learning_rate: 0.001
train_batch_size: 16
eval_batch_size: 16
seed: 42
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: linear
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss
0.7819	1.0	1250	0.6605
0.6951	2.0	2500	0.6324
0.6588	3.0	3750	0.6552
0.6606	4.0	5000	0.6459
0.6204	5.0	6250	0.6616
0.5902	6.0	7500	0.6793
0.567	7.0	8750	0.6592
0.5452	8.0	10000	0.6582
0.5296	9.0	11250	0.6896
0.5073	10.0	12500	0.6497
0.4521	11.0	13750	0.6788
0.4289	12.0	15000	0.6858
0.3918	13.0	16250	0.6804
0.3683	14.0	17500	0.7224
0.3235	15.0	18750	0.7345
0.2884	16.0	20000	0.7899
0.2587	17.0	21250	0.8118
0.2296	18.0	22500	0.8464
0.1957	19.0	23750	0.8771
0.1702	20.0	25000	0.8954

A-Asif/Mental-health-fine-tuned

results