metadata
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: transformers
results: []
transformers
This model was trained from scratch on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.3956
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: 0.0002
- train_batch_size: 48
- eval_batch_size: 12
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 74
- training_steps: 743
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2297 | 1.8 | 74 | 0.4019 |
| 0.1551 | 3.61 | 148 | 0.4087 |
| 0.1306 | 5.41 | 222 | 0.4018 |
| 0.0894 | 7.22 | 296 | 0.3998 |
| 0.0799 | 9.02 | 370 | 0.3972 |
| 0.0782 | 10.83 | 444 | 0.3965 |
| 0.0748 | 12.63 | 518 | 0.3967 |
| 0.0617 | 14.44 | 592 | 0.3964 |
| 0.0666 | 16.24 | 666 | 0.3956 |
| 0.0753 | 18.05 | 740 | 0.3956 |
Framework versions
- Transformers 4.39.2
- Pytorch 2.1.0+cu118
- Datasets 2.16.0
- Tokenizers 0.15.2