learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 8
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
num_epochs: 200
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Per Hf Metric	Per Avg
4.214	1.0	102	2.6404	1.0	1.0
2.2959	2.0	204	1.5080	0.6936	0.6893
1.4046	3.0	306	0.8916	0.2267	0.2498
0.8131	4.0	408	0.6238	0.1059	0.1375
0.7166	5.0	510	0.7134	0.0997	0.1269
0.6686	6.0	612	0.6974	0.0792	0.1089
0.5977	7.0	714	0.4408	0.0804	0.1065
0.6328	8.0	816	0.8702	0.0740	0.1031
0.5317	9.0	918	0.7305	0.0780	0.1073
0.4816	10.0	1020	0.7411	0.0732	0.0994
0.5379	11.0	1122	0.6265	0.0687	0.0930
0.4539	12.0	1224	0.8386	0.0827	0.1100
0.4151	13.0	1326	0.5374	0.0644	0.0873
0.3461	14.0	1428	0.7327	0.0687	0.0928
0.5253	15.0	1530	0.4329	0.0671	0.0900
0.3975	16.0	1632	1.0215	0.0683	0.0950
0.3331	17.0	1734	0.9336	0.0649	0.0954
0.4153	18.0	1836	1.0176	0.0718	0.1009
0.3062	19.0	1938	0.8331	0.0668	0.0939
0.3671	20.0	2040	0.6999	0.0723	0.1033
0.2515	21.0	2142	0.7128	0.0687	0.0975
0.2466	22.0	2244	0.8877	0.0756	0.1049
0.3599	23.0	2346	0.8683	0.0724	0.1034
0.2695	24.0	2448	0.9040	0.0676	0.0978
0.2305	25.0	2550	0.8124	0.0692	0.0978

alinerodrigues/wav2vec2-large-xlsr-facebook-1b-words-phoneme-exp-1-v17

wav2vec2-large-xlsr-facebook-1b-words-phoneme-exp-1-v17