learning_rate: 0.0002
train_batch_size: 4
eval_batch_size: 4
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 8
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
0.8915	0.1496	100	0.8518
0.8464	0.2992	200	0.8102
0.7874	0.4488	300	0.7927
0.7999	0.5984	400	0.7814
0.7901	0.7479	500	0.7731
0.7801	0.8975	600	0.7647
0.7585	1.0471	700	0.7639
0.7592	1.1967	800	0.7576
0.7431	1.3463	900	0.7542
0.7555	1.4959	1000	0.7501
0.7354	1.6455	1100	0.7456
0.7281	1.7951	1200	0.7422
0.7312	1.9447	1300	0.7395
0.6984	2.0942	1400	0.7389
0.7037	2.2438	1500	0.7382
0.6913	2.3934	1600	0.7357
0.7229	2.5430	1700	0.7341
0.7095	2.6926	1800	0.7326
0.6994	2.8422	1900	0.7319
0.6995	2.9918	2000	0.7298
0.6887	3.1414	2100	0.7314
0.6712	3.2909	2200	0.7308
0.6867	3.4405	2300	0.7300
0.6817	3.5901	2400	0.7299
0.681	3.7397	2500	0.7296

advy/phi2-mentalchat16k

phi2-mentalchat16k