learning_rate: 5e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: 104
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Per	F1
10769.5240	1.0	104	1769.2606	1.0	0.0
3577.9186	2.0	208	1750.9899	1.0	0.0
3495.1671	3.0	312	1570.0214	1.0	0.0
2535.6373	4.0	416	783.3173	0.3755	0.7214
1357.6378	5.0	520	455.1570	0.1670	0.8635
928.3119	6.0	624	352.7345	0.1363	0.8895
750.2390	7.0	728	316.2893	0.1147	0.9068
650.8412	8.0	832	296.6050	0.1112	0.9090
596.2695	9.0	936	287.3040	0.1067	0.9131
569.7062	10.0	1040	284.0506	0.1047	0.9142

waelhasan/wav2vec2-l2-arctic-phoneme-model

wav2vec2-l2-arctic-phoneme-model