learning_rate: 1e-05
train_batch_size: 64
eval_batch_size: 64
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: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1 Macro	F1 Weighted
0.3710	1.0	539	0.3667	0.9399	0.2785	0.9265
0.3190	2.0	1078	0.3273	0.9450	0.3737	0.9394
0.2832	3.0	1617	0.3055	0.9513	0.5054	0.9483
0.2518	4.0	2156	0.3008	0.9529	0.6363	0.9515
0.1736	5.0	2695	0.3219	0.9520	0.6821	0.9520
0.1768	6.0	3234	0.3548	0.9520	0.6803	0.9518
0.1445	7.0	3773	0.3569	0.9524	0.6808	0.9525
0.1154	8.0	4312	0.3944	0.9517	0.6895	0.9522
0.0974	9.0	4851	0.4116	0.9524	0.6966	0.9527
0.1000	10.0	5390	0.4149	0.9531	0.6886	0.9532

DPhO05/codebert-td

codebert-td