|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: mbay_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. --> |
|
|
|
# mbay_model |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 2.0621 |
|
- Bleu: 5.0201 |
|
- Gen Len: 14.5313 |
|
|
|
## 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: 16 |
|
- eval_batch_size: 16 |
|
- 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 | Bleu | Gen Len | |
|
|:-------------:|:-----:|:-----:|:---------------:|:------:|:-------:| |
|
| 2.56 | 1.0 | 2479 | 2.3016 | 2.673 | 14.9178 | |
|
| 2.4556 | 2.0 | 4958 | 2.2282 | 3.1563 | 15.0853 | |
|
| 2.3879 | 3.0 | 7437 | 2.1786 | 3.5498 | 14.9548 | |
|
| 2.3574 | 4.0 | 9916 | 2.1417 | 4.0704 | 15.0213 | |
|
| 2.3192 | 5.0 | 12395 | 2.1145 | 4.4057 | 15.0418 | |
|
| 2.3068 | 6.0 | 14874 | 2.0944 | 4.5467 | 14.9812 | |
|
| 2.2855 | 7.0 | 17353 | 2.0796 | 4.7223 | 14.7415 | |
|
| 2.2584 | 8.0 | 19832 | 2.0701 | 4.7772 | 14.5867 | |
|
| 2.2302 | 9.0 | 22311 | 2.0637 | 4.9559 | 14.6012 | |
|
| 2.2502 | 10.0 | 24790 | 2.0621 | 5.0201 | 14.5313 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.33.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.5 |
|
- Tokenizers 0.13.3 |
|
|
