metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: BARTModel_ExerciseLog
results: []
BARTModel_ExerciseLog
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: 3.7026
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: 2000
- eval_batch_size: 400
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 15
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 1 | 7.3041 |
| No log | 2.0 | 2 | 5.6712 |
| No log | 3.0 | 3 | 4.9672 |
| No log | 4.0 | 4 | 4.5629 |
| No log | 5.0 | 5 | 4.3160 |
| No log | 6.0 | 6 | 4.1601 |
| No log | 7.0 | 7 | 4.0556 |
| No log | 8.0 | 8 | 3.9802 |
| No log | 9.0 | 9 | 3.9111 |
| No log | 10.0 | 10 | 3.8495 |
| No log | 11.0 | 11 | 3.7991 |
| No log | 12.0 | 12 | 3.7606 |
| No log | 13.0 | 13 | 3.7318 |
| No log | 14.0 | 14 | 3.7124 |
| No log | 15.0 | 15 | 3.7026 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1