learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
optimizer: Use 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: 500
num_epochs: 10

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1
No log	1.0	25	4.6523	0.0887	0.0838	0.0560
No log	2.0	50	3.5605	0.2066	0.1706	0.1388
No log	3.0	75	2.5508	0.3304	0.2882	0.2838
No log	4.0	100	2.0977	0.4117	0.4221	0.4049
No log	5.0	125	1.8730	0.4861	0.4941	0.4822
No log	6.0	150	1.8164	0.5232	0.5279	0.5205
No log	7.0	175	1.7070	0.5346	0.5397	0.5340
No log	8.0	200	1.6543	0.5584	0.5662	0.5593
No log	9.0	225	1.6123	0.5616	0.5706	0.5642
No log	10.0	250	1.5537	0.5775	0.5838	0.5757

Kudod/Cognitive-Distortions-Llama-3.1-8B-v1

Cognitive-Distortions-Llama-3.1-8B-v1