|
--- |
|
license: apache-2.0 |
|
base_model: t5-small |
|
tags: |
|
- generated_from_trainer |
|
datasets: |
|
- opus_books |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: my_awesome_opus_books_model |
|
results: |
|
- task: |
|
name: Sequence-to-sequence Language Modeling |
|
type: text2text-generation |
|
dataset: |
|
name: opus_books |
|
type: opus_books |
|
config: en-fr |
|
split: train |
|
args: en-fr |
|
metrics: |
|
- name: Bleu |
|
type: bleu |
|
value: 8.665 |
|
--- |
|
|
|
<!-- 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. --> |
|
|
|
# my_awesome_opus_books_model |
|
|
|
This model is a fine-tuned version of [t5-small](https://huggingface.co/t5-small) on the opus_books dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1887 |
|
- Bleu: 8.665 |
|
- Gen Len: 17.52 |
|
|
|
## 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: 0.0002 |
|
- 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: 20 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len | |
|
|:-------------:|:-----:|:------:|:---------------:|:------:|:-------:| |
|
| 1.6522 | 1.0 | 6355 | 1.4220 | 6.8084 | 17.5646 | |
|
| 1.5046 | 2.0 | 12710 | 1.3440 | 7.2961 | 17.5479 | |
|
| 1.424 | 3.0 | 19065 | 1.3085 | 7.6625 | 17.5388 | |
|
| 1.3927 | 4.0 | 25420 | 1.2794 | 7.8254 | 17.5447 | |
|
| 1.3279 | 5.0 | 31775 | 1.2606 | 8.0112 | 17.5417 | |
|
| 1.2972 | 6.0 | 38130 | 1.2440 | 8.159 | 17.5222 | |
|
| 1.263 | 7.0 | 44485 | 1.2328 | 8.2809 | 17.5201 | |
|
| 1.2414 | 8.0 | 50840 | 1.2263 | 8.3546 | 17.5234 | |
|
| 1.2216 | 9.0 | 57195 | 1.2144 | 8.4076 | 17.537 | |
|
| 1.1954 | 10.0 | 63550 | 1.2076 | 8.425 | 17.5313 | |
|
| 1.1741 | 11.0 | 69905 | 1.2069 | 8.4543 | 17.5247 | |
|
| 1.1573 | 12.0 | 76260 | 1.1971 | 8.5306 | 17.5245 | |
|
| 1.1423 | 13.0 | 82615 | 1.1989 | 8.6061 | 17.5168 | |
|
| 1.1329 | 14.0 | 88970 | 1.1946 | 8.6169 | 17.5322 | |
|
| 1.1145 | 15.0 | 95325 | 1.1926 | 8.6135 | 17.5258 | |
|
| 1.1007 | 16.0 | 101680 | 1.1889 | 8.6164 | 17.5314 | |
|
| 1.1127 | 17.0 | 108035 | 1.1882 | 8.686 | 17.5217 | |
|
| 1.0888 | 18.0 | 114390 | 1.1884 | 8.6621 | 17.5209 | |
|
| 1.0737 | 19.0 | 120745 | 1.1883 | 8.673 | 17.5209 | |
|
| 1.0733 | 20.0 | 127100 | 1.1887 | 8.665 | 17.52 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.32.1 |
|
- Pytorch 2.0.1+cu118 |
|
- Datasets 2.14.4 |
|
- Tokenizers 0.13.3 |
|
|