learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: 50
num_epochs: 3
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Cer
44.2054	0.1289	200	5.4975	100.0
5.0916	0.2579	400	4.7077	100.0
4.8758	0.3868	600	4.6568	100.0
4.8539	0.5158	800	4.6120	100.0
4.7493	0.6447	1000	4.5950	100.0
4.5763	0.7737	1200	4.3522	98.5076
3.7522	0.9026	1400	3.0023	54.3478
2.71	1.0316	1600	2.6582	48.0200
2.3514	1.1605	1800	2.3269	42.1034
1.9845	1.2895	2000	1.9847	36.9918
1.7755	1.4184	2200	1.8688	35.3643
1.6234	1.5474	2400	1.7565	33.8837
1.5417	1.6763	2600	1.7060	33.1199
1.4338	1.8053	2800	1.6633	33.5194
1.3403	1.9342	3000	1.5921	32.7791
1.2466	2.0632	3200	1.5050	31.0458
1.1278	2.1921	3400	1.4261	29.5828
1.0863	2.3211	3600	1.3675	28.9189
1.0236	2.4500	3800	1.3119	27.9318
0.9973	2.5790	4000	1.2762	27.2150
0.9749	2.7079	4200	1.3005	27.4677
0.9365	2.8369	4400	1.2889	27.6204
0.8997	2.9658	4600	1.2614	27.0035

Gummybear05/wav2vec2-Y_speed3

wav2vec2-E30_speed3