learning_rate: 0.0003
train_batch_size: 1
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 2
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.05
num_epochs: 3

Training Loss	Epoch	Step	Validation Loss	F1
7.8289	0.1143	2	11.7201	0.0
7.7600	0.2286	4	11.1490	0.0
7.1921	0.3429	6	9.1765	0.4
5.2447	0.4571	8	3.0182	0.5
2.2606	0.5714	10	4.1422	0.6
2.3043	0.6857	12	1.3106	0.63
2.5684	0.8000	14	7.5408	0.64
4.4282	0.9143	16	4.1099	0.65
2.8737	1.0000	18	4.5994	0.655
2.9612	1.1143	20	3.7934	0.66
2.2100	1.2286	22	2.1396	0.662
1.2427	1.3429	24	1.2675	0.664
0.8553	1.4571	26	1.0446	0.665
0.6509	1.5714	28	0.7819	0.666
0.5359	1.6857	30	0.8467	0.6667
0.5303	1.8000	32	0.7678	0.6667
0.5960	1.9143	34	1.0589	0.6667
0.6265	2.0000	36	0.8152	0.6667
0.5092	2.1143	38	0.7012	0.6667
0.4895	2.2286	40	0.7282	0.6667
0.4743	2.3429	42	0.6964	0.6667
0.4662	2.4571	44	0.7031	0.6667
0.4744	2.5714	46	0.7032	0.6667
0.4507	2.6857	48	0.6957	0.6667
0.4737	2.8000	50	0.6960	0.6667

Jsevere/llama2-7b-admissions-qa-merged

llama2-7b-admissions-qa-merged