learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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
num_epochs: 22
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	2.2759	34	0.6738	0.5833
No log	4.5517	68	0.6755	0.5833
No log	6.8276	102	0.6814	0.5417
0.7006	9.0690	136	0.7188	0.4167
0.7006	11.3448	170	0.6764	0.5833
0.7006	13.6207	204	0.6791	0.5833
0.6950	15.8966	238	0.6874	0.4792
0.6950	18.1379	272	0.6789	0.5625
0.6950	20.4138	306	0.6804	0.5208

kunal-sh/wav2vec2-large-xls-r-300m-dm32

wav2vec2-large-xls-r-300m-dm32