learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 40
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
optimizer: Use 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: 2

Training Loss	Epoch	Step	Validation Loss
0.7442	0.1363	50	0.8824
0.5925	0.2727	100	0.6583
0.587	0.4090	150	0.5422
0.4862	0.5453	200	0.4668
0.4211	0.6817	250	0.4176
0.4013	0.8180	300	0.3846
0.4198	0.9543	350	0.3644
0.2427	1.0913	400	0.3562
0.2783	1.2277	450	0.3468
0.22	1.3640	500	0.3399
0.2263	1.5003	550	0.3335
0.2177	1.6367	600	0.3277
0.2579	1.7730	650	0.3251
0.1985	1.9093	700	0.3246

danielgombas/llama_1b_step2_batch_v5

llama_1b_step2_batch_v4