learning_rate: 0.0002
train_batch_size: 3
eval_batch_size: 3
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 6
optimizer: Use adamw_torch 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: 0.03
num_epochs: 4
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.0076	0.1122	100	0.9827
0.9399	0.2243	200	0.9345
0.9054	0.3365	300	0.9031
0.8561	0.4487	400	0.8859
0.8794	0.5609	500	0.8711
0.844	0.6730	600	0.8557
0.8305	0.7852	700	0.8461
0.8207	0.8974	800	0.8400
0.8117	1.0090	900	0.8529
0.7338	1.1211	1000	0.8448
0.7422	1.2333	1100	0.8332
0.6964	1.3455	1200	0.8273
0.7064	1.4577	1300	0.8252
0.7201	1.5698	1400	0.8170
0.7162	1.6820	1500	0.8121
0.688	1.7942	1600	0.8088
0.7166	1.9063	1700	0.7998
0.636	2.0179	1800	0.8447
0.5388	2.1301	1900	0.8485
0.5319	2.2423	2000	0.8444
0.5396	2.3545	2100	0.8498
0.5523	2.4666	2200	0.8446

advy/gemma2-mentalchat16k

gemma2-mentalchat16k