metadata
license: mit
base_model: gpt2
tags:
- generated_from_trainer
model-index:
- name: model
results: []
model
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.5952
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: 2e-06
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8102 | 0.14 | 500 | 3.6588 |
| 3.7552 | 0.27 | 1000 | 3.6436 |
| 3.7437 | 0.41 | 1500 | 3.6327 |
| 3.7243 | 0.55 | 2000 | 3.6255 |
| 3.7095 | 0.68 | 2500 | 3.6187 |
| 3.6972 | 0.82 | 3000 | 3.6148 |
| 3.6993 | 0.96 | 3500 | 3.6104 |
| 3.6896 | 1.09 | 4000 | 3.6069 |
| 3.6824 | 1.23 | 4500 | 3.6051 |
| 3.674 | 1.37 | 5000 | 3.6024 |
| 3.6823 | 1.5 | 5500 | 3.6015 |
| 3.6823 | 1.64 | 6000 | 3.6002 |
| 3.6687 | 1.78 | 6500 | 3.5988 |
| 3.6759 | 1.92 | 7000 | 3.5974 |
| 3.6735 | 2.05 | 7500 | 3.5968 |
| 3.6571 | 2.19 | 8000 | 3.5961 |
| 3.6575 | 2.33 | 8500 | 3.5959 |
| 3.6757 | 2.46 | 9000 | 3.5955 |
| 3.6749 | 2.6 | 9500 | 3.5952 |
| 3.6662 | 2.74 | 10000 | 3.5952 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0