库名称：transformers
基础模型：openai/clip-vit-large-patch14-336
标签：
- 训练生成
模型索引：
- 名称：clip-finetuned-csu-p14-336-e3l57-l
结果：[]
clip-finetuned-csu-p14-336-e3l57-l
该模型是基于openai/clip-vit-large-patch14-336在未知数据集上微调的版本。
在评估集上取得了以下结果：
模型描述
需要更多信息
预期用途与限制
需要更多信息
训练与评估数据
需要更多信息
训练过程
训练超参数
训练过程中使用了以下超参数：
- 学习率：5e-07
- 训练批次大小：128
- 评估批次大小：8
- 随机种子：42
- 优化器：Adam（β1=0.9，β2=0.999，epsilon=1e-08）
- 学习率调度器类型：线性
- 训练轮次：3.0
训练结果
| 训练损失 |
轮次 |
步数 |
验证损失 |
| 0.3812 |
0.0533 |
500 |
1.1163 |
| 0.2683 |
0.1067 |
1000 |
0.9684 |
| 0.2119 |
0.1600 |
1500 |
0.9100 |
| 0.1889 |
0.2133 |
2000 |
0.8620 |
| 0.2071 |
0.2666 |
2500 |
0.7918 |
| 0.1588 |
0.3200 |
3000 |
0.7657 |
| 0.1718 |
0.3733 |
3500 |
0.7610 |
| 0.1113 |
0.4266 |
4000 |
0.7458 |
| 0.1313 |
0.4799 |
4500 |
0.7168 |
| 0.1649 |
0.5333 |
5000 |
0.7019 |
| 0.1245 |
0.5866 |
5500 |
0.6812 |
| 0.1286 |
0.6399 |
6000 |
0.6502 |
| 0.1076 |
0.6933 |
6500 |
0.6154 |
| 0.1477 |
0.7466 |
7000 |
0.6118 |
| 0.1315 |
0.7999 |
7500 |
0.6016 |
| 0.1413 |
0.8532 |
8000 |
0.5849 |
| 0.124 |
0.9066 |
8500 |
0.5766 |
| 0.1215 |
0.9599 |
9000 |
0.5559 |
| 0.131 |
1.0132 |
9500 |
0.5633 |
| 0.0348 |
1.0666 |
10000 |
0.5531 |
| 0.0687 |
1.1199 |
10500 |
0.5495 |
| 0.0749 |
1.1732 |
11000 |
0.5474 |
| 0.1083 |
1.2265 |
11500 |
0.5416 |
| 0.0485 |
1.2799 |
12000 |
0.5412 |
| 0.0449 |
1.3332 |
12500 |
0.5511 |
| 0.0847 |
1.3865 |
13000 |
0.5492 |
| 0.0702 |
1.4398 |
13500 |
0.5509 |
| 0.0487 |
1.4932 |
14000 |
0.5447 |
| 0.072 |
1.5465 |
14500 |
0.5490 |
| 0.0325 |
1.5998 |
15000 |
0.5443 |
| 0.0894 |
1.6532 |
15500 |
0.5264 |
| 0.0503 |
1.7065 |
16000 |
0.5209 |
| 0.0568 |
1.7598 |
16500 |
0.5083 |
| 0.0589 |
1.8131 |
17000 |
0.5093 |
| 0.0892 |
1.8665 |
17500 |
0.4983 |
| 0.0584 |
1.9198 |
18000 |
0.4886 |
| 0.063 |
1.9731 |
18500 |
0.4945 |
| 0.0493 |
2.0265 |
19000 |
0.4956 |
| 0.0246 |
2.0798 |
19500 |
0.4871 |
| 0.0385 |
2.1331 |
20000 |
0.4830 |
| 0.0574 |
2.1864 |
20500 |
0.4849 |
| 0.039 |
2.2398 |
21000 |
0.4872 |
| 0.0653 |
2.2931 |
21500 |
0.4838 |
| 0.0325 |
2.3464 |
22000 |
0.4876 |
| 0.0578 |
2.3997 |
22500 |
0.4870 |
| 0.039 |
2.4531 |
23000 |
0.4805 |
| 0.0536 |
2.5064 |
23500 |
0.4824 |
| 0.0382 |
2.5597 |
24000 |
0.4809 |
| 0.0479 |
2.6131 |
24500 |
0.4749 |
| 0.0268 |
2.6664 |
25000 |
0.4723 |
| 0.0406 |
2.7197 |
25500 |
0.4743 |
| 0.0349 |
2.7730 |
26000 |
0.4718 |
| 0.017 |
2.8264 |
26500 |
0.4721 |
| 0.0286 |
2.8797 |
27000 |
0.4709 |
| 0.0265 |
2.9330 |
27500 |
0.4708 |
| 0.0552 |
2.9863 |
28000 |
0.4700 |
框架版本
- Transformers 4.45.0.dev0
- Pytorch 1.12.1
- Datasets 2.21.0
- Tokenizers 0.19.1
Safetensors
Transformers%20--%3e%3cdefs%3e%3cstyle%3e%20.st0%20{%20fill:%20none;%20}%20.st1%20{%20fill:%20%235ce6cf;%20}%20.st2%20{%20fill:%20%230080ff;%20}%20.st3%20{%20clip-path:%20url(%23clippath);%20}%20%3c/style%3e%3cclipPath%20id='clippath'%3e%3crect%20class='st0'%20y='0'%20width='120'%20height='32'/%3e%3c/clipPath%3e%3c/defs%3e%3cg%20class='st3'%3e%3cg%3e%3cpath%20class='st1'%20d='M22.4,32H3.2c-1,0-2-.5-2.6-1.4-.6-.9-.7-2-.4-2.9L9.8,2.1C10.3.8,11.5,0,12.8,0s2.5.8,3,2.1l9.6,25.6c.4,1,.2,2.1-.4,2.9-.6.9-1.6,1.4-2.6,1.4ZM7.8,25.6h10l-5-13.3-5,13.3Z'/%3e%3cpath%20class='st2'%20d='M33.6,32c-1.3,0-2.5-.8-3-2.1L21,4.3c-.6-1.7.2-3.5,1.9-4.1,1.7-.6,3.5.2,4.1,1.9l9.6,25.6c.6,1.7-.2,3.5-1.9,4.1-.4.1-.8.2-1.1.2h0Z'/%3e%3cpath%20d='M71.8,9.1h-6.9v4.6h6.9c2.5,0,4.6,2,4.6,4.6h-6.9c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h2.3c1.7,0,3.2-.4,4.6-1.2v1.2h4.6v-13.7c0-5-4.1-9.1-9.1-9.1h0ZM71.8,27.4h-2.3c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h6.9c0,2.5-2,4.6-4.6,4.6h0Z'/%3e%3cpath%20d='M52.3,9.1h-4.6V0h-4.6V32h9.1c5,0,9.1-4.1,9.1-9.1v-4.6c0-5.1-4.1-9.1-9.1-9.1h0ZM56.9,22.9c0,2.5-2,4.6-4.6,4.6h-4.6v-13.7h4.6c2.5,0,4.6,2,4.6,4.6v4.6h0Z'/%3e%3cpath%20d='M110.9,13.7h9.1v-4.6h-9.1c-5.1,0-9.1,4.1-9.1,9.1v4.6c0,5.1,4.1,9.1,9.1,9.1h9.1v-4.6h-9.1c-2.5,0-4.6-2-4.6-4.6h13.7v-4.6h-13.7c0-2.5,2-4.6,4.6-4.6h0Z'/%3e%3cpath%20d='M93.6,18.3h-4.6c-1.3,0-2.3-1-2.3-2.3s1-2.3,2.3-2.3h10.3v-4.6h-10.3c-3.8,0-6.9,3.1-6.9,6.9s3.1,6.9,6.9,6.9h4.6c1.3,0,2.3,1,2.3,2.3s-1,2.3-2.3,2.3h-10.3v4.6h10.3c3.8,0,6.9-3.1,6.9-6.9s-3.1-6.9-6.9-6.9Z'/%3e%3c/g%3e%3c/g%3e%3c/svg%3e)