|
--- |
|
license: apache-2.0 |
|
base_model: google/long-t5-tglobal-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: long_t5 |
|
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. --> |
|
|
|
# long_t5 |
|
|
|
This model is a fine-tuned version of [google/long-t5-tglobal-base](https://huggingface.co/google/long-t5-tglobal-base) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5355 |
|
- Rouge1: 0.4922 |
|
- Rouge2: 0.3075 |
|
- Rougel: 0.448 |
|
- Rougelsum: 0.4476 |
|
- Gen Len: 25.2419 |
|
|
|
## 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: 2 |
|
- 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 | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:------:|:------:|:---------:|:-------:| |
|
| 2.16 | 1.0 | 3200 | 1.6302 | 0.4745 | 0.2896 | 0.4315 | 0.4311 | 25.1044 | |
|
| 1.9936 | 2.0 | 6400 | 1.5803 | 0.4888 | 0.3046 | 0.4468 | 0.4463 | 25.2094 | |
|
| 1.8414 | 3.0 | 9600 | 1.5484 | 0.4905 | 0.3048 | 0.446 | 0.4455 | 25.695 | |
|
| 1.8103 | 4.0 | 12800 | 1.5363 | 0.4903 | 0.3058 | 0.4464 | 0.4465 | 24.9725 | |
|
| 1.7387 | 5.0 | 16000 | 1.5355 | 0.4922 | 0.3075 | 0.448 | 0.4476 | 25.2419 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.41.2 |
|
- Pytorch 2.3.1+cu118 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
