metadata
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: my_awesome_model
results: []
my_awesome_model
This model is a fine-tuned version of pile-of-law/legalbert-large-1.7M-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7448
- Accuracy: 0.6333
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: 6
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 150 | 0.6502 | 0.6 |
| No log | 2.0 | 300 | 0.6360 | 0.66 |
| No log | 3.0 | 450 | 0.6546 | 0.69 |
| 0.6614 | 4.0 | 600 | 0.6632 | 0.6333 |
| 0.6614 | 5.0 | 750 | 0.7435 | 0.65 |
| 0.6614 | 6.0 | 900 | 0.7448 | 0.6333 |
Framework versions
- Transformers 4.29.2
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3