mt5-aym-lex-try3
This model is a fine-tuned version of alvations/mt5-aym-lex on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.1687
- Chrf: 20.013
- Bleu: 4.4299
- Gen Len: 17.1254
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: 5e-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
- lr_scheduler_warmup_steps: 5
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss | Chrf | Bleu | Gen Len |
|---|---|---|---|---|---|---|
| 0.2142 | 0.0 | 20 | 0.1750 | 20.6672 | 4.6405 | 17.0733 |
| 0.1881 | 0.01 | 40 | 0.1704 | 20.1942 | 4.484 | 17.1141 |
| 0.2355 | 0.01 | 60 | 0.1690 | 20.0147 | 4.4349 | 17.1302 |
| 0.1939 | 0.02 | 80 | 0.1688 | 20.0311 | 4.4427 | 17.1319 |
| 0.1985 | 0.02 | 100 | 0.1687 | 20.013 | 4.4299 | 17.1254 |
Framework versions
- Transformers 4.29.1
- Pytorch 2.0.0+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3