<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
gpt-m
This model is a fine-tuned version of gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.0096
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: 0.0002
- 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: linear
- training_steps: 10000
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3775 | 0.06 | 500 | 0.0302 |
| 0.0207 | 0.11 | 1000 | 0.0188 |
| 0.0182 | 0.17 | 1500 | 0.0179 |
| 0.0171 | 0.22 | 2000 | 0.0152 |
| 0.0178 | 0.28 | 2500 | 0.0161 |
| 0.0147 | 0.33 | 3000 | 0.0150 |
| 0.0157 | 0.39 | 3500 | 0.0137 |
| 0.0137 | 0.44 | 4000 | 0.0126 |
| 0.0133 | 0.5 | 4500 | 0.0137 |
| 0.012 | 0.56 | 5000 | 0.0120 |
| 0.0122 | 0.61 | 5500 | 0.0117 |
| 0.0129 | 0.67 | 6000 | 0.0118 |
| 0.0113 | 0.72 | 6500 | 0.0114 |
| 0.0106 | 0.78 | 7000 | 0.0109 |
| 0.0119 | 0.83 | 7500 | 0.0108 |
| 0.0122 | 0.89 | 8000 | 0.0102 |
| 0.0105 | 0.94 | 8500 | 0.0101 |
| 0.0094 | 1.0 | 9000 | 0.0098 |
| 0.01 | 1.06 | 9500 | 0.0097 |
| 0.0097 | 1.11 | 10000 | 0.0096 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1+cu116
- Datasets 2.9.0
- Tokenizers 0.13.2
