distilgpt_finetuned_on_imdb
This model is a fine-tuned version of distilgpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.7202
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: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.9191 | 1.0 | 1740 | 3.8071 |
| 3.8521 | 2.0 | 3480 | 3.7726 |
| 3.8118 | 3.0 | 5220 | 3.7570 |
| 3.7841 | 4.0 | 6960 | 3.7433 |
| 3.7563 | 5.0 | 8700 | 3.7383 |
| 3.7394 | 6.0 | 10440 | 3.7281 |
| 3.7246 | 7.0 | 12180 | 3.7250 |
| 3.7109 | 8.0 | 13920 | 3.7217 |
| 3.7026 | 9.0 | 15660 | 3.7195 |
| 3.6986 | 10.0 | 17400 | 3.7202 |
Framework versions
- Transformers 4.28.0
- Pytorch 2.0.1+cu118
- Datasets 2.12.0
- Tokenizers 0.13.3
- Downloads last month
- 7
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.