metadata
base_model: OFA-Sys/chinese-clip-vit-base-patch16
tags:
- generated_from_trainer
model-index:
- name: aoi_clip_clean_new_sampler_fomula_clean
results: []
aoi_clip_clean_new_sampler_fomula_clean
This model is a fine-tuned version of OFA-Sys/chinese-clip-vit-base-patch16 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.5840
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: 40
- eval_batch_size: 44
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 60.0
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.4036 | 6.0 | 8874 | 3.0113 |
| 2.1954 | 12.0 | 17748 | 3.1597 |
| 2.0709 | 18.0 | 26622 | 3.2060 |
| 2.0132 | 24.0 | 35496 | 3.3071 |
| 1.9783 | 30.0 | 44370 | 3.3543 |
| 1.9672 | 36.0 | 53244 | 3.4592 |
| 1.9536 | 42.0 | 62118 | 3.4736 |
| 1.9473 | 48.0 | 70992 | 3.5317 |
| 1.9479 | 54.0 | 79866 | 3.5620 |
| 1.9411 | 60.0 | 88740 | 3.5840 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1