Legal_QA_BERT_augmented_17

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 3.9583

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

• learning_rate: 2e-05
• train_batch_size: 32
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 17

Training results

Training Loss	Epoch	Step	Validation Loss
No log	1.0	15	4.3302
No log	2.0	30	3.7975
No log	3.0	45	3.4189
No log	4.0	60	3.2313
No log	5.0	75	3.2055
No log	6.0	90	3.1888
No log	7.0	105	3.2470
No log	8.0	120	3.4233
No log	9.0	135	3.4465
No log	10.0	150	3.6328
No log	11.0	165	3.7262
No log	12.0	180	3.7712
No log	13.0	195	3.8782
No log	14.0	210	3.9330
No log	15.0	225	4.0671
No log	16.0	240	3.8164
No log	17.0	255	3.9583

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.14.7
• Tokenizers 0.15.0