learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 0.1
num_epochs: 20
mixed_precision_training: Native AMP
label_smoothing_factor: 0.1

Training Loss	Epoch	Step	Validation Loss	Accuracy
2.0479	1.0	126	2.0465	0.2639
1.9198	2.0	252	1.7636	0.3472
1.7474	3.0	378	1.5941	0.4514
1.4198	4.0	504	1.3667	0.5486
1.4462	5.0	630	1.2058	0.6458
1.1219	6.0	756	1.0412	0.7708
1.4561	7.0	882	0.9866	0.7708
1.1193	8.0	1008	0.9222	0.8264
1.1304	9.0	1134	0.9000	0.8125
0.9479	10.0	1260	0.8796	0.8194
0.9131	11.0	1386	0.8657	0.8194
0.8876	12.0	1512	0.8330	0.8681
0.8605	13.0	1638	0.8073	0.8611
0.9696	14.0	1764	0.8280	0.8403
0.9908	15.0	1890	0.8373	0.8403
0.8529	16.0	2016	0.8283	0.8681
0.6335	17.0	2142	0.8225	0.8542
0.7234	18.0	2268	0.8164	0.8611
1.0229	19.0	2394	0.8132	0.8542
0.8715	20.0	2520	0.8083	0.8611

amnesiackid/distilhubert-finetuned-ravdess

distilhubert-finetuned-ravdess