Matcha_clips_224_fintuned_5

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 1.5168
• Accuracy: 0.7326

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: 4
• eval_batch_size: 4
• 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
• lr_scheduler_warmup_ratio: 0.1
• training_steps: 1140

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.5414	0.1	114	0.9738	0.6628
0.175	1.1	228	1.3822	0.7093
0.0043	2.1	342	1.1047	0.7442
0.0034	3.1	456	1.4682	0.7093
0.0038	4.1	570	1.4363	0.7209
0.0005	5.1	684	1.4663	0.7209
0.0005	6.1	798	1.4943	0.7326
0.0004	7.1	912	1.5062	0.7326
0.0004	8.1	1026	1.5134	0.7326
0.0004	9.1	1140	1.5168	0.7326

Framework versions

• Transformers 4.51.3
• Pytorch 2.3.1+cu121
• Datasets 3.6.0
• Tokenizers 0.21.1