metadata
license: mit
base_model: openai-community/gpt2
tags:
- generated_from_trainer
model-index:
- name: GPT2_EmpAI
results: []
GPT2_EmpAI
This model is a fine-tuned version of openai-community/gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.7913
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: 1e-05
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 16000
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1721 | 1.0 | 5998 | 3.0468 |
| 3.0007 | 2.0 | 11997 | 2.9220 |
| 2.834 | 3.0 | 17995 | 2.8383 |
| 2.7228 | 4.0 | 23994 | 2.8011 |
| 2.6584 | 5.0 | 29990 | 2.7913 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2