metadata
license: mit
library_name: peft
tags:
- generated_from_trainer
base_model: facebook/bart-large-mnli
metrics:
- f1
- precision
- recall
- accuracy
model-index:
- name: eu_adapter01
results: []
eu_adapter01
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:
- Loss: 0.6074
- F1: 0.8169
- Precision: 0.7945
- Recall: 0.8406
- Accuracy: 0.8267
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: 0.0002
- train_batch_size: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 20
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 | Precision | Recall | Accuracy |
|---|---|---|---|---|---|---|---|
| 0.6875 | 0.625 | 10 | 0.6413 | 0.5625 | 1.0 | 0.3913 | 0.72 |
| 0.6028 | 1.25 | 20 | 0.6077 | 0.7971 | 0.7971 | 0.7971 | 0.8133 |
| 0.5901 | 1.875 | 30 | 0.6074 | 0.8169 | 0.7945 | 0.8406 | 0.8267 |
Framework versions
- PEFT 0.10.0
- Transformers 4.41.2
- Pytorch 2.2.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1