metadata
library_name: transformers
license: mit
base_model: mlburnham/Political_DEBATE_large_v1.0
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: nli-stance-finetuning-laurer
results: []
nli-stance-finetuning-laurer
This model is a fine-tuned version of mlburnham/Political_DEBATE_large_v1.0 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.0075
- Accuracy: 0.8140
- F1 Macro: 0.7763
- Accuracy Balanced: 0.7736
- F1 Micro: 0.8140
- Precision Macro: 0.8120
- Recall Macro: 0.7736
- Precision Micro: 0.8140
- Recall Micro: 0.8140
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: 4
- eval_batch_size: 10
- seed: 1234
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.25
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | Accuracy Balanced | F1 Micro | Precision Macro | Recall Macro | Precision Micro | Recall Micro |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.3663 | 1.0 | 538 | 1.0075 | 0.8140 | 0.7763 | 0.7736 | 0.8140 | 0.8120 | 0.7736 | 0.8140 | 0.8140 |
| 0.3854 | 2.0 | 1076 | 1.1733 | 0.7326 | 0.6903 | 0.7285 | 0.7326 | 0.6831 | 0.7285 | 0.7326 | 0.7326 |
| 0.1758 | 3.0 | 1614 | 1.4595 | 0.7326 | 0.6823 | 0.7215 | 0.7326 | 0.6760 | 0.7215 | 0.7326 | 0.7326 |
| 0.0743 | 4.0 | 2152 | 1.6271 | 0.7442 | 0.6692 | 0.6851 | 0.7442 | 0.6634 | 0.6851 | 0.7442 | 0.7442 |
| 0.0343 | 5.0 | 2690 | 1.7175 | 0.7326 | 0.6575 | 0.6750 | 0.7326 | 0.6531 | 0.6750 | 0.7326 | 0.7326 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.5.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1