learning_rate: 3e-05
train_batch_size: 16
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 32
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: linear
num_epochs: 10
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.6929	1.0	115	0.3841	0.8211	0.8730
0.5861	2.0	230	0.3717	0.8358	0.8847
0.518	3.0	345	0.3726	0.8431	0.8869
0.4114	4.0	460	0.4192	0.8358	0.8847
0.3647	5.0	575	0.4534	0.8407	0.8896
0.2789	6.0	690	0.4335	0.8603	0.9016
0.1847	7.0	805	0.4983	0.8431	0.8889
0.1367	8.0	920	0.5195	0.8505	0.8935
0.1079	9.0	1035	0.5435	0.8603	0.9012
0.1012	10.0	1150	0.5486	0.8578	0.8997

jhj1769/Llama3B_LoRA_mrpc

Llama3B_LoRA_mrpc