learning_rate: 2e-05
train_batch_size: 32
eval_batch_size: 64
seed: 42
gradient_accumulation_steps: 2
total_train_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: cosine
lr_scheduler_warmup_steps: 500
num_epochs: 20
mixed_precision_training: Native AMP
label_smoothing_factor: 0.1

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.6993	1.0	100	1.5844	0.3845	0.3695	0.3845	0.3545
1.2593	2.0	200	1.0278	0.7662	0.7766	0.7662	0.7634
0.8076	3.0	300	0.6558	0.9056	0.9076	0.9056	0.9059
0.6413	4.0	400	0.5866	0.9282	0.9310	0.9282	0.9280
0.5734	5.0	500	0.5556	0.9451	0.9457	0.9451	0.9450
0.5203	6.0	600	0.5825	0.9338	0.9389	0.9338	0.9344
0.4843	7.0	700	0.5588	0.9451	0.9464	0.9451	0.9450

Woolv7007/Egyptian_text_classification

arabert-hate-speech