metadata
library_name: transformers
license: apache-2.0
base_model: distilbert/distilgpt2
tags:
- generated_from_trainer
model-index:
- name: test_eli5_clm-model
results: []
test_eli5_clm-model
This model is a fine-tuned version of distilbert/distilgpt2 on the dany0407/eli5_category dataset, as part of the HuggingFace Casual Language modelling guide. It achieves the following results on the evaluation set:
- Loss: 3.8031
Model description
Distil gpt2 fine-tuned on eli5 dataset
Intended uses & limitations
exploration and re-aquainting myself with fineruning/training at home
Training and evaluation data
dany0407/eli5_category
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: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9157 | 1.0 | 1325 | 3.8137 |
| 3.8203 | 2.0 | 2650 | 3.8041 |
| 3.7755 | 3.0 | 3975 | 3.8031 |
Framework versions
- Transformers 4.57.3
- Pytorch 2.9.1
- Datasets 4.4.1
- Tokenizers 0.22.1