|
--- |
|
library_name: transformers |
|
license: apache-2.0 |
|
base_model: google/long-t5-tglobal-base |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: model |
|
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. --> |
|
|
|
# model |
|
|
|
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: 1.9329 |
|
- Rouge: 0.1619 |
|
- Meteor: 0.1091 |
|
|
|
## 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: 0.00021414319413263157 |
|
- train_batch_size: 1 |
|
- eval_batch_size: 1 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 3 |
|
- total_train_batch_size: 3 |
|
- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments |
|
- lr_scheduler_type: linear |
|
- num_epochs: 1 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Rouge | Meteor | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:| |
|
| 8.9561 | 0.1 | 25 | 2.1054 | 0.1332 | 0.0870 | |
|
| 8.0871 | 0.2 | 50 | 2.0333 | 0.1512 | 0.0986 | |
|
| 7.8116 | 0.3 | 75 | 2.0106 | 0.1457 | 0.0949 | |
|
| 7.1444 | 0.4 | 100 | 1.9853 | 0.1500 | 0.0989 | |
|
| 7.333 | 0.5 | 125 | 1.9705 | 0.1561 | 0.1057 | |
|
| 6.8319 | 0.6 | 150 | 1.9586 | 0.1596 | 0.1088 | |
|
| 7.2472 | 0.7 | 175 | 1.9541 | 0.1607 | 0.1078 | |
|
| 7.7008 | 0.8 | 200 | 1.9407 | 0.1592 | 0.1083 | |
|
| 7.3862 | 0.9 | 225 | 1.9361 | 0.1620 | 0.1096 | |
|
| 6.6446 | 1.0 | 250 | 1.9329 | 0.1619 | 0.1091 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.0.dev0 |
|
- Pytorch 2.4.1+cu121 |
|
- Datasets 3.0.2 |
|
- Tokenizers 0.20.1 |
|
|
