|
--- |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- rouge |
|
model-index: |
|
- name: t5-v1-base-s-q-c-multi-task-qgen |
|
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. --> |
|
|
|
# t5-v1-base-s-q-c-multi-task-qgen |
|
|
|
This model is a fine-tuned version of [anshoomehra/t5-v1-base-s-q-multi-task-qgen](https://huggingface.co/anshoomehra/t5-v1-base-s-q-multi-task-qgen) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.5165 |
|
- Rouge1: 0.5819 |
|
- Rouge2: 0.4231 |
|
- Rougel: 0.5487 |
|
- Rougelsum: 0.5491 |
|
|
|
## 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: 0.0003 |
|
- train_batch_size: 6 |
|
- eval_batch_size: 6 |
|
- 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:------:|:------:|:------:|:---------:| |
|
| 1.9372 | 1.0 | 942 | 1.4811 | 0.5555 | 0.3861 | 0.5243 | 0.5237 | |
|
| 1.2665 | 2.0 | 1884 | 1.4050 | 0.5688 | 0.4056 | 0.5385 | 0.539 | |
|
| 0.955 | 3.0 | 2826 | 1.4131 | 0.5733 | 0.4101 | 0.5426 | 0.5436 | |
|
| 0.7471 | 4.0 | 3768 | 1.4436 | 0.5769 | 0.4179 | 0.5464 | 0.5466 | |
|
| 0.6382 | 5.0 | 4710 | 1.5165 | 0.5819 | 0.4231 | 0.5487 | 0.5491 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.23.0.dev0 |
|
- Pytorch 1.12.1+cu113 |
|
- Datasets 2.5.2 |
|
- Tokenizers 0.13.0 |
|
|
