wav2vec2-base-random-stop-classification-4

This model is a fine-tuned version of on the audiofolder dataset. It achieves the following results on the evaluation set:

• Loss: 0.3843
• Accuracy: 0.8706

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: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.6928	0.99	18	0.6588	0.6267
0.6746	1.97	36	0.5702	0.6969
0.5823	2.96	54	0.5035	0.7772
0.5573	4.0	73	0.4111	0.8188
0.5324	4.99	91	0.4359	0.7997
0.6058	5.97	109	0.4688	0.7875
0.4805	6.96	127	0.4055	0.8351
0.4641	8.0	146	0.4024	0.8351
0.4292	8.99	164	0.3913	0.8474
0.4217	9.97	182	0.3975	0.8522
0.3892	10.96	200	0.3808	0.8460
0.4056	12.0	219	0.4126	0.8515
0.3848	12.99	237	0.3602	0.8508
0.3698	13.97	255	0.3913	0.8488
0.3893	14.96	273	0.3611	0.8692
0.3341	16.0	292	0.3791	0.8624
0.3376	16.99	310	0.3578	0.8624
0.3331	17.97	328	0.3660	0.8658
0.3215	18.96	346	0.3817	0.8535
0.2982	20.0	365	0.4000	0.8658
0.2885	20.99	383	0.3674	0.8658
0.3124	21.97	401	0.3770	0.8672
0.2926	22.96	419	0.3779	0.8651
0.2941	24.0	438	0.3775	0.8733
0.2699	24.66	450	0.3843	0.8706

Framework versions

• Transformers 4.27.4
• Pytorch 1.13.0
• Datasets 2.7.1
• Tokenizers 0.13.2