learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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: 100
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss
1.6312	0.1348	50	1.4909
1.8023	0.2695	100	1.7316
1.8044	0.4043	150	1.7173
1.6679	0.5391	200	1.1123
1.3583	0.6739	250	0.8995
1.1691	0.8086	300	0.6657
0.9808	0.9434	350	0.7485
0.605	1.0782	400	0.5601
0.5032	1.2129	450	0.4895
0.4466	1.3477	500	0.4132
0.4158	1.4825	550	0.3070
0.3581	1.6173	600	0.2680
0.3132	1.7520	650	0.2225
0.2682	1.8868	700	0.1625
0.2197	2.0216	750	0.1424
0.1341	2.1563	800	0.1202
0.1058	2.2911	850	0.1032
0.1038	2.4259	900	0.0847
0.0784	2.5606	950	0.0702
0.0764	2.6954	1000	0.0529
0.0737	2.8302	1050	0.0451
0.062	2.9650	1100	0.0430

jonathanagustin/legal-mcq-gemma-2b

legal-mcq-gemma-2b