learning_rate: 2e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
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: linear
num_epochs: 15

Training Loss	Epoch	Step	Validation Loss	F1
No log	1.0	336	3.3880	0.0048
6.8408	2.0	672	3.3921	0.0072
6.7062	3.0	1008	3.3780	0.0090
6.7062	4.0	1344	3.3591	0.0084
6.5719	5.0	1680	3.3621	0.0061
6.5001	6.0	2016	3.3828	0.0059
6.5001	7.0	2352	3.3970	0.0066
6.3904	8.0	2688	3.4140	0.0048
6.3042	9.0	3024	3.4417	0.0039
6.3042	10.0	3360	3.4631	0.0025
6.1978	11.0	3696	3.4738	0.0028
6.1852	12.0	4032	3.5027	0.0013
6.1852	13.0	4368	3.5194	0.0
6.1082	14.0	4704	3.5289	0.0012
6.0711	15.0	5040	3.5338	0.0011

harshrtr07/legal-bert-cuad-risk-analyzer

legal-bert-cuad-risk-analyzer