learning_rate: 1e-05
train_batch_size: 16
eval_batch_size: 32
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
lr_scheduler_warmup_steps: 0.1
num_epochs: 8
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	F1 Macro	F1 Weighted	Accuracy
1.1041	1.0	241	1.1195	0.2019	0.2338	0.3913
1.0805	2.0	482	1.0591	0.3482	0.3674	0.4329
1.0198	3.0	723	1.0200	0.4292	0.4372	0.5026
0.8924	4.0	964	0.9479	0.5501	0.5548	0.5650
0.8358	5.0	1205	0.9566	0.5629	0.5643	0.5640
0.8206	6.0	1446	1.0262	0.5591	0.5638	0.5754
0.7342	7.0	1687	1.0105	0.5684	0.5724	0.5817
0.6855	8.0	1928	1.0500	0.5458	0.5490	0.5557

oscaruv28/tass-xlnet

tass-xlnet