learning_rate: 0.0001
train_batch_size: 2
eval_batch_size: 2
seed: 42
gradient_accumulation_steps: 8
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_8BIT with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: constant_with_warmup
lr_scheduler_warmup_steps: 50
training_steps: 100

Training Loss	Epoch	Step	Validation Loss
5.061	7.2727	10	3.1055
3.6905	14.5455	20	2.6699
2.4714	21.8182	30	1.8229
0.9142	29.0909	40	1.8090
0.0188	36.3636	50	3.1047
0.0544	43.6364	60	3.8352
0.0316	50.9091	70	3.7350
0.0116	58.1818	80	3.7428
0.0005	65.4545	90	4.4955
0.0001	72.7273	100	4.2902

stlee9048/fine_tune_output

fine_tune_output