metadata
license: apache-2.0
base_model: distilbert/distilgpt2
tags:
- generated_from_trainer
datasets:
- eli5_category
model-index:
- name: custom_model
results: []
custom_model
This model is a fine-tuned version of distilbert/distilgpt2 on the eli5_category dataset. It achieves the following results on the evaluation set:
- Loss: 3.8342
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: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9476 | 1.0 | 1293 | 3.8435 |
| 3.856 | 2.0 | 2586 | 3.8343 |
| 3.8016 | 3.0 | 3879 | 3.8342 |
Framework versions
- Transformers 4.40.1
- Pytorch 2.0.0+cpu
- Datasets 2.17.0
- Tokenizers 0.19.1