Delete folder llama_factory with huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- llama_factory/v2-20241220-pos/README.md +0 -62
- llama_factory/v2-20241220-pos/adapter_config.json +0 -26
- llama_factory/v2-20241220-pos/added_tokens.json +0 -16
- llama_factory/v2-20241220-pos/all_results.json +0 -8
- llama_factory/v2-20241220-pos/chat_template.json +0 -3
- llama_factory/v2-20241220-pos/merges.txt +0 -0
- llama_factory/v2-20241220-pos/preprocessor_config.json +0 -29
- llama_factory/v2-20241220-pos/special_tokens_map.json +0 -31
- llama_factory/v2-20241220-pos/tokenizer_config.json +0 -144
- llama_factory/v2-20241220-pos/train_results.json +0 -8
- llama_factory/v2-20241220-pos/trainer_log.jsonl +0 -13
- llama_factory/v2-20241220-pos/trainer_state.json +0 -126
- llama_factory/v2-20241220-pos/training_loss.png +0 -0
- llama_factory/v2-20241220-pos/vocab.json +0 -0
- llama_factory/v2-20241220/README.md +0 -62
- llama_factory/v2-20241220/adapter_config.json +0 -26
- llama_factory/v2-20241220/added_tokens.json +0 -16
- llama_factory/v2-20241220/all_results.json +0 -8
- llama_factory/v2-20241220/chat_template.json +0 -3
- llama_factory/v2-20241220/merges.txt +0 -0
- llama_factory/v2-20241220/preprocessor_config.json +0 -29
- llama_factory/v2-20241220/special_tokens_map.json +0 -31
- llama_factory/v2-20241220/tokenizer_config.json +0 -144
- llama_factory/v2-20241220/train_results.json +0 -8
- llama_factory/v2-20241220/trainer_log.jsonl +0 -19
- llama_factory/v2-20241220/trainer_state.json +0 -168
- llama_factory/v2-20241220/training_loss.png +0 -0
- llama_factory/v2-20241220/vocab.json +0 -0
- llama_factory/v3-20241225-1_10/README.md +0 -62
- llama_factory/v3-20241225-1_10/adapter_config.json +0 -26
- llama_factory/v3-20241225-1_10/added_tokens.json +0 -16
- llama_factory/v3-20241225-1_10/all_results.json +0 -8
- llama_factory/v3-20241225-1_10/chat_template.json +0 -3
- llama_factory/v3-20241225-1_10/merges.txt +0 -0
- llama_factory/v3-20241225-1_10/preprocessor_config.json +0 -29
- llama_factory/v3-20241225-1_10/special_tokens_map.json +0 -31
- llama_factory/v3-20241225-1_10/tokenizer_config.json +0 -144
- llama_factory/v3-20241225-1_10/train_results.json +0 -8
- llama_factory/v3-20241225-1_10/trainer_log.jsonl +0 -82
- llama_factory/v3-20241225-1_10/trainer_state.json +0 -609
- llama_factory/v3-20241225-1_10/training_loss.png +0 -0
- llama_factory/v3-20241225-1_10/vocab.json +0 -0
- llama_factory/v3-20241225-1_5/README.md +0 -62
- llama_factory/v3-20241225-1_5/adapter_config.json +0 -26
- llama_factory/v3-20241225-1_5/added_tokens.json +0 -16
- llama_factory/v3-20241225-1_5/all_results.json +0 -8
- llama_factory/v3-20241225-1_5/chat_template.json +0 -3
- llama_factory/v3-20241225-1_5/merges.txt +0 -0
- llama_factory/v3-20241225-1_5/preprocessor_config.json +0 -29
- llama_factory/v3-20241225-1_5/special_tokens_map.json +0 -31
llama_factory/v2-20241220-pos/README.md
DELETED
|
@@ -1,62 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: peft
|
| 3 |
-
license: other
|
| 4 |
-
base_model: /disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct
|
| 5 |
-
tags:
|
| 6 |
-
- llama-factory
|
| 7 |
-
- lora
|
| 8 |
-
- generated_from_trainer
|
| 9 |
-
model-index:
|
| 10 |
-
- name: v2-20241220-pos
|
| 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 |
-
# v2-20241220-pos
|
| 18 |
-
|
| 19 |
-
This model is a fine-tuned version of [/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct](https://huggingface.co//disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct) on the M^2RAR-20241220-MLLM-Pos dataset.
|
| 20 |
-
|
| 21 |
-
## Model description
|
| 22 |
-
|
| 23 |
-
More information needed
|
| 24 |
-
|
| 25 |
-
## Intended uses & limitations
|
| 26 |
-
|
| 27 |
-
More information needed
|
| 28 |
-
|
| 29 |
-
## Training and evaluation data
|
| 30 |
-
|
| 31 |
-
More information needed
|
| 32 |
-
|
| 33 |
-
## Training procedure
|
| 34 |
-
|
| 35 |
-
### Training hyperparameters
|
| 36 |
-
|
| 37 |
-
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate: 0.0001
|
| 39 |
-
- train_batch_size: 2
|
| 40 |
-
- eval_batch_size: 8
|
| 41 |
-
- seed: 42
|
| 42 |
-
- distributed_type: multi-GPU
|
| 43 |
-
- num_devices: 2
|
| 44 |
-
- gradient_accumulation_steps: 16
|
| 45 |
-
- total_train_batch_size: 64
|
| 46 |
-
- total_eval_batch_size: 16
|
| 47 |
-
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
-
- lr_scheduler_type: cosine
|
| 49 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
-
- num_epochs: 3.0
|
| 51 |
-
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
### Framework versions
|
| 57 |
-
|
| 58 |
-
- PEFT 0.12.0
|
| 59 |
-
- Transformers 4.46.1
|
| 60 |
-
- Pytorch 2.3.1+cu121
|
| 61 |
-
- Datasets 3.1.0
|
| 62 |
-
- Tokenizers 0.20.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/adapter_config.json
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"fan_in_fan_out": false,
|
| 7 |
-
"inference_mode": true,
|
| 8 |
-
"init_lora_weights": true,
|
| 9 |
-
"layer_replication": null,
|
| 10 |
-
"layers_pattern": null,
|
| 11 |
-
"layers_to_transform": null,
|
| 12 |
-
"loftq_config": {},
|
| 13 |
-
"lora_alpha": 256,
|
| 14 |
-
"lora_dropout": 0.0,
|
| 15 |
-
"megatron_config": null,
|
| 16 |
-
"megatron_core": "megatron.core",
|
| 17 |
-
"modules_to_save": null,
|
| 18 |
-
"peft_type": "LORA",
|
| 19 |
-
"r": 128,
|
| 20 |
-
"rank_pattern": {},
|
| 21 |
-
"revision": null,
|
| 22 |
-
"target_modules": "^(?!.*visual).*(?:q_proj|down_proj|v_proj|o_proj|k_proj|up_proj|gate_proj).*",
|
| 23 |
-
"task_type": "CAUSAL_LM",
|
| 24 |
-
"use_dora": false,
|
| 25 |
-
"use_rslora": false
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/added_tokens.json
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<|box_end|>": 151649,
|
| 3 |
-
"<|box_start|>": 151648,
|
| 4 |
-
"<|endoftext|>": 151643,
|
| 5 |
-
"<|im_end|>": 151645,
|
| 6 |
-
"<|im_start|>": 151644,
|
| 7 |
-
"<|image_pad|>": 151655,
|
| 8 |
-
"<|object_ref_end|>": 151647,
|
| 9 |
-
"<|object_ref_start|>": 151646,
|
| 10 |
-
"<|quad_end|>": 151651,
|
| 11 |
-
"<|quad_start|>": 151650,
|
| 12 |
-
"<|video_pad|>": 151656,
|
| 13 |
-
"<|vision_end|>": 151653,
|
| 14 |
-
"<|vision_pad|>": 151654,
|
| 15 |
-
"<|vision_start|>": 151652
|
| 16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/all_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.56,
|
| 3 |
-
"total_flos": 4.173594118670254e+17,
|
| 4 |
-
"train_loss": 1.6055979132652283,
|
| 5 |
-
"train_runtime": 1821.5091,
|
| 6 |
-
"train_samples_per_second": 0.494,
|
| 7 |
-
"train_steps_per_second": 0.007
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/chat_template.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama_factory/v2-20241220-pos/preprocessor_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_convert_rgb": true,
|
| 3 |
-
"do_normalize": true,
|
| 4 |
-
"do_rescale": true,
|
| 5 |
-
"do_resize": true,
|
| 6 |
-
"image_mean": [
|
| 7 |
-
0.48145466,
|
| 8 |
-
0.4578275,
|
| 9 |
-
0.40821073
|
| 10 |
-
],
|
| 11 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
-
"image_std": [
|
| 13 |
-
0.26862954,
|
| 14 |
-
0.26130258,
|
| 15 |
-
0.27577711
|
| 16 |
-
],
|
| 17 |
-
"max_pixels": 12845056,
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"min_pixels": 3136,
|
| 20 |
-
"patch_size": 14,
|
| 21 |
-
"processor_class": "Qwen2VLProcessor",
|
| 22 |
-
"resample": 3,
|
| 23 |
-
"rescale_factor": 0.00392156862745098,
|
| 24 |
-
"size": {
|
| 25 |
-
"max_pixels": 12845056,
|
| 26 |
-
"min_pixels": 3136
|
| 27 |
-
},
|
| 28 |
-
"temporal_patch_size": 2
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/tokenizer_config.json
DELETED
|
@@ -1,144 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"151643": {
|
| 5 |
-
"content": "<|endoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"151644": {
|
| 13 |
-
"content": "<|im_start|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"151645": {
|
| 21 |
-
"content": "<|im_end|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"151646": {
|
| 29 |
-
"content": "<|object_ref_start|>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"151647": {
|
| 37 |
-
"content": "<|object_ref_end|>",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"151648": {
|
| 45 |
-
"content": "<|box_start|>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"151649": {
|
| 53 |
-
"content": "<|box_end|>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"151650": {
|
| 61 |
-
"content": "<|quad_start|>",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"151651": {
|
| 69 |
-
"content": "<|quad_end|>",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"151652": {
|
| 77 |
-
"content": "<|vision_start|>",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": false,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": true
|
| 83 |
-
},
|
| 84 |
-
"151653": {
|
| 85 |
-
"content": "<|vision_end|>",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"151654": {
|
| 93 |
-
"content": "<|vision_pad|>",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"151655": {
|
| 101 |
-
"content": "<|image_pad|>",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"151656": {
|
| 109 |
-
"content": "<|video_pad|>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
}
|
| 116 |
-
},
|
| 117 |
-
"additional_special_tokens": [
|
| 118 |
-
"<|im_start|>",
|
| 119 |
-
"<|im_end|>",
|
| 120 |
-
"<|object_ref_start|>",
|
| 121 |
-
"<|object_ref_end|>",
|
| 122 |
-
"<|box_start|>",
|
| 123 |
-
"<|box_end|>",
|
| 124 |
-
"<|quad_start|>",
|
| 125 |
-
"<|quad_end|>",
|
| 126 |
-
"<|vision_start|>",
|
| 127 |
-
"<|vision_end|>",
|
| 128 |
-
"<|vision_pad|>",
|
| 129 |
-
"<|image_pad|>",
|
| 130 |
-
"<|video_pad|>"
|
| 131 |
-
],
|
| 132 |
-
"bos_token": null,
|
| 133 |
-
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 134 |
-
"clean_up_tokenization_spaces": false,
|
| 135 |
-
"eos_token": "<|im_end|>",
|
| 136 |
-
"errors": "replace",
|
| 137 |
-
"model_max_length": 32768,
|
| 138 |
-
"pad_token": "<|endoftext|>",
|
| 139 |
-
"padding_side": "right",
|
| 140 |
-
"processor_class": "Qwen2VLProcessor",
|
| 141 |
-
"split_special_tokens": false,
|
| 142 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 143 |
-
"unk_token": null
|
| 144 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/train_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.56,
|
| 3 |
-
"total_flos": 4.173594118670254e+17,
|
| 4 |
-
"train_loss": 1.6055979132652283,
|
| 5 |
-
"train_runtime": 1821.5091,
|
| 6 |
-
"train_samples_per_second": 0.494,
|
| 7 |
-
"train_steps_per_second": 0.007
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/trainer_log.jsonl
DELETED
|
@@ -1,13 +0,0 @@
|
|
| 1 |
-
{"current_steps": 1, "total_steps": 12, "loss": 1.7861, "lr": 5e-05, "epoch": 0.21333333333333335, "percentage": 8.33, "elapsed_time": "0:02:26", "remaining_time": "0:26:52"}
|
| 2 |
-
{"current_steps": 2, "total_steps": 12, "loss": 1.7271, "lr": 0.0001, "epoch": 0.4266666666666667, "percentage": 16.67, "elapsed_time": "0:05:12", "remaining_time": "0:26:04"}
|
| 3 |
-
{"current_steps": 3, "total_steps": 12, "loss": 1.6749, "lr": 9.755282581475769e-05, "epoch": 0.64, "percentage": 25.0, "elapsed_time": "0:07:38", "remaining_time": "0:22:55"}
|
| 4 |
-
{"current_steps": 4, "total_steps": 12, "loss": 1.6561, "lr": 9.045084971874738e-05, "epoch": 0.8533333333333334, "percentage": 33.33, "elapsed_time": "0:10:17", "remaining_time": "0:20:35"}
|
| 5 |
-
{"current_steps": 5, "total_steps": 12, "loss": 1.6393, "lr": 7.938926261462366e-05, "epoch": 1.0666666666666667, "percentage": 41.67, "elapsed_time": "0:12:23", "remaining_time": "0:17:20"}
|
| 6 |
-
{"current_steps": 6, "total_steps": 12, "loss": 1.5852, "lr": 6.545084971874738e-05, "epoch": 1.28, "percentage": 50.0, "elapsed_time": "0:14:45", "remaining_time": "0:14:45"}
|
| 7 |
-
{"current_steps": 7, "total_steps": 12, "loss": 1.5696, "lr": 5e-05, "epoch": 1.4933333333333334, "percentage": 58.33, "elapsed_time": "0:17:15", "remaining_time": "0:12:19"}
|
| 8 |
-
{"current_steps": 8, "total_steps": 12, "loss": 1.5286, "lr": 3.4549150281252636e-05, "epoch": 1.7066666666666666, "percentage": 66.67, "elapsed_time": "0:19:31", "remaining_time": "0:09:45"}
|
| 9 |
-
{"current_steps": 9, "total_steps": 12, "loss": 1.5246, "lr": 2.061073738537635e-05, "epoch": 1.92, "percentage": 75.0, "elapsed_time": "0:21:51", "remaining_time": "0:07:17"}
|
| 10 |
-
{"current_steps": 10, "total_steps": 12, "loss": 1.5174, "lr": 9.549150281252633e-06, "epoch": 2.1333333333333333, "percentage": 83.33, "elapsed_time": "0:24:56", "remaining_time": "0:04:59"}
|
| 11 |
-
{"current_steps": 11, "total_steps": 12, "loss": 1.525, "lr": 2.4471741852423237e-06, "epoch": 2.3466666666666667, "percentage": 91.67, "elapsed_time": "0:26:57", "remaining_time": "0:02:27"}
|
| 12 |
-
{"current_steps": 12, "total_steps": 12, "loss": 1.5334, "lr": 0.0, "epoch": 2.56, "percentage": 100.0, "elapsed_time": "0:29:49", "remaining_time": "0:00:00"}
|
| 13 |
-
{"current_steps": 12, "total_steps": 12, "epoch": 2.56, "percentage": 100.0, "elapsed_time": "0:30:21", "remaining_time": "0:00:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/trainer_state.json
DELETED
|
@@ -1,126 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.56,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 12,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.21333333333333335,
|
| 13 |
-
"grad_norm": 0.5428073406219482,
|
| 14 |
-
"learning_rate": 5e-05,
|
| 15 |
-
"loss": 1.7861,
|
| 16 |
-
"step": 1
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.4266666666666667,
|
| 20 |
-
"grad_norm": 0.5242983102798462,
|
| 21 |
-
"learning_rate": 0.0001,
|
| 22 |
-
"loss": 1.7271,
|
| 23 |
-
"step": 2
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.64,
|
| 27 |
-
"grad_norm": 0.36863189935684204,
|
| 28 |
-
"learning_rate": 9.755282581475769e-05,
|
| 29 |
-
"loss": 1.6749,
|
| 30 |
-
"step": 3
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.8533333333333334,
|
| 34 |
-
"grad_norm": 0.4955863058567047,
|
| 35 |
-
"learning_rate": 9.045084971874738e-05,
|
| 36 |
-
"loss": 1.6561,
|
| 37 |
-
"step": 4
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 1.0666666666666667,
|
| 41 |
-
"grad_norm": 0.3081843852996826,
|
| 42 |
-
"learning_rate": 7.938926261462366e-05,
|
| 43 |
-
"loss": 1.6393,
|
| 44 |
-
"step": 5
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 1.28,
|
| 48 |
-
"grad_norm": 0.23544219136238098,
|
| 49 |
-
"learning_rate": 6.545084971874738e-05,
|
| 50 |
-
"loss": 1.5852,
|
| 51 |
-
"step": 6
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 1.4933333333333334,
|
| 55 |
-
"grad_norm": 0.22464187443256378,
|
| 56 |
-
"learning_rate": 5e-05,
|
| 57 |
-
"loss": 1.5696,
|
| 58 |
-
"step": 7
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 1.7066666666666666,
|
| 62 |
-
"grad_norm": 0.188608318567276,
|
| 63 |
-
"learning_rate": 3.4549150281252636e-05,
|
| 64 |
-
"loss": 1.5286,
|
| 65 |
-
"step": 8
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 1.92,
|
| 69 |
-
"grad_norm": 0.1828916221857071,
|
| 70 |
-
"learning_rate": 2.061073738537635e-05,
|
| 71 |
-
"loss": 1.5246,
|
| 72 |
-
"step": 9
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 2.1333333333333333,
|
| 76 |
-
"grad_norm": 0.18487173318862915,
|
| 77 |
-
"learning_rate": 9.549150281252633e-06,
|
| 78 |
-
"loss": 1.5174,
|
| 79 |
-
"step": 10
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 2.3466666666666667,
|
| 83 |
-
"grad_norm": 0.17777486145496368,
|
| 84 |
-
"learning_rate": 2.4471741852423237e-06,
|
| 85 |
-
"loss": 1.525,
|
| 86 |
-
"step": 11
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 2.56,
|
| 90 |
-
"grad_norm": 0.1764741837978363,
|
| 91 |
-
"learning_rate": 0.0,
|
| 92 |
-
"loss": 1.5334,
|
| 93 |
-
"step": 12
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 2.56,
|
| 97 |
-
"step": 12,
|
| 98 |
-
"total_flos": 4.173594118670254e+17,
|
| 99 |
-
"train_loss": 1.6055979132652283,
|
| 100 |
-
"train_runtime": 1821.5091,
|
| 101 |
-
"train_samples_per_second": 0.494,
|
| 102 |
-
"train_steps_per_second": 0.007
|
| 103 |
-
}
|
| 104 |
-
],
|
| 105 |
-
"logging_steps": 1,
|
| 106 |
-
"max_steps": 12,
|
| 107 |
-
"num_input_tokens_seen": 0,
|
| 108 |
-
"num_train_epochs": 3,
|
| 109 |
-
"save_steps": 200,
|
| 110 |
-
"stateful_callbacks": {
|
| 111 |
-
"TrainerControl": {
|
| 112 |
-
"args": {
|
| 113 |
-
"should_epoch_stop": false,
|
| 114 |
-
"should_evaluate": false,
|
| 115 |
-
"should_log": false,
|
| 116 |
-
"should_save": true,
|
| 117 |
-
"should_training_stop": true
|
| 118 |
-
},
|
| 119 |
-
"attributes": {}
|
| 120 |
-
}
|
| 121 |
-
},
|
| 122 |
-
"total_flos": 4.173594118670254e+17,
|
| 123 |
-
"train_batch_size": 2,
|
| 124 |
-
"trial_name": null,
|
| 125 |
-
"trial_params": null
|
| 126 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220-pos/training_loss.png
DELETED
|
Binary file (37.6 kB)
|
|
|
llama_factory/v2-20241220-pos/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama_factory/v2-20241220/README.md
DELETED
|
@@ -1,62 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: peft
|
| 3 |
-
license: other
|
| 4 |
-
base_model: /disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct
|
| 5 |
-
tags:
|
| 6 |
-
- llama-factory
|
| 7 |
-
- lora
|
| 8 |
-
- generated_from_trainer
|
| 9 |
-
model-index:
|
| 10 |
-
- name: llama_factory
|
| 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 |
-
# llama_factory
|
| 18 |
-
|
| 19 |
-
This model is a fine-tuned version of [/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct](https://huggingface.co//disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct) on the M^2RAR-20241220-MLLM dataset.
|
| 20 |
-
|
| 21 |
-
## Model description
|
| 22 |
-
|
| 23 |
-
More information needed
|
| 24 |
-
|
| 25 |
-
## Intended uses & limitations
|
| 26 |
-
|
| 27 |
-
More information needed
|
| 28 |
-
|
| 29 |
-
## Training and evaluation data
|
| 30 |
-
|
| 31 |
-
More information needed
|
| 32 |
-
|
| 33 |
-
## Training procedure
|
| 34 |
-
|
| 35 |
-
### Training hyperparameters
|
| 36 |
-
|
| 37 |
-
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate: 0.0001
|
| 39 |
-
- train_batch_size: 2
|
| 40 |
-
- eval_batch_size: 8
|
| 41 |
-
- seed: 42
|
| 42 |
-
- distributed_type: multi-GPU
|
| 43 |
-
- num_devices: 2
|
| 44 |
-
- gradient_accumulation_steps: 16
|
| 45 |
-
- total_train_batch_size: 64
|
| 46 |
-
- total_eval_batch_size: 16
|
| 47 |
-
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
-
- lr_scheduler_type: cosine
|
| 49 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
-
- num_epochs: 3.0
|
| 51 |
-
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
### Framework versions
|
| 57 |
-
|
| 58 |
-
- PEFT 0.12.0
|
| 59 |
-
- Transformers 4.46.1
|
| 60 |
-
- Pytorch 2.3.1+cu121
|
| 61 |
-
- Datasets 3.1.0
|
| 62 |
-
- Tokenizers 0.20.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/adapter_config.json
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"fan_in_fan_out": false,
|
| 7 |
-
"inference_mode": true,
|
| 8 |
-
"init_lora_weights": true,
|
| 9 |
-
"layer_replication": null,
|
| 10 |
-
"layers_pattern": null,
|
| 11 |
-
"layers_to_transform": null,
|
| 12 |
-
"loftq_config": {},
|
| 13 |
-
"lora_alpha": 256,
|
| 14 |
-
"lora_dropout": 0.0,
|
| 15 |
-
"megatron_config": null,
|
| 16 |
-
"megatron_core": "megatron.core",
|
| 17 |
-
"modules_to_save": null,
|
| 18 |
-
"peft_type": "LORA",
|
| 19 |
-
"r": 128,
|
| 20 |
-
"rank_pattern": {},
|
| 21 |
-
"revision": null,
|
| 22 |
-
"target_modules": "^(?!.*visual).*(?:up_proj|q_proj|o_proj|gate_proj|v_proj|down_proj|k_proj).*",
|
| 23 |
-
"task_type": "CAUSAL_LM",
|
| 24 |
-
"use_dora": false,
|
| 25 |
-
"use_rslora": false
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/added_tokens.json
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<|box_end|>": 151649,
|
| 3 |
-
"<|box_start|>": 151648,
|
| 4 |
-
"<|endoftext|>": 151643,
|
| 5 |
-
"<|im_end|>": 151645,
|
| 6 |
-
"<|im_start|>": 151644,
|
| 7 |
-
"<|image_pad|>": 151655,
|
| 8 |
-
"<|object_ref_end|>": 151647,
|
| 9 |
-
"<|object_ref_start|>": 151646,
|
| 10 |
-
"<|quad_end|>": 151651,
|
| 11 |
-
"<|quad_start|>": 151650,
|
| 12 |
-
"<|video_pad|>": 151656,
|
| 13 |
-
"<|vision_end|>": 151653,
|
| 14 |
-
"<|vision_pad|>": 151654,
|
| 15 |
-
"<|vision_start|>": 151652
|
| 16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/all_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.88,
|
| 3 |
-
"total_flos": 5.97913280723288e+17,
|
| 4 |
-
"train_loss": 1.5128402180141873,
|
| 5 |
-
"train_runtime": 2593.9911,
|
| 6 |
-
"train_samples_per_second": 0.463,
|
| 7 |
-
"train_steps_per_second": 0.007
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/chat_template.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama_factory/v2-20241220/preprocessor_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_convert_rgb": true,
|
| 3 |
-
"do_normalize": true,
|
| 4 |
-
"do_rescale": true,
|
| 5 |
-
"do_resize": true,
|
| 6 |
-
"image_mean": [
|
| 7 |
-
0.48145466,
|
| 8 |
-
0.4578275,
|
| 9 |
-
0.40821073
|
| 10 |
-
],
|
| 11 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
-
"image_std": [
|
| 13 |
-
0.26862954,
|
| 14 |
-
0.26130258,
|
| 15 |
-
0.27577711
|
| 16 |
-
],
|
| 17 |
-
"max_pixels": 12845056,
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"min_pixels": 3136,
|
| 20 |
-
"patch_size": 14,
|
| 21 |
-
"processor_class": "Qwen2VLProcessor",
|
| 22 |
-
"resample": 3,
|
| 23 |
-
"rescale_factor": 0.00392156862745098,
|
| 24 |
-
"size": {
|
| 25 |
-
"max_pixels": 12845056,
|
| 26 |
-
"min_pixels": 3136
|
| 27 |
-
},
|
| 28 |
-
"temporal_patch_size": 2
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/tokenizer_config.json
DELETED
|
@@ -1,144 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"151643": {
|
| 5 |
-
"content": "<|endoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"151644": {
|
| 13 |
-
"content": "<|im_start|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"151645": {
|
| 21 |
-
"content": "<|im_end|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"151646": {
|
| 29 |
-
"content": "<|object_ref_start|>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"151647": {
|
| 37 |
-
"content": "<|object_ref_end|>",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"151648": {
|
| 45 |
-
"content": "<|box_start|>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"151649": {
|
| 53 |
-
"content": "<|box_end|>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"151650": {
|
| 61 |
-
"content": "<|quad_start|>",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"151651": {
|
| 69 |
-
"content": "<|quad_end|>",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"151652": {
|
| 77 |
-
"content": "<|vision_start|>",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": false,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": true
|
| 83 |
-
},
|
| 84 |
-
"151653": {
|
| 85 |
-
"content": "<|vision_end|>",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"151654": {
|
| 93 |
-
"content": "<|vision_pad|>",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"151655": {
|
| 101 |
-
"content": "<|image_pad|>",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"151656": {
|
| 109 |
-
"content": "<|video_pad|>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
}
|
| 116 |
-
},
|
| 117 |
-
"additional_special_tokens": [
|
| 118 |
-
"<|im_start|>",
|
| 119 |
-
"<|im_end|>",
|
| 120 |
-
"<|object_ref_start|>",
|
| 121 |
-
"<|object_ref_end|>",
|
| 122 |
-
"<|box_start|>",
|
| 123 |
-
"<|box_end|>",
|
| 124 |
-
"<|quad_start|>",
|
| 125 |
-
"<|quad_end|>",
|
| 126 |
-
"<|vision_start|>",
|
| 127 |
-
"<|vision_end|>",
|
| 128 |
-
"<|vision_pad|>",
|
| 129 |
-
"<|image_pad|>",
|
| 130 |
-
"<|video_pad|>"
|
| 131 |
-
],
|
| 132 |
-
"bos_token": null,
|
| 133 |
-
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 134 |
-
"clean_up_tokenization_spaces": false,
|
| 135 |
-
"eos_token": "<|im_end|>",
|
| 136 |
-
"errors": "replace",
|
| 137 |
-
"model_max_length": 32768,
|
| 138 |
-
"pad_token": "<|endoftext|>",
|
| 139 |
-
"padding_side": "right",
|
| 140 |
-
"processor_class": "Qwen2VLProcessor",
|
| 141 |
-
"split_special_tokens": false,
|
| 142 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 143 |
-
"unk_token": null
|
| 144 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/train_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.88,
|
| 3 |
-
"total_flos": 5.97913280723288e+17,
|
| 4 |
-
"train_loss": 1.5128402180141873,
|
| 5 |
-
"train_runtime": 2593.9911,
|
| 6 |
-
"train_samples_per_second": 0.463,
|
| 7 |
-
"train_steps_per_second": 0.007
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/trainer_log.jsonl
DELETED
|
@@ -1,19 +0,0 @@
|
|
| 1 |
-
{"current_steps": 1, "total_steps": 18, "loss": 1.6395, "lr": 5e-05, "epoch": 0.16, "percentage": 5.56, "elapsed_time": "0:02:35", "remaining_time": "0:44:07"}
|
| 2 |
-
{"current_steps": 2, "total_steps": 18, "loss": 1.6454, "lr": 0.0001, "epoch": 0.32, "percentage": 11.11, "elapsed_time": "0:05:01", "remaining_time": "0:40:08"}
|
| 3 |
-
{"current_steps": 3, "total_steps": 18, "loss": 1.6031, "lr": 9.903926402016153e-05, "epoch": 0.48, "percentage": 16.67, "elapsed_time": "0:07:13", "remaining_time": "0:36:09"}
|
| 4 |
-
{"current_steps": 4, "total_steps": 18, "loss": 1.6443, "lr": 9.619397662556435e-05, "epoch": 0.64, "percentage": 22.22, "elapsed_time": "0:09:34", "remaining_time": "0:33:31"}
|
| 5 |
-
{"current_steps": 5, "total_steps": 18, "loss": 1.5788, "lr": 9.157348061512727e-05, "epoch": 0.8, "percentage": 27.78, "elapsed_time": "0:12:14", "remaining_time": "0:31:49"}
|
| 6 |
-
{"current_steps": 6, "total_steps": 18, "loss": 1.586, "lr": 8.535533905932738e-05, "epoch": 0.96, "percentage": 33.33, "elapsed_time": "0:14:59", "remaining_time": "0:29:59"}
|
| 7 |
-
{"current_steps": 7, "total_steps": 18, "loss": 1.5621, "lr": 7.777851165098012e-05, "epoch": 1.12, "percentage": 38.89, "elapsed_time": "0:17:18", "remaining_time": "0:27:11"}
|
| 8 |
-
{"current_steps": 8, "total_steps": 18, "loss": 1.4846, "lr": 6.91341716182545e-05, "epoch": 1.28, "percentage": 44.44, "elapsed_time": "0:20:05", "remaining_time": "0:25:07"}
|
| 9 |
-
{"current_steps": 9, "total_steps": 18, "loss": 1.488, "lr": 5.9754516100806423e-05, "epoch": 1.44, "percentage": 50.0, "elapsed_time": "0:22:24", "remaining_time": "0:22:24"}
|
| 10 |
-
{"current_steps": 10, "total_steps": 18, "loss": 1.4901, "lr": 5e-05, "epoch": 1.6, "percentage": 55.56, "elapsed_time": "0:24:58", "remaining_time": "0:19:58"}
|
| 11 |
-
{"current_steps": 11, "total_steps": 18, "loss": 1.4207, "lr": 4.0245483899193595e-05, "epoch": 1.76, "percentage": 61.11, "elapsed_time": "0:27:21", "remaining_time": "0:17:24"}
|
| 12 |
-
{"current_steps": 12, "total_steps": 18, "loss": 1.4992, "lr": 3.086582838174551e-05, "epoch": 1.92, "percentage": 66.67, "elapsed_time": "0:29:33", "remaining_time": "0:14:46"}
|
| 13 |
-
{"current_steps": 13, "total_steps": 18, "loss": 1.4965, "lr": 2.2221488349019903e-05, "epoch": 2.08, "percentage": 72.22, "elapsed_time": "0:31:52", "remaining_time": "0:12:15"}
|
| 14 |
-
{"current_steps": 14, "total_steps": 18, "loss": 1.4594, "lr": 1.4644660940672627e-05, "epoch": 2.24, "percentage": 77.78, "elapsed_time": "0:33:51", "remaining_time": "0:09:40"}
|
| 15 |
-
{"current_steps": 15, "total_steps": 18, "loss": 1.42, "lr": 8.426519384872733e-06, "epoch": 2.4, "percentage": 83.33, "elapsed_time": "0:35:57", "remaining_time": "0:07:11"}
|
| 16 |
-
{"current_steps": 16, "total_steps": 18, "loss": 1.411, "lr": 3.8060233744356633e-06, "epoch": 2.56, "percentage": 88.89, "elapsed_time": "0:38:11", "remaining_time": "0:04:46"}
|
| 17 |
-
{"current_steps": 17, "total_steps": 18, "loss": 1.4063, "lr": 9.607359798384785e-07, "epoch": 2.7199999999999998, "percentage": 94.44, "elapsed_time": "0:40:31", "remaining_time": "0:02:23"}
|
| 18 |
-
{"current_steps": 18, "total_steps": 18, "loss": 1.3964, "lr": 0.0, "epoch": 2.88, "percentage": 100.0, "elapsed_time": "0:42:45", "remaining_time": "0:00:00"}
|
| 19 |
-
{"current_steps": 18, "total_steps": 18, "epoch": 2.88, "percentage": 100.0, "elapsed_time": "0:43:13", "remaining_time": "0:00:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/trainer_state.json
DELETED
|
@@ -1,168 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.88,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 18,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.16,
|
| 13 |
-
"grad_norm": 0.49046701192855835,
|
| 14 |
-
"learning_rate": 5e-05,
|
| 15 |
-
"loss": 1.6395,
|
| 16 |
-
"step": 1
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.32,
|
| 20 |
-
"grad_norm": 0.47982165217399597,
|
| 21 |
-
"learning_rate": 0.0001,
|
| 22 |
-
"loss": 1.6454,
|
| 23 |
-
"step": 2
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.48,
|
| 27 |
-
"grad_norm": 0.3478511571884155,
|
| 28 |
-
"learning_rate": 9.903926402016153e-05,
|
| 29 |
-
"loss": 1.6031,
|
| 30 |
-
"step": 3
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.64,
|
| 34 |
-
"grad_norm": 0.465070515871048,
|
| 35 |
-
"learning_rate": 9.619397662556435e-05,
|
| 36 |
-
"loss": 1.6443,
|
| 37 |
-
"step": 4
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.8,
|
| 41 |
-
"grad_norm": 0.28730812668800354,
|
| 42 |
-
"learning_rate": 9.157348061512727e-05,
|
| 43 |
-
"loss": 1.5788,
|
| 44 |
-
"step": 5
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.96,
|
| 48 |
-
"grad_norm": 0.2595618665218353,
|
| 49 |
-
"learning_rate": 8.535533905932738e-05,
|
| 50 |
-
"loss": 1.586,
|
| 51 |
-
"step": 6
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 1.12,
|
| 55 |
-
"grad_norm": 0.22310923039913177,
|
| 56 |
-
"learning_rate": 7.777851165098012e-05,
|
| 57 |
-
"loss": 1.5621,
|
| 58 |
-
"step": 7
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 1.28,
|
| 62 |
-
"grad_norm": 0.20716898143291473,
|
| 63 |
-
"learning_rate": 6.91341716182545e-05,
|
| 64 |
-
"loss": 1.4846,
|
| 65 |
-
"step": 8
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 1.44,
|
| 69 |
-
"grad_norm": 0.20206721127033234,
|
| 70 |
-
"learning_rate": 5.9754516100806423e-05,
|
| 71 |
-
"loss": 1.488,
|
| 72 |
-
"step": 9
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 1.6,
|
| 76 |
-
"grad_norm": 0.1985960155725479,
|
| 77 |
-
"learning_rate": 5e-05,
|
| 78 |
-
"loss": 1.4901,
|
| 79 |
-
"step": 10
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 1.76,
|
| 83 |
-
"grad_norm": 0.18855780363082886,
|
| 84 |
-
"learning_rate": 4.0245483899193595e-05,
|
| 85 |
-
"loss": 1.4207,
|
| 86 |
-
"step": 11
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 1.92,
|
| 90 |
-
"grad_norm": 0.18942952156066895,
|
| 91 |
-
"learning_rate": 3.086582838174551e-05,
|
| 92 |
-
"loss": 1.4992,
|
| 93 |
-
"step": 12
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 2.08,
|
| 97 |
-
"grad_norm": 0.19068744778633118,
|
| 98 |
-
"learning_rate": 2.2221488349019903e-05,
|
| 99 |
-
"loss": 1.4965,
|
| 100 |
-
"step": 13
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 2.24,
|
| 104 |
-
"grad_norm": 0.1741170436143875,
|
| 105 |
-
"learning_rate": 1.4644660940672627e-05,
|
| 106 |
-
"loss": 1.4594,
|
| 107 |
-
"step": 14
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 2.4,
|
| 111 |
-
"grad_norm": 0.16722294688224792,
|
| 112 |
-
"learning_rate": 8.426519384872733e-06,
|
| 113 |
-
"loss": 1.42,
|
| 114 |
-
"step": 15
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 2.56,
|
| 118 |
-
"grad_norm": 0.1697998344898224,
|
| 119 |
-
"learning_rate": 3.8060233744356633e-06,
|
| 120 |
-
"loss": 1.411,
|
| 121 |
-
"step": 16
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 2.7199999999999998,
|
| 125 |
-
"grad_norm": 0.17374582588672638,
|
| 126 |
-
"learning_rate": 9.607359798384785e-07,
|
| 127 |
-
"loss": 1.4063,
|
| 128 |
-
"step": 17
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 2.88,
|
| 132 |
-
"grad_norm": 0.17088964581489563,
|
| 133 |
-
"learning_rate": 0.0,
|
| 134 |
-
"loss": 1.3964,
|
| 135 |
-
"step": 18
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 2.88,
|
| 139 |
-
"step": 18,
|
| 140 |
-
"total_flos": 5.97913280723288e+17,
|
| 141 |
-
"train_loss": 1.5128402180141873,
|
| 142 |
-
"train_runtime": 2593.9911,
|
| 143 |
-
"train_samples_per_second": 0.463,
|
| 144 |
-
"train_steps_per_second": 0.007
|
| 145 |
-
}
|
| 146 |
-
],
|
| 147 |
-
"logging_steps": 1,
|
| 148 |
-
"max_steps": 18,
|
| 149 |
-
"num_input_tokens_seen": 0,
|
| 150 |
-
"num_train_epochs": 3,
|
| 151 |
-
"save_steps": 200,
|
| 152 |
-
"stateful_callbacks": {
|
| 153 |
-
"TrainerControl": {
|
| 154 |
-
"args": {
|
| 155 |
-
"should_epoch_stop": false,
|
| 156 |
-
"should_evaluate": false,
|
| 157 |
-
"should_log": false,
|
| 158 |
-
"should_save": true,
|
| 159 |
-
"should_training_stop": true
|
| 160 |
-
},
|
| 161 |
-
"attributes": {}
|
| 162 |
-
}
|
| 163 |
-
},
|
| 164 |
-
"total_flos": 5.97913280723288e+17,
|
| 165 |
-
"train_batch_size": 2,
|
| 166 |
-
"trial_name": null,
|
| 167 |
-
"trial_params": null
|
| 168 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v2-20241220/training_loss.png
DELETED
|
Binary file (42.7 kB)
|
|
|
llama_factory/v2-20241220/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama_factory/v3-20241225-1_10/README.md
DELETED
|
@@ -1,62 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: peft
|
| 3 |
-
license: other
|
| 4 |
-
base_model: /disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct
|
| 5 |
-
tags:
|
| 6 |
-
- llama-factory
|
| 7 |
-
- lora
|
| 8 |
-
- generated_from_trainer
|
| 9 |
-
model-index:
|
| 10 |
-
- name: v3-20241225-1_10
|
| 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 |
-
# v3-20241225-1_10
|
| 18 |
-
|
| 19 |
-
This model is a fine-tuned version of [/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct](https://huggingface.co//disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct) on the M^2RAR-20241225-MLLM-1_10 dataset.
|
| 20 |
-
|
| 21 |
-
## Model description
|
| 22 |
-
|
| 23 |
-
More information needed
|
| 24 |
-
|
| 25 |
-
## Intended uses & limitations
|
| 26 |
-
|
| 27 |
-
More information needed
|
| 28 |
-
|
| 29 |
-
## Training and evaluation data
|
| 30 |
-
|
| 31 |
-
More information needed
|
| 32 |
-
|
| 33 |
-
## Training procedure
|
| 34 |
-
|
| 35 |
-
### Training hyperparameters
|
| 36 |
-
|
| 37 |
-
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate: 0.0001
|
| 39 |
-
- train_batch_size: 2
|
| 40 |
-
- eval_batch_size: 8
|
| 41 |
-
- seed: 42
|
| 42 |
-
- distributed_type: multi-GPU
|
| 43 |
-
- num_devices: 2
|
| 44 |
-
- gradient_accumulation_steps: 16
|
| 45 |
-
- total_train_batch_size: 64
|
| 46 |
-
- total_eval_batch_size: 16
|
| 47 |
-
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
-
- lr_scheduler_type: cosine
|
| 49 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
-
- num_epochs: 3.0
|
| 51 |
-
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
### Framework versions
|
| 57 |
-
|
| 58 |
-
- PEFT 0.12.0
|
| 59 |
-
- Transformers 4.46.1
|
| 60 |
-
- Pytorch 2.3.1+cu121
|
| 61 |
-
- Datasets 3.1.0
|
| 62 |
-
- Tokenizers 0.20.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/adapter_config.json
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"fan_in_fan_out": false,
|
| 7 |
-
"inference_mode": true,
|
| 8 |
-
"init_lora_weights": true,
|
| 9 |
-
"layer_replication": null,
|
| 10 |
-
"layers_pattern": null,
|
| 11 |
-
"layers_to_transform": null,
|
| 12 |
-
"loftq_config": {},
|
| 13 |
-
"lora_alpha": 256,
|
| 14 |
-
"lora_dropout": 0.0,
|
| 15 |
-
"megatron_config": null,
|
| 16 |
-
"megatron_core": "megatron.core",
|
| 17 |
-
"modules_to_save": null,
|
| 18 |
-
"peft_type": "LORA",
|
| 19 |
-
"r": 128,
|
| 20 |
-
"rank_pattern": {},
|
| 21 |
-
"revision": null,
|
| 22 |
-
"target_modules": "^(?!.*visual).*(?:o_proj|down_proj|q_proj|gate_proj|up_proj|v_proj|k_proj).*",
|
| 23 |
-
"task_type": "CAUSAL_LM",
|
| 24 |
-
"use_dora": false,
|
| 25 |
-
"use_rslora": false
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/added_tokens.json
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<|box_end|>": 151649,
|
| 3 |
-
"<|box_start|>": 151648,
|
| 4 |
-
"<|endoftext|>": 151643,
|
| 5 |
-
"<|im_end|>": 151645,
|
| 6 |
-
"<|im_start|>": 151644,
|
| 7 |
-
"<|image_pad|>": 151655,
|
| 8 |
-
"<|object_ref_end|>": 151647,
|
| 9 |
-
"<|object_ref_start|>": 151646,
|
| 10 |
-
"<|quad_end|>": 151651,
|
| 11 |
-
"<|quad_start|>": 151650,
|
| 12 |
-
"<|video_pad|>": 151656,
|
| 13 |
-
"<|vision_end|>": 151653,
|
| 14 |
-
"<|vision_pad|>": 151654,
|
| 15 |
-
"<|vision_start|>": 151652
|
| 16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/all_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.9547511312217196,
|
| 3 |
-
"total_flos": 1.9929234183615939e+18,
|
| 4 |
-
"train_loss": 1.4086421551527801,
|
| 5 |
-
"train_runtime": 8849.9709,
|
| 6 |
-
"train_samples_per_second": 0.598,
|
| 7 |
-
"train_steps_per_second": 0.009
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/chat_template.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama_factory/v3-20241225-1_10/preprocessor_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_convert_rgb": true,
|
| 3 |
-
"do_normalize": true,
|
| 4 |
-
"do_rescale": true,
|
| 5 |
-
"do_resize": true,
|
| 6 |
-
"image_mean": [
|
| 7 |
-
0.48145466,
|
| 8 |
-
0.4578275,
|
| 9 |
-
0.40821073
|
| 10 |
-
],
|
| 11 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
-
"image_std": [
|
| 13 |
-
0.26862954,
|
| 14 |
-
0.26130258,
|
| 15 |
-
0.27577711
|
| 16 |
-
],
|
| 17 |
-
"max_pixels": 12845056,
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"min_pixels": 3136,
|
| 20 |
-
"patch_size": 14,
|
| 21 |
-
"processor_class": "Qwen2VLProcessor",
|
| 22 |
-
"resample": 3,
|
| 23 |
-
"rescale_factor": 0.00392156862745098,
|
| 24 |
-
"size": {
|
| 25 |
-
"max_pixels": 12845056,
|
| 26 |
-
"min_pixels": 3136
|
| 27 |
-
},
|
| 28 |
-
"temporal_patch_size": 2
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/tokenizer_config.json
DELETED
|
@@ -1,144 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"added_tokens_decoder": {
|
| 4 |
-
"151643": {
|
| 5 |
-
"content": "<|endoftext|>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"151644": {
|
| 13 |
-
"content": "<|im_start|>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"151645": {
|
| 21 |
-
"content": "<|im_end|>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"151646": {
|
| 29 |
-
"content": "<|object_ref_start|>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"151647": {
|
| 37 |
-
"content": "<|object_ref_end|>",
|
| 38 |
-
"lstrip": false,
|
| 39 |
-
"normalized": false,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
},
|
| 44 |
-
"151648": {
|
| 45 |
-
"content": "<|box_start|>",
|
| 46 |
-
"lstrip": false,
|
| 47 |
-
"normalized": false,
|
| 48 |
-
"rstrip": false,
|
| 49 |
-
"single_word": false,
|
| 50 |
-
"special": true
|
| 51 |
-
},
|
| 52 |
-
"151649": {
|
| 53 |
-
"content": "<|box_end|>",
|
| 54 |
-
"lstrip": false,
|
| 55 |
-
"normalized": false,
|
| 56 |
-
"rstrip": false,
|
| 57 |
-
"single_word": false,
|
| 58 |
-
"special": true
|
| 59 |
-
},
|
| 60 |
-
"151650": {
|
| 61 |
-
"content": "<|quad_start|>",
|
| 62 |
-
"lstrip": false,
|
| 63 |
-
"normalized": false,
|
| 64 |
-
"rstrip": false,
|
| 65 |
-
"single_word": false,
|
| 66 |
-
"special": true
|
| 67 |
-
},
|
| 68 |
-
"151651": {
|
| 69 |
-
"content": "<|quad_end|>",
|
| 70 |
-
"lstrip": false,
|
| 71 |
-
"normalized": false,
|
| 72 |
-
"rstrip": false,
|
| 73 |
-
"single_word": false,
|
| 74 |
-
"special": true
|
| 75 |
-
},
|
| 76 |
-
"151652": {
|
| 77 |
-
"content": "<|vision_start|>",
|
| 78 |
-
"lstrip": false,
|
| 79 |
-
"normalized": false,
|
| 80 |
-
"rstrip": false,
|
| 81 |
-
"single_word": false,
|
| 82 |
-
"special": true
|
| 83 |
-
},
|
| 84 |
-
"151653": {
|
| 85 |
-
"content": "<|vision_end|>",
|
| 86 |
-
"lstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"rstrip": false,
|
| 89 |
-
"single_word": false,
|
| 90 |
-
"special": true
|
| 91 |
-
},
|
| 92 |
-
"151654": {
|
| 93 |
-
"content": "<|vision_pad|>",
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"normalized": false,
|
| 96 |
-
"rstrip": false,
|
| 97 |
-
"single_word": false,
|
| 98 |
-
"special": true
|
| 99 |
-
},
|
| 100 |
-
"151655": {
|
| 101 |
-
"content": "<|image_pad|>",
|
| 102 |
-
"lstrip": false,
|
| 103 |
-
"normalized": false,
|
| 104 |
-
"rstrip": false,
|
| 105 |
-
"single_word": false,
|
| 106 |
-
"special": true
|
| 107 |
-
},
|
| 108 |
-
"151656": {
|
| 109 |
-
"content": "<|video_pad|>",
|
| 110 |
-
"lstrip": false,
|
| 111 |
-
"normalized": false,
|
| 112 |
-
"rstrip": false,
|
| 113 |
-
"single_word": false,
|
| 114 |
-
"special": true
|
| 115 |
-
}
|
| 116 |
-
},
|
| 117 |
-
"additional_special_tokens": [
|
| 118 |
-
"<|im_start|>",
|
| 119 |
-
"<|im_end|>",
|
| 120 |
-
"<|object_ref_start|>",
|
| 121 |
-
"<|object_ref_end|>",
|
| 122 |
-
"<|box_start|>",
|
| 123 |
-
"<|box_end|>",
|
| 124 |
-
"<|quad_start|>",
|
| 125 |
-
"<|quad_end|>",
|
| 126 |
-
"<|vision_start|>",
|
| 127 |
-
"<|vision_end|>",
|
| 128 |
-
"<|vision_pad|>",
|
| 129 |
-
"<|image_pad|>",
|
| 130 |
-
"<|video_pad|>"
|
| 131 |
-
],
|
| 132 |
-
"bos_token": null,
|
| 133 |
-
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}",
|
| 134 |
-
"clean_up_tokenization_spaces": false,
|
| 135 |
-
"eos_token": "<|im_end|>",
|
| 136 |
-
"errors": "replace",
|
| 137 |
-
"model_max_length": 32768,
|
| 138 |
-
"pad_token": "<|endoftext|>",
|
| 139 |
-
"padding_side": "right",
|
| 140 |
-
"processor_class": "Qwen2VLProcessor",
|
| 141 |
-
"split_special_tokens": false,
|
| 142 |
-
"tokenizer_class": "Qwen2Tokenizer",
|
| 143 |
-
"unk_token": null
|
| 144 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/train_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.9547511312217196,
|
| 3 |
-
"total_flos": 1.9929234183615939e+18,
|
| 4 |
-
"train_loss": 1.4086421551527801,
|
| 5 |
-
"train_runtime": 8849.9709,
|
| 6 |
-
"train_samples_per_second": 0.598,
|
| 7 |
-
"train_steps_per_second": 0.009
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/trainer_log.jsonl
DELETED
|
@@ -1,82 +0,0 @@
|
|
| 1 |
-
{"current_steps": 1, "total_steps": 81, "loss": 1.6301, "lr": 1.1111111111111112e-05, "epoch": 0.03619909502262444, "percentage": 1.23, "elapsed_time": "0:01:57", "remaining_time": "2:36:51"}
|
| 2 |
-
{"current_steps": 2, "total_steps": 81, "loss": 1.6279, "lr": 2.2222222222222223e-05, "epoch": 0.07239819004524888, "percentage": 2.47, "elapsed_time": "0:03:51", "remaining_time": "2:32:14"}
|
| 3 |
-
{"current_steps": 3, "total_steps": 81, "loss": 1.5965, "lr": 3.3333333333333335e-05, "epoch": 0.1085972850678733, "percentage": 3.7, "elapsed_time": "0:05:22", "remaining_time": "2:19:46"}
|
| 4 |
-
{"current_steps": 4, "total_steps": 81, "loss": 1.6076, "lr": 4.4444444444444447e-05, "epoch": 0.14479638009049775, "percentage": 4.94, "elapsed_time": "0:07:16", "remaining_time": "2:19:57"}
|
| 5 |
-
{"current_steps": 5, "total_steps": 81, "loss": 1.6144, "lr": 5.555555555555556e-05, "epoch": 0.18099547511312217, "percentage": 6.17, "elapsed_time": "0:09:17", "remaining_time": "2:21:09"}
|
| 6 |
-
{"current_steps": 6, "total_steps": 81, "loss": 1.5657, "lr": 6.666666666666667e-05, "epoch": 0.2171945701357466, "percentage": 7.41, "elapsed_time": "0:11:14", "remaining_time": "2:20:31"}
|
| 7 |
-
{"current_steps": 7, "total_steps": 81, "loss": 1.5651, "lr": 7.777777777777778e-05, "epoch": 0.25339366515837103, "percentage": 8.64, "elapsed_time": "0:12:54", "remaining_time": "2:16:29"}
|
| 8 |
-
{"current_steps": 8, "total_steps": 81, "loss": 1.5488, "lr": 8.888888888888889e-05, "epoch": 0.2895927601809955, "percentage": 9.88, "elapsed_time": "0:14:46", "remaining_time": "2:14:46"}
|
| 9 |
-
{"current_steps": 9, "total_steps": 81, "loss": 1.5898, "lr": 0.0001, "epoch": 0.3257918552036199, "percentage": 11.11, "elapsed_time": "0:16:59", "remaining_time": "2:15:59"}
|
| 10 |
-
{"current_steps": 10, "total_steps": 81, "loss": 1.5448, "lr": 9.99524110790929e-05, "epoch": 0.36199095022624433, "percentage": 12.35, "elapsed_time": "0:18:38", "remaining_time": "2:12:19"}
|
| 11 |
-
{"current_steps": 11, "total_steps": 81, "loss": 1.5285, "lr": 9.980973490458728e-05, "epoch": 0.39819004524886875, "percentage": 13.58, "elapsed_time": "0:20:38", "remaining_time": "2:11:19"}
|
| 12 |
-
{"current_steps": 12, "total_steps": 81, "loss": 1.5645, "lr": 9.957224306869053e-05, "epoch": 0.4343891402714932, "percentage": 14.81, "elapsed_time": "0:21:58", "remaining_time": "2:06:21"}
|
| 13 |
-
{"current_steps": 13, "total_steps": 81, "loss": 1.4987, "lr": 9.924038765061042e-05, "epoch": 0.47058823529411764, "percentage": 16.05, "elapsed_time": "0:23:58", "remaining_time": "2:05:23"}
|
| 14 |
-
{"current_steps": 14, "total_steps": 81, "loss": 1.4982, "lr": 9.881480035599667e-05, "epoch": 0.5067873303167421, "percentage": 17.28, "elapsed_time": "0:25:56", "remaining_time": "2:04:08"}
|
| 15 |
-
{"current_steps": 15, "total_steps": 81, "loss": 1.5061, "lr": 9.829629131445342e-05, "epoch": 0.5429864253393665, "percentage": 18.52, "elapsed_time": "0:27:36", "remaining_time": "2:01:29"}
|
| 16 |
-
{"current_steps": 16, "total_steps": 81, "loss": 1.4963, "lr": 9.768584753741134e-05, "epoch": 0.579185520361991, "percentage": 19.75, "elapsed_time": "0:29:04", "remaining_time": "1:58:08"}
|
| 17 |
-
{"current_steps": 17, "total_steps": 81, "loss": 1.5242, "lr": 9.698463103929542e-05, "epoch": 0.6153846153846154, "percentage": 20.99, "elapsed_time": "0:31:04", "remaining_time": "1:56:57"}
|
| 18 |
-
{"current_steps": 18, "total_steps": 81, "loss": 1.49, "lr": 9.619397662556435e-05, "epoch": 0.6515837104072398, "percentage": 22.22, "elapsed_time": "0:33:00", "remaining_time": "1:55:32"}
|
| 19 |
-
{"current_steps": 19, "total_steps": 81, "loss": 1.5342, "lr": 9.53153893518325e-05, "epoch": 0.6877828054298643, "percentage": 23.46, "elapsed_time": "0:34:40", "remaining_time": "1:53:07"}
|
| 20 |
-
{"current_steps": 20, "total_steps": 81, "loss": 1.5256, "lr": 9.435054165891109e-05, "epoch": 0.7239819004524887, "percentage": 24.69, "elapsed_time": "0:36:06", "remaining_time": "1:50:07"}
|
| 21 |
-
{"current_steps": 21, "total_steps": 81, "loss": 1.5167, "lr": 9.330127018922194e-05, "epoch": 0.7601809954751131, "percentage": 25.93, "elapsed_time": "0:37:59", "remaining_time": "1:48:33"}
|
| 22 |
-
{"current_steps": 22, "total_steps": 81, "loss": 1.5255, "lr": 9.21695722906443e-05, "epoch": 0.7963800904977375, "percentage": 27.16, "elapsed_time": "0:39:30", "remaining_time": "1:45:57"}
|
| 23 |
-
{"current_steps": 23, "total_steps": 81, "loss": 1.5062, "lr": 9.09576022144496e-05, "epoch": 0.832579185520362, "percentage": 28.4, "elapsed_time": "0:41:33", "remaining_time": "1:44:47"}
|
| 24 |
-
{"current_steps": 24, "total_steps": 81, "loss": 1.4894, "lr": 8.966766701456177e-05, "epoch": 0.8687782805429864, "percentage": 29.63, "elapsed_time": "0:43:16", "remaining_time": "1:42:46"}
|
| 25 |
-
{"current_steps": 25, "total_steps": 81, "loss": 1.4553, "lr": 8.83022221559489e-05, "epoch": 0.9049773755656109, "percentage": 30.86, "elapsed_time": "0:45:18", "remaining_time": "1:41:29"}
|
| 26 |
-
{"current_steps": 26, "total_steps": 81, "loss": 1.4824, "lr": 8.68638668405062e-05, "epoch": 0.9411764705882353, "percentage": 32.1, "elapsed_time": "0:47:17", "remaining_time": "1:40:03"}
|
| 27 |
-
{"current_steps": 27, "total_steps": 81, "loss": 1.5244, "lr": 8.535533905932738e-05, "epoch": 0.9773755656108597, "percentage": 33.33, "elapsed_time": "0:49:09", "remaining_time": "1:38:18"}
|
| 28 |
-
{"current_steps": 28, "total_steps": 81, "loss": 1.4473, "lr": 8.377951038078302e-05, "epoch": 1.0248868778280542, "percentage": 34.57, "elapsed_time": "0:50:46", "remaining_time": "1:36:06"}
|
| 29 |
-
{"current_steps": 29, "total_steps": 81, "loss": 1.4101, "lr": 8.213938048432697e-05, "epoch": 1.0610859728506787, "percentage": 35.8, "elapsed_time": "0:52:32", "remaining_time": "1:34:13"}
|
| 30 |
-
{"current_steps": 30, "total_steps": 81, "loss": 1.4621, "lr": 8.043807145043604e-05, "epoch": 1.0972850678733033, "percentage": 37.04, "elapsed_time": "0:54:57", "remaining_time": "1:33:26"}
|
| 31 |
-
{"current_steps": 31, "total_steps": 81, "loss": 1.4011, "lr": 7.86788218175523e-05, "epoch": 1.1334841628959276, "percentage": 38.27, "elapsed_time": "0:56:27", "remaining_time": "1:31:03"}
|
| 32 |
-
{"current_steps": 32, "total_steps": 81, "loss": 1.4529, "lr": 7.68649804173412e-05, "epoch": 1.169683257918552, "percentage": 39.51, "elapsed_time": "0:58:11", "remaining_time": "1:29:06"}
|
| 33 |
-
{"current_steps": 33, "total_steps": 81, "loss": 1.4195, "lr": 7.500000000000001e-05, "epoch": 1.2058823529411764, "percentage": 40.74, "elapsed_time": "0:59:41", "remaining_time": "1:26:48"}
|
| 34 |
-
{"current_steps": 34, "total_steps": 81, "loss": 1.4106, "lr": 7.308743066175172e-05, "epoch": 1.242081447963801, "percentage": 41.98, "elapsed_time": "1:01:39", "remaining_time": "1:25:14"}
|
| 35 |
-
{"current_steps": 35, "total_steps": 81, "loss": 1.3482, "lr": 7.113091308703498e-05, "epoch": 1.2782805429864252, "percentage": 43.21, "elapsed_time": "1:03:15", "remaining_time": "1:23:08"}
|
| 36 |
-
{"current_steps": 36, "total_steps": 81, "loss": 1.4463, "lr": 6.91341716182545e-05, "epoch": 1.3144796380090498, "percentage": 44.44, "elapsed_time": "1:05:39", "remaining_time": "1:22:03"}
|
| 37 |
-
{"current_steps": 37, "total_steps": 81, "loss": 1.3528, "lr": 6.710100716628344e-05, "epoch": 1.3506787330316743, "percentage": 45.68, "elapsed_time": "1:07:30", "remaining_time": "1:20:17"}
|
| 38 |
-
{"current_steps": 38, "total_steps": 81, "loss": 1.3881, "lr": 6.503528997521366e-05, "epoch": 1.3868778280542986, "percentage": 46.91, "elapsed_time": "1:09:10", "remaining_time": "1:18:16"}
|
| 39 |
-
{"current_steps": 39, "total_steps": 81, "loss": 1.374, "lr": 6.294095225512603e-05, "epoch": 1.4230769230769231, "percentage": 48.15, "elapsed_time": "1:10:59", "remaining_time": "1:16:27"}
|
| 40 |
-
{"current_steps": 40, "total_steps": 81, "loss": 1.3717, "lr": 6.0821980696905146e-05, "epoch": 1.4592760180995474, "percentage": 49.38, "elapsed_time": "1:12:39", "remaining_time": "1:14:28"}
|
| 41 |
-
{"current_steps": 41, "total_steps": 81, "loss": 1.37, "lr": 5.868240888334653e-05, "epoch": 1.495475113122172, "percentage": 50.62, "elapsed_time": "1:14:09", "remaining_time": "1:12:21"}
|
| 42 |
-
{"current_steps": 42, "total_steps": 81, "loss": 1.359, "lr": 5.6526309611002594e-05, "epoch": 1.5316742081447963, "percentage": 51.85, "elapsed_time": "1:15:42", "remaining_time": "1:10:17"}
|
| 43 |
-
{"current_steps": 43, "total_steps": 81, "loss": 1.421, "lr": 5.435778713738292e-05, "epoch": 1.5678733031674208, "percentage": 53.09, "elapsed_time": "1:17:41", "remaining_time": "1:08:39"}
|
| 44 |
-
{"current_steps": 44, "total_steps": 81, "loss": 1.4027, "lr": 5.218096936826681e-05, "epoch": 1.6040723981900453, "percentage": 54.32, "elapsed_time": "1:19:38", "remaining_time": "1:06:58"}
|
| 45 |
-
{"current_steps": 45, "total_steps": 81, "loss": 1.3634, "lr": 5e-05, "epoch": 1.6402714932126696, "percentage": 55.56, "elapsed_time": "1:21:20", "remaining_time": "1:05:04"}
|
| 46 |
-
{"current_steps": 46, "total_steps": 81, "loss": 1.361, "lr": 4.781903063173321e-05, "epoch": 1.6764705882352942, "percentage": 56.79, "elapsed_time": "1:22:56", "remaining_time": "1:03:06"}
|
| 47 |
-
{"current_steps": 47, "total_steps": 81, "loss": 1.3613, "lr": 4.564221286261709e-05, "epoch": 1.7126696832579187, "percentage": 58.02, "elapsed_time": "1:24:43", "remaining_time": "1:01:17"}
|
| 48 |
-
{"current_steps": 48, "total_steps": 81, "loss": 1.367, "lr": 4.347369038899744e-05, "epoch": 1.748868778280543, "percentage": 59.26, "elapsed_time": "1:26:23", "remaining_time": "0:59:23"}
|
| 49 |
-
{"current_steps": 49, "total_steps": 81, "loss": 1.3626, "lr": 4.131759111665349e-05, "epoch": 1.7850678733031673, "percentage": 60.49, "elapsed_time": "1:28:19", "remaining_time": "0:57:40"}
|
| 50 |
-
{"current_steps": 50, "total_steps": 81, "loss": 1.3847, "lr": 3.917801930309486e-05, "epoch": 1.8212669683257918, "percentage": 61.73, "elapsed_time": "1:30:31", "remaining_time": "0:56:07"}
|
| 51 |
-
{"current_steps": 51, "total_steps": 81, "loss": 1.3584, "lr": 3.705904774487396e-05, "epoch": 1.8574660633484164, "percentage": 62.96, "elapsed_time": "1:32:36", "remaining_time": "0:54:28"}
|
| 52 |
-
{"current_steps": 52, "total_steps": 81, "loss": 1.393, "lr": 3.4964710024786354e-05, "epoch": 1.8936651583710407, "percentage": 64.2, "elapsed_time": "1:34:40", "remaining_time": "0:52:47"}
|
| 53 |
-
{"current_steps": 53, "total_steps": 81, "loss": 1.3333, "lr": 3.289899283371657e-05, "epoch": 1.9298642533936652, "percentage": 65.43, "elapsed_time": "1:36:20", "remaining_time": "0:50:53"}
|
| 54 |
-
{"current_steps": 54, "total_steps": 81, "loss": 1.3567, "lr": 3.086582838174551e-05, "epoch": 1.9660633484162897, "percentage": 66.67, "elapsed_time": "1:38:07", "remaining_time": "0:49:03"}
|
| 55 |
-
{"current_steps": 55, "total_steps": 81, "loss": 1.3388, "lr": 2.886908691296504e-05, "epoch": 2.013574660633484, "percentage": 67.9, "elapsed_time": "1:40:11", "remaining_time": "0:47:21"}
|
| 56 |
-
{"current_steps": 56, "total_steps": 81, "loss": 1.3288, "lr": 2.6912569338248315e-05, "epoch": 2.0497737556561084, "percentage": 69.14, "elapsed_time": "1:41:57", "remaining_time": "0:45:31"}
|
| 57 |
-
{"current_steps": 57, "total_steps": 81, "loss": 1.2998, "lr": 2.500000000000001e-05, "epoch": 2.085972850678733, "percentage": 70.37, "elapsed_time": "1:43:55", "remaining_time": "0:43:45"}
|
| 58 |
-
{"current_steps": 58, "total_steps": 81, "loss": 1.2406, "lr": 2.3135019582658802e-05, "epoch": 2.1221719457013575, "percentage": 71.6, "elapsed_time": "1:45:51", "remaining_time": "0:41:58"}
|
| 59 |
-
{"current_steps": 59, "total_steps": 81, "loss": 1.2579, "lr": 2.132117818244771e-05, "epoch": 2.158371040723982, "percentage": 72.84, "elapsed_time": "1:47:46", "remaining_time": "0:40:11"}
|
| 60 |
-
{"current_steps": 60, "total_steps": 81, "loss": 1.2737, "lr": 1.9561928549563968e-05, "epoch": 2.1945701357466065, "percentage": 74.07, "elapsed_time": "1:49:12", "remaining_time": "0:38:13"}
|
| 61 |
-
{"current_steps": 61, "total_steps": 81, "loss": 1.3014, "lr": 1.7860619515673033e-05, "epoch": 2.230769230769231, "percentage": 75.31, "elapsed_time": "1:51:16", "remaining_time": "0:36:28"}
|
| 62 |
-
{"current_steps": 62, "total_steps": 81, "loss": 1.3528, "lr": 1.622048961921699e-05, "epoch": 2.266968325791855, "percentage": 76.54, "elapsed_time": "1:53:05", "remaining_time": "0:34:39"}
|
| 63 |
-
{"current_steps": 63, "total_steps": 81, "loss": 1.2639, "lr": 1.4644660940672627e-05, "epoch": 2.3031674208144794, "percentage": 77.78, "elapsed_time": "1:54:54", "remaining_time": "0:32:49"}
|
| 64 |
-
{"current_steps": 64, "total_steps": 81, "loss": 1.3244, "lr": 1.3136133159493802e-05, "epoch": 2.339366515837104, "percentage": 79.01, "elapsed_time": "1:57:14", "remaining_time": "0:31:08"}
|
| 65 |
-
{"current_steps": 65, "total_steps": 81, "loss": 1.3534, "lr": 1.1697777844051105e-05, "epoch": 2.3755656108597285, "percentage": 80.25, "elapsed_time": "1:59:18", "remaining_time": "0:29:22"}
|
| 66 |
-
{"current_steps": 66, "total_steps": 81, "loss": 1.2637, "lr": 1.0332332985438248e-05, "epoch": 2.411764705882353, "percentage": 81.48, "elapsed_time": "2:00:39", "remaining_time": "0:27:25"}
|
| 67 |
-
{"current_steps": 67, "total_steps": 81, "loss": 1.3538, "lr": 9.042397785550405e-06, "epoch": 2.4479638009049776, "percentage": 82.72, "elapsed_time": "2:02:40", "remaining_time": "0:25:37"}
|
| 68 |
-
{"current_steps": 68, "total_steps": 81, "loss": 1.3247, "lr": 7.830427709355725e-06, "epoch": 2.484162895927602, "percentage": 83.95, "elapsed_time": "2:04:17", "remaining_time": "0:23:45"}
|
| 69 |
-
{"current_steps": 69, "total_steps": 81, "loss": 1.2721, "lr": 6.698729810778065e-06, "epoch": 2.520361990950226, "percentage": 85.19, "elapsed_time": "2:06:07", "remaining_time": "0:21:56"}
|
| 70 |
-
{"current_steps": 70, "total_steps": 81, "loss": 1.2966, "lr": 5.649458341088915e-06, "epoch": 2.5565610859728505, "percentage": 86.42, "elapsed_time": "2:07:32", "remaining_time": "0:20:02"}
|
| 71 |
-
{"current_steps": 71, "total_steps": 81, "loss": 1.2594, "lr": 4.684610648167503e-06, "epoch": 2.5927601809954752, "percentage": 87.65, "elapsed_time": "2:09:29", "remaining_time": "0:18:14"}
|
| 72 |
-
{"current_steps": 72, "total_steps": 81, "loss": 1.2951, "lr": 3.8060233744356633e-06, "epoch": 2.6289592760180995, "percentage": 88.89, "elapsed_time": "2:11:02", "remaining_time": "0:16:22"}
|
| 73 |
-
{"current_steps": 73, "total_steps": 81, "loss": 1.3408, "lr": 3.0153689607045845e-06, "epoch": 2.665158371040724, "percentage": 90.12, "elapsed_time": "2:13:04", "remaining_time": "0:14:35"}
|
| 74 |
-
{"current_steps": 74, "total_steps": 81, "loss": 1.2951, "lr": 2.314152462588659e-06, "epoch": 2.7013574660633486, "percentage": 91.36, "elapsed_time": "2:15:00", "remaining_time": "0:12:46"}
|
| 75 |
-
{"current_steps": 75, "total_steps": 81, "loss": 1.2927, "lr": 1.70370868554659e-06, "epoch": 2.737556561085973, "percentage": 92.59, "elapsed_time": "2:16:56", "remaining_time": "0:10:57"}
|
| 76 |
-
{"current_steps": 76, "total_steps": 81, "loss": 1.3133, "lr": 1.1851996440033319e-06, "epoch": 2.773755656108597, "percentage": 93.83, "elapsed_time": "2:18:48", "remaining_time": "0:09:07"}
|
| 77 |
-
{"current_steps": 77, "total_steps": 81, "loss": 1.3135, "lr": 7.596123493895991e-07, "epoch": 2.8099547511312215, "percentage": 95.06, "elapsed_time": "2:20:21", "remaining_time": "0:07:17"}
|
| 78 |
-
{"current_steps": 78, "total_steps": 81, "loss": 1.2631, "lr": 4.277569313094809e-07, "epoch": 2.8461538461538463, "percentage": 96.3, "elapsed_time": "2:22:03", "remaining_time": "0:05:27"}
|
| 79 |
-
{"current_steps": 79, "total_steps": 81, "loss": 1.2773, "lr": 1.9026509541272275e-07, "epoch": 2.8823529411764706, "percentage": 97.53, "elapsed_time": "2:23:50", "remaining_time": "0:03:38"}
|
| 80 |
-
{"current_steps": 80, "total_steps": 81, "loss": 1.2997, "lr": 4.7588920907110094e-08, "epoch": 2.918552036199095, "percentage": 98.77, "elapsed_time": "2:25:32", "remaining_time": "0:01:49"}
|
| 81 |
-
{"current_steps": 81, "total_steps": 81, "loss": 1.268, "lr": 0.0, "epoch": 2.9547511312217196, "percentage": 100.0, "elapsed_time": "2:26:50", "remaining_time": "0:00:00"}
|
| 82 |
-
{"current_steps": 81, "total_steps": 81, "epoch": 2.9547511312217196, "percentage": 100.0, "elapsed_time": "2:27:29", "remaining_time": "0:00:00"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/trainer_state.json
DELETED
|
@@ -1,609 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"best_metric": null,
|
| 3 |
-
"best_model_checkpoint": null,
|
| 4 |
-
"epoch": 2.9547511312217196,
|
| 5 |
-
"eval_steps": 500,
|
| 6 |
-
"global_step": 81,
|
| 7 |
-
"is_hyper_param_search": false,
|
| 8 |
-
"is_local_process_zero": true,
|
| 9 |
-
"is_world_process_zero": true,
|
| 10 |
-
"log_history": [
|
| 11 |
-
{
|
| 12 |
-
"epoch": 0.03619909502262444,
|
| 13 |
-
"grad_norm": 0.4522567093372345,
|
| 14 |
-
"learning_rate": 1.1111111111111112e-05,
|
| 15 |
-
"loss": 1.6301,
|
| 16 |
-
"step": 1
|
| 17 |
-
},
|
| 18 |
-
{
|
| 19 |
-
"epoch": 0.07239819004524888,
|
| 20 |
-
"grad_norm": 0.4915740489959717,
|
| 21 |
-
"learning_rate": 2.2222222222222223e-05,
|
| 22 |
-
"loss": 1.6279,
|
| 23 |
-
"step": 2
|
| 24 |
-
},
|
| 25 |
-
{
|
| 26 |
-
"epoch": 0.1085972850678733,
|
| 27 |
-
"grad_norm": 0.4293298125267029,
|
| 28 |
-
"learning_rate": 3.3333333333333335e-05,
|
| 29 |
-
"loss": 1.5965,
|
| 30 |
-
"step": 3
|
| 31 |
-
},
|
| 32 |
-
{
|
| 33 |
-
"epoch": 0.14479638009049775,
|
| 34 |
-
"grad_norm": 0.30257710814476013,
|
| 35 |
-
"learning_rate": 4.4444444444444447e-05,
|
| 36 |
-
"loss": 1.6076,
|
| 37 |
-
"step": 4
|
| 38 |
-
},
|
| 39 |
-
{
|
| 40 |
-
"epoch": 0.18099547511312217,
|
| 41 |
-
"grad_norm": 0.338920921087265,
|
| 42 |
-
"learning_rate": 5.555555555555556e-05,
|
| 43 |
-
"loss": 1.6144,
|
| 44 |
-
"step": 5
|
| 45 |
-
},
|
| 46 |
-
{
|
| 47 |
-
"epoch": 0.2171945701357466,
|
| 48 |
-
"grad_norm": 0.393881618976593,
|
| 49 |
-
"learning_rate": 6.666666666666667e-05,
|
| 50 |
-
"loss": 1.5657,
|
| 51 |
-
"step": 6
|
| 52 |
-
},
|
| 53 |
-
{
|
| 54 |
-
"epoch": 0.25339366515837103,
|
| 55 |
-
"grad_norm": 0.2913854718208313,
|
| 56 |
-
"learning_rate": 7.777777777777778e-05,
|
| 57 |
-
"loss": 1.5651,
|
| 58 |
-
"step": 7
|
| 59 |
-
},
|
| 60 |
-
{
|
| 61 |
-
"epoch": 0.2895927601809955,
|
| 62 |
-
"grad_norm": 0.2615966498851776,
|
| 63 |
-
"learning_rate": 8.888888888888889e-05,
|
| 64 |
-
"loss": 1.5488,
|
| 65 |
-
"step": 8
|
| 66 |
-
},
|
| 67 |
-
{
|
| 68 |
-
"epoch": 0.3257918552036199,
|
| 69 |
-
"grad_norm": 0.2777751386165619,
|
| 70 |
-
"learning_rate": 0.0001,
|
| 71 |
-
"loss": 1.5898,
|
| 72 |
-
"step": 9
|
| 73 |
-
},
|
| 74 |
-
{
|
| 75 |
-
"epoch": 0.36199095022624433,
|
| 76 |
-
"grad_norm": 0.24253539741039276,
|
| 77 |
-
"learning_rate": 9.99524110790929e-05,
|
| 78 |
-
"loss": 1.5448,
|
| 79 |
-
"step": 10
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"epoch": 0.39819004524886875,
|
| 83 |
-
"grad_norm": 0.21929268538951874,
|
| 84 |
-
"learning_rate": 9.980973490458728e-05,
|
| 85 |
-
"loss": 1.5285,
|
| 86 |
-
"step": 11
|
| 87 |
-
},
|
| 88 |
-
{
|
| 89 |
-
"epoch": 0.4343891402714932,
|
| 90 |
-
"grad_norm": 0.2206713855266571,
|
| 91 |
-
"learning_rate": 9.957224306869053e-05,
|
| 92 |
-
"loss": 1.5645,
|
| 93 |
-
"step": 12
|
| 94 |
-
},
|
| 95 |
-
{
|
| 96 |
-
"epoch": 0.47058823529411764,
|
| 97 |
-
"grad_norm": 0.19960802793502808,
|
| 98 |
-
"learning_rate": 9.924038765061042e-05,
|
| 99 |
-
"loss": 1.4987,
|
| 100 |
-
"step": 13
|
| 101 |
-
},
|
| 102 |
-
{
|
| 103 |
-
"epoch": 0.5067873303167421,
|
| 104 |
-
"grad_norm": 0.20623129606246948,
|
| 105 |
-
"learning_rate": 9.881480035599667e-05,
|
| 106 |
-
"loss": 1.4982,
|
| 107 |
-
"step": 14
|
| 108 |
-
},
|
| 109 |
-
{
|
| 110 |
-
"epoch": 0.5429864253393665,
|
| 111 |
-
"grad_norm": 0.2134510725736618,
|
| 112 |
-
"learning_rate": 9.829629131445342e-05,
|
| 113 |
-
"loss": 1.5061,
|
| 114 |
-
"step": 15
|
| 115 |
-
},
|
| 116 |
-
{
|
| 117 |
-
"epoch": 0.579185520361991,
|
| 118 |
-
"grad_norm": 0.20414741337299347,
|
| 119 |
-
"learning_rate": 9.768584753741134e-05,
|
| 120 |
-
"loss": 1.4963,
|
| 121 |
-
"step": 16
|
| 122 |
-
},
|
| 123 |
-
{
|
| 124 |
-
"epoch": 0.6153846153846154,
|
| 125 |
-
"grad_norm": 0.19349144399166107,
|
| 126 |
-
"learning_rate": 9.698463103929542e-05,
|
| 127 |
-
"loss": 1.5242,
|
| 128 |
-
"step": 17
|
| 129 |
-
},
|
| 130 |
-
{
|
| 131 |
-
"epoch": 0.6515837104072398,
|
| 132 |
-
"grad_norm": 0.19233722984790802,
|
| 133 |
-
"learning_rate": 9.619397662556435e-05,
|
| 134 |
-
"loss": 1.49,
|
| 135 |
-
"step": 18
|
| 136 |
-
},
|
| 137 |
-
{
|
| 138 |
-
"epoch": 0.6877828054298643,
|
| 139 |
-
"grad_norm": 0.1920696496963501,
|
| 140 |
-
"learning_rate": 9.53153893518325e-05,
|
| 141 |
-
"loss": 1.5342,
|
| 142 |
-
"step": 19
|
| 143 |
-
},
|
| 144 |
-
{
|
| 145 |
-
"epoch": 0.7239819004524887,
|
| 146 |
-
"grad_norm": 0.18896055221557617,
|
| 147 |
-
"learning_rate": 9.435054165891109e-05,
|
| 148 |
-
"loss": 1.5256,
|
| 149 |
-
"step": 20
|
| 150 |
-
},
|
| 151 |
-
{
|
| 152 |
-
"epoch": 0.7601809954751131,
|
| 153 |
-
"grad_norm": 0.18282486498355865,
|
| 154 |
-
"learning_rate": 9.330127018922194e-05,
|
| 155 |
-
"loss": 1.5167,
|
| 156 |
-
"step": 21
|
| 157 |
-
},
|
| 158 |
-
{
|
| 159 |
-
"epoch": 0.7963800904977375,
|
| 160 |
-
"grad_norm": 0.19715480506420135,
|
| 161 |
-
"learning_rate": 9.21695722906443e-05,
|
| 162 |
-
"loss": 1.5255,
|
| 163 |
-
"step": 22
|
| 164 |
-
},
|
| 165 |
-
{
|
| 166 |
-
"epoch": 0.832579185520362,
|
| 167 |
-
"grad_norm": 0.17317330837249756,
|
| 168 |
-
"learning_rate": 9.09576022144496e-05,
|
| 169 |
-
"loss": 1.5062,
|
| 170 |
-
"step": 23
|
| 171 |
-
},
|
| 172 |
-
{
|
| 173 |
-
"epoch": 0.8687782805429864,
|
| 174 |
-
"grad_norm": 0.18779075145721436,
|
| 175 |
-
"learning_rate": 8.966766701456177e-05,
|
| 176 |
-
"loss": 1.4894,
|
| 177 |
-
"step": 24
|
| 178 |
-
},
|
| 179 |
-
{
|
| 180 |
-
"epoch": 0.9049773755656109,
|
| 181 |
-
"grad_norm": 0.1841159462928772,
|
| 182 |
-
"learning_rate": 8.83022221559489e-05,
|
| 183 |
-
"loss": 1.4553,
|
| 184 |
-
"step": 25
|
| 185 |
-
},
|
| 186 |
-
{
|
| 187 |
-
"epoch": 0.9411764705882353,
|
| 188 |
-
"grad_norm": 0.1778552532196045,
|
| 189 |
-
"learning_rate": 8.68638668405062e-05,
|
| 190 |
-
"loss": 1.4824,
|
| 191 |
-
"step": 26
|
| 192 |
-
},
|
| 193 |
-
{
|
| 194 |
-
"epoch": 0.9773755656108597,
|
| 195 |
-
"grad_norm": 0.18053092062473297,
|
| 196 |
-
"learning_rate": 8.535533905932738e-05,
|
| 197 |
-
"loss": 1.5244,
|
| 198 |
-
"step": 27
|
| 199 |
-
},
|
| 200 |
-
{
|
| 201 |
-
"epoch": 1.0248868778280542,
|
| 202 |
-
"grad_norm": 0.17003145813941956,
|
| 203 |
-
"learning_rate": 8.377951038078302e-05,
|
| 204 |
-
"loss": 1.4473,
|
| 205 |
-
"step": 28
|
| 206 |
-
},
|
| 207 |
-
{
|
| 208 |
-
"epoch": 1.0610859728506787,
|
| 209 |
-
"grad_norm": 0.1815570592880249,
|
| 210 |
-
"learning_rate": 8.213938048432697e-05,
|
| 211 |
-
"loss": 1.4101,
|
| 212 |
-
"step": 29
|
| 213 |
-
},
|
| 214 |
-
{
|
| 215 |
-
"epoch": 1.0972850678733033,
|
| 216 |
-
"grad_norm": 0.17359577119350433,
|
| 217 |
-
"learning_rate": 8.043807145043604e-05,
|
| 218 |
-
"loss": 1.4621,
|
| 219 |
-
"step": 30
|
| 220 |
-
},
|
| 221 |
-
{
|
| 222 |
-
"epoch": 1.1334841628959276,
|
| 223 |
-
"grad_norm": 0.18072284758090973,
|
| 224 |
-
"learning_rate": 7.86788218175523e-05,
|
| 225 |
-
"loss": 1.4011,
|
| 226 |
-
"step": 31
|
| 227 |
-
},
|
| 228 |
-
{
|
| 229 |
-
"epoch": 1.169683257918552,
|
| 230 |
-
"grad_norm": 0.18027463555335999,
|
| 231 |
-
"learning_rate": 7.68649804173412e-05,
|
| 232 |
-
"loss": 1.4529,
|
| 233 |
-
"step": 32
|
| 234 |
-
},
|
| 235 |
-
{
|
| 236 |
-
"epoch": 1.2058823529411764,
|
| 237 |
-
"grad_norm": 0.18900279700756073,
|
| 238 |
-
"learning_rate": 7.500000000000001e-05,
|
| 239 |
-
"loss": 1.4195,
|
| 240 |
-
"step": 33
|
| 241 |
-
},
|
| 242 |
-
{
|
| 243 |
-
"epoch": 1.242081447963801,
|
| 244 |
-
"grad_norm": 0.17625436186790466,
|
| 245 |
-
"learning_rate": 7.308743066175172e-05,
|
| 246 |
-
"loss": 1.4106,
|
| 247 |
-
"step": 34
|
| 248 |
-
},
|
| 249 |
-
{
|
| 250 |
-
"epoch": 1.2782805429864252,
|
| 251 |
-
"grad_norm": 0.18460573256015778,
|
| 252 |
-
"learning_rate": 7.113091308703498e-05,
|
| 253 |
-
"loss": 1.3482,
|
| 254 |
-
"step": 35
|
| 255 |
-
},
|
| 256 |
-
{
|
| 257 |
-
"epoch": 1.3144796380090498,
|
| 258 |
-
"grad_norm": 0.1863405853509903,
|
| 259 |
-
"learning_rate": 6.91341716182545e-05,
|
| 260 |
-
"loss": 1.4463,
|
| 261 |
-
"step": 36
|
| 262 |
-
},
|
| 263 |
-
{
|
| 264 |
-
"epoch": 1.3506787330316743,
|
| 265 |
-
"grad_norm": 0.188517764210701,
|
| 266 |
-
"learning_rate": 6.710100716628344e-05,
|
| 267 |
-
"loss": 1.3528,
|
| 268 |
-
"step": 37
|
| 269 |
-
},
|
| 270 |
-
{
|
| 271 |
-
"epoch": 1.3868778280542986,
|
| 272 |
-
"grad_norm": 0.1890035718679428,
|
| 273 |
-
"learning_rate": 6.503528997521366e-05,
|
| 274 |
-
"loss": 1.3881,
|
| 275 |
-
"step": 38
|
| 276 |
-
},
|
| 277 |
-
{
|
| 278 |
-
"epoch": 1.4230769230769231,
|
| 279 |
-
"grad_norm": 0.19418419897556305,
|
| 280 |
-
"learning_rate": 6.294095225512603e-05,
|
| 281 |
-
"loss": 1.374,
|
| 282 |
-
"step": 39
|
| 283 |
-
},
|
| 284 |
-
{
|
| 285 |
-
"epoch": 1.4592760180995474,
|
| 286 |
-
"grad_norm": 0.1959460824728012,
|
| 287 |
-
"learning_rate": 6.0821980696905146e-05,
|
| 288 |
-
"loss": 1.3717,
|
| 289 |
-
"step": 40
|
| 290 |
-
},
|
| 291 |
-
{
|
| 292 |
-
"epoch": 1.495475113122172,
|
| 293 |
-
"grad_norm": 0.20840130746364594,
|
| 294 |
-
"learning_rate": 5.868240888334653e-05,
|
| 295 |
-
"loss": 1.37,
|
| 296 |
-
"step": 41
|
| 297 |
-
},
|
| 298 |
-
{
|
| 299 |
-
"epoch": 1.5316742081447963,
|
| 300 |
-
"grad_norm": 0.21801875531673431,
|
| 301 |
-
"learning_rate": 5.6526309611002594e-05,
|
| 302 |
-
"loss": 1.359,
|
| 303 |
-
"step": 42
|
| 304 |
-
},
|
| 305 |
-
{
|
| 306 |
-
"epoch": 1.5678733031674208,
|
| 307 |
-
"grad_norm": 0.20987379550933838,
|
| 308 |
-
"learning_rate": 5.435778713738292e-05,
|
| 309 |
-
"loss": 1.421,
|
| 310 |
-
"step": 43
|
| 311 |
-
},
|
| 312 |
-
{
|
| 313 |
-
"epoch": 1.6040723981900453,
|
| 314 |
-
"grad_norm": 0.19880157709121704,
|
| 315 |
-
"learning_rate": 5.218096936826681e-05,
|
| 316 |
-
"loss": 1.4027,
|
| 317 |
-
"step": 44
|
| 318 |
-
},
|
| 319 |
-
{
|
| 320 |
-
"epoch": 1.6402714932126696,
|
| 321 |
-
"grad_norm": 0.20954720675945282,
|
| 322 |
-
"learning_rate": 5e-05,
|
| 323 |
-
"loss": 1.3634,
|
| 324 |
-
"step": 45
|
| 325 |
-
},
|
| 326 |
-
{
|
| 327 |
-
"epoch": 1.6764705882352942,
|
| 328 |
-
"grad_norm": 0.20119519531726837,
|
| 329 |
-
"learning_rate": 4.781903063173321e-05,
|
| 330 |
-
"loss": 1.361,
|
| 331 |
-
"step": 46
|
| 332 |
-
},
|
| 333 |
-
{
|
| 334 |
-
"epoch": 1.7126696832579187,
|
| 335 |
-
"grad_norm": 0.20504230260849,
|
| 336 |
-
"learning_rate": 4.564221286261709e-05,
|
| 337 |
-
"loss": 1.3613,
|
| 338 |
-
"step": 47
|
| 339 |
-
},
|
| 340 |
-
{
|
| 341 |
-
"epoch": 1.748868778280543,
|
| 342 |
-
"grad_norm": 0.20827656984329224,
|
| 343 |
-
"learning_rate": 4.347369038899744e-05,
|
| 344 |
-
"loss": 1.367,
|
| 345 |
-
"step": 48
|
| 346 |
-
},
|
| 347 |
-
{
|
| 348 |
-
"epoch": 1.7850678733031673,
|
| 349 |
-
"grad_norm": 0.21221719682216644,
|
| 350 |
-
"learning_rate": 4.131759111665349e-05,
|
| 351 |
-
"loss": 1.3626,
|
| 352 |
-
"step": 49
|
| 353 |
-
},
|
| 354 |
-
{
|
| 355 |
-
"epoch": 1.8212669683257918,
|
| 356 |
-
"grad_norm": 0.21247024834156036,
|
| 357 |
-
"learning_rate": 3.917801930309486e-05,
|
| 358 |
-
"loss": 1.3847,
|
| 359 |
-
"step": 50
|
| 360 |
-
},
|
| 361 |
-
{
|
| 362 |
-
"epoch": 1.8574660633484164,
|
| 363 |
-
"grad_norm": 0.21873697638511658,
|
| 364 |
-
"learning_rate": 3.705904774487396e-05,
|
| 365 |
-
"loss": 1.3584,
|
| 366 |
-
"step": 51
|
| 367 |
-
},
|
| 368 |
-
{
|
| 369 |
-
"epoch": 1.8936651583710407,
|
| 370 |
-
"grad_norm": 0.21476612985134125,
|
| 371 |
-
"learning_rate": 3.4964710024786354e-05,
|
| 372 |
-
"loss": 1.393,
|
| 373 |
-
"step": 52
|
| 374 |
-
},
|
| 375 |
-
{
|
| 376 |
-
"epoch": 1.9298642533936652,
|
| 377 |
-
"grad_norm": 0.21541458368301392,
|
| 378 |
-
"learning_rate": 3.289899283371657e-05,
|
| 379 |
-
"loss": 1.3333,
|
| 380 |
-
"step": 53
|
| 381 |
-
},
|
| 382 |
-
{
|
| 383 |
-
"epoch": 1.9660633484162897,
|
| 384 |
-
"grad_norm": 0.2195931226015091,
|
| 385 |
-
"learning_rate": 3.086582838174551e-05,
|
| 386 |
-
"loss": 1.3567,
|
| 387 |
-
"step": 54
|
| 388 |
-
},
|
| 389 |
-
{
|
| 390 |
-
"epoch": 2.013574660633484,
|
| 391 |
-
"grad_norm": 0.22267796099185944,
|
| 392 |
-
"learning_rate": 2.886908691296504e-05,
|
| 393 |
-
"loss": 1.3388,
|
| 394 |
-
"step": 55
|
| 395 |
-
},
|
| 396 |
-
{
|
| 397 |
-
"epoch": 2.0497737556561084,
|
| 398 |
-
"grad_norm": 0.2236703336238861,
|
| 399 |
-
"learning_rate": 2.6912569338248315e-05,
|
| 400 |
-
"loss": 1.3288,
|
| 401 |
-
"step": 56
|
| 402 |
-
},
|
| 403 |
-
{
|
| 404 |
-
"epoch": 2.085972850678733,
|
| 405 |
-
"grad_norm": 0.22568458318710327,
|
| 406 |
-
"learning_rate": 2.500000000000001e-05,
|
| 407 |
-
"loss": 1.2998,
|
| 408 |
-
"step": 57
|
| 409 |
-
},
|
| 410 |
-
{
|
| 411 |
-
"epoch": 2.1221719457013575,
|
| 412 |
-
"grad_norm": 0.22315552830696106,
|
| 413 |
-
"learning_rate": 2.3135019582658802e-05,
|
| 414 |
-
"loss": 1.2406,
|
| 415 |
-
"step": 58
|
| 416 |
-
},
|
| 417 |
-
{
|
| 418 |
-
"epoch": 2.158371040723982,
|
| 419 |
-
"grad_norm": 0.22059525549411774,
|
| 420 |
-
"learning_rate": 2.132117818244771e-05,
|
| 421 |
-
"loss": 1.2579,
|
| 422 |
-
"step": 59
|
| 423 |
-
},
|
| 424 |
-
{
|
| 425 |
-
"epoch": 2.1945701357466065,
|
| 426 |
-
"grad_norm": 0.24967165291309357,
|
| 427 |
-
"learning_rate": 1.9561928549563968e-05,
|
| 428 |
-
"loss": 1.2737,
|
| 429 |
-
"step": 60
|
| 430 |
-
},
|
| 431 |
-
{
|
| 432 |
-
"epoch": 2.230769230769231,
|
| 433 |
-
"grad_norm": 0.2367183119058609,
|
| 434 |
-
"learning_rate": 1.7860619515673033e-05,
|
| 435 |
-
"loss": 1.3014,
|
| 436 |
-
"step": 61
|
| 437 |
-
},
|
| 438 |
-
{
|
| 439 |
-
"epoch": 2.266968325791855,
|
| 440 |
-
"grad_norm": 0.2517261207103729,
|
| 441 |
-
"learning_rate": 1.622048961921699e-05,
|
| 442 |
-
"loss": 1.3528,
|
| 443 |
-
"step": 62
|
| 444 |
-
},
|
| 445 |
-
{
|
| 446 |
-
"epoch": 2.3031674208144794,
|
| 447 |
-
"grad_norm": 0.235427126288414,
|
| 448 |
-
"learning_rate": 1.4644660940672627e-05,
|
| 449 |
-
"loss": 1.2639,
|
| 450 |
-
"step": 63
|
| 451 |
-
},
|
| 452 |
-
{
|
| 453 |
-
"epoch": 2.339366515837104,
|
| 454 |
-
"grad_norm": 0.22943593561649323,
|
| 455 |
-
"learning_rate": 1.3136133159493802e-05,
|
| 456 |
-
"loss": 1.3244,
|
| 457 |
-
"step": 64
|
| 458 |
-
},
|
| 459 |
-
{
|
| 460 |
-
"epoch": 2.3755656108597285,
|
| 461 |
-
"grad_norm": 0.22623376548290253,
|
| 462 |
-
"learning_rate": 1.1697777844051105e-05,
|
| 463 |
-
"loss": 1.3534,
|
| 464 |
-
"step": 65
|
| 465 |
-
},
|
| 466 |
-
{
|
| 467 |
-
"epoch": 2.411764705882353,
|
| 468 |
-
"grad_norm": 0.240826815366745,
|
| 469 |
-
"learning_rate": 1.0332332985438248e-05,
|
| 470 |
-
"loss": 1.2637,
|
| 471 |
-
"step": 66
|
| 472 |
-
},
|
| 473 |
-
{
|
| 474 |
-
"epoch": 2.4479638009049776,
|
| 475 |
-
"grad_norm": 0.2174130380153656,
|
| 476 |
-
"learning_rate": 9.042397785550405e-06,
|
| 477 |
-
"loss": 1.3538,
|
| 478 |
-
"step": 67
|
| 479 |
-
},
|
| 480 |
-
{
|
| 481 |
-
"epoch": 2.484162895927602,
|
| 482 |
-
"grad_norm": 0.23589667677879333,
|
| 483 |
-
"learning_rate": 7.830427709355725e-06,
|
| 484 |
-
"loss": 1.3247,
|
| 485 |
-
"step": 68
|
| 486 |
-
},
|
| 487 |
-
{
|
| 488 |
-
"epoch": 2.520361990950226,
|
| 489 |
-
"grad_norm": 0.24112889170646667,
|
| 490 |
-
"learning_rate": 6.698729810778065e-06,
|
| 491 |
-
"loss": 1.2721,
|
| 492 |
-
"step": 69
|
| 493 |
-
},
|
| 494 |
-
{
|
| 495 |
-
"epoch": 2.5565610859728505,
|
| 496 |
-
"grad_norm": 0.23095567524433136,
|
| 497 |
-
"learning_rate": 5.649458341088915e-06,
|
| 498 |
-
"loss": 1.2966,
|
| 499 |
-
"step": 70
|
| 500 |
-
},
|
| 501 |
-
{
|
| 502 |
-
"epoch": 2.5927601809954752,
|
| 503 |
-
"grad_norm": 0.2425680309534073,
|
| 504 |
-
"learning_rate": 4.684610648167503e-06,
|
| 505 |
-
"loss": 1.2594,
|
| 506 |
-
"step": 71
|
| 507 |
-
},
|
| 508 |
-
{
|
| 509 |
-
"epoch": 2.6289592760180995,
|
| 510 |
-
"grad_norm": 0.2282722145318985,
|
| 511 |
-
"learning_rate": 3.8060233744356633e-06,
|
| 512 |
-
"loss": 1.2951,
|
| 513 |
-
"step": 72
|
| 514 |
-
},
|
| 515 |
-
{
|
| 516 |
-
"epoch": 2.665158371040724,
|
| 517 |
-
"grad_norm": 0.2365112006664276,
|
| 518 |
-
"learning_rate": 3.0153689607045845e-06,
|
| 519 |
-
"loss": 1.3408,
|
| 520 |
-
"step": 73
|
| 521 |
-
},
|
| 522 |
-
{
|
| 523 |
-
"epoch": 2.7013574660633486,
|
| 524 |
-
"grad_norm": 0.23960916697978973,
|
| 525 |
-
"learning_rate": 2.314152462588659e-06,
|
| 526 |
-
"loss": 1.2951,
|
| 527 |
-
"step": 74
|
| 528 |
-
},
|
| 529 |
-
{
|
| 530 |
-
"epoch": 2.737556561085973,
|
| 531 |
-
"grad_norm": 0.23407232761383057,
|
| 532 |
-
"learning_rate": 1.70370868554659e-06,
|
| 533 |
-
"loss": 1.2927,
|
| 534 |
-
"step": 75
|
| 535 |
-
},
|
| 536 |
-
{
|
| 537 |
-
"epoch": 2.773755656108597,
|
| 538 |
-
"grad_norm": 0.23612752556800842,
|
| 539 |
-
"learning_rate": 1.1851996440033319e-06,
|
| 540 |
-
"loss": 1.3133,
|
| 541 |
-
"step": 76
|
| 542 |
-
},
|
| 543 |
-
{
|
| 544 |
-
"epoch": 2.8099547511312215,
|
| 545 |
-
"grad_norm": 0.24510255455970764,
|
| 546 |
-
"learning_rate": 7.596123493895991e-07,
|
| 547 |
-
"loss": 1.3135,
|
| 548 |
-
"step": 77
|
| 549 |
-
},
|
| 550 |
-
{
|
| 551 |
-
"epoch": 2.8461538461538463,
|
| 552 |
-
"grad_norm": 0.25504744052886963,
|
| 553 |
-
"learning_rate": 4.277569313094809e-07,
|
| 554 |
-
"loss": 1.2631,
|
| 555 |
-
"step": 78
|
| 556 |
-
},
|
| 557 |
-
{
|
| 558 |
-
"epoch": 2.8823529411764706,
|
| 559 |
-
"grad_norm": 0.22783517837524414,
|
| 560 |
-
"learning_rate": 1.9026509541272275e-07,
|
| 561 |
-
"loss": 1.2773,
|
| 562 |
-
"step": 79
|
| 563 |
-
},
|
| 564 |
-
{
|
| 565 |
-
"epoch": 2.918552036199095,
|
| 566 |
-
"grad_norm": 0.23234006762504578,
|
| 567 |
-
"learning_rate": 4.7588920907110094e-08,
|
| 568 |
-
"loss": 1.2997,
|
| 569 |
-
"step": 80
|
| 570 |
-
},
|
| 571 |
-
{
|
| 572 |
-
"epoch": 2.9547511312217196,
|
| 573 |
-
"grad_norm": 0.24794724583625793,
|
| 574 |
-
"learning_rate": 0.0,
|
| 575 |
-
"loss": 1.268,
|
| 576 |
-
"step": 81
|
| 577 |
-
},
|
| 578 |
-
{
|
| 579 |
-
"epoch": 2.9547511312217196,
|
| 580 |
-
"step": 81,
|
| 581 |
-
"total_flos": 1.9929234183615939e+18,
|
| 582 |
-
"train_loss": 1.4086421551527801,
|
| 583 |
-
"train_runtime": 8849.9709,
|
| 584 |
-
"train_samples_per_second": 0.598,
|
| 585 |
-
"train_steps_per_second": 0.009
|
| 586 |
-
}
|
| 587 |
-
],
|
| 588 |
-
"logging_steps": 1,
|
| 589 |
-
"max_steps": 81,
|
| 590 |
-
"num_input_tokens_seen": 0,
|
| 591 |
-
"num_train_epochs": 3,
|
| 592 |
-
"save_steps": 200,
|
| 593 |
-
"stateful_callbacks": {
|
| 594 |
-
"TrainerControl": {
|
| 595 |
-
"args": {
|
| 596 |
-
"should_epoch_stop": false,
|
| 597 |
-
"should_evaluate": false,
|
| 598 |
-
"should_log": false,
|
| 599 |
-
"should_save": true,
|
| 600 |
-
"should_training_stop": true
|
| 601 |
-
},
|
| 602 |
-
"attributes": {}
|
| 603 |
-
}
|
| 604 |
-
},
|
| 605 |
-
"total_flos": 1.9929234183615939e+18,
|
| 606 |
-
"train_batch_size": 2,
|
| 607 |
-
"trial_name": null,
|
| 608 |
-
"trial_params": null
|
| 609 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_10/training_loss.png
DELETED
|
Binary file (51.8 kB)
|
|
|
llama_factory/v3-20241225-1_10/vocab.json
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama_factory/v3-20241225-1_5/README.md
DELETED
|
@@ -1,62 +0,0 @@
|
|
| 1 |
-
---
|
| 2 |
-
library_name: peft
|
| 3 |
-
license: other
|
| 4 |
-
base_model: /disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct
|
| 5 |
-
tags:
|
| 6 |
-
- llama-factory
|
| 7 |
-
- lora
|
| 8 |
-
- generated_from_trainer
|
| 9 |
-
model-index:
|
| 10 |
-
- name: v3-20241225-1_5
|
| 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 |
-
# v3-20241225-1_5
|
| 18 |
-
|
| 19 |
-
This model is a fine-tuned version of [/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct](https://huggingface.co//disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct) on the M^2RAR-20241225-MLLM-1_5 dataset.
|
| 20 |
-
|
| 21 |
-
## Model description
|
| 22 |
-
|
| 23 |
-
More information needed
|
| 24 |
-
|
| 25 |
-
## Intended uses & limitations
|
| 26 |
-
|
| 27 |
-
More information needed
|
| 28 |
-
|
| 29 |
-
## Training and evaluation data
|
| 30 |
-
|
| 31 |
-
More information needed
|
| 32 |
-
|
| 33 |
-
## Training procedure
|
| 34 |
-
|
| 35 |
-
### Training hyperparameters
|
| 36 |
-
|
| 37 |
-
The following hyperparameters were used during training:
|
| 38 |
-
- learning_rate: 0.0001
|
| 39 |
-
- train_batch_size: 2
|
| 40 |
-
- eval_batch_size: 8
|
| 41 |
-
- seed: 42
|
| 42 |
-
- distributed_type: multi-GPU
|
| 43 |
-
- num_devices: 2
|
| 44 |
-
- gradient_accumulation_steps: 16
|
| 45 |
-
- total_train_batch_size: 64
|
| 46 |
-
- total_eval_batch_size: 16
|
| 47 |
-
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
| 48 |
-
- lr_scheduler_type: cosine
|
| 49 |
-
- lr_scheduler_warmup_ratio: 0.1
|
| 50 |
-
- num_epochs: 3.0
|
| 51 |
-
|
| 52 |
-
### Training results
|
| 53 |
-
|
| 54 |
-
|
| 55 |
-
|
| 56 |
-
### Framework versions
|
| 57 |
-
|
| 58 |
-
- PEFT 0.12.0
|
| 59 |
-
- Transformers 4.46.1
|
| 60 |
-
- Pytorch 2.3.1+cu121
|
| 61 |
-
- Datasets 3.1.0
|
| 62 |
-
- Tokenizers 0.20.3
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_5/adapter_config.json
DELETED
|
@@ -1,26 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"alpha_pattern": {},
|
| 3 |
-
"auto_mapping": null,
|
| 4 |
-
"base_model_name_or_path": "/disk/maziao/model-zoo/hf-repo/models--Qwen--Qwen2-VL-7B-Instruct",
|
| 5 |
-
"bias": "none",
|
| 6 |
-
"fan_in_fan_out": false,
|
| 7 |
-
"inference_mode": true,
|
| 8 |
-
"init_lora_weights": true,
|
| 9 |
-
"layer_replication": null,
|
| 10 |
-
"layers_pattern": null,
|
| 11 |
-
"layers_to_transform": null,
|
| 12 |
-
"loftq_config": {},
|
| 13 |
-
"lora_alpha": 256,
|
| 14 |
-
"lora_dropout": 0.0,
|
| 15 |
-
"megatron_config": null,
|
| 16 |
-
"megatron_core": "megatron.core",
|
| 17 |
-
"modules_to_save": null,
|
| 18 |
-
"peft_type": "LORA",
|
| 19 |
-
"r": 128,
|
| 20 |
-
"rank_pattern": {},
|
| 21 |
-
"revision": null,
|
| 22 |
-
"target_modules": "^(?!.*visual).*(?:q_proj|down_proj|k_proj|up_proj|gate_proj|v_proj|o_proj).*",
|
| 23 |
-
"task_type": "CAUSAL_LM",
|
| 24 |
-
"use_dora": false,
|
| 25 |
-
"use_rslora": false
|
| 26 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_5/added_tokens.json
DELETED
|
@@ -1,16 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"<|box_end|>": 151649,
|
| 3 |
-
"<|box_start|>": 151648,
|
| 4 |
-
"<|endoftext|>": 151643,
|
| 5 |
-
"<|im_end|>": 151645,
|
| 6 |
-
"<|im_start|>": 151644,
|
| 7 |
-
"<|image_pad|>": 151655,
|
| 8 |
-
"<|object_ref_end|>": 151647,
|
| 9 |
-
"<|object_ref_start|>": 151646,
|
| 10 |
-
"<|quad_end|>": 151651,
|
| 11 |
-
"<|quad_start|>": 151650,
|
| 12 |
-
"<|video_pad|>": 151656,
|
| 13 |
-
"<|vision_end|>": 151653,
|
| 14 |
-
"<|vision_pad|>": 151654,
|
| 15 |
-
"<|vision_start|>": 151652
|
| 16 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_5/all_results.json
DELETED
|
@@ -1,8 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"epoch": 2.987551867219917,
|
| 3 |
-
"total_flos": 2.252458950505005e+18,
|
| 4 |
-
"train_loss": 1.4155288457870483,
|
| 5 |
-
"train_runtime": 9888.3803,
|
| 6 |
-
"train_samples_per_second": 0.584,
|
| 7 |
-
"train_steps_per_second": 0.009
|
| 8 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_5/chat_template.json
DELETED
|
@@ -1,3 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_5/merges.txt
DELETED
|
The diff for this file is too large to render.
See raw diff
|
|
|
llama_factory/v3-20241225-1_5/preprocessor_config.json
DELETED
|
@@ -1,29 +0,0 @@
|
|
| 1 |
-
{
|
| 2 |
-
"do_convert_rgb": true,
|
| 3 |
-
"do_normalize": true,
|
| 4 |
-
"do_rescale": true,
|
| 5 |
-
"do_resize": true,
|
| 6 |
-
"image_mean": [
|
| 7 |
-
0.48145466,
|
| 8 |
-
0.4578275,
|
| 9 |
-
0.40821073
|
| 10 |
-
],
|
| 11 |
-
"image_processor_type": "Qwen2VLImageProcessor",
|
| 12 |
-
"image_std": [
|
| 13 |
-
0.26862954,
|
| 14 |
-
0.26130258,
|
| 15 |
-
0.27577711
|
| 16 |
-
],
|
| 17 |
-
"max_pixels": 12845056,
|
| 18 |
-
"merge_size": 2,
|
| 19 |
-
"min_pixels": 3136,
|
| 20 |
-
"patch_size": 14,
|
| 21 |
-
"processor_class": "Qwen2VLProcessor",
|
| 22 |
-
"resample": 3,
|
| 23 |
-
"rescale_factor": 0.00392156862745098,
|
| 24 |
-
"size": {
|
| 25 |
-
"max_pixels": 12845056,
|
| 26 |
-
"min_pixels": 3136
|
| 27 |
-
},
|
| 28 |
-
"temporal_patch_size": 2
|
| 29 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
llama_factory/v3-20241225-1_5/special_tokens_map.json
DELETED
|
@@ -1,31 +0,0 @@
|
|
| 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 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|