learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
num_epochs: 3.0
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Wer Ortho	Wer
0.1324	0.1	500	0.1401	28.4331	14.2598
0.1154	0.2	1000	0.1158	78.2105	68.0602
0.106	0.3	1500	0.1073	44.4435	30.8810
0.0878	0.4	2000	0.0916	137.0165	128.9766
0.0982	0.5	2500	0.1022	181.8600	176.1832
0.0784	0.6	3000	0.0889	101.1986	91.6390
0.0802	0.7	3500	0.0814	56.4498	44.5975
0.0705	0.8	4000	0.0834	52.7781	41.1760
0.0753	0.9	4500	0.0807	210.9888	206.4460
0.0778	1.0	5000	0.0764	277.0980	275.3281
0.0534	1.1	5500	0.0796	248.0980	245.4206
0.0574	1.2	6000	0.0828	297.6858	297.2156
0.0553	1.3	6500	0.0755	246.3392	244.6851
0.0548	1.4	7000	0.0742	383.3272	386.8018
0.049	1.5	7500	0.0742	187.3127	182.0145
0.0549	1.6	8000	0.0759	250.2355	247.9754
0.0514	1.7	8500	0.0738	308.1355	308.5257
0.0565	1.8	9000	0.0739	153.9500	147.8599
0.0587	1.9	9500	0.0715	282.6388	281.4569
0.0575	2.0	10000	0.0709	286.4367	285.5370
0.0429	2.1	10500	0.0753	74.2237	64.2203
0.0391	2.2	11000	0.0768	369.1016	372.4500
0.0456	2.3	11500	0.0752	84.3226	75.1626
0.0373	2.4	12000	0.0757	127.9561	120.1080
0.0401	2.5	12500	0.0717	201.8650	197.4975
0.0381	2.6	13000	0.0742	90.5474	80.6946
0.0437	2.7	13500	0.0725	402.4980	406.9978
0.039	2.8	14000	0.0705	134.6089	126.1199
0.0354	2.9	14500	0.0701	190.7826	187.0045
0.0414	3.0	15000	0.0720	137.5675	130.9970

Ycharo/whisper-turbo-fr-pho-large

whisper-turbo-fr-pho-large