metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: legalbert-large-1.7M-1_class_actions
    results: []

legalbert-large-1.7M-1_class_actions

This model is a fine-tuned version of pile-of-law/legalbert-large-1.7M-1 on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.6901
Accuracy: 0.55

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 14

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	150	0.6892	0.55
No log	2.0	300	0.6913	0.55
No log	3.0	450	0.7061	0.45
0.7143	4.0	600	0.6908	0.55
0.7143	5.0	750	0.6925	0.55
0.7143	6.0	900	0.6951	0.45
0.7164	7.0	1050	0.6893	0.55
0.7164	8.0	1200	0.6884	0.55
0.7164	9.0	1350	0.6910	0.55
0.7042	10.0	1500	0.6882	0.55
0.7042	11.0	1650	0.7099	0.45
0.7042	12.0	1800	0.6910	0.55
0.7042	13.0	1950	0.6910	0.55
0.6999	14.0	2100	0.6901	0.55

Framework versions

Transformers 4.29.2
Pytorch 2.0.1+cu118
Datasets 2.12.0
Tokenizers 0.13.3