metadata
library_name: transformers
base_model: openai/clip-vit-base-patch32
tags:
- generated_from_trainer
model-index:
- name: logo-matching-base
results: []
logo-matching-base
This model is a fine-tuned version of openai/clip-vit-base-patch32 on an unknown dataset. It achieves the following results on the evaluation set:
- Adjusted Rand Score: 0.0402
- Adjusted Mutual Info Score: 0.0818
- Homogeneity Score: 0.1156
- Completeness Score: 0.4826
- Fowlkes Mallows Score: 0.4235
- Pair Confusion Matrix: [[15374, 32276], [3428, 10178]]
- Loss: 0.0402
Model description
More information needed
Intended uses & limitations
More information needed
Training and evaluation data
More information needed
Training procedure
Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 1e-05
- train_batch_size: 32
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Adjusted Rand Score | Adjusted Mutual Info Score | Homogeneity Score | Completeness Score | Fowlkes Mallows Score | Pair Confusion Matrix | Validation Loss |
|---|---|---|---|---|---|---|---|---|---|
| 0.6833 | 1.0 | 34 | 0.0691 | 0.0960 | 0.1237 | 0.5110 | 0.4440 | [[16212, 31438], [2986, 10620]] | 0.0691 |
| 0.5711 | 2.0 | 68 | 0.0479 | 0.1605 | 0.2478 | 0.4802 | 0.3262 | [[30178, 17472], [7800, 5806]] | 0.0479 |
| 0.5048 | 3.0 | 102 | 0.0694 | 0.1445 | 0.2069 | 0.4853 | 0.3562 | [[28728, 18922], [6962, 6644]] | 0.0694 |
| 0.4474 | 4.0 | 136 | 0.0640 | 0.1520 | 0.2011 | 0.5054 | 0.3601 | [[27632, 20018], [6716, 6890]] | 0.0640 |
| 0.4433 | 5.0 | 170 | 0.0450 | 0.0923 | 0.1295 | 0.4857 | 0.4179 | [[16938, 30712], [3792, 9814]] | 0.0450 |
| 0.4582 | 6.0 | 204 | 0.1236 | 0.1550 | 0.1349 | 0.7626 | 0.5091 | [[13668, 33982], [754, 12852]] | 0.1236 |
| 0.4384 | 7.0 | 238 | 0.0837 | 0.1718 | 0.2242 | 0.5223 | 0.3648 | [[29196, 18454], [6850, 6756]] | 0.0837 |
| 0.4388 | 8.0 | 272 | 0.2021 | 0.2045 | 0.2252 | 0.5851 | 0.4533 | [[30796, 16854], [5202, 8404]] | 0.2021 |
| 0.4136 | 9.0 | 306 | 0.0964 | 0.1118 | 0.1082 | 0.6507 | 0.4900 | [[12770, 34880], [1174, 12432]] | 0.0964 |
| 0.4148 | 10.0 | 340 | 0.0174 | 0.1329 | 0.2074 | 0.4634 | 0.3148 | [[28346, 19304], [7786, 5820]] | 0.0174 |
| 0.4146 | 11.0 | 374 | 0.0578 | 0.1546 | 0.2132 | 0.5013 | 0.3500 | [[28252, 19398], [7026, 6580]] | 0.0578 |
| 0.4096 | 12.0 | 408 | 0.0835 | 0.1595 | 0.2378 | 0.4866 | 0.3489 | [[31128, 16522], [7482, 6124]] | 0.0835 |
| 0.3973 | 13.0 | 442 | 0.1255 | 0.1904 | 0.2738 | 0.5047 | 0.3619 | [[33812, 13838], [7670, 5936]] | 0.1255 |
| 0.4051 | 14.0 | 476 | 0.1816 | 0.1869 | 0.2432 | 0.5246 | 0.4169 | [[33010, 14640], [6422, 7184]] | 0.1816 |
| 0.4062 | 15.0 | 510 | 0.2598 | 0.2182 | 0.2648 | 0.5641 | 0.4795 | [[33538, 14112], [5216, 8390]] | 0.2598 |
| 0.4025 | 16.0 | 544 | 0.0908 | 0.1006 | 0.1138 | 0.5697 | 0.4760 | [[14202, 33448], [1794, 11812]] | 0.0908 |
| 0.4043 | 17.0 | 578 | 0.0615 | 0.1185 | 0.1434 | 0.5431 | 0.4324 | [[16966, 30684], [3408, 10198]] | 0.0615 |
| 0.4013 | 18.0 | 612 | 0.2412 | 0.2010 | 0.2598 | 0.5344 | 0.4579 | [[34176, 13474], [5818, 7788]] | 0.2412 |
| 0.4006 | 19.0 | 646 | 0.2402 | 0.2522 | 0.3445 | 0.5460 | 0.4233 | [[37986, 9664], [7382, 6224]] | 0.2402 |
| 0.4044 | 20.0 | 680 | 0.0402 | 0.0818 | 0.1156 | 0.4826 | 0.4235 | [[15374, 32276], [3428, 10178]] | 0.0402 |
Framework versions
- Transformers 4.47.1
- Pytorch 2.5.1+cu121
- Datasets 3.2.0
- Tokenizers 0.21.0