learning_rate: 0.0001
train_batch_size: 16
eval_batch_size: 8
seed: 42
optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
num_epochs: 8

Training Loss	Epoch	Step	Validation Loss	Accuracy	Balanced Accuracy	F1 Weighted	F1 Macro	Precision	Recall
No log	1.0	380	0.2469	0.9366	0.9378	0.9369	0.9367	0.9374	0.9366
0.3756	2.0	760	0.1898	0.9297	0.9299	0.9299	0.9308	0.9320	0.9297
0.1284	3.0	1140	0.1994	0.9482	0.9486	0.9480	0.9483	0.9513	0.9482
0.0501	4.0	1520	0.2381	0.9551	0.9540	0.9553	0.9553	0.9558	0.9551
0.0501	5.0	1900	0.2212	0.9447	0.9451	0.9449	0.9455	0.9452	0.9447
0.0167	6.0	2280	0.2934	0.9516	0.9518	0.9517	0.9521	0.9531	0.9516
0.0061	7.0	2660	0.3348	0.9516	0.9518	0.9517	0.9521	0.9534	0.9516
0.0042	8.0	3040	0.3155	0.9516	0.9518	0.9516	0.9520	0.9535	0.9516

thenlpresearcher/meta-llama_Llama-3_2-3B_StereoDetect_Model

meta-llama_Llama-3_2-3B_StereoDetect_Model