metadata
license: apache-2.0
base_model: aparajitha/bart-base-sci
tags:
- generated_from_trainer
model-index:
- name: bart-base-sci-ms-fl
results: []
bart-base-sci-ms-fl
This model is a fine-tuned version of aparajitha/bart-base-sci on the None dataset. It achieves the following results on the evaluation set:
- Loss: 2.3036
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: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 6
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 274 | 2.5338 |
| 3.0007 | 2.0 | 548 | 2.4135 |
| 3.0007 | 3.0 | 822 | 2.3471 |
| 2.4247 | 4.0 | 1096 | 2.3202 |
| 2.4247 | 5.0 | 1370 | 2.3081 |
| 2.2917 | 6.0 | 1644 | 2.3036 |
Framework versions
- Transformers 4.43.4
- Pytorch 1.13.1
- Datasets 2.12.0
- Tokenizers 0.19.1