metadata
base_model: Zelyanoth/my_fon_translation_model
tags:
- generated_from_trainer
datasets:
- generator
metrics:
- bleu
model-index:
- name: my_fon_translation_model
results:
- task:
name: Sequence-to-sequence Language Modeling
type: text2text-generation
dataset:
name: generator
type: generator
config: default
split: train
args: default
metrics:
- name: Bleu
type: bleu
value: 4.6993
my_fon_translation_model
This model is a fine-tuned version of Zelyanoth/my_fon_translation_model on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 5.3862
- Bleu: 4.6993
- Gen Len: 8.9558
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: 1.87e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 9
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Gen Len |
|---|---|---|---|---|---|
| 1.3141 | 1.0 | 13165 | 5.0069 | 3.3364 | 9.1891 |
| 1.1534 | 2.0 | 26330 | 5.1888 | 3.7137 | 9.1076 |
| 1.1158 | 3.0 | 39495 | 5.1695 | 4.1907 | 8.9998 |
| 0.9801 | 4.0 | 52660 | 5.2281 | 4.2697 | 8.8066 |
| 0.941 | 5.0 | 65825 | 5.3425 | 4.3691 | 9.0261 |
| 0.8676 | 6.0 | 78990 | 5.3371 | 4.0892 | 9.3749 |
| 0.8247 | 7.0 | 92155 | 5.3622 | 4.4876 | 9.1058 |
| 0.7925 | 8.0 | 105320 | 5.3538 | 4.728 | 8.9704 |
| 0.7639 | 9.0 | 118485 | 5.3862 | 4.6993 | 8.9558 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.1.2
- Datasets 2.18.0
- Tokenizers 0.15.2