metadata
license: mit
base_model: microsoft/DialoGPT-large
tags:
- generated_from_trainer
model-index:
- name: DialoGPT-large-faqs-block-size-32-bs-16-lr-1e-05
results: []
DialoGPT-large-faqs-block-size-32-bs-16-lr-1e-05
This model is a fine-tuned version of microsoft/DialoGPT-large on the None dataset. It achieves the following results on the evaluation set:
- Loss: 3.1840
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: 1e-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: 20
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 1.0 | 161 | 3.4530 |
| No log | 2.0 | 322 | 2.9557 |
| No log | 3.0 | 483 | 2.7615 |
| 3.4514 | 4.0 | 644 | 2.6893 |
| 3.4514 | 5.0 | 805 | 2.6696 |
| 3.4514 | 6.0 | 966 | 2.6738 |
| 1.9345 | 7.0 | 1127 | 2.6820 |
| 1.9345 | 8.0 | 1288 | 2.7452 |
| 1.9345 | 9.0 | 1449 | 2.8237 |
| 1.3641 | 10.0 | 1610 | 2.9001 |
| 1.3641 | 11.0 | 1771 | 2.9492 |
| 1.3641 | 12.0 | 1932 | 3.0018 |
| 1.0356 | 13.0 | 2093 | 3.0482 |
| 1.0356 | 14.0 | 2254 | 3.0798 |
| 1.0356 | 15.0 | 2415 | 3.1145 |
| 0.8385 | 16.0 | 2576 | 3.1357 |
| 0.8385 | 17.0 | 2737 | 3.1498 |
| 0.8385 | 18.0 | 2898 | 3.1750 |
| 0.7252 | 19.0 | 3059 | 3.1823 |
| 0.7252 | 20.0 | 3220 | 3.1840 |
Framework versions
- Transformers 4.33.0.dev0
- Pytorch 2.0.1+cu118
- Datasets 2.14.4.dev0
- Tokenizers 0.13.3