sail-clip-hendrix-10epochs

This model is a fine-tuned version of openai/clip-vit-large-patch14 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 6.6413

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: 64
• eval_batch_size: 64
• seed: 42
• optimizer: Use 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: 10

Training results

Training Loss	Epoch	Step	Validation Loss
4.0802	0.5525	100	4.0790
3.756	1.1050	200	3.8015
3.5546	1.6575	300	3.5559
3.0525	2.2099	400	3.4319
2.8911	2.7624	500	3.3547
2.2105	3.3149	600	3.3261
2.1826	3.8674	700	3.1662
1.575	4.4199	800	3.4461
1.5164	4.9724	900	3.2057
0.8215	5.5249	1000	4.0640
0.4965	6.0773	1100	5.4518
0.4627	6.6298	1200	4.9572
0.3134	7.1823	1300	5.4385
0.2787	7.7348	1400	5.5018
0.1514	8.2873	1500	5.9184
0.1919	8.8398	1600	6.4257
0.1198	9.3923	1700	6.5754
0.0896	9.9448	1800	6.6413

Framework versions

• Transformers 4.49.0
• Pytorch 2.6.0+cu124
• Datasets 3.4.0
• Tokenizers 0.21.1