metadata
library_name: transformers
license: mit
base_model: facebook/bart-large-mnli
tags:
- generated_from_keras_callback
model-index:
- name: zero-shot-prompt-classifier-bart-ft
results: []
zero-shot-prompt-classifier-bart-ft
This model is a fine-tuned version of facebook/bart-large-mnli on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.4474
- Train Accuracy: 0.7843
- Validation Loss: 1.5942
- Validation Accuracy: 0.4657
- Epoch: 4
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:
- optimizer: {'name': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': False, 'is_legacy_optimizer': False, 'learning_rate': 5e-06, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-07, 'amsgrad': False}
- training_precision: float32
Training results
| Train Loss | Train Accuracy | Validation Loss | Validation Accuracy | Epoch |
|---|---|---|---|---|
| 0.9969 | 0.5490 | 0.9182 | 0.6225 | 0 |
| 0.7647 | 0.6601 | 1.0025 | 0.5441 | 1 |
| 0.6465 | 0.7157 | 1.1472 | 0.5392 | 2 |
| 0.5849 | 0.7418 | 1.1974 | 0.5049 | 3 |
| 0.4474 | 0.7843 | 1.5942 | 0.4657 | 4 |
Framework versions
- Transformers 4.44.2
- TensorFlow 2.18.0-dev20240717
- Datasets 2.21.0
- Tokenizers 0.19.1