learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 16
seed: 42
distributed_type: multi-GPU
num_devices: 4
total_train_batch_size: 64
total_eval_batch_size: 64
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: 400
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	F1	Threshold	F1 At 05
2.7287	0.3509	200	2.7492	0.5840	0.51	0.5812
2.5910	0.7018	400	2.5378	0.6425	0.4400	0.5598
2.1510	1.0526	600	2.4344	0.6753	0.4400	0.6593
1.9984	1.4035	800	2.4543	0.6859	0.47	0.6792
1.9386	1.7544	1000	2.3035	0.6940	0.4600	0.6847
1.4981	2.1053	1200	2.5572	0.6912	0.4400	0.6846
1.4341	2.4561	1400	2.5054	0.6929	0.47	0.6866
1.4262	2.8070	1600	2.7249	0.6915	0.4200	0.6888
1.0158	3.1579	1800	3.1633	0.6895	0.4400	0.6845
0.9583	3.5088	2000	3.4025	0.6751	0.36	0.6680
0.9158	3.8596	2200	3.1368	0.6871	0.36	0.6797
0.6699	4.2105	2400	4.0544	0.6762	0.53	0.6762
0.6745	4.5614	2600	3.7200	0.6816	0.38	0.6793
0.7178	4.9123	2800	3.9016	0.6801	0.49	0.6791

DrinkIcedT/roberta-large_MBTI_I_MBTI_agg_balanced_75

roberta-large_MBTI_I_MBTI_agg_balanced_75