metadata
license: apache-2.0
tags:
- generated_from_trainer
model-index:
- name: mt5-eng2nep
results: []
mt5-eng2nep
This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.1564
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: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8723 | 0.26 | 500 | 2.9644 |
| 3.2224 | 0.53 | 1000 | 2.5132 |
| 2.9924 | 0.79 | 1500 | 2.3622 |
| 2.842 | 1.05 | 2000 | 2.2799 |
| 2.7975 | 1.32 | 2500 | 2.2186 |
| 2.7526 | 1.58 | 3000 | 2.1765 |
| 2.7554 | 1.84 | 3500 | 2.1564 |
Framework versions
- Transformers 4.13.0
- Pytorch 1.11.0
- Datasets 1.16.1
- Tokenizers 0.10.3