learning_rate: 5e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
optimizer: Use OptimizerNames.ADAMW_TORCH 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: 10
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss
0.6958	0.5	10	0.4475
0.4296	1.0	20	0.2968
0.2364	1.5	30	0.1774
0.1452	2.0	40	0.0756
0.0155	2.5	50	0.0066
0.0058	3.0	60	0.0030
0.0032	3.5	70	0.0021
0.0025	4.0	80	0.0016
0.0021	4.5	90	0.0013
0.0016	5.0	100	0.0012
0.0015	5.5	110	0.0010
0.0013	6.0	120	0.0010
0.0012	6.5	130	0.0009
0.0011	7.0	140	0.0008
0.001	7.5	150	0.0008
0.001	8.0	160	0.0007
0.0011	8.5	170	0.0007
0.0009	9.0	180	0.0007
0.001	9.5	190	0.0007
0.0009	10.0	200	0.0007

advy/distilbert-mental-health-classifier

distilbert-mental-health-classifier