<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
clip-homer-2m
This model is a fine-tuned version of clip-homer-2m on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.5687
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.4564 | 1.0 | 62500 | 1.1970 |
| 1.0737 | 2.0 | 125000 | 0.8098 |
| 0.6867 | 3.0 | 187500 | 0.5687 |
Framework versions
- Transformers 4.32.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.14.1
- Tokenizers 0.13.3
