metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: distilgpt2-finetuned-furryirl2
results: []
distilgpt2-finetuned-furryirl2
This model is a fine-tuned version of distilgpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3031
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-05
- 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: 8
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.8899 | 1.0 | 852 | 3.5930 |
| 3.7515 | 2.0 | 1704 | 3.4929 |
| 3.6564 | 3.0 | 2556 | 3.4250 |
| 3.6221 | 4.0 | 3408 | 3.3787 |
| 3.5517 | 5.0 | 4260 | 3.3441 |
| 3.5009 | 6.0 | 5112 | 3.3200 |
| 3.5012 | 7.0 | 5964 | 3.3080 |
| 3.4741 | 8.0 | 6816 | 3.3031 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.2.1+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1