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	Precision	Recall	F1
No log	2.2759	34	0.6780	0.6042	1.0	0.05	0.0952
No log	4.5517	68	0.6760	0.5833	0.0	0.0	0.0
No log	6.8276	102	0.6773	0.625	1.0	0.1	0.1818
0.7001	9.0690	136	0.6883	0.6875	0.8571	0.3	0.4444
0.7001	11.3448	170	0.6647	0.5833	0.0	0.0	0.0
0.7001	13.6207	204	0.6157	0.6458	1.0	0.15	0.2609
0.6642	15.8966	238	0.6353	0.6667	1.0	0.2	0.3333
0.6642	18.1379	272	0.6527	0.7292	1.0	0.35	0.5185
0.6642	20.4138	306	0.5059	0.7917	0.8125	0.65	0.7222

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

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