metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: sft_cml4
results: []
sft_cml4
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4024
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 |
|---|---|---|---|
| 3.6594 | 0.32 | 200 | 3.5973 |
| 3.3107 | 0.64 | 400 | 3.4906 |
| 3.0987 | 0.96 | 600 | 3.3723 |
| 2.1443 | 1.28 | 800 | 3.4440 |
| 1.9649 | 1.6 | 1000 | 3.4159 |
| 1.9109 | 1.92 | 1200 | 3.4024 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1