chordektomie-iau

This model is a fine-tuned version of facebook/wav2vec2-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3381
• Accuracy: 0.9091

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6948	1.0	6	0.6942	0.4091
0.6393	2.0	12	0.6864	0.4091
0.5059	3.0	18	0.5804	0.7727
0.3832	4.0	24	0.6555	0.5909
0.3113	5.0	30	0.4741	0.8182
0.2529	6.0	36	0.2765	0.9545
0.1891	7.0	42	0.2377	0.9545
0.1966	8.0	48	0.2146	0.9545
0.1326	9.0	54	0.2941	0.9091
0.1938	10.0	60	0.3241	0.9091
0.0933	11.0	66	0.3281	0.9091
0.0831	12.0	72	0.4237	0.8636
0.0801	13.0	78	0.3362	0.9091
0.0632	14.0	84	0.3377	0.9091
0.0746	15.0	90	0.3381	0.9091

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.0
• Datasets 2.12.0
• Tokenizers 0.15.1