Model save
Browse files- README.md +134 -0
- adapter_model.safetensors +1 -1
- chat_template.json +3 -0
- preprocessor_config.json +29 -0
README.md
ADDED
@@ -0,0 +1,134 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
library_name: peft
|
3 |
+
license: apache-2.0
|
4 |
+
base_model: ben81828/CADICA_qwenvl_direction
|
5 |
+
tags:
|
6 |
+
- llama-factory
|
7 |
+
- generated_from_trainer
|
8 |
+
model-index:
|
9 |
+
- name: qwenvl-2B-cadica-direction-then-detect-and-classify-scale6
|
10 |
+
results: []
|
11 |
+
---
|
12 |
+
|
13 |
+
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
14 |
+
should probably proofread and complete it, then remove this comment. -->
|
15 |
+
|
16 |
+
# qwenvl-2B-cadica-direction-then-detect-and-classify-scale6
|
17 |
+
|
18 |
+
This model is a fine-tuned version of [ben81828/CADICA_qwenvl_direction](https://huggingface.co/ben81828/CADICA_qwenvl_direction) on an unknown dataset.
|
19 |
+
It achieves the following results on the evaluation set:
|
20 |
+
- Loss: 0.4078
|
21 |
+
- Num Input Tokens Seen: 35305984
|
22 |
+
|
23 |
+
## Model description
|
24 |
+
|
25 |
+
More information needed
|
26 |
+
|
27 |
+
## Intended uses & limitations
|
28 |
+
|
29 |
+
More information needed
|
30 |
+
|
31 |
+
## Training and evaluation data
|
32 |
+
|
33 |
+
More information needed
|
34 |
+
|
35 |
+
## Training procedure
|
36 |
+
|
37 |
+
### Training hyperparameters
|
38 |
+
|
39 |
+
The following hyperparameters were used during training:
|
40 |
+
- learning_rate: 0.0001
|
41 |
+
- train_batch_size: 1
|
42 |
+
- eval_batch_size: 1
|
43 |
+
- seed: 42
|
44 |
+
- distributed_type: multi-GPU
|
45 |
+
- num_devices: 4
|
46 |
+
- gradient_accumulation_steps: 6
|
47 |
+
- total_train_batch_size: 24
|
48 |
+
- total_eval_batch_size: 4
|
49 |
+
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
|
50 |
+
- lr_scheduler_type: cosine
|
51 |
+
- lr_scheduler_warmup_ratio: 0.05
|
52 |
+
- training_steps: 3400
|
53 |
+
|
54 |
+
### Training results
|
55 |
+
|
56 |
+
| Training Loss | Epoch | Step | Validation Loss | Input Tokens Seen |
|
57 |
+
|:-------------:|:------:|:----:|:---------------:|:-----------------:|
|
58 |
+
| 1.3918 | 0.0148 | 50 | 1.0422 | 516240 |
|
59 |
+
| 0.8208 | 0.0295 | 100 | 0.8917 | 1030696 |
|
60 |
+
| 0.8125 | 0.0443 | 150 | 0.9009 | 1550792 |
|
61 |
+
| 0.7675 | 0.0591 | 200 | 0.9007 | 2071176 |
|
62 |
+
| 0.7558 | 0.0739 | 250 | 0.8108 | 2587272 |
|
63 |
+
| 0.78 | 0.0886 | 300 | 0.8194 | 3107200 |
|
64 |
+
| 0.6602 | 0.1034 | 350 | 0.7663 | 3625752 |
|
65 |
+
| 0.6739 | 0.1182 | 400 | 0.7039 | 4142592 |
|
66 |
+
| 0.5661 | 0.1329 | 450 | 0.7133 | 4663320 |
|
67 |
+
| 0.6283 | 0.1477 | 500 | 0.6505 | 5183664 |
|
68 |
+
| 0.5957 | 0.1625 | 550 | 0.6883 | 5703016 |
|
69 |
+
| 0.6331 | 0.1773 | 600 | 0.5883 | 6222736 |
|
70 |
+
| 0.5483 | 0.1920 | 650 | 0.6101 | 6743120 |
|
71 |
+
| 0.477 | 0.2068 | 700 | 0.5884 | 7262832 |
|
72 |
+
| 0.514 | 0.2216 | 750 | 0.4666 | 7779872 |
|
73 |
+
| 0.4239 | 0.2363 | 800 | 0.4822 | 8301976 |
|
74 |
+
| 0.4949 | 0.2511 | 850 | 0.6122 | 8822832 |
|
75 |
+
| 0.4852 | 0.2659 | 900 | 0.5606 | 9345160 |
|
76 |
+
| 0.4737 | 0.2806 | 950 | 0.4791 | 9863168 |
|
77 |
+
| 0.4005 | 0.2954 | 1000 | 0.5501 | 10379136 |
|
78 |
+
| 0.3991 | 0.3102 | 1050 | 0.4378 | 10897528 |
|
79 |
+
| 0.4624 | 0.3250 | 1100 | 0.5301 | 11413120 |
|
80 |
+
| 0.4432 | 0.3397 | 1150 | 0.4249 | 11933632 |
|
81 |
+
| 0.3296 | 0.3545 | 1200 | 0.2966 | 12456040 |
|
82 |
+
| 0.335 | 0.3693 | 1250 | 0.3185 | 12972696 |
|
83 |
+
| 0.3594 | 0.3840 | 1300 | 0.4716 | 13493264 |
|
84 |
+
| 0.3731 | 0.3988 | 1350 | 0.5566 | 14014736 |
|
85 |
+
| 0.388 | 0.4136 | 1400 | 0.3866 | 14532288 |
|
86 |
+
| 0.3131 | 0.4284 | 1450 | 0.4740 | 15050992 |
|
87 |
+
| 0.2928 | 0.4431 | 1500 | 0.4049 | 15572048 |
|
88 |
+
| 0.3588 | 0.4579 | 1550 | 0.2871 | 16091960 |
|
89 |
+
| 0.3879 | 0.4727 | 1600 | 0.3136 | 16609960 |
|
90 |
+
| 0.2698 | 0.4874 | 1650 | 0.4020 | 17130896 |
|
91 |
+
| 0.3904 | 0.5022 | 1700 | 0.3297 | 17650984 |
|
92 |
+
| 0.3173 | 0.5170 | 1750 | 0.4491 | 18169344 |
|
93 |
+
| 0.3127 | 0.5318 | 1800 | 0.3499 | 18691928 |
|
94 |
+
| 0.2828 | 0.5465 | 1850 | 0.3781 | 19212992 |
|
95 |
+
| 0.306 | 0.5613 | 1900 | 0.3766 | 19735976 |
|
96 |
+
| 0.2992 | 0.5761 | 1950 | 0.3468 | 20253288 |
|
97 |
+
| 0.2341 | 0.5908 | 2000 | 0.3366 | 20770728 |
|
98 |
+
| 0.2931 | 0.6056 | 2050 | 0.3386 | 21291664 |
|
99 |
+
| 0.1826 | 0.6204 | 2100 | 0.5386 | 21813984 |
|
100 |
+
| 0.2387 | 0.6352 | 2150 | 0.2581 | 22332144 |
|
101 |
+
| 0.2662 | 0.6499 | 2200 | 0.4840 | 22849552 |
|
102 |
+
| 0.2332 | 0.6647 | 2250 | 0.4966 | 23366784 |
|
103 |
+
| 0.2481 | 0.6795 | 2300 | 0.2418 | 23883032 |
|
104 |
+
| 0.2313 | 0.6942 | 2350 | 0.1870 | 24401256 |
|
105 |
+
| 0.262 | 0.7090 | 2400 | 0.3471 | 24921872 |
|
106 |
+
| 0.2412 | 0.7238 | 2450 | 0.3456 | 25439896 |
|
107 |
+
| 0.2382 | 0.7386 | 2500 | 0.2543 | 25961056 |
|
108 |
+
| 0.2364 | 0.7533 | 2550 | 0.3871 | 26477208 |
|
109 |
+
| 0.2082 | 0.7681 | 2600 | 0.3406 | 26997904 |
|
110 |
+
| 0.1736 | 0.7829 | 2650 | 0.2697 | 27521088 |
|
111 |
+
| 0.2225 | 0.7976 | 2700 | 0.4155 | 28042992 |
|
112 |
+
| 0.2501 | 0.8124 | 2750 | 0.4115 | 28561248 |
|
113 |
+
| 0.2507 | 0.8272 | 2800 | 0.3223 | 29079576 |
|
114 |
+
| 0.1928 | 0.8419 | 2850 | 0.2828 | 29600536 |
|
115 |
+
| 0.2029 | 0.8567 | 2900 | 0.3943 | 30118072 |
|
116 |
+
| 0.1692 | 0.8715 | 2950 | 0.2034 | 30637448 |
|
117 |
+
| 0.234 | 0.8863 | 3000 | 0.2556 | 31159736 |
|
118 |
+
| 0.2303 | 0.9010 | 3050 | 0.2253 | 31679080 |
|
119 |
+
| 0.1999 | 0.9158 | 3100 | 0.2710 | 32196176 |
|
120 |
+
| 0.2069 | 0.9306 | 3150 | 0.2029 | 32713824 |
|
121 |
+
| 0.2135 | 0.9453 | 3200 | 0.3564 | 33235872 |
|
122 |
+
| 0.1964 | 0.9601 | 3250 | 0.3081 | 33752488 |
|
123 |
+
| 0.2131 | 0.9749 | 3300 | 0.3541 | 34269496 |
|
124 |
+
| 0.1779 | 0.9897 | 3350 | 0.2255 | 34784784 |
|
125 |
+
| 0.2173 | 1.0044 | 3400 | 0.4078 | 35305984 |
|
126 |
+
|
127 |
+
|
128 |
+
### Framework versions
|
129 |
+
|
130 |
+
- PEFT 0.12.0
|
131 |
+
- Transformers 4.47.0.dev0
|
132 |
+
- Pytorch 2.5.1+cu121
|
133 |
+
- Datasets 3.1.0
|
134 |
+
- Tokenizers 0.20.3
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 29034840
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e895c1cddd40eb0dbe387456240309b06d66fe014fd793905368c3b37bbbff4a
|
3 |
size 29034840
|
chat_template.json
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
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 |
+
}
|
preprocessor_config.json
ADDED
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
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 |
+
}
|