metadata
license: apache-2.0
base_model: distilgpt2
tags:
- generated_from_trainer
model-index:
- name: Task3_2
results: []
Task3_2
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.0013
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.2956 | 1.0 | 871 | 3.0864 |
| 3.053 | 2.0 | 1742 | 3.0407 |
| 2.9593 | 3.0 | 2613 | 3.0220 |
| 2.9048 | 4.0 | 3484 | 3.0057 |
| 2.8384 | 5.0 | 4355 | 3.0057 |
| 2.7976 | 6.0 | 5226 | 3.0029 |
| 2.763 | 7.0 | 6097 | 3.0013 |
| 2.7373 | 8.0 | 6968 | 3.0029 |
| 2.7106 | 9.0 | 7839 | 3.0038 |
| 2.6965 | 10.0 | 8710 | 3.0068 |
Framework versions
- Transformers 4.32.1
- Pytorch 2.0.1+cu118
- Datasets 2.14.4
- Tokenizers 0.13.3