scifive_ten_epoch / README.md
vsamuel's picture
End of training
8aeeb9d verified
---
base_model: razent/SciFive-base-Pubmed_PMC
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: scifive_ten_epoch
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
# scifive_ten_epoch
This model is a fine-tuned version of [razent/SciFive-base-Pubmed_PMC](https://huggingface.co/razent/SciFive-base-Pubmed_PMC) on the None dataset.
It achieves the following results on the evaluation set:
- Loss: 1.7913
- Rouge1: 0.366
- Rouge2: 0.2107
- Rougel: 0.3132
- Rougelsum: 0.3131
- Gen Len: 17.33
## 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: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel | Rougelsum | Gen Len |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:|
| No log | 1.0 | 275 | 2.2002 | 0.2752 | 0.1436 | 0.2395 | 0.24 | 17.32 |
| 2.3887 | 2.0 | 550 | 1.9610 | 0.347 | 0.2007 | 0.2959 | 0.2961 | 17.73 |
| 2.3887 | 3.0 | 825 | 1.8986 | 0.3664 | 0.2121 | 0.3098 | 0.3101 | 17.5 |
| 1.7972 | 4.0 | 1100 | 1.8486 | 0.3805 | 0.2309 | 0.3267 | 0.327 | 17.1 |
| 1.7972 | 5.0 | 1375 | 1.8232 | 0.372 | 0.2178 | 0.313 | 0.313 | 17.64 |
| 1.6528 | 6.0 | 1650 | 1.8005 | 0.3836 | 0.2271 | 0.3208 | 0.3209 | 17.44 |
| 1.6528 | 7.0 | 1925 | 1.7969 | 0.3821 | 0.2278 | 0.3251 | 0.3253 | 17.25 |
| 1.5676 | 8.0 | 2200 | 1.7872 | 0.3806 | 0.2242 | 0.3224 | 0.323 | 17.3 |
| 1.5676 | 9.0 | 2475 | 1.7888 | 0.3697 | 0.2135 | 0.3135 | 0.3133 | 17.36 |
| 1.5288 | 10.0 | 2750 | 1.7913 | 0.366 | 0.2107 | 0.3132 | 0.3131 | 17.33 |
### Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.1