learning_rate: 5e-05
train_batch_size: 48
eval_batch_size: 48
seed: 42
optimizer: Use adamw_torch_fused 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: 500
num_epochs: 20

Training Loss	Epoch	Step	Validation Loss
0.9290	1.0	1593	0.7520
0.7912	2.0	3186	0.6916
0.6925	3.0	4779	0.6674
0.6328	4.0	6372	0.6530
0.5876	5.0	7965	0.6518
0.5512	6.0	9558	0.6486
0.5192	7.0	11151	0.6481
0.4837	8.0	12744	0.6568
0.4569	9.0	14337	0.6597
0.4498	10.0	15930	0.6719
0.4183	11.0	17523	0.6749
0.4106	12.0	19116	0.6812
0.3903	13.0	20709	0.6894
0.3725	14.0	22302	0.6962
0.3683	15.0	23895	0.6999
0.3617	16.0	25488	0.7060
0.3462	17.0	27081	0.7104
0.3505	18.0	28674	0.7125
0.3445	19.0	30267	0.7138
0.3416	20.0	31860	0.7158

anupa41222/mt5-base-bias-aware-v3

mt5-base-bias-aware-v3