learning_rate: 1e-05
train_batch_size: 1
eval_batch_size: 1
seed: 42
optimizer: Use OptimizerNames.PAGED_ADAMW_8BIT 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
training_steps: 40
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
4.6008	0.0029	2	6.9022
4.3327	0.0057	4	6.9022
4.6788	0.0086	6	6.7334
4.1284	0.0114	8	5.6978
2.5702	0.0143	10	4.6321
1.5963	0.0171	12	4.3133
1.3669	0.02	14	4.2577
1.1867	0.0229	16	4.3040
1.7891	0.0257	18	4.3839
1.14	0.0286	20	5.0947
0.7743	0.0314	22	4.4104
0.965	0.0343	24	4.0427
0.8264	0.0371	26	3.9472
0.7508	0.04	28	3.9840
0.4857	0.0429	30	4.0175
0.609	0.0457	32	4.2039
1.2697	0.0486	34	4.1989
0.6072	0.0514	36	4.0805
0.6064	0.0543	38	3.9941
0.7662	0.0571	40	3.9591

snaoi-csl/whisper-ft-large-1000-f

whisper-ft-large-1000-f