metadata
license: apache-2.0
base_model: facebook/bart-base
tags:
- generated_from_trainer
model-index:
- name: pubmed-abs-sub-03
results: []
pubmed-abs-sub-03
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: 0.1916
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: 16
- eval_batch_size: 16
- 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 |
|---|---|---|---|
| 0.5622 | 0.11 | 500 | 0.4754 |
| 0.4051 | 0.21 | 1000 | 0.3731 |
| 0.3978 | 0.32 | 1500 | 0.3332 |
| 0.3669 | 0.43 | 2000 | 0.3047 |
| 0.3059 | 0.54 | 2500 | 0.2824 |
| 0.294 | 0.64 | 3000 | 0.2632 |
| 0.2774 | 0.75 | 3500 | 0.2579 |
| 0.3134 | 0.86 | 4000 | 0.2408 |
| 0.2865 | 0.96 | 4500 | 0.2345 |
| 0.2103 | 1.07 | 5000 | 0.2320 |
| 0.1974 | 1.18 | 5500 | 0.2289 |
| 0.2026 | 1.28 | 6000 | 0.2303 |
| 0.1931 | 1.39 | 6500 | 0.2155 |
| 0.2027 | 1.5 | 7000 | 0.2167 |
| 0.1977 | 1.61 | 7500 | 0.2120 |
| 0.1836 | 1.71 | 8000 | 0.2100 |
| 0.2204 | 1.82 | 8500 | 0.2043 |
| 0.1731 | 1.93 | 9000 | 0.2009 |
| 0.1479 | 2.03 | 9500 | 0.2004 |
| 0.1277 | 2.14 | 10000 | 0.2040 |
| 0.136 | 2.25 | 10500 | 0.2022 |
| 0.1577 | 2.35 | 11000 | 0.1986 |
| 0.1305 | 2.46 | 11500 | 0.1963 |
| 0.159 | 2.57 | 12000 | 0.1936 |
| 0.1603 | 2.68 | 12500 | 0.1939 |
| 0.1195 | 2.78 | 13000 | 0.1926 |
| 0.1203 | 2.89 | 13500 | 0.1922 |
| 0.1437 | 3.0 | 14000 | 0.1916 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1
- Datasets 2.14.5
- Tokenizers 0.13.3