learning_rate: 0.0001
train_batch_size: 8
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 32
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: cosine
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
2.6118	0.4545	20	0.6795	0.6193	0.7300	0.6193	0.6174
2.4002	0.9091	40	0.5451	0.7386	0.7327	0.7386	0.7270
2.1361	1.3636	60	0.8168	0.6705	0.6832	0.6705	0.6747
2.589	1.8182	80	0.5943	0.6364	0.6591	0.6364	0.6426
2.8187	2.2727	100	0.8248	0.5852	0.7404	0.5852	0.5725
2.08	2.7273	120	0.5875	0.7386	0.7409	0.7386	0.7166
1.1623	3.1818	140	0.6528	0.7159	0.7080	0.7159	0.7084
1.5022	3.6364	160	0.6610	0.6932	0.6828	0.6932	0.6834
0.898	4.0909	180	0.7076	0.6705	0.6683	0.6705	0.6693
0.7971	4.5455	200	0.8023	0.7045	0.6969	0.7045	0.6983
0.582	5.0	220	0.8326	0.6875	0.6827	0.6875	0.6846

AmirMohseni/router-mmBERT-base-v2-text-only

router-mmBERT-base-v2-text-only