learning_rate: 0.0002
train_batch_size: 128
eval_batch_size: 256
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 512
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: 0.05
num_epochs: 12
mixed_precision_training: Native AMP
label_smoothing_factor: 0.05

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	1.0	37	0.5892	0.7383	0.8479
No log	2.0	74	0.5829	0.7372	0.8464
2.4270	3.0	111	0.5547	0.7419	0.8504
2.4270	4.0	148	0.5311	0.7344	0.8415
2.4270	5.0	185	0.5291	0.7404	0.8472
2.1988	6.0	222	0.5170	0.7432	0.8496
2.1988	7.0	259	0.4517	0.7854	0.8643
2.1988	8.0	296	0.4865	0.7653	0.8406
1.9616	9.0	333	0.4380	0.7875	0.8614
1.9616	10.0	370	0.4546	0.7698	0.8367
1.7220	11.0	407	0.4355	0.7901	0.8552
1.7220	12.0	444	0.4334	0.7963	0.8622

cagrigungor/signet

signet