learning_rate: 0.0004
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use 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_steps: 132
num_epochs: 100
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
4.858	5.0	200	2.6999	1.0
2.2652	10.0	400	1.2382	1.0042
0.8587	15.0	600	0.5870	0.6960
0.3893	20.0	800	0.5675	0.6122
0.257	25.0	1000	0.4928	0.4822
0.1862	30.0	1200	0.4408	0.4885
0.148	35.0	1400	0.5587	0.4298
0.1203	40.0	1600	0.5393	0.4549
0.1094	45.0	1800	0.4889	0.4403
0.0908	50.0	2000	0.6539	0.4298
0.0766	55.0	2200	0.4469	0.4109
0.0675	60.0	2400	0.4109	0.4004
0.0622	65.0	2600	0.4543	0.3962
0.0617	70.0	2800	0.5189	0.3920
0.0529	75.0	3000	0.4261	0.3878
0.0514	80.0	3200	0.5161	0.3920
0.0473	85.0	3400	0.4789	0.3983
0.0419	90.0	3600	0.5161	0.4088
0.0405	95.0	3800	0.5263	0.4067

susmitabhatt/xlsr-a-clp

xlsr-a-clp