|
--- |
|
base_model: samzirbo/gendered |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- bleu |
|
model-index: |
|
- name: desambiguated |
|
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. --> |
|
|
|
# desambiguated |
|
|
|
This model is a fine-tuned version of [samzirbo/gendered](https://huggingface.co/samzirbo/gendered) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.1796 |
|
- Bleu: 43.8537 |
|
- Meteor: 0.6914 |
|
- Chrf++: 62.7374 |
|
|
|
## 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: 0.0001 |
|
- train_batch_size: 64 |
|
- eval_batch_size: 64 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: cosine |
|
- lr_scheduler_warmup_steps: 1000 |
|
- training_steps: 10000 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Bleu | Meteor | Chrf++ | |
|
|:-------------:|:-----:|:-----:|:---------------:|:-------:|:------:|:-------:| |
|
| 1.5616 | 4.0 | 2500 | 1.1681 | 44.0169 | 0.6907 | 62.7853 | |
|
| 1.4542 | 8.0 | 5000 | 1.1767 | 43.9936 | 0.6914 | 62.7456 | |
|
| 1.3907 | 12.0 | 7500 | 1.1790 | 43.9284 | 0.6918 | 62.7791 | |
|
| 1.3672 | 16.0 | 10000 | 1.1796 | 43.8537 | 0.6914 | 62.7374 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.19.1 |
|
- Tokenizers 0.15.2 |
|
|
