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: 0.1834
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: 20
- training_steps: 205
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.3619 | 0.6119 | 41 | 0.3519 |
| 0.217 | 1.2239 | 82 | 0.2386 |
| 0.186 | 1.8358 | 123 | 0.2015 |
| 0.1619 | 2.4478 | 164 | 0.1864 |
| 0.1597 | 3.0597 | 205 | 0.1834 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.0.1+cu118
- Datasets 2.16.0
- Tokenizers 0.19.1