": 0.9644337770019638, "percentage": 96.42, "elapsed_time": "3:55:04", "remaining_time": "0:08:43"}
|
| 226 |
+
{"current_steps": 2220, "total_steps": 2292, "loss": 0.5025, "lr": 3.08930240580102e-08, "epoch": 0.9687977307440541, "percentage": 96.86, "elapsed_time": "3:56:07", "remaining_time": "0:07:39"}
|
| 227 |
+
{"current_steps": 2230, "total_steps": 2292, "loss": 0.5138, "lr": 2.3014952028240223e-08, "epoch": 0.9731616844861445, "percentage": 97.29, "elapsed_time": "3:57:07", "remaining_time": "0:06:35"}
|
| 228 |
+
{"current_steps": 2240, "total_steps": 2292, "loss": 0.5067, "lr": 1.6292141653366232e-08, "epoch": 0.9775256382282348, "percentage": 97.73, "elapsed_time": "3:58:09", "remaining_time": "0:05:31"}
|
| 229 |
+
{"current_steps": 2250, "total_steps": 2292, "loss": 0.5188, "lr": 1.0726153437379816e-08, "epoch": 0.9818895919703251, "percentage": 98.17, "elapsed_time": "3:59:10", "remaining_time": "0:04:27"}
|
| 230 |
+
{"current_steps": 2260, "total_steps": 2292, "loss": 0.5151, "lr": 6.3182793618110634e-09, "epoch": 0.9862535457124154, "percentage": 98.6, "elapsed_time": "4:00:11", "remaining_time": "0:03:24"}
|
| 231 |
+
{"current_steps": 2270, "total_steps": 2292, "loss": 0.5197, "lr": 3.0695425858329187e-09, "epoch": 0.9906174994545058, "percentage": 99.04, "elapsed_time": "4:01:12", "remaining_time": "0:02:20"}
|
| 232 |
+
{"current_steps": 2280, "total_steps": 2292, "loss": 0.5223, "lr": 9.806972087605949e-10, "epoch": 0.9949814531965961, "percentage": 99.48, "elapsed_time": "4:02:13", "remaining_time": "0:01:16"}
|
| 233 |
+
{"current_steps": 2290, "total_steps": 2292, "loss": 0.5178, "lr": 5.222809501492787e-11, "epoch": 0.9993454069386865, "percentage": 99.91, "elapsed_time": "4:03:15", "remaining_time": "0:00:12"}
|
| 234 |
+
{"current_steps": 2292, "total_steps": 2292, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "4:03:47", "remaining_time": "0:00:00"}
|
trainer_state.json
ADDED
|
@@ -0,0 +1,1678 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 2292,
|
| 8 |
+
"is_hyper_param_search": false,
|
| 9 |
+
"is_local_process_zero": true,
|
| 10 |
+
"is_world_process_zero": true,
|
| 11 |
+
"log_history": [
|
| 12 |
+
{
|
| 13 |
+
"epoch": 0.004363953742090334,
|
| 14 |
+
"grad_norm": 26.499397821507202,
|
| 15 |
+
"learning_rate": 3.91304347826087e-07,
|
| 16 |
+
"loss": 1.5146,
|
| 17 |
+
"step": 10
|
| 18 |
+
},
|
| 19 |
+
{
|
| 20 |
+
"epoch": 0.008727907484180668,
|
| 21 |
+
"grad_norm": 18.696221795032976,
|
| 22 |
+
"learning_rate": 8.260869565217392e-07,
|
| 23 |
+
"loss": 1.3975,
|
| 24 |
+
"step": 20
|
| 25 |
+
},
|
| 26 |
+
{
|
| 27 |
+
"epoch": 0.013091861226271002,
|
| 28 |
+
"grad_norm": 5.195746812383845,
|
| 29 |
+
"learning_rate": 1.2608695652173913e-06,
|
| 30 |
+
"loss": 1.0301,
|
| 31 |
+
"step": 30
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"epoch": 0.017455814968361336,
|
| 35 |
+
"grad_norm": 2.9388986813240305,
|
| 36 |
+
"learning_rate": 1.6956521739130435e-06,
|
| 37 |
+
"loss": 0.9338,
|
| 38 |
+
"step": 40
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"epoch": 0.02181976871045167,
|
| 42 |
+
"grad_norm": 2.157896980678217,
|
| 43 |
+
"learning_rate": 2.130434782608696e-06,
|
| 44 |
+
"loss": 0.834,
|
| 45 |
+
"step": 50
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"epoch": 0.026183722452542003,
|
| 49 |
+
"grad_norm": 2.030356833343019,
|
| 50 |
+
"learning_rate": 2.5652173913043484e-06,
|
| 51 |
+
"loss": 0.7817,
|
| 52 |
+
"step": 60
|
| 53 |
+
},
|
| 54 |
+
{
|
| 55 |
+
"epoch": 0.030547676194632337,
|
| 56 |
+
"grad_norm": 2.010110703082707,
|
| 57 |
+
"learning_rate": 3e-06,
|
| 58 |
+
"loss": 0.7423,
|
| 59 |
+
"step": 70
|
| 60 |
+
},
|
| 61 |
+
{
|
| 62 |
+
"epoch": 0.03491162993672267,
|
| 63 |
+
"grad_norm": 2.036582614030934,
|
| 64 |
+
"learning_rate": 3.4347826086956526e-06,
|
| 65 |
+
"loss": 0.7193,
|
| 66 |
+
"step": 80
|
| 67 |
+
},
|
| 68 |
+
{
|
| 69 |
+
"epoch": 0.039275583678813,
|
| 70 |
+
"grad_norm": 1.9487163653762136,
|
| 71 |
+
"learning_rate": 3.869565217391304e-06,
|
| 72 |
+
"loss": 0.6965,
|
| 73 |
+
"step": 90
|
| 74 |
+
},
|
| 75 |
+
{
|
| 76 |
+
"epoch": 0.04363953742090334,
|
| 77 |
+
"grad_norm": 1.8884072181165537,
|
| 78 |
+
"learning_rate": 4.304347826086957e-06,
|
| 79 |
+
"loss": 0.6863,
|
| 80 |
+
"step": 100
|
| 81 |
+
},
|
| 82 |
+
{
|
| 83 |
+
"epoch": 0.04800349116299367,
|
| 84 |
+
"grad_norm": 1.9672176130957406,
|
| 85 |
+
"learning_rate": 4.739130434782609e-06,
|
| 86 |
+
"loss": 0.6761,
|
| 87 |
+
"step": 110
|
| 88 |
+
},
|
| 89 |
+
{
|
| 90 |
+
"epoch": 0.05236744490508401,
|
| 91 |
+
"grad_norm": 1.9175860223528627,
|
| 92 |
+
"learning_rate": 5.173913043478262e-06,
|
| 93 |
+
"loss": 0.669,
|
| 94 |
+
"step": 120
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"epoch": 0.05673139864717434,
|
| 98 |
+
"grad_norm": 4.64170340673796,
|
| 99 |
+
"learning_rate": 5.608695652173914e-06,
|
| 100 |
+
"loss": 0.6553,
|
| 101 |
+
"step": 130
|
| 102 |
+
},
|
| 103 |
+
{
|
| 104 |
+
"epoch": 0.061095352389264675,
|
| 105 |
+
"grad_norm": 2.4419914657221766,
|
| 106 |
+
"learning_rate": 6.043478260869565e-06,
|
| 107 |
+
"loss": 0.6635,
|
| 108 |
+
"step": 140
|
| 109 |
+
},
|
| 110 |
+
{
|
| 111 |
+
"epoch": 0.065459306131355,
|
| 112 |
+
"grad_norm": 2.219811974469962,
|
| 113 |
+
"learning_rate": 6.478260869565218e-06,
|
| 114 |
+
"loss": 0.6417,
|
| 115 |
+
"step": 150
|
| 116 |
+
},
|
| 117 |
+
{
|
| 118 |
+
"epoch": 0.06982325987344534,
|
| 119 |
+
"grad_norm": 1.8731532270945315,
|
| 120 |
+
"learning_rate": 6.91304347826087e-06,
|
| 121 |
+
"loss": 0.6427,
|
| 122 |
+
"step": 160
|
| 123 |
+
},
|
| 124 |
+
{
|
| 125 |
+
"epoch": 0.07418721361553568,
|
| 126 |
+
"grad_norm": 1.9110914927729745,
|
| 127 |
+
"learning_rate": 7.347826086956522e-06,
|
| 128 |
+
"loss": 0.6442,
|
| 129 |
+
"step": 170
|
| 130 |
+
},
|
| 131 |
+
{
|
| 132 |
+
"epoch": 0.078551167357626,
|
| 133 |
+
"grad_norm": 1.9295608959806378,
|
| 134 |
+
"learning_rate": 7.782608695652174e-06,
|
| 135 |
+
"loss": 0.6369,
|
| 136 |
+
"step": 180
|
| 137 |
+
},
|
| 138 |
+
{
|
| 139 |
+
"epoch": 0.08291512109971634,
|
| 140 |
+
"grad_norm": 1.7914358748612738,
|
| 141 |
+
"learning_rate": 8.217391304347827e-06,
|
| 142 |
+
"loss": 0.639,
|
| 143 |
+
"step": 190
|
| 144 |
+
},
|
| 145 |
+
{
|
| 146 |
+
"epoch": 0.08727907484180668,
|
| 147 |
+
"grad_norm": 1.9446891106680222,
|
| 148 |
+
"learning_rate": 8.65217391304348e-06,
|
| 149 |
+
"loss": 0.6414,
|
| 150 |
+
"step": 200
|
| 151 |
+
},
|
| 152 |
+
{
|
| 153 |
+
"epoch": 0.09164302858389702,
|
| 154 |
+
"grad_norm": 2.1347110290826032,
|
| 155 |
+
"learning_rate": 9.086956521739132e-06,
|
| 156 |
+
"loss": 0.6392,
|
| 157 |
+
"step": 210
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"epoch": 0.09600698232598734,
|
| 161 |
+
"grad_norm": 1.9030077411906519,
|
| 162 |
+
"learning_rate": 9.521739130434784e-06,
|
| 163 |
+
"loss": 0.6407,
|
| 164 |
+
"step": 220
|
| 165 |
+
},
|
| 166 |
+
{
|
| 167 |
+
"epoch": 0.10037093606807768,
|
| 168 |
+
"grad_norm": 1.9072699967620688,
|
| 169 |
+
"learning_rate": 9.956521739130436e-06,
|
| 170 |
+
"loss": 0.6296,
|
| 171 |
+
"step": 230
|
| 172 |
+
},
|
| 173 |
+
{
|
| 174 |
+
"epoch": 0.10473488981016801,
|
| 175 |
+
"grad_norm": 6.11411147753339,
|
| 176 |
+
"learning_rate": 9.999529953691501e-06,
|
| 177 |
+
"loss": 0.6364,
|
| 178 |
+
"step": 240
|
| 179 |
+
},
|
| 180 |
+
{
|
| 181 |
+
"epoch": 0.10909884355225835,
|
| 182 |
+
"grad_norm": 1.9274840356722631,
|
| 183 |
+
"learning_rate": 9.997905215717636e-06,
|
| 184 |
+
"loss": 0.6271,
|
| 185 |
+
"step": 250
|
| 186 |
+
},
|
| 187 |
+
{
|
| 188 |
+
"epoch": 0.11346279729434867,
|
| 189 |
+
"grad_norm": 1.6084651209610894,
|
| 190 |
+
"learning_rate": 9.995120360083208e-06,
|
| 191 |
+
"loss": 0.625,
|
| 192 |
+
"step": 260
|
| 193 |
+
},
|
| 194 |
+
{
|
| 195 |
+
"epoch": 0.11782675103643901,
|
| 196 |
+
"grad_norm": 1.9201552574955696,
|
| 197 |
+
"learning_rate": 9.991176033211077e-06,
|
| 198 |
+
"loss": 0.6271,
|
| 199 |
+
"step": 270
|
| 200 |
+
},
|
| 201 |
+
{
|
| 202 |
+
"epoch": 0.12219070477852935,
|
| 203 |
+
"grad_norm": 1.8527351849291473,
|
| 204 |
+
"learning_rate": 9.98607315066148e-06,
|
| 205 |
+
"loss": 0.62,
|
| 206 |
+
"step": 280
|
| 207 |
+
},
|
| 208 |
+
{
|
| 209 |
+
"epoch": 0.12655465852061967,
|
| 210 |
+
"grad_norm": 2.1728262084174137,
|
| 211 |
+
"learning_rate": 9.979812896919497e-06,
|
| 212 |
+
"loss": 0.6234,
|
| 213 |
+
"step": 290
|
| 214 |
+
},
|
| 215 |
+
{
|
| 216 |
+
"epoch": 0.13091861226271,
|
| 217 |
+
"grad_norm": 2.5508242501465848,
|
| 218 |
+
"learning_rate": 9.97239672512011e-06,
|
| 219 |
+
"loss": 0.6228,
|
| 220 |
+
"step": 300
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"epoch": 0.13528256600480035,
|
| 224 |
+
"grad_norm": 1.8024605834099054,
|
| 225 |
+
"learning_rate": 9.963826356710913e-06,
|
| 226 |
+
"loss": 0.6189,
|
| 227 |
+
"step": 310
|
| 228 |
+
},
|
| 229 |
+
{
|
| 230 |
+
"epoch": 0.13964651974689068,
|
| 231 |
+
"grad_norm": 1.7899544274401067,
|
| 232 |
+
"learning_rate": 9.954103781052508e-06,
|
| 233 |
+
"loss": 0.622,
|
| 234 |
+
"step": 320
|
| 235 |
+
},
|
| 236 |
+
{
|
| 237 |
+
"epoch": 0.14401047348898102,
|
| 238 |
+
"grad_norm": 2.6634929838451162,
|
| 239 |
+
"learning_rate": 9.943231254956749e-06,
|
| 240 |
+
"loss": 0.6215,
|
| 241 |
+
"step": 330
|
| 242 |
+
},
|
| 243 |
+
{
|
| 244 |
+
"epoch": 0.14837442723107136,
|
| 245 |
+
"grad_norm": 1.6887392545009612,
|
| 246 |
+
"learning_rate": 9.93121130216288e-06,
|
| 247 |
+
"loss": 0.6095,
|
| 248 |
+
"step": 340
|
| 249 |
+
},
|
| 250 |
+
{
|
| 251 |
+
"epoch": 0.1527383809731617,
|
| 252 |
+
"grad_norm": 1.564527068427684,
|
| 253 |
+
"learning_rate": 9.918046712751731e-06,
|
| 254 |
+
"loss": 0.6073,
|
| 255 |
+
"step": 350
|
| 256 |
+
},
|
| 257 |
+
{
|
| 258 |
+
"epoch": 0.157102334715252,
|
| 259 |
+
"grad_norm": 1.7759578419290645,
|
| 260 |
+
"learning_rate": 9.903740542498071e-06,
|
| 261 |
+
"loss": 0.6095,
|
| 262 |
+
"step": 360
|
| 263 |
+
},
|
| 264 |
+
{
|
| 265 |
+
"epoch": 0.16146628845734234,
|
| 266 |
+
"grad_norm": 2.604040660939313,
|
| 267 |
+
"learning_rate": 9.888296112161308e-06,
|
| 268 |
+
"loss": 0.6039,
|
| 269 |
+
"step": 370
|
| 270 |
+
},
|
| 271 |
+
{
|
| 272 |
+
"epoch": 0.16583024219943268,
|
| 273 |
+
"grad_norm": 1.7552723705971771,
|
| 274 |
+
"learning_rate": 9.87171700671467e-06,
|
| 275 |
+
"loss": 0.6049,
|
| 276 |
+
"step": 380
|
| 277 |
+
},
|
| 278 |
+
{
|
| 279 |
+
"epoch": 0.17019419594152302,
|
| 280 |
+
"grad_norm": 2.786695194524141,
|
| 281 |
+
"learning_rate": 9.854007074513056e-06,
|
| 282 |
+
"loss": 0.6069,
|
| 283 |
+
"step": 390
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"epoch": 0.17455814968361336,
|
| 287 |
+
"grad_norm": 1.6966428135982474,
|
| 288 |
+
"learning_rate": 9.835170426399757e-06,
|
| 289 |
+
"loss": 0.6067,
|
| 290 |
+
"step": 400
|
| 291 |
+
},
|
| 292 |
+
{
|
| 293 |
+
"epoch": 0.1789221034257037,
|
| 294 |
+
"grad_norm": 3.1900936362907073,
|
| 295 |
+
"learning_rate": 9.815211434752236e-06,
|
| 296 |
+
"loss": 0.6021,
|
| 297 |
+
"step": 410
|
| 298 |
+
},
|
| 299 |
+
{
|
| 300 |
+
"epoch": 0.18328605716779403,
|
| 301 |
+
"grad_norm": 2.0950790085022795,
|
| 302 |
+
"learning_rate": 9.79413473246722e-06,
|
| 303 |
+
"loss": 0.6064,
|
| 304 |
+
"step": 420
|
| 305 |
+
},
|
| 306 |
+
{
|
| 307 |
+
"epoch": 0.18765001090988437,
|
| 308 |
+
"grad_norm": 1.8573324559272892,
|
| 309 |
+
"learning_rate": 9.771945211885294e-06,
|
| 310 |
+
"loss": 0.5962,
|
| 311 |
+
"step": 430
|
| 312 |
+
},
|
| 313 |
+
{
|
| 314 |
+
"epoch": 0.19201396465197468,
|
| 315 |
+
"grad_norm": 1.7147053708189852,
|
| 316 |
+
"learning_rate": 9.748648023655302e-06,
|
| 317 |
+
"loss": 0.6005,
|
| 318 |
+
"step": 440
|
| 319 |
+
},
|
| 320 |
+
{
|
| 321 |
+
"epoch": 0.19637791839406502,
|
| 322 |
+
"grad_norm": 1.620349780247674,
|
| 323 |
+
"learning_rate": 9.724248575538764e-06,
|
| 324 |
+
"loss": 0.5922,
|
| 325 |
+
"step": 450
|
| 326 |
+
},
|
| 327 |
+
{
|
| 328 |
+
"epoch": 0.20074187213615535,
|
| 329 |
+
"grad_norm": 1.654417334838078,
|
| 330 |
+
"learning_rate": 9.698752531154623e-06,
|
| 331 |
+
"loss": 0.5977,
|
| 332 |
+
"step": 460
|
| 333 |
+
},
|
| 334 |
+
{
|
| 335 |
+
"epoch": 0.2051058258782457,
|
| 336 |
+
"grad_norm": 3.7007534847341335,
|
| 337 |
+
"learning_rate": 9.672165808664609e-06,
|
| 338 |
+
"loss": 0.5989,
|
| 339 |
+
"step": 470
|
| 340 |
+
},
|
| 341 |
+
{
|
| 342 |
+
"epoch": 0.20946977962033603,
|
| 343 |
+
"grad_norm": 1.8306160811104213,
|
| 344 |
+
"learning_rate": 9.6444945793995e-06,
|
| 345 |
+
"loss": 0.5914,
|
| 346 |
+
"step": 480
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"epoch": 0.21383373336242636,
|
| 350 |
+
"grad_norm": 1.9518306293763308,
|
| 351 |
+
"learning_rate": 9.61574526642664e-06,
|
| 352 |
+
"loss": 0.5883,
|
| 353 |
+
"step": 490
|
| 354 |
+
},
|
| 355 |
+
{
|
| 356 |
+
"epoch": 0.2181976871045167,
|
| 357 |
+
"grad_norm": 1.4825723400886388,
|
| 358 |
+
"learning_rate": 9.585924543058997e-06,
|
| 359 |
+
"loss": 0.591,
|
| 360 |
+
"step": 500
|
| 361 |
+
},
|
| 362 |
+
{
|
| 363 |
+
"epoch": 0.2181976871045167,
|
| 364 |
+
"eval_loss": 0.5827435255050659,
|
| 365 |
+
"eval_runtime": 69.7858,
|
| 366 |
+
"eval_samples_per_second": 53.062,
|
| 367 |
+
"eval_steps_per_second": 3.324,
|
| 368 |
+
"step": 500
|
| 369 |
+
},
|
| 370 |
+
{
|
| 371 |
+
"epoch": 0.22256164084660704,
|
| 372 |
+
"grad_norm": 1.480013652739435,
|
| 373 |
+
"learning_rate": 9.555039331306164e-06,
|
| 374 |
+
"loss": 0.5893,
|
| 375 |
+
"step": 510
|
| 376 |
+
},
|
| 377 |
+
{
|
| 378 |
+
"epoch": 0.22692559458869735,
|
| 379 |
+
"grad_norm": 1.697064020550412,
|
| 380 |
+
"learning_rate": 9.523096800267602e-06,
|
| 381 |
+
"loss": 0.5967,
|
| 382 |
+
"step": 520
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"epoch": 0.2312895483307877,
|
| 386 |
+
"grad_norm": 1.4577169028061336,
|
| 387 |
+
"learning_rate": 9.490104364468557e-06,
|
| 388 |
+
"loss": 0.5876,
|
| 389 |
+
"step": 530
|
| 390 |
+
},
|
| 391 |
+
{
|
| 392 |
+
"epoch": 0.23565350207287802,
|
| 393 |
+
"grad_norm": 1.407863250608549,
|
| 394 |
+
"learning_rate": 9.456069682138981e-06,
|
| 395 |
+
"loss": 0.5879,
|
| 396 |
+
"step": 540
|
| 397 |
+
},
|
| 398 |
+
{
|
| 399 |
+
"epoch": 0.24001745581496836,
|
| 400 |
+
"grad_norm": 1.5047099371255703,
|
| 401 |
+
"learning_rate": 9.421000653435908e-06,
|
| 402 |
+
"loss": 0.5898,
|
| 403 |
+
"step": 550
|
| 404 |
+
},
|
| 405 |
+
{
|
| 406 |
+
"epoch": 0.2443814095570587,
|
| 407 |
+
"grad_norm": 1.5343210297318903,
|
| 408 |
+
"learning_rate": 9.38490541860966e-06,
|
| 409 |
+
"loss": 0.5938,
|
| 410 |
+
"step": 560
|
| 411 |
+
},
|
| 412 |
+
{
|
| 413 |
+
"epoch": 0.24874536329914904,
|
| 414 |
+
"grad_norm": 1.4956667878525625,
|
| 415 |
+
"learning_rate": 9.347792356114324e-06,
|
| 416 |
+
"loss": 0.5893,
|
| 417 |
+
"step": 570
|
| 418 |
+
},
|
| 419 |
+
{
|
| 420 |
+
"epoch": 0.25310931704123935,
|
| 421 |
+
"grad_norm": 1.5101062644216703,
|
| 422 |
+
"learning_rate": 9.30967008066294e-06,
|
| 423 |
+
"loss": 0.5976,
|
| 424 |
+
"step": 580
|
| 425 |
+
},
|
| 426 |
+
{
|
| 427 |
+
"epoch": 0.2574732707833297,
|
| 428 |
+
"grad_norm": 1.5236342080851415,
|
| 429 |
+
"learning_rate": 9.27054744122785e-06,
|
| 430 |
+
"loss": 0.592,
|
| 431 |
+
"step": 590
|
| 432 |
+
},
|
| 433 |
+
{
|
| 434 |
+
"epoch": 0.26183722452542,
|
| 435 |
+
"grad_norm": 1.6140869174258692,
|
| 436 |
+
"learning_rate": 9.230433518986664e-06,
|
| 437 |
+
"loss": 0.5888,
|
| 438 |
+
"step": 600
|
| 439 |
+
},
|
| 440 |
+
{
|
| 441 |
+
"epoch": 0.2662011782675104,
|
| 442 |
+
"grad_norm": 1.419486174653226,
|
| 443 |
+
"learning_rate": 9.189337625214324e-06,
|
| 444 |
+
"loss": 0.5842,
|
| 445 |
+
"step": 610
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"epoch": 0.2705651320096007,
|
| 449 |
+
"grad_norm": 1.5576946265406408,
|
| 450 |
+
"learning_rate": 9.147269299121782e-06,
|
| 451 |
+
"loss": 0.582,
|
| 452 |
+
"step": 620
|
| 453 |
+
},
|
| 454 |
+
{
|
| 455 |
+
"epoch": 0.274929085751691,
|
| 456 |
+
"grad_norm": 1.4457336642256946,
|
| 457 |
+
"learning_rate": 9.104238305641731e-06,
|
| 458 |
+
"loss": 0.579,
|
| 459 |
+
"step": 630
|
| 460 |
+
},
|
| 461 |
+
{
|
| 462 |
+
"epoch": 0.27929303949378137,
|
| 463 |
+
"grad_norm": 1.5422960552682006,
|
| 464 |
+
"learning_rate": 9.060254633161973e-06,
|
| 465 |
+
"loss": 0.5889,
|
| 466 |
+
"step": 640
|
| 467 |
+
},
|
| 468 |
+
{
|
| 469 |
+
"epoch": 0.2836569932358717,
|
| 470 |
+
"grad_norm": 1.5024597086356501,
|
| 471 |
+
"learning_rate": 9.015328491206901e-06,
|
| 472 |
+
"loss": 0.5793,
|
| 473 |
+
"step": 650
|
| 474 |
+
},
|
| 475 |
+
{
|
| 476 |
+
"epoch": 0.28802094697796204,
|
| 477 |
+
"grad_norm": 1.3686070974882203,
|
| 478 |
+
"learning_rate": 8.969470308067662e-06,
|
| 479 |
+
"loss": 0.5807,
|
| 480 |
+
"step": 660
|
| 481 |
+
},
|
| 482 |
+
{
|
| 483 |
+
"epoch": 0.29238490072005235,
|
| 484 |
+
"grad_norm": 2.6998427178862894,
|
| 485 |
+
"learning_rate": 8.922690728381527e-06,
|
| 486 |
+
"loss": 0.5748,
|
| 487 |
+
"step": 670
|
| 488 |
+
},
|
| 489 |
+
{
|
| 490 |
+
"epoch": 0.2967488544621427,
|
| 491 |
+
"grad_norm": 2.065649261696864,
|
| 492 |
+
"learning_rate": 8.875000610661052e-06,
|
| 493 |
+
"loss": 0.5688,
|
| 494 |
+
"step": 680
|
| 495 |
+
},
|
| 496 |
+
{
|
| 497 |
+
"epoch": 0.30111280820423303,
|
| 498 |
+
"grad_norm": 1.5958849520041398,
|
| 499 |
+
"learning_rate": 8.826411024773595e-06,
|
| 500 |
+
"loss": 0.5727,
|
| 501 |
+
"step": 690
|
| 502 |
+
},
|
| 503 |
+
{
|
| 504 |
+
"epoch": 0.3054767619463234,
|
| 505 |
+
"grad_norm": 1.4305834347213016,
|
| 506 |
+
"learning_rate": 8.776933249371769e-06,
|
| 507 |
+
"loss": 0.5621,
|
| 508 |
+
"step": 700
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"epoch": 0.3098407156884137,
|
| 512 |
+
"grad_norm": 1.4826756109906936,
|
| 513 |
+
"learning_rate": 8.726578769275426e-06,
|
| 514 |
+
"loss": 0.57,
|
| 515 |
+
"step": 710
|
| 516 |
+
},
|
| 517 |
+
{
|
| 518 |
+
"epoch": 0.314204669430504,
|
| 519 |
+
"grad_norm": 1.4919661778521895,
|
| 520 |
+
"learning_rate": 8.675359272805796e-06,
|
| 521 |
+
"loss": 0.5733,
|
| 522 |
+
"step": 720
|
| 523 |
+
},
|
| 524 |
+
{
|
| 525 |
+
"epoch": 0.3185686231725944,
|
| 526 |
+
"grad_norm": 1.539486119661036,
|
| 527 |
+
"learning_rate": 8.62328664907239e-06,
|
| 528 |
+
"loss": 0.5617,
|
| 529 |
+
"step": 730
|
| 530 |
+
},
|
| 531 |
+
{
|
| 532 |
+
"epoch": 0.3229325769146847,
|
| 533 |
+
"grad_norm": 2.412337158368947,
|
| 534 |
+
"learning_rate": 8.570372985213283e-06,
|
| 535 |
+
"loss": 0.5748,
|
| 536 |
+
"step": 740
|
| 537 |
+
},
|
| 538 |
+
{
|
| 539 |
+
"epoch": 0.32729653065677505,
|
| 540 |
+
"grad_norm": 1.4949607784946515,
|
| 541 |
+
"learning_rate": 8.516630563589436e-06,
|
| 542 |
+
"loss": 0.5765,
|
| 543 |
+
"step": 750
|
| 544 |
+
},
|
| 545 |
+
{
|
| 546 |
+
"epoch": 0.33166048439886536,
|
| 547 |
+
"grad_norm": 2.1389988555015527,
|
| 548 |
+
"learning_rate": 8.462071858933717e-06,
|
| 549 |
+
"loss": 0.5717,
|
| 550 |
+
"step": 760
|
| 551 |
+
},
|
| 552 |
+
{
|
| 553 |
+
"epoch": 0.33602443814095573,
|
| 554 |
+
"grad_norm": 1.7992243083658257,
|
| 555 |
+
"learning_rate": 8.406709535455242e-06,
|
| 556 |
+
"loss": 0.5728,
|
| 557 |
+
"step": 770
|
| 558 |
+
},
|
| 559 |
+
{
|
| 560 |
+
"epoch": 0.34038839188304604,
|
| 561 |
+
"grad_norm": 1.7459966293740241,
|
| 562 |
+
"learning_rate": 8.35055644389976e-06,
|
| 563 |
+
"loss": 0.5621,
|
| 564 |
+
"step": 780
|
| 565 |
+
},
|
| 566 |
+
{
|
| 567 |
+
"epoch": 0.34475234562513635,
|
| 568 |
+
"grad_norm": 1.6584257041747206,
|
| 569 |
+
"learning_rate": 8.293625618566723e-06,
|
| 570 |
+
"loss": 0.5676,
|
| 571 |
+
"step": 790
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"epoch": 0.3491162993672267,
|
| 575 |
+
"grad_norm": 2.234742145469745,
|
| 576 |
+
"learning_rate": 8.23593027428375e-06,
|
| 577 |
+
"loss": 0.5657,
|
| 578 |
+
"step": 800
|
| 579 |
+
},
|
| 580 |
+
{
|
| 581 |
+
"epoch": 0.353480253109317,
|
| 582 |
+
"grad_norm": 1.4160485895062545,
|
| 583 |
+
"learning_rate": 8.177483803339203e-06,
|
| 584 |
+
"loss": 0.5739,
|
| 585 |
+
"step": 810
|
| 586 |
+
},
|
| 587 |
+
{
|
| 588 |
+
"epoch": 0.3578442068514074,
|
| 589 |
+
"grad_norm": 1.6236310717790317,
|
| 590 |
+
"learning_rate": 8.118299772373546e-06,
|
| 591 |
+
"loss": 0.5708,
|
| 592 |
+
"step": 820
|
| 593 |
+
},
|
| 594 |
+
{
|
| 595 |
+
"epoch": 0.3622081605934977,
|
| 596 |
+
"grad_norm": 1.4409935142518557,
|
| 597 |
+
"learning_rate": 8.05839191923025e-06,
|
| 598 |
+
"loss": 0.5652,
|
| 599 |
+
"step": 830
|
| 600 |
+
},
|
| 601 |
+
{
|
| 602 |
+
"epoch": 0.36657211433558806,
|
| 603 |
+
"grad_norm": 1.7422827738179059,
|
| 604 |
+
"learning_rate": 7.997774149766962e-06,
|
| 605 |
+
"loss": 0.5665,
|
| 606 |
+
"step": 840
|
| 607 |
+
},
|
| 608 |
+
{
|
| 609 |
+
"epoch": 0.37093606807767837,
|
| 610 |
+
"grad_norm": 1.4654585573940748,
|
| 611 |
+
"learning_rate": 7.936460534627648e-06,
|
| 612 |
+
"loss": 0.5592,
|
| 613 |
+
"step": 850
|
| 614 |
+
},
|
| 615 |
+
{
|
| 616 |
+
"epoch": 0.37530002181976874,
|
| 617 |
+
"grad_norm": 1.5684193622827431,
|
| 618 |
+
"learning_rate": 7.874465305976527e-06,
|
| 619 |
+
"loss": 0.558,
|
| 620 |
+
"step": 860
|
| 621 |
+
},
|
| 622 |
+
{
|
| 623 |
+
"epoch": 0.37966397556185905,
|
| 624 |
+
"grad_norm": 1.8405640707393334,
|
| 625 |
+
"learning_rate": 7.81180285419447e-06,
|
| 626 |
+
"loss": 0.5653,
|
| 627 |
+
"step": 870
|
| 628 |
+
},
|
| 629 |
+
{
|
| 630 |
+
"epoch": 0.38402792930394936,
|
| 631 |
+
"grad_norm": 1.475228530845922,
|
| 632 |
+
"learning_rate": 7.748487724538707e-06,
|
| 633 |
+
"loss": 0.5587,
|
| 634 |
+
"step": 880
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"epoch": 0.3883918830460397,
|
| 638 |
+
"grad_norm": 1.331005791046321,
|
| 639 |
+
"learning_rate": 7.684534613766566e-06,
|
| 640 |
+
"loss": 0.574,
|
| 641 |
+
"step": 890
|
| 642 |
+
},
|
| 643 |
+
{
|
| 644 |
+
"epoch": 0.39275583678813003,
|
| 645 |
+
"grad_norm": 1.3582718830868108,
|
| 646 |
+
"learning_rate": 7.619958366724043e-06,
|
| 647 |
+
"loss": 0.5657,
|
| 648 |
+
"step": 900
|
| 649 |
+
},
|
| 650 |
+
{
|
| 651 |
+
"epoch": 0.3971197905302204,
|
| 652 |
+
"grad_norm": 1.3639931742020133,
|
| 653 |
+
"learning_rate": 7.554773972900024e-06,
|
| 654 |
+
"loss": 0.5642,
|
| 655 |
+
"step": 910
|
| 656 |
+
},
|
| 657 |
+
{
|
| 658 |
+
"epoch": 0.4014837442723107,
|
| 659 |
+
"grad_norm": 1.4421529537691287,
|
| 660 |
+
"learning_rate": 7.488996562946886e-06,
|
| 661 |
+
"loss": 0.5585,
|
| 662 |
+
"step": 920
|
| 663 |
+
},
|
| 664 |
+
{
|
| 665 |
+
"epoch": 0.40584769801440107,
|
| 666 |
+
"grad_norm": 1.4453139064733957,
|
| 667 |
+
"learning_rate": 7.422641405168386e-06,
|
| 668 |
+
"loss": 0.5611,
|
| 669 |
+
"step": 930
|
| 670 |
+
},
|
| 671 |
+
{
|
| 672 |
+
"epoch": 0.4102116517564914,
|
| 673 |
+
"grad_norm": 1.41874403862543,
|
| 674 |
+
"learning_rate": 7.355723901975546e-06,
|
| 675 |
+
"loss": 0.5556,
|
| 676 |
+
"step": 940
|
| 677 |
+
},
|
| 678 |
+
{
|
| 679 |
+
"epoch": 0.4145756054985817,
|
| 680 |
+
"grad_norm": 1.569355186279227,
|
| 681 |
+
"learning_rate": 7.288259586311455e-06,
|
| 682 |
+
"loss": 0.5638,
|
| 683 |
+
"step": 950
|
| 684 |
+
},
|
| 685 |
+
{
|
| 686 |
+
"epoch": 0.41893955924067205,
|
| 687 |
+
"grad_norm": 1.340010425244894,
|
| 688 |
+
"learning_rate": 7.22026411804573e-06,
|
| 689 |
+
"loss": 0.554,
|
| 690 |
+
"step": 960
|
| 691 |
+
},
|
| 692 |
+
{
|
| 693 |
+
"epoch": 0.42330351298276236,
|
| 694 |
+
"grad_norm": 1.4102271417835663,
|
| 695 |
+
"learning_rate": 7.151753280339554e-06,
|
| 696 |
+
"loss": 0.5574,
|
| 697 |
+
"step": 970
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"epoch": 0.42766746672485273,
|
| 701 |
+
"grad_norm": 1.4168840313026727,
|
| 702 |
+
"learning_rate": 7.082742975982057e-06,
|
| 703 |
+
"loss": 0.5613,
|
| 704 |
+
"step": 980
|
| 705 |
+
},
|
| 706 |
+
{
|
| 707 |
+
"epoch": 0.43203142046694304,
|
| 708 |
+
"grad_norm": 1.4932003760222727,
|
| 709 |
+
"learning_rate": 7.0132492236989694e-06,
|
| 710 |
+
"loss": 0.5549,
|
| 711 |
+
"step": 990
|
| 712 |
+
},
|
| 713 |
+
{
|
| 714 |
+
"epoch": 0.4363953742090334,
|
| 715 |
+
"grad_norm": 1.3727246781695526,
|
| 716 |
+
"learning_rate": 6.94328815443432e-06,
|
| 717 |
+
"loss": 0.5605,
|
| 718 |
+
"step": 1000
|
| 719 |
+
},
|
| 720 |
+
{
|
| 721 |
+
"epoch": 0.4363953742090334,
|
| 722 |
+
"eval_loss": 0.545971155166626,
|
| 723 |
+
"eval_runtime": 68.1299,
|
| 724 |
+
"eval_samples_per_second": 54.352,
|
| 725 |
+
"eval_steps_per_second": 3.405,
|
| 726 |
+
"step": 1000
|
| 727 |
+
},
|
| 728 |
+
{
|
| 729 |
+
"epoch": 0.4407593279511237,
|
| 730 |
+
"grad_norm": 1.5610600215808323,
|
| 731 |
+
"learning_rate": 6.872876007606127e-06,
|
| 732 |
+
"loss": 0.5505,
|
| 733 |
+
"step": 1010
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"epoch": 0.4451232816932141,
|
| 737 |
+
"grad_norm": 1.2665441451258144,
|
| 738 |
+
"learning_rate": 6.802029127336884e-06,
|
| 739 |
+
"loss": 0.5511,
|
| 740 |
+
"step": 1020
|
| 741 |
+
},
|
| 742 |
+
{
|
| 743 |
+
"epoch": 0.4494872354353044,
|
| 744 |
+
"grad_norm": 1.4767565256072326,
|
| 745 |
+
"learning_rate": 6.73076395865975e-06,
|
| 746 |
+
"loss": 0.5479,
|
| 747 |
+
"step": 1030
|
| 748 |
+
},
|
| 749 |
+
{
|
| 750 |
+
"epoch": 0.4538511891773947,
|
| 751 |
+
"grad_norm": 1.3450898726192824,
|
| 752 |
+
"learning_rate": 6.6590970437013135e-06,
|
| 753 |
+
"loss": 0.5549,
|
| 754 |
+
"step": 1040
|
| 755 |
+
},
|
| 756 |
+
{
|
| 757 |
+
"epoch": 0.45821514291948506,
|
| 758 |
+
"grad_norm": 1.3691285786320522,
|
| 759 |
+
"learning_rate": 6.587045017841828e-06,
|
| 760 |
+
"loss": 0.5566,
|
| 761 |
+
"step": 1050
|
| 762 |
+
},
|
| 763 |
+
{
|
| 764 |
+
"epoch": 0.4625790966615754,
|
| 765 |
+
"grad_norm": 1.407701866024824,
|
| 766 |
+
"learning_rate": 6.514624605853785e-06,
|
| 767 |
+
"loss": 0.5519,
|
| 768 |
+
"step": 1060
|
| 769 |
+
},
|
| 770 |
+
{
|
| 771 |
+
"epoch": 0.46694305040366574,
|
| 772 |
+
"grad_norm": 1.7016011593861633,
|
| 773 |
+
"learning_rate": 6.441852618019757e-06,
|
| 774 |
+
"loss": 0.5453,
|
| 775 |
+
"step": 1070
|
| 776 |
+
},
|
| 777 |
+
{
|
| 778 |
+
"epoch": 0.47130700414575605,
|
| 779 |
+
"grad_norm": 2.0081488788972495,
|
| 780 |
+
"learning_rate": 6.368745946230371e-06,
|
| 781 |
+
"loss": 0.5509,
|
| 782 |
+
"step": 1080
|
| 783 |
+
},
|
| 784 |
+
{
|
| 785 |
+
"epoch": 0.4756709578878464,
|
| 786 |
+
"grad_norm": 1.4313272433739415,
|
| 787 |
+
"learning_rate": 6.295321560063358e-06,
|
| 788 |
+
"loss": 0.5558,
|
| 789 |
+
"step": 1090
|
| 790 |
+
},
|
| 791 |
+
{
|
| 792 |
+
"epoch": 0.4800349116299367,
|
| 793 |
+
"grad_norm": 1.3908306510503996,
|
| 794 |
+
"learning_rate": 6.221596502844558e-06,
|
| 795 |
+
"loss": 0.5496,
|
| 796 |
+
"step": 1100
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"epoch": 0.48439886537202703,
|
| 800 |
+
"grad_norm": 1.4083635646126667,
|
| 801 |
+
"learning_rate": 6.147587887691812e-06,
|
| 802 |
+
"loss": 0.5447,
|
| 803 |
+
"step": 1110
|
| 804 |
+
},
|
| 805 |
+
{
|
| 806 |
+
"epoch": 0.4887628191141174,
|
| 807 |
+
"grad_norm": 17.48008864471473,
|
| 808 |
+
"learning_rate": 6.073312893542644e-06,
|
| 809 |
+
"loss": 0.5507,
|
| 810 |
+
"step": 1120
|
| 811 |
+
},
|
| 812 |
+
{
|
| 813 |
+
"epoch": 0.4931267728562077,
|
| 814 |
+
"grad_norm": 1.7242442516057832,
|
| 815 |
+
"learning_rate": 5.998788761166689e-06,
|
| 816 |
+
"loss": 0.5497,
|
| 817 |
+
"step": 1130
|
| 818 |
+
},
|
| 819 |
+
{
|
| 820 |
+
"epoch": 0.49749072659829807,
|
| 821 |
+
"grad_norm": 1.6226845226734892,
|
| 822 |
+
"learning_rate": 5.9240327891637296e-06,
|
| 823 |
+
"loss": 0.5521,
|
| 824 |
+
"step": 1140
|
| 825 |
+
},
|
| 826 |
+
{
|
| 827 |
+
"epoch": 0.5018546803403884,
|
| 828 |
+
"grad_norm": 1.6604002116905412,
|
| 829 |
+
"learning_rate": 5.849062329948353e-06,
|
| 830 |
+
"loss": 0.5451,
|
| 831 |
+
"step": 1150
|
| 832 |
+
},
|
| 833 |
+
{
|
| 834 |
+
"epoch": 0.5062186340824787,
|
| 835 |
+
"grad_norm": 1.5873724924653319,
|
| 836 |
+
"learning_rate": 5.773894785722082e-06,
|
| 837 |
+
"loss": 0.547,
|
| 838 |
+
"step": 1160
|
| 839 |
+
},
|
| 840 |
+
{
|
| 841 |
+
"epoch": 0.5105825878245691,
|
| 842 |
+
"grad_norm": 1.4609962799328036,
|
| 843 |
+
"learning_rate": 5.698547604433963e-06,
|
| 844 |
+
"loss": 0.551,
|
| 845 |
+
"step": 1170
|
| 846 |
+
},
|
| 847 |
+
{
|
| 848 |
+
"epoch": 0.5149465415666594,
|
| 849 |
+
"grad_norm": 2.35781566677412,
|
| 850 |
+
"learning_rate": 5.623038275730543e-06,
|
| 851 |
+
"loss": 0.5482,
|
| 852 |
+
"step": 1180
|
| 853 |
+
},
|
| 854 |
+
{
|
| 855 |
+
"epoch": 0.5193104953087497,
|
| 856 |
+
"grad_norm": 1.7956175108962174,
|
| 857 |
+
"learning_rate": 5.547384326896152e-06,
|
| 858 |
+
"loss": 0.5378,
|
| 859 |
+
"step": 1190
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"epoch": 0.52367444905084,
|
| 863 |
+
"grad_norm": 1.3754392835784166,
|
| 864 |
+
"learning_rate": 5.4716033187844565e-06,
|
| 865 |
+
"loss": 0.5289,
|
| 866 |
+
"step": 1200
|
| 867 |
+
},
|
| 868 |
+
{
|
| 869 |
+
"epoch": 0.5280384027929304,
|
| 870 |
+
"grad_norm": 1.351125298582442,
|
| 871 |
+
"learning_rate": 5.3957128417422196e-06,
|
| 872 |
+
"loss": 0.5375,
|
| 873 |
+
"step": 1210
|
| 874 |
+
},
|
| 875 |
+
{
|
| 876 |
+
"epoch": 0.5324023565350208,
|
| 877 |
+
"grad_norm": 1.2885359407090353,
|
| 878 |
+
"learning_rate": 5.319730511526225e-06,
|
| 879 |
+
"loss": 0.5484,
|
| 880 |
+
"step": 1220
|
| 881 |
+
},
|
| 882 |
+
{
|
| 883 |
+
"epoch": 0.5367663102771111,
|
| 884 |
+
"grad_norm": 1.4931791483959027,
|
| 885 |
+
"learning_rate": 5.243673965214276e-06,
|
| 886 |
+
"loss": 0.5352,
|
| 887 |
+
"step": 1230
|
| 888 |
+
},
|
| 889 |
+
{
|
| 890 |
+
"epoch": 0.5411302640192014,
|
| 891 |
+
"grad_norm": 1.3301082529926556,
|
| 892 |
+
"learning_rate": 5.167560857111286e-06,
|
| 893 |
+
"loss": 0.5407,
|
| 894 |
+
"step": 1240
|
| 895 |
+
},
|
| 896 |
+
{
|
| 897 |
+
"epoch": 0.5454942177612917,
|
| 898 |
+
"grad_norm": 1.3023885557832229,
|
| 899 |
+
"learning_rate": 5.091408854651327e-06,
|
| 900 |
+
"loss": 0.5354,
|
| 901 |
+
"step": 1250
|
| 902 |
+
},
|
| 903 |
+
{
|
| 904 |
+
"epoch": 0.549858171503382,
|
| 905 |
+
"grad_norm": 1.8840653667484866,
|
| 906 |
+
"learning_rate": 5.0152356342966624e-06,
|
| 907 |
+
"loss": 0.5425,
|
| 908 |
+
"step": 1260
|
| 909 |
+
},
|
| 910 |
+
{
|
| 911 |
+
"epoch": 0.5542221252454724,
|
| 912 |
+
"grad_norm": 1.3585936189959857,
|
| 913 |
+
"learning_rate": 4.939058877434672e-06,
|
| 914 |
+
"loss": 0.5386,
|
| 915 |
+
"step": 1270
|
| 916 |
+
},
|
| 917 |
+
{
|
| 918 |
+
"epoch": 0.5585860789875627,
|
| 919 |
+
"grad_norm": 1.4612137856640806,
|
| 920 |
+
"learning_rate": 4.862896266273627e-06,
|
| 921 |
+
"loss": 0.5512,
|
| 922 |
+
"step": 1280
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"epoch": 0.562950032729653,
|
| 926 |
+
"grad_norm": 1.3030406905808916,
|
| 927 |
+
"learning_rate": 4.786765479738293e-06,
|
| 928 |
+
"loss": 0.5422,
|
| 929 |
+
"step": 1290
|
| 930 |
+
},
|
| 931 |
+
{
|
| 932 |
+
"epoch": 0.5673139864717434,
|
| 933 |
+
"grad_norm": 1.3169625647849659,
|
| 934 |
+
"learning_rate": 4.7106841893662755e-06,
|
| 935 |
+
"loss": 0.5377,
|
| 936 |
+
"step": 1300
|
| 937 |
+
},
|
| 938 |
+
{
|
| 939 |
+
"epoch": 0.5716779402138338,
|
| 940 |
+
"grad_norm": 1.4365133088202295,
|
| 941 |
+
"learning_rate": 4.634670055206092e-06,
|
| 942 |
+
"loss": 0.5429,
|
| 943 |
+
"step": 1310
|
| 944 |
+
},
|
| 945 |
+
{
|
| 946 |
+
"epoch": 0.5760418939559241,
|
| 947 |
+
"grad_norm": 1.400666928678306,
|
| 948 |
+
"learning_rate": 4.5587407217179094e-06,
|
| 949 |
+
"loss": 0.5441,
|
| 950 |
+
"step": 1320
|
| 951 |
+
},
|
| 952 |
+
{
|
| 953 |
+
"epoch": 0.5804058476980144,
|
| 954 |
+
"grad_norm": 1.4020862611201026,
|
| 955 |
+
"learning_rate": 4.482913813677896e-06,
|
| 956 |
+
"loss": 0.5372,
|
| 957 |
+
"step": 1330
|
| 958 |
+
},
|
| 959 |
+
{
|
| 960 |
+
"epoch": 0.5847698014401047,
|
| 961 |
+
"grad_norm": 1.3899074056942011,
|
| 962 |
+
"learning_rate": 4.407206932087143e-06,
|
| 963 |
+
"loss": 0.5431,
|
| 964 |
+
"step": 1340
|
| 965 |
+
},
|
| 966 |
+
{
|
| 967 |
+
"epoch": 0.589133755182195,
|
| 968 |
+
"grad_norm": 1.2780180293099543,
|
| 969 |
+
"learning_rate": 4.331637650086111e-06,
|
| 970 |
+
"loss": 0.5354,
|
| 971 |
+
"step": 1350
|
| 972 |
+
},
|
| 973 |
+
{
|
| 974 |
+
"epoch": 0.5934977089242854,
|
| 975 |
+
"grad_norm": 1.3047906646065353,
|
| 976 |
+
"learning_rate": 4.256223508875536e-06,
|
| 977 |
+
"loss": 0.536,
|
| 978 |
+
"step": 1360
|
| 979 |
+
},
|
| 980 |
+
{
|
| 981 |
+
"epoch": 0.5978616626663757,
|
| 982 |
+
"grad_norm": 2.2450550137169025,
|
| 983 |
+
"learning_rate": 4.180982013644749e-06,
|
| 984 |
+
"loss": 0.5345,
|
| 985 |
+
"step": 1370
|
| 986 |
+
},
|
| 987 |
+
{
|
| 988 |
+
"epoch": 0.6022256164084661,
|
| 989 |
+
"grad_norm": 1.2604878888770283,
|
| 990 |
+
"learning_rate": 4.105930629508369e-06,
|
| 991 |
+
"loss": 0.5349,
|
| 992 |
+
"step": 1380
|
| 993 |
+
},
|
| 994 |
+
{
|
| 995 |
+
"epoch": 0.6065895701505564,
|
| 996 |
+
"grad_norm": 1.4408134764916174,
|
| 997 |
+
"learning_rate": 4.0310867774522724e-06,
|
| 998 |
+
"loss": 0.5338,
|
| 999 |
+
"step": 1390
|
| 1000 |
+
},
|
| 1001 |
+
{
|
| 1002 |
+
"epoch": 0.6109535238926468,
|
| 1003 |
+
"grad_norm": 1.194095025493141,
|
| 1004 |
+
"learning_rate": 3.95646783028983e-06,
|
| 1005 |
+
"loss": 0.5332,
|
| 1006 |
+
"step": 1400
|
| 1007 |
+
},
|
| 1008 |
+
{
|
| 1009 |
+
"epoch": 0.6153174776347371,
|
| 1010 |
+
"grad_norm": 1.3682237212576729,
|
| 1011 |
+
"learning_rate": 3.882091108629311e-06,
|
| 1012 |
+
"loss": 0.5305,
|
| 1013 |
+
"step": 1410
|
| 1014 |
+
},
|
| 1015 |
+
{
|
| 1016 |
+
"epoch": 0.6196814313768274,
|
| 1017 |
+
"grad_norm": 1.3808616625009607,
|
| 1018 |
+
"learning_rate": 3.807973876853414e-06,
|
| 1019 |
+
"loss": 0.5333,
|
| 1020 |
+
"step": 1420
|
| 1021 |
+
},
|
| 1022 |
+
{
|
| 1023 |
+
"epoch": 0.6240453851189177,
|
| 1024 |
+
"grad_norm": 1.3166679869381683,
|
| 1025 |
+
"learning_rate": 3.734133339111844e-06,
|
| 1026 |
+
"loss": 0.5305,
|
| 1027 |
+
"step": 1430
|
| 1028 |
+
},
|
| 1029 |
+
{
|
| 1030 |
+
"epoch": 0.628409338861008,
|
| 1031 |
+
"grad_norm": 2.075662539665934,
|
| 1032 |
+
"learning_rate": 3.660586635327869e-06,
|
| 1033 |
+
"loss": 0.5386,
|
| 1034 |
+
"step": 1440
|
| 1035 |
+
},
|
| 1036 |
+
{
|
| 1037 |
+
"epoch": 0.6327732926030984,
|
| 1038 |
+
"grad_norm": 1.3904648380650928,
|
| 1039 |
+
"learning_rate": 3.587350837219788e-06,
|
| 1040 |
+
"loss": 0.5396,
|
| 1041 |
+
"step": 1450
|
| 1042 |
+
},
|
| 1043 |
+
{
|
| 1044 |
+
"epoch": 0.6371372463451888,
|
| 1045 |
+
"grad_norm": 1.492731925374217,
|
| 1046 |
+
"learning_rate": 3.5144429443382356e-06,
|
| 1047 |
+
"loss": 0.5366,
|
| 1048 |
+
"step": 1460
|
| 1049 |
+
},
|
| 1050 |
+
{
|
| 1051 |
+
"epoch": 0.6415012000872791,
|
| 1052 |
+
"grad_norm": 1.2451404313444014,
|
| 1053 |
+
"learning_rate": 3.4418798801202256e-06,
|
| 1054 |
+
"loss": 0.5255,
|
| 1055 |
+
"step": 1470
|
| 1056 |
+
},
|
| 1057 |
+
{
|
| 1058 |
+
"epoch": 0.6458651538293694,
|
| 1059 |
+
"grad_norm": 1.5668762418599276,
|
| 1060 |
+
"learning_rate": 3.3696784879608747e-06,
|
| 1061 |
+
"loss": 0.5307,
|
| 1062 |
+
"step": 1480
|
| 1063 |
+
},
|
| 1064 |
+
{
|
| 1065 |
+
"epoch": 0.6502291075714598,
|
| 1066 |
+
"grad_norm": 1.4372909935764755,
|
| 1067 |
+
"learning_rate": 3.2978555273037006e-06,
|
| 1068 |
+
"loss": 0.5269,
|
| 1069 |
+
"step": 1490
|
| 1070 |
+
},
|
| 1071 |
+
{
|
| 1072 |
+
"epoch": 0.6545930613135501,
|
| 1073 |
+
"grad_norm": 1.3776181734494666,
|
| 1074 |
+
"learning_rate": 3.2264276697504026e-06,
|
| 1075 |
+
"loss": 0.5252,
|
| 1076 |
+
"step": 1500
|
| 1077 |
+
},
|
| 1078 |
+
{
|
| 1079 |
+
"epoch": 0.6545930613135501,
|
| 1080 |
+
"eval_loss": 0.5199297666549683,
|
| 1081 |
+
"eval_runtime": 69.8992,
|
| 1082 |
+
"eval_samples_per_second": 52.976,
|
| 1083 |
+
"eval_steps_per_second": 3.319,
|
| 1084 |
+
"step": 1500
|
| 1085 |
+
},
|
| 1086 |
+
{
|
| 1087 |
+
"epoch": 0.6589570150556404,
|
| 1088 |
+
"grad_norm": 1.4365144824102365,
|
| 1089 |
+
"learning_rate": 3.1554114951910387e-06,
|
| 1090 |
+
"loss": 0.5312,
|
| 1091 |
+
"step": 1510
|
| 1092 |
+
},
|
| 1093 |
+
{
|
| 1094 |
+
"epoch": 0.6633209687977307,
|
| 1095 |
+
"grad_norm": 1.2422304913068782,
|
| 1096 |
+
"learning_rate": 3.0848234879554916e-06,
|
| 1097 |
+
"loss": 0.5283,
|
| 1098 |
+
"step": 1520
|
| 1099 |
+
},
|
| 1100 |
+
{
|
| 1101 |
+
"epoch": 0.667684922539821,
|
| 1102 |
+
"grad_norm": 1.2495828228531431,
|
| 1103 |
+
"learning_rate": 3.0146800329871107e-06,
|
| 1104 |
+
"loss": 0.5359,
|
| 1105 |
+
"step": 1530
|
| 1106 |
+
},
|
| 1107 |
+
{
|
| 1108 |
+
"epoch": 0.6720488762819115,
|
| 1109 |
+
"grad_norm": 1.3009383931934748,
|
| 1110 |
+
"learning_rate": 2.944997412039422e-06,
|
| 1111 |
+
"loss": 0.5286,
|
| 1112 |
+
"step": 1540
|
| 1113 |
+
},
|
| 1114 |
+
{
|
| 1115 |
+
"epoch": 0.6764128300240018,
|
| 1116 |
+
"grad_norm": 1.3215444464354889,
|
| 1117 |
+
"learning_rate": 2.8757917998968042e-06,
|
| 1118 |
+
"loss": 0.5345,
|
| 1119 |
+
"step": 1550
|
| 1120 |
+
},
|
| 1121 |
+
{
|
| 1122 |
+
"epoch": 0.6807767837660921,
|
| 1123 |
+
"grad_norm": 1.199193600939233,
|
| 1124 |
+
"learning_rate": 2.807079260619976e-06,
|
| 1125 |
+
"loss": 0.5226,
|
| 1126 |
+
"step": 1560
|
| 1127 |
+
},
|
| 1128 |
+
{
|
| 1129 |
+
"epoch": 0.6851407375081824,
|
| 1130 |
+
"grad_norm": 1.3916367911407932,
|
| 1131 |
+
"learning_rate": 2.7388757438171953e-06,
|
| 1132 |
+
"loss": 0.5294,
|
| 1133 |
+
"step": 1570
|
| 1134 |
+
},
|
| 1135 |
+
{
|
| 1136 |
+
"epoch": 0.6895046912502727,
|
| 1137 |
+
"grad_norm": 1.2821114411807195,
|
| 1138 |
+
"learning_rate": 2.6711970809420327e-06,
|
| 1139 |
+
"loss": 0.5243,
|
| 1140 |
+
"step": 1580
|
| 1141 |
+
},
|
| 1142 |
+
{
|
| 1143 |
+
"epoch": 0.6938686449923631,
|
| 1144 |
+
"grad_norm": 1.2276903910497599,
|
| 1145 |
+
"learning_rate": 2.6040589816185534e-06,
|
| 1146 |
+
"loss": 0.5227,
|
| 1147 |
+
"step": 1590
|
| 1148 |
+
},
|
| 1149 |
+
{
|
| 1150 |
+
"epoch": 0.6982325987344534,
|
| 1151 |
+
"grad_norm": 1.2534508386414063,
|
| 1152 |
+
"learning_rate": 2.5374770299947837e-06,
|
| 1153 |
+
"loss": 0.5336,
|
| 1154 |
+
"step": 1600
|
| 1155 |
+
},
|
| 1156 |
+
{
|
| 1157 |
+
"epoch": 0.7025965524765437,
|
| 1158 |
+
"grad_norm": 1.2952567981586396,
|
| 1159 |
+
"learning_rate": 2.471466681125316e-06,
|
| 1160 |
+
"loss": 0.5242,
|
| 1161 |
+
"step": 1610
|
| 1162 |
+
},
|
| 1163 |
+
{
|
| 1164 |
+
"epoch": 0.706960506218634,
|
| 1165 |
+
"grad_norm": 1.2491075248862247,
|
| 1166 |
+
"learning_rate": 2.4060432573838686e-06,
|
| 1167 |
+
"loss": 0.5229,
|
| 1168 |
+
"step": 1620
|
| 1169 |
+
},
|
| 1170 |
+
{
|
| 1171 |
+
"epoch": 0.7113244599607245,
|
| 1172 |
+
"grad_norm": 1.3070997549733596,
|
| 1173 |
+
"learning_rate": 2.3412219449066316e-06,
|
| 1174 |
+
"loss": 0.5238,
|
| 1175 |
+
"step": 1630
|
| 1176 |
+
},
|
| 1177 |
+
{
|
| 1178 |
+
"epoch": 0.7156884137028148,
|
| 1179 |
+
"grad_norm": 1.2500083040545036,
|
| 1180 |
+
"learning_rate": 2.2770177900672658e-06,
|
| 1181 |
+
"loss": 0.527,
|
| 1182 |
+
"step": 1640
|
| 1183 |
+
},
|
| 1184 |
+
{
|
| 1185 |
+
"epoch": 0.7200523674449051,
|
| 1186 |
+
"grad_norm": 1.2464501526769323,
|
| 1187 |
+
"learning_rate": 2.213445695984318e-06,
|
| 1188 |
+
"loss": 0.5208,
|
| 1189 |
+
"step": 1650
|
| 1190 |
+
},
|
| 1191 |
+
{
|
| 1192 |
+
"epoch": 0.7244163211869954,
|
| 1193 |
+
"grad_norm": 1.2752274285884029,
|
| 1194 |
+
"learning_rate": 2.150520419061896e-06,
|
| 1195 |
+
"loss": 0.5268,
|
| 1196 |
+
"step": 1660
|
| 1197 |
+
},
|
| 1198 |
+
{
|
| 1199 |
+
"epoch": 0.7287802749290857,
|
| 1200 |
+
"grad_norm": 1.243680862493251,
|
| 1201 |
+
"learning_rate": 2.0882565655644054e-06,
|
| 1202 |
+
"loss": 0.5233,
|
| 1203 |
+
"step": 1670
|
| 1204 |
+
},
|
| 1205 |
+
{
|
| 1206 |
+
"epoch": 0.7331442286711761,
|
| 1207 |
+
"grad_norm": 1.6747464378055472,
|
| 1208 |
+
"learning_rate": 2.026668588226133e-06,
|
| 1209 |
+
"loss": 0.5254,
|
| 1210 |
+
"step": 1680
|
| 1211 |
+
},
|
| 1212 |
+
{
|
| 1213 |
+
"epoch": 0.7375081824132664,
|
| 1214 |
+
"grad_norm": 1.2620103056544976,
|
| 1215 |
+
"learning_rate": 1.965770782896455e-06,
|
| 1216 |
+
"loss": 0.5224,
|
| 1217 |
+
"step": 1690
|
| 1218 |
+
},
|
| 1219 |
+
{
|
| 1220 |
+
"epoch": 0.7418721361553567,
|
| 1221 |
+
"grad_norm": 1.3278419822937977,
|
| 1222 |
+
"learning_rate": 1.9055772852214916e-06,
|
| 1223 |
+
"loss": 0.515,
|
| 1224 |
+
"step": 1700
|
| 1225 |
+
},
|
| 1226 |
+
{
|
| 1227 |
+
"epoch": 0.746236089897447,
|
| 1228 |
+
"grad_norm": 1.6987330727891572,
|
| 1229 |
+
"learning_rate": 1.8461020673629172e-06,
|
| 1230 |
+
"loss": 0.5144,
|
| 1231 |
+
"step": 1710
|
| 1232 |
+
},
|
| 1233 |
+
{
|
| 1234 |
+
"epoch": 0.7506000436395375,
|
| 1235 |
+
"grad_norm": 1.3497988296955354,
|
| 1236 |
+
"learning_rate": 1.7873589347547321e-06,
|
| 1237 |
+
"loss": 0.5173,
|
| 1238 |
+
"step": 1720
|
| 1239 |
+
},
|
| 1240 |
+
{
|
| 1241 |
+
"epoch": 0.7549639973816278,
|
| 1242 |
+
"grad_norm": 1.6208371219517643,
|
| 1243 |
+
"learning_rate": 1.729361522898737e-06,
|
| 1244 |
+
"loss": 0.5228,
|
| 1245 |
+
"step": 1730
|
| 1246 |
+
},
|
| 1247 |
+
{
|
| 1248 |
+
"epoch": 0.7593279511237181,
|
| 1249 |
+
"grad_norm": 1.308791373132814,
|
| 1250 |
+
"learning_rate": 1.6721232941994526e-06,
|
| 1251 |
+
"loss": 0.5282,
|
| 1252 |
+
"step": 1740
|
| 1253 |
+
},
|
| 1254 |
+
{
|
| 1255 |
+
"epoch": 0.7636919048658084,
|
| 1256 |
+
"grad_norm": 1.2618118893101176,
|
| 1257 |
+
"learning_rate": 1.6156575348392122e-06,
|
| 1258 |
+
"loss": 0.5208,
|
| 1259 |
+
"step": 1750
|
| 1260 |
+
},
|
| 1261 |
+
{
|
| 1262 |
+
"epoch": 0.7680558586078987,
|
| 1263 |
+
"grad_norm": 1.3104736125525216,
|
| 1264 |
+
"learning_rate": 1.559977351694158e-06,
|
| 1265 |
+
"loss": 0.5208,
|
| 1266 |
+
"step": 1760
|
| 1267 |
+
},
|
| 1268 |
+
{
|
| 1269 |
+
"epoch": 0.7724198123499891,
|
| 1270 |
+
"grad_norm": 1.2487367116120625,
|
| 1271 |
+
"learning_rate": 1.5050956692918739e-06,
|
| 1272 |
+
"loss": 0.5186,
|
| 1273 |
+
"step": 1770
|
| 1274 |
+
},
|
| 1275 |
+
{
|
| 1276 |
+
"epoch": 0.7767837660920794,
|
| 1277 |
+
"grad_norm": 1.156634335046638,
|
| 1278 |
+
"learning_rate": 1.4510252268113263e-06,
|
| 1279 |
+
"loss": 0.5192,
|
| 1280 |
+
"step": 1780
|
| 1281 |
+
},
|
| 1282 |
+
{
|
| 1283 |
+
"epoch": 0.7811477198341698,
|
| 1284 |
+
"grad_norm": 1.3021570425828364,
|
| 1285 |
+
"learning_rate": 1.3977785751258345e-06,
|
| 1286 |
+
"loss": 0.5211,
|
| 1287 |
+
"step": 1790
|
| 1288 |
+
},
|
| 1289 |
+
{
|
| 1290 |
+
"epoch": 0.7855116735762601,
|
| 1291 |
+
"grad_norm": 1.2504588787454711,
|
| 1292 |
+
"learning_rate": 1.34536807388976e-06,
|
| 1293 |
+
"loss": 0.5159,
|
| 1294 |
+
"step": 1800
|
| 1295 |
+
},
|
| 1296 |
+
{
|
| 1297 |
+
"epoch": 0.7898756273183504,
|
| 1298 |
+
"grad_norm": 1.991690391624192,
|
| 1299 |
+
"learning_rate": 1.2938058886695643e-06,
|
| 1300 |
+
"loss": 0.5169,
|
| 1301 |
+
"step": 1810
|
| 1302 |
+
},
|
| 1303 |
+
{
|
| 1304 |
+
"epoch": 0.7942395810604408,
|
| 1305 |
+
"grad_norm": 1.4484577791210265,
|
| 1306 |
+
"learning_rate": 1.2431039881199374e-06,
|
| 1307 |
+
"loss": 0.5246,
|
| 1308 |
+
"step": 1820
|
| 1309 |
+
},
|
| 1310 |
+
{
|
| 1311 |
+
"epoch": 0.7986035348025311,
|
| 1312 |
+
"grad_norm": 1.2031874504717428,
|
| 1313 |
+
"learning_rate": 1.1932741412056187e-06,
|
| 1314 |
+
"loss": 0.5238,
|
| 1315 |
+
"step": 1830
|
| 1316 |
+
},
|
| 1317 |
+
{
|
| 1318 |
+
"epoch": 0.8029674885446214,
|
| 1319 |
+
"grad_norm": 1.4251143516882596,
|
| 1320 |
+
"learning_rate": 1.1443279144695746e-06,
|
| 1321 |
+
"loss": 0.5202,
|
| 1322 |
+
"step": 1840
|
| 1323 |
+
},
|
| 1324 |
+
{
|
| 1325 |
+
"epoch": 0.8073314422867117,
|
| 1326 |
+
"grad_norm": 1.428433930967254,
|
| 1327 |
+
"learning_rate": 1.0962766693481686e-06,
|
| 1328 |
+
"loss": 0.5178,
|
| 1329 |
+
"step": 1850
|
| 1330 |
+
},
|
| 1331 |
+
{
|
| 1332 |
+
"epoch": 0.8116953960288021,
|
| 1333 |
+
"grad_norm": 1.3957444052098604,
|
| 1334 |
+
"learning_rate": 1.049131559533933e-06,
|
| 1335 |
+
"loss": 0.5142,
|
| 1336 |
+
"step": 1860
|
| 1337 |
+
},
|
| 1338 |
+
{
|
| 1339 |
+
"epoch": 0.8160593497708925,
|
| 1340 |
+
"grad_norm": 1.7513113973659105,
|
| 1341 |
+
"learning_rate": 1.002903528386564e-06,
|
| 1342 |
+
"loss": 0.5188,
|
| 1343 |
+
"step": 1870
|
| 1344 |
+
},
|
| 1345 |
+
{
|
| 1346 |
+
"epoch": 0.8204233035129828,
|
| 1347 |
+
"grad_norm": 1.3254734615581885,
|
| 1348 |
+
"learning_rate": 9.576033063927398e-07,
|
| 1349 |
+
"loss": 0.5207,
|
| 1350 |
+
"step": 1880
|
| 1351 |
+
},
|
| 1352 |
+
{
|
| 1353 |
+
"epoch": 0.8247872572550731,
|
| 1354 |
+
"grad_norm": 1.3416379717629452,
|
| 1355 |
+
"learning_rate": 9.132414086753578e-07,
|
| 1356 |
+
"loss": 0.5134,
|
| 1357 |
+
"step": 1890
|
| 1358 |
+
},
|
| 1359 |
+
{
|
| 1360 |
+
"epoch": 0.8291512109971634,
|
| 1361 |
+
"grad_norm": 1.2636084433299684,
|
| 1362 |
+
"learning_rate": 8.698281325527502e-07,
|
| 1363 |
+
"loss": 0.5144,
|
| 1364 |
+
"step": 1900
|
| 1365 |
+
},
|
| 1366 |
+
{
|
| 1367 |
+
"epoch": 0.8335151647392538,
|
| 1368 |
+
"grad_norm": 1.718038484652991,
|
| 1369 |
+
"learning_rate": 8.273735551484613e-07,
|
| 1370 |
+
"loss": 0.5158,
|
| 1371 |
+
"step": 1910
|
| 1372 |
+
},
|
| 1373 |
+
{
|
| 1374 |
+
"epoch": 0.8378791184813441,
|
| 1375 |
+
"grad_norm": 1.365124227466459,
|
| 1376 |
+
"learning_rate": 7.858875310521447e-07,
|
| 1377 |
+
"loss": 0.5116,
|
| 1378 |
+
"step": 1920
|
| 1379 |
+
},
|
| 1380 |
+
{
|
| 1381 |
+
"epoch": 0.8422430722234344,
|
| 1382 |
+
"grad_norm": 1.2857842722903012,
|
| 1383 |
+
"learning_rate": 7.45379690032102e-07,
|
| 1384 |
+
"loss": 0.5213,
|
| 1385 |
+
"step": 1930
|
| 1386 |
+
},
|
| 1387 |
+
{
|
| 1388 |
+
"epoch": 0.8466070259655247,
|
| 1389 |
+
"grad_norm": 1.8949074875975938,
|
| 1390 |
+
"learning_rate": 7.058594348000142e-07,
|
| 1391 |
+
"loss": 0.5126,
|
| 1392 |
+
"step": 1940
|
| 1393 |
+
},
|
| 1394 |
+
{
|
| 1395 |
+
"epoch": 0.8509709797076151,
|
| 1396 |
+
"grad_norm": 2.0508297274530425,
|
| 1397 |
+
"learning_rate": 6.673359388283796e-07,
|
| 1398 |
+
"loss": 0.5118,
|
| 1399 |
+
"step": 1950
|
| 1400 |
+
},
|
| 1401 |
+
{
|
| 1402 |
+
"epoch": 0.8553349334497055,
|
| 1403 |
+
"grad_norm": 1.2982410941631513,
|
| 1404 |
+
"learning_rate": 6.29818144221161e-07,
|
| 1405 |
+
"loss": 0.5256,
|
| 1406 |
+
"step": 1960
|
| 1407 |
+
},
|
| 1408 |
+
{
|
| 1409 |
+
"epoch": 0.8596988871917958,
|
| 1410 |
+
"grad_norm": 1.3881080528727965,
|
| 1411 |
+
"learning_rate": 5.933147596381295e-07,
|
| 1412 |
+
"loss": 0.5178,
|
| 1413 |
+
"step": 1970
|
| 1414 |
+
},
|
| 1415 |
+
{
|
| 1416 |
+
"epoch": 0.8640628409338861,
|
| 1417 |
+
"grad_norm": 1.2689567204311927,
|
| 1418 |
+
"learning_rate": 5.578342582734153e-07,
|
| 1419 |
+
"loss": 0.5106,
|
| 1420 |
+
"step": 1980
|
| 1421 |
+
},
|
| 1422 |
+
{
|
| 1423 |
+
"epoch": 0.8684267946759764,
|
| 1424 |
+
"grad_norm": 1.3514399003622013,
|
| 1425 |
+
"learning_rate": 5.233848758886945e-07,
|
| 1426 |
+
"loss": 0.515,
|
| 1427 |
+
"step": 1990
|
| 1428 |
+
},
|
| 1429 |
+
{
|
| 1430 |
+
"epoch": 0.8727907484180668,
|
| 1431 |
+
"grad_norm": 1.8878476820927994,
|
| 1432 |
+
"learning_rate": 4.899746089015006e-07,
|
| 1433 |
+
"loss": 0.5075,
|
| 1434 |
+
"step": 2000
|
| 1435 |
+
},
|
| 1436 |
+
{
|
| 1437 |
+
"epoch": 0.8727907484180668,
|
| 1438 |
+
"eval_loss": 0.5055009722709656,
|
| 1439 |
+
"eval_runtime": 68.9834,
|
| 1440 |
+
"eval_samples_per_second": 53.68,
|
| 1441 |
+
"eval_steps_per_second": 3.363,
|
| 1442 |
+
"step": 2000
|
| 1443 |
+
},
|
| 1444 |
+
{
|
| 1445 |
+
"epoch": 0.8771547021601571,
|
| 1446 |
+
"grad_norm": 1.1864343347355735,
|
| 1447 |
+
"learning_rate": 4.57611212529091e-07,
|
| 1448 |
+
"loss": 0.5118,
|
| 1449 |
+
"step": 2010
|
| 1450 |
+
},
|
| 1451 |
+
{
|
| 1452 |
+
"epoch": 0.8815186559022474,
|
| 1453 |
+
"grad_norm": 1.3391728742114728,
|
| 1454 |
+
"learning_rate": 4.263021989882965e-07,
|
| 1455 |
+
"loss": 0.5209,
|
| 1456 |
+
"step": 2020
|
| 1457 |
+
},
|
| 1458 |
+
{
|
| 1459 |
+
"epoch": 0.8858826096443377,
|
| 1460 |
+
"grad_norm": 1.265995062918622,
|
| 1461 |
+
"learning_rate": 3.9605483575178517e-07,
|
| 1462 |
+
"loss": 0.5172,
|
| 1463 |
+
"step": 2030
|
| 1464 |
+
},
|
| 1465 |
+
{
|
| 1466 |
+
"epoch": 0.8902465633864282,
|
| 1467 |
+
"grad_norm": 1.3612996127522512,
|
| 1468 |
+
"learning_rate": 3.6687614386112403e-07,
|
| 1469 |
+
"loss": 0.51,
|
| 1470 |
+
"step": 2040
|
| 1471 |
+
},
|
| 1472 |
+
{
|
| 1473 |
+
"epoch": 0.8946105171285185,
|
| 1474 |
+
"grad_norm": 1.1822823920287409,
|
| 1475 |
+
"learning_rate": 3.38772896297056e-07,
|
| 1476 |
+
"loss": 0.512,
|
| 1477 |
+
"step": 2050
|
| 1478 |
+
},
|
| 1479 |
+
{
|
| 1480 |
+
"epoch": 0.8989744708706088,
|
| 1481 |
+
"grad_norm": 1.4239619500028629,
|
| 1482 |
+
"learning_rate": 3.117516164073459e-07,
|
| 1483 |
+
"loss": 0.519,
|
| 1484 |
+
"step": 2060
|
| 1485 |
+
},
|
| 1486 |
+
{
|
| 1487 |
+
"epoch": 0.9033384246126991,
|
| 1488 |
+
"grad_norm": 1.3503881714270254,
|
| 1489 |
+
"learning_rate": 2.858185763925764e-07,
|
| 1490 |
+
"loss": 0.5104,
|
| 1491 |
+
"step": 2070
|
| 1492 |
+
},
|
| 1493 |
+
{
|
| 1494 |
+
"epoch": 0.9077023783547894,
|
| 1495 |
+
"grad_norm": 1.3564880256851914,
|
| 1496 |
+
"learning_rate": 2.6097979585024193e-07,
|
| 1497 |
+
"loss": 0.5136,
|
| 1498 |
+
"step": 2080
|
| 1499 |
+
},
|
| 1500 |
+
{
|
| 1501 |
+
"epoch": 0.9120663320968798,
|
| 1502 |
+
"grad_norm": 1.2482713788944904,
|
| 1503 |
+
"learning_rate": 2.3724104037747553e-07,
|
| 1504 |
+
"loss": 0.5085,
|
| 1505 |
+
"step": 2090
|
| 1506 |
+
},
|
| 1507 |
+
{
|
| 1508 |
+
"epoch": 0.9164302858389701,
|
| 1509 |
+
"grad_norm": 1.4746577210230283,
|
| 1510 |
+
"learning_rate": 2.146078202327284e-07,
|
| 1511 |
+
"loss": 0.5159,
|
| 1512 |
+
"step": 2100
|
| 1513 |
+
},
|
| 1514 |
+
{
|
| 1515 |
+
"epoch": 0.9207942395810604,
|
| 1516 |
+
"grad_norm": 2.19277205698307,
|
| 1517 |
+
"learning_rate": 1.9308538905673135e-07,
|
| 1518 |
+
"loss": 0.5118,
|
| 1519 |
+
"step": 2110
|
| 1520 |
+
},
|
| 1521 |
+
{
|
| 1522 |
+
"epoch": 0.9251581933231507,
|
| 1523 |
+
"grad_norm": 1.3172149163534492,
|
| 1524 |
+
"learning_rate": 1.7267874265301187e-07,
|
| 1525 |
+
"loss": 0.5139,
|
| 1526 |
+
"step": 2120
|
| 1527 |
+
},
|
| 1528 |
+
{
|
| 1529 |
+
"epoch": 0.9295221470652411,
|
| 1530 |
+
"grad_norm": 1.217984783068752,
|
| 1531 |
+
"learning_rate": 1.533926178282641e-07,
|
| 1532 |
+
"loss": 0.5084,
|
| 1533 |
+
"step": 2130
|
| 1534 |
+
},
|
| 1535 |
+
{
|
| 1536 |
+
"epoch": 0.9338861008073315,
|
| 1537 |
+
"grad_norm": 1.3602984814635521,
|
| 1538 |
+
"learning_rate": 1.3523149129283987e-07,
|
| 1539 |
+
"loss": 0.5222,
|
| 1540 |
+
"step": 2140
|
| 1541 |
+
},
|
| 1542 |
+
{
|
| 1543 |
+
"epoch": 0.9382500545494218,
|
| 1544 |
+
"grad_norm": 1.3460153750821495,
|
| 1545 |
+
"learning_rate": 1.1819957862160835e-07,
|
| 1546 |
+
"loss": 0.5069,
|
| 1547 |
+
"step": 2150
|
| 1548 |
+
},
|
| 1549 |
+
{
|
| 1550 |
+
"epoch": 0.9426140082915121,
|
| 1551 |
+
"grad_norm": 1.4510294571460467,
|
| 1552 |
+
"learning_rate": 1.0230083327543661e-07,
|
| 1553 |
+
"loss": 0.5142,
|
| 1554 |
+
"step": 2160
|
| 1555 |
+
},
|
| 1556 |
+
{
|
| 1557 |
+
"epoch": 0.9469779620336024,
|
| 1558 |
+
"grad_norm": 1.396143496017602,
|
| 1559 |
+
"learning_rate": 8.753894568350573e-08,
|
| 1560 |
+
"loss": 0.5155,
|
| 1561 |
+
"step": 2170
|
| 1562 |
+
},
|
| 1563 |
+
{
|
| 1564 |
+
"epoch": 0.9513419157756928,
|
| 1565 |
+
"grad_norm": 1.437628267014867,
|
| 1566 |
+
"learning_rate": 7.391734238668846e-08,
|
| 1567 |
+
"loss": 0.5074,
|
| 1568 |
+
"step": 2180
|
| 1569 |
+
},
|
| 1570 |
+
{
|
| 1571 |
+
"epoch": 0.9557058695177831,
|
| 1572 |
+
"grad_norm": 1.3148582495813304,
|
| 1573 |
+
"learning_rate": 6.143918524217696e-08,
|
| 1574 |
+
"loss": 0.5176,
|
| 1575 |
+
"step": 2190
|
| 1576 |
+
},
|
| 1577 |
+
{
|
| 1578 |
+
"epoch": 0.9600698232598734,
|
| 1579 |
+
"grad_norm": 1.267741565404716,
|
| 1580 |
+
"learning_rate": 5.01073706895483e-08,
|
| 1581 |
+
"loss": 0.5137,
|
| 1582 |
+
"step": 2200
|
| 1583 |
+
},
|
| 1584 |
+
{
|
| 1585 |
+
"epoch": 0.9644337770019638,
|
| 1586 |
+
"grad_norm": 1.2859440475396895,
|
| 1587 |
+
"learning_rate": 3.992452907844502e-08,
|
| 1588 |
+
"loss": 0.5142,
|
| 1589 |
+
"step": 2210
|
| 1590 |
+
},
|
| 1591 |
+
{
|
| 1592 |
+
"epoch": 0.9687977307440541,
|
| 1593 |
+
"grad_norm": 1.2296422531635047,
|
| 1594 |
+
"learning_rate": 3.08930240580102e-08,
|
| 1595 |
+
"loss": 0.5025,
|
| 1596 |
+
"step": 2220
|
| 1597 |
+
},
|
| 1598 |
+
{
|
| 1599 |
+
"epoch": 0.9731616844861445,
|
| 1600 |
+
"grad_norm": 1.3046489064561737,
|
| 1601 |
+
"learning_rate": 2.3014952028240223e-08,
|
| 1602 |
+
"loss": 0.5138,
|
| 1603 |
+
"step": 2230
|
| 1604 |
+
},
|
| 1605 |
+
{
|
| 1606 |
+
"epoch": 0.9775256382282348,
|
| 1607 |
+
"grad_norm": 1.238897807436414,
|
| 1608 |
+
"learning_rate": 1.6292141653366232e-08,
|
| 1609 |
+
"loss": 0.5067,
|
| 1610 |
+
"step": 2240
|
| 1611 |
+
},
|
| 1612 |
+
{
|
| 1613 |
+
"epoch": 0.9818895919703251,
|
| 1614 |
+
"grad_norm": 1.2689478765861664,
|
| 1615 |
+
"learning_rate": 1.0726153437379816e-08,
|
| 1616 |
+
"loss": 0.5188,
|
| 1617 |
+
"step": 2250
|
| 1618 |
+
},
|
| 1619 |
+
{
|
| 1620 |
+
"epoch": 0.9862535457124154,
|
| 1621 |
+
"grad_norm": 2.492246786468264,
|
| 1622 |
+
"learning_rate": 6.3182793618110634e-09,
|
| 1623 |
+
"loss": 0.5151,
|
| 1624 |
+
"step": 2260
|
| 1625 |
+
},
|
| 1626 |
+
{
|
| 1627 |
+
"epoch": 0.9906174994545058,
|
| 1628 |
+
"grad_norm": 1.2722668029711148,
|
| 1629 |
+
"learning_rate": 3.0695425858329187e-09,
|
| 1630 |
+
"loss": 0.5197,
|
| 1631 |
+
"step": 2270
|
| 1632 |
+
},
|
| 1633 |
+
{
|
| 1634 |
+
"epoch": 0.9949814531965961,
|
| 1635 |
+
"grad_norm": 1.3363964992431479,
|
| 1636 |
+
"learning_rate": 9.806972087605949e-10,
|
| 1637 |
+
"loss": 0.5223,
|
| 1638 |
+
"step": 2280
|
| 1639 |
+
},
|
| 1640 |
+
{
|
| 1641 |
+
"epoch": 0.9993454069386865,
|
| 1642 |
+
"grad_norm": 1.5575122083398747,
|
| 1643 |
+
"learning_rate": 5.222809501492787e-11,
|
| 1644 |
+
"loss": 0.5178,
|
| 1645 |
+
"step": 2290
|
| 1646 |
+
},
|
| 1647 |
+
{
|
| 1648 |
+
"epoch": 1.0,
|
| 1649 |
+
"step": 2292,
|
| 1650 |
+
"total_flos": 2450977789313024.0,
|
| 1651 |
+
"train_loss": 0.5714389552828737,
|
| 1652 |
+
"train_runtime": 14627.8115,
|
| 1653 |
+
"train_samples_per_second": 25.06,
|
| 1654 |
+
"train_steps_per_second": 0.157
|
| 1655 |
+
}
|
| 1656 |
+
],
|
| 1657 |
+
"logging_steps": 10,
|
| 1658 |
+
"max_steps": 2292,
|
| 1659 |
+
"num_input_tokens_seen": 0,
|
| 1660 |
+
"num_train_epochs": 1,
|
| 1661 |
+
"save_steps": 200,
|
| 1662 |
+
"stateful_callbacks": {
|
| 1663 |
+
"TrainerControl": {
|
| 1664 |
+
"args": {
|
| 1665 |
+
"should_epoch_stop": false,
|
| 1666 |
+
"should_evaluate": false,
|
| 1667 |
+
"should_log": false,
|
| 1668 |
+
"should_save": true,
|
| 1669 |
+
"should_training_stop": true
|
| 1670 |
+
},
|
| 1671 |
+
"attributes": {}
|
| 1672 |
+
}
|
| 1673 |
+
},
|
| 1674 |
+
"total_flos": 2450977789313024.0,
|
| 1675 |
+
"train_batch_size": 10,
|
| 1676 |
+
"trial_name": null,
|
| 1677 |
+
"trial_params": null
|
| 1678 |
+
}
|
training_args.bin
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:abc257a329b9cd885b1f9cc2ceb9276c6ce119c98357b543a5e79912544658fa
|
| 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
|
|
|