metadata
license: mit
base_model: gpt2
tags:
- Distily
- generated_from_trainer
model-index:
- name: gpt2_model_card_distily_test
results: []
gpt2_model_card_distily_test
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2109.6001
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: 1
- eval_batch_size: 2
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 1.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0 | 0 | 13504.0 |
| 2552.5 | 0.2002 | 2000 | 2404.8000 |
| 1984.5 | 0.4004 | 4000 | 2262.3999 |
| 2222.25 | 0.6006 | 6000 | 2133.6001 |
| 2066.0 | 0.8008 | 8000 | 2109.6001 |
Framework versions
- Transformers 4.43.3
- Pytorch 2.3.0
- Datasets 2.20.0
- Tokenizers 0.19.1