learning_rate: 0.0001
train_batch_size: 32
eval_batch_size: 8
seed: 42
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: 10
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
1.8119	0.8772	100	0.7517	0.5877
0.6048	1.7544	200	0.5188	0.4507
0.3757	2.6316	300	0.4527	0.3911
0.2723	3.5088	400	0.4244	0.3730
0.201	4.3860	500	0.4285	0.3570
0.1673	5.2632	600	0.4191	0.3491
0.1376	6.1404	700	0.4138	0.3359
0.1207	7.0175	800	0.4201	0.3276
0.1062	7.8947	900	0.4203	0.3224
0.0904	8.7719	1000	0.4377	0.3243
0.0769	9.6491	1100	0.4207	0.3186
0.0761	10.5263	1200	0.4357	0.3153
0.0695	11.4035	1300	0.4268	0.3113
0.0628	12.2807	1400	0.4365	0.3112
0.0616	13.1579	1500	0.4552	0.3122
0.0527	14.0351	1600	0.4504	0.3057
0.0545	14.9123	1700	0.4545	0.3085
0.0489	15.7895	1800	0.4650	0.3100
0.0453	16.6667	1900	0.4364	0.3046
0.042	17.5439	2000	0.4629	0.3064
0.0401	18.4211	2100	0.4764	0.3067
0.0383	19.2982	2200	0.4638	0.3018
0.0343	20.1754	2300	0.4760	0.2992
0.0322	21.0526	2400	0.4854	0.3010
0.0317	21.9298	2500	0.4758	0.2984
0.0318	22.8070	2600	0.4760	0.2964
0.0308	23.6842	2700	0.4947	0.2962
0.0262	24.5614	2800	0.4842	0.2960
0.0273	25.4386	2900	0.4903	0.2935
0.0257	26.3158	3000	0.4819	0.2951
0.025	27.1930	3100	0.4736	0.2932
0.023	28.0702	3200	0.4883	0.2923
0.0233	28.9474	3300	0.4848	0.2933
0.0242	29.8246	3400	0.4837	0.2932

npallewela/wav2vec2-base-timit

wav2vec2-base demo - Nuwan