metadata
license: mit
tags:
- generated_from_trainer
datasets:
- squad_modified_for_t5_qg_2
model-index:
- name: greek-m2m100-4ep-512
results: []
greek-m2m100-4ep-512
This model is a fine-tuned version of facebook/m2m100_418M on the squad_modified_for_t5_qg_2 dataset. It achieves the following results on the evaluation set:
- Loss: 1.2974
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: 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
- num_epochs: 4
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.9785 | 0.34 | 100 | 1.4949 |
| 1.5296 | 0.67 | 200 | 1.4161 |
| 1.4651 | 1.01 | 300 | 1.3816 |
| 1.246 | 1.35 | 400 | 1.3648 |
| 1.2419 | 1.69 | 500 | 1.3383 |
| 1.2132 | 2.03 | 600 | 1.3348 |
| 1.0558 | 2.36 | 700 | 1.3216 |
| 1.0584 | 2.7 | 800 | 1.3078 |
| 1.035 | 3.04 | 900 | 1.3108 |
| 0.9301 | 3.38 | 1000 | 1.3030 |
| 0.9222 | 3.72 | 1100 | 1.2974 |
Framework versions
- Transformers 4.27.0.dev0
- Pytorch 1.13.1+cu116
- Datasets 2.10.1
- Tokenizers 0.13.2