metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: exercise_model
results: []
exercise_model
This model is a fine-tuned version of facebook/bart-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.7260
- Accuracy: 0.45
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: 18
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| No log | 1.0 | 5 | 5.9810 | 0.0 |
| No log | 2.0 | 10 | 4.8367 | 0.1 |
| No log | 3.0 | 15 | 4.2524 | 0.2 |
| No log | 4.0 | 20 | 3.7825 | 0.3 |
| No log | 5.0 | 25 | 3.4538 | 0.5 |
| No log | 6.0 | 30 | 3.1687 | 0.5 |
| No log | 7.0 | 35 | 2.8498 | 0.5 |
| No log | 8.0 | 40 | 2.4818 | 0.5 |
| No log | 9.0 | 45 | 2.2022 | 0.5 |
| No log | 10.0 | 50 | 2.0670 | 0.45 |
| No log | 11.0 | 55 | 1.9735 | 0.45 |
| No log | 12.0 | 60 | 1.9018 | 0.45 |
| No log | 13.0 | 65 | 1.8420 | 0.4 |
| No log | 14.0 | 70 | 1.7969 | 0.4 |
| No log | 15.0 | 75 | 1.7639 | 0.45 |
| No log | 16.0 | 80 | 1.7433 | 0.45 |
| No log | 17.0 | 85 | 1.7305 | 0.45 |
| No log | 18.0 | 90 | 1.7260 | 0.45 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1