first_tldr / README.md
Archeane's picture
update model card README.md
744c159
---
license: bsd-3-clause
tags:
- generated_from_trainer
metrics:
- rouge
model-index:
- name: first_tldr
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. -->
# first_tldr
This model is a fine-tuned version of [pszemraj/long-t5-tglobal-base-16384-book-summary](https://huggingface.co/pszemraj/long-t5-tglobal-base-16384-book-summary) on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 1.4427
- Rouge1: 0.3859
- Rouge2: 0.1307
- Rougel: 0.2443
## 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: 0.0005
- train_batch_size: 1
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 128
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
### Training results
| Training Loss | Epoch | Step | Validation Loss | Rouge1 | Rouge2 | Rougel |
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|
| No log | 0.98 | 47 | 1.4361 | 0.3848 | 0.1323 | 0.2419 |
| No log | 1.97 | 94 | 1.4427 | 0.3859 | 0.1307 | 0.2443 |
### Framework versions
- Transformers 4.28.0
- Pytorch 1.12.1+cu116
- Datasets 2.4.0
- Tokenizers 0.12.1