learning_rate: 1e-05
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 16
total_train_batch_size: 32
optimizer: Use OptimizerNames.ADAMW_BNB 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: 400
num_epochs: 12
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer
47.9820	0.3655	100	1.6261	0.9067
25.3799	0.7311	200	1.1184	0.7250
13.3183	1.0950	300	0.7334	0.5913
10.1569	1.4606	400	0.6567	0.5504
9.7609	1.8261	500	0.6045	0.5910
7.0938	2.1901	600	0.5780	0.4806
6.2773	2.5556	700	0.5605	0.4492
6.1845	2.9212	800	0.5456	0.4197
4.0962	3.2851	900	0.5604	0.3930
4.0550	3.6507	1000	0.5475	0.4016
4.0792	4.0146	1100	0.5453	0.4018
2.6259	4.3802	1200	0.5656	0.3850
2.5990	4.7457	1300	0.5657	0.3807
2.5943	5.1097	1400	0.5835	0.3954
1.6042	5.4752	1500	0.5895	0.3897
1.7266	5.8408	1600	0.5925	0.3899
1.5761	6.2047	1700	0.6114	0.3970
0.9729	6.5703	1800	0.6162	0.3910
1.0095	6.9358	1900	0.6183	0.3951
0.7495	7.2997	2000	0.6421	0.3900
0.5854	7.6653	2100	0.6433	0.3860
0.6154	8.0292	2200	0.6487	0.3807
0.4020	8.3948	2300	0.6630	0.3912
0.3542	8.7603	2400	0.6704	0.3937
0.3408	9.1243	2500	0.6825	0.3895
0.2131	9.4898	2600	0.6918	0.3869
0.2272	9.8554	2700	0.6987	0.3902
0.1663	10.2193	2800	0.7089	0.3899
0.1338	10.5849	2900	0.7169	0.3886
0.1414	10.9504	3000	0.7181	0.3845
0.0960	11.3144	3100	0.7297	0.3871
0.0895	11.6799	3200	0.7325	0.3873

khier12/800min_whisper_small_FT_Algerian_Dialect

800min_whisper_small_FT_Algerian_Dialect