learning_rate: 1e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 4
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
lr_scheduler_warmup_steps: 500
training_steps: 5000
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.1178	0.4568	500	0.7252	0.6090
1.0189	0.9137	1000	0.6767	0.5898
1.0088	1.3705	1500	0.6489	0.5756
0.9925	1.8273	2000	0.6216	0.5655
0.9547	2.2841	2500	0.6037	0.5563
0.9475	2.7410	3000	0.5900	0.55
0.9093	3.1978	3500	0.5794	0.5460
0.957	3.6546	4000	0.5727	0.5443
0.8822	4.1115	4500	0.5681	0.5405
0.8718	4.5683	5000	0.5665	0.5395

bijaykumarsingh/indicwav2vec-assamese-asr

indicwav2vec-assamese-asr