metadata
license: apache-2.0
base_model: distilbert/distilgpt2
tags:
- generated_from_trainer
metrics:
- bleu
model-index:
- name: distilgpt2-finetuned
results: []
distilgpt2-finetuned
This model is a fine-tuned version of distilbert/distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.8114
- Bleu: 0.0101
- Bertscore Precision: 0.1499
- Bertscore Recall: 0.1656
- Bertscore F1: 0.1571
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
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Bleu | Bertscore Precision | Bertscore Recall | Bertscore F1 |
|---|---|---|---|---|---|---|---|
| 4.1924 | 1.0 | 644 | 4.0681 | 0.0091 | 0.1493 | 0.1649 | 0.1564 |
| 4.0754 | 2.0 | 1288 | 3.8779 | 0.0099 | 0.1498 | 0.1654 | 0.1569 |
| 3.8277 | 3.0 | 1932 | 3.8114 | 0.0101 | 0.1499 | 0.1656 | 0.1571 |
Framework versions
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1