metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: sft_extra
results: []
sft_extra
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3974
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: 0.0005
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.66 | 0.32 | 200 | 3.5982 |
| 3.319 | 0.64 | 400 | 3.4866 |
| 3.1101 | 0.96 | 600 | 3.3663 |
| 2.1529 | 1.28 | 800 | 3.4439 |
| 1.9697 | 1.6 | 1000 | 3.4081 |
| 1.9158 | 1.92 | 1200 | 3.3974 |
Framework versions
- Transformers 4.41.1
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1