metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: pubmed-abs-sub-01
results: []
pubmed-abs-sub-01
This model is a fine-tuned version of facebook/bart-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2198
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: 5e-05
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 10
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5498 | 0.21 | 500 | 0.4620 |
| 0.4403 | 0.43 | 1000 | 0.3597 |
| 0.3556 | 0.64 | 1500 | 0.3199 |
| 0.3367 | 0.86 | 2000 | 0.2803 |
| 0.2754 | 1.07 | 2500 | 0.2695 |
| 0.268 | 1.28 | 3000 | 0.2568 |
| 0.2449 | 1.5 | 3500 | 0.2485 |
| 0.2271 | 1.71 | 4000 | 0.2398 |
| 0.2238 | 1.93 | 4500 | 0.2337 |
| 0.1857 | 2.14 | 5000 | 0.2310 |
| 0.1802 | 2.35 | 5500 | 0.2273 |
| 0.1798 | 2.57 | 6000 | 0.2219 |
| 0.1905 | 2.78 | 6500 | 0.2205 |
| 0.1925 | 3.0 | 7000 | 0.2198 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3