learning_rate: 0.0001
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_steps: 6000
num_epochs: 30
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer	Cer
1.267	0.7819	1000	inf	47.6367	13.5610
0.5584	1.5637	2000	inf	26.4059	7.2903
0.4211	2.3456	3000	inf	23.4538	6.4409
0.5473	3.1274	4000	inf	21.6233	6.0101
0.4631	3.9093	5000	inf	21.4830	5.9161
0.2869	4.6912	6000	inf	21.6286	6.0356
0.4572	5.4730	7000	inf	22.4768	6.2442
0.2378	6.2549	8000	inf	21.7372	6.1153
0.3479	7.0367	9000	inf	22.6372	6.2812
0.368	7.8186	10000	inf	23.1700	6.3923
0.5023	8.6005	11000	inf	22.2996	6.2065
0.4695	9.3823	12000	inf	21.2941	5.9487
0.0	10.1642	13000	nan	100.0	100.0

davidilag/wav2vec2-xls-r-1b-scandinavian-E4-100h-30-epochs-20250124

wav2vec2-xls-r-1b-scandinavian-E4-100h-30-epochs-20250124