learning_rate: 3e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
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
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	4	2.6348	0.0442
No log	2.0	8	2.6417	0.0796
2.502	3.0	12	2.6435	0.0708
2.502	4.0	16	2.6424	0.0973
2.4303	5.0	20	2.6419	0.0973
2.4303	6.0	24	2.6426	0.0796
2.4303	7.0	28	2.6442	0.0531
2.4895	8.0	32	2.6432	0.1150
2.4895	9.0	36	2.6429	0.1150
2.4245	10.0	40	2.6429	0.1150

ltenny/mind_model_fine_tune_of_wav2vec2

mind_model_fine_tune_of_wav2vec2