metadata
library_name: transformers
license: apache-2.0
base_model: google/mt5-base
tags:
- generated_from_trainer
model-index:
- name: mt5-base-encoding-correction-10k
results: []
mt5-base-encoding-correction-10k
This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0340
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: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 3000
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.0415 | 1.0 | 2500 | 0.0354 |
| 0.0326 | 2.0 | 5000 | 0.0277 |
| 0.0243 | 3.0 | 7500 | 0.0273 |
| 0.0251 | 4.0 | 10000 | 0.0267 |
| 0.0131 | 5.0 | 12500 | 0.0252 |
| 0.0153 | 6.0 | 15000 | 0.0268 |
| 0.0124 | 7.0 | 17500 | 0.0279 |
| 0.0083 | 8.0 | 20000 | 0.0340 |
Framework versions
- Transformers 5.10.2
- Pytorch 2.11.0+cu128
- Datasets 4.0.0
- Tokenizers 0.22.2