learning_rate: 5e-06
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: 500
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
2.3309	0.3929	100	1.5693
1.1568	0.7859	200	1.0259
0.769	1.1768	300	0.7513
0.6402	1.5697	400	0.6505
0.5844	1.9627	500	0.5912
0.544	2.3536	600	0.5423
0.5056	2.7466	700	0.5103
0.4821	3.1375	800	0.4866
0.4416	3.5305	900	0.4645
0.4135	3.9234	1000	0.4332
0.3833	4.3143	1100	0.4058
0.3734	4.7073	1200	0.3918
0.3546	5.0982	1300	0.3831
0.367	5.4912	1400	0.3771
0.3376	5.8841	1500	0.3712
0.3317	6.2750	1600	0.3695
0.3376	6.6680	1700	0.3665
0.3405	7.0589	1800	0.3646
0.3312	7.4519	1900	0.3628
0.3304	7.8448	2000	0.3618
0.3077	8.2358	2100	0.3604
0.3378	8.6287	2200	0.3589
0.3269	9.0196	2300	0.3580
0.3198	9.4126	2400	0.3580
0.3208	9.8055	2500	0.3576

aarushidicious1/mistral-7b-legal-lora

mistral-7b-legal-lora