gpt-neo-125m-finetuned-philosopher_rave
This model is a fine-tuned version of EleutherAI/gpt-neo-125m on the Triangles/philosopher dataset. It achieves the following results on the evaluation set:
- Loss: 2.9098
Model description
Trained for 10 epochs
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: 3e-07
- 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
- num_epochs: 10.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 155 | 3.0789 |
| No log | 2.0 | 310 | 3.0298 |
| No log | 3.0 | 465 | 2.9946 |
| 3.0535 | 4.0 | 620 | 2.9683 |
| 3.0535 | 5.0 | 775 | 2.9484 |
| 3.0535 | 6.0 | 930 | 2.9334 |
| 2.9563 | 7.0 | 1085 | 2.9224 |
| 2.9563 | 8.0 | 1240 | 2.9150 |
| 2.9563 | 9.0 | 1395 | 2.9108 |
| 2.9115 | 10.0 | 1550 | 2.9098 |
Framework versions
- Transformers 4.39.3
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
- Downloads last month
- 0