metadata
library_name: transformers
license: apache-2.0
base_model: distilbert-base-uncased
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: legalcase_outcomepred_model
results: []
legalcase_outcomepred_model
This model is a fine-tuned version of distilbert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.0116
- Accuracy: 0.3307
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 1.7752 | 0.9981 | 132 | 1.8412 | 0.2640 |
| 1.6453 | 1.9962 | 264 | 1.8323 | 0.2867 |
| 1.6322 | 2.9943 | 396 | 1.7919 | 0.2985 |
| 1.4239 | 4.0 | 529 | 1.8052 | 0.3188 |
| 1.3082 | 4.9981 | 661 | 1.8625 | 0.3217 |
| 1.2395 | 5.9962 | 793 | 1.8780 | 0.3382 |
| 1.103 | 6.9943 | 925 | 1.9332 | 0.3302 |
| 1.0687 | 8.0 | 1058 | 1.9723 | 0.3382 |
| 1.0303 | 8.9981 | 1190 | 2.0012 | 0.3363 |
| 0.9643 | 9.9811 | 1320 | 2.0116 | 0.3307 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 3.0.0
- Tokenizers 0.19.1