metadata
base_model: razent/SciFive-base-Pubmed_PMC
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: scifive_five_epoch
results: []
scifive_five_epoch
This model is a fine-tuned version of razent/SciFive-base-Pubmed_PMC on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.9038
- Rouge1: 0.3532
- Rouge2: 0.1988
- Rougel: 0.2922
- Rougelsum: 0.2938
- Gen Len: 17.78
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: 4
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 275 | 2.2317 | 0.2625 | 0.1384 | 0.2222 | 0.2216 | 16.68 |
| 2.4127 | 2.0 | 550 | 2.0008 | 0.3456 | 0.1909 | 0.2904 | 0.2898 | 18.24 |
| 2.4127 | 3.0 | 825 | 1.9520 | 0.3624 | 0.2103 | 0.3047 | 0.3048 | 17.88 |
| 1.8512 | 4.0 | 1100 | 1.9108 | 0.3694 | 0.2119 | 0.3056 | 0.3063 | 17.84 |
| 1.8512 | 5.0 | 1375 | 1.9038 | 0.3532 | 0.1988 | 0.2922 | 0.2938 | 17.78 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1