learning_rate: 0.0002
train_batch_size: 8
eval_batch_size: 8
seed: 42
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: linear
num_epochs: 60
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
2.1353	1.0	139	1.9285
1.9822	2.0	278	1.8529
1.9022	3.0	417	1.8243
1.8912	4.0	556	1.7883
1.8558	5.0	695	1.7695
1.8085	6.0	834	1.7462
1.7729	7.0	973	1.7221
1.7632	8.0	1112	1.7094
1.7223	9.0	1251	1.6918
1.7366	10.0	1390	1.6697
1.6836	11.0	1529	1.6653
1.6776	12.0	1668	1.6525
1.6403	13.0	1807	1.6346
1.6133	14.0	1946	1.6269
1.6346	15.0	2085	1.6153
1.5812	16.0	2224	1.6100
1.5702	17.0	2363	1.6006
1.559	18.0	2502	1.5873
1.5219	19.0	2641	1.5776
1.5567	20.0	2780	1.5783
1.5193	21.0	2919	1.5766
1.5193	22.0	3058	1.5583
1.5099	23.0	3197	1.5551
1.4913	24.0	3336	1.5540
1.4496	25.0	3475	1.5455
1.4585	26.0	3614	1.5379
1.4256	27.0	3753	1.5241
1.4639	28.0	3892	1.5230
1.4259	29.0	4031	1.5130
1.4356	30.0	4170	1.5222
1.394	31.0	4309	1.5073
1.4016	32.0	4448	1.5061
1.4223	33.0	4587	1.4983
1.3854	34.0	4726	1.5008
1.3802	35.0	4865	1.4984
1.3678	36.0	5004	1.4852
1.342	37.0	5143	1.4777
1.3877	38.0	5282	1.4846
1.3682	39.0	5421	1.4791
1.3461	40.0	5560	1.4760
1.3457	41.0	5699	1.4820
1.3465	42.0	5838	1.4785
1.3364	43.0	5977	1.4788
1.3239	44.0	6116	1.4692
1.3257	45.0	6255	1.4681
1.3079	46.0	6394	1.4614
1.3376	47.0	6533	1.4662
1.3037	48.0	6672	1.4611
1.3028	49.0	6811	1.4626
1.3216	50.0	6950	1.4543
1.2998	51.0	7089	1.4583
1.3263	52.0	7228	1.4601
1.2912	53.0	7367	1.4579
1.296	54.0	7506	1.4583
1.3045	55.0	7645	1.4563
1.2935	56.0	7784	1.4546
1.2967	57.0	7923	1.4537
1.3178	58.0	8062	1.4535
1.2809	59.0	8201	1.4546
1.2846	60.0	8340	1.4543

Fatma5000/lora-legal-model-Bert

lora-legal-model-Bert