metadata
license: mit
base_model: microsoft/DialoGPT-medium
tags:
- generated_from_trainer
model-index:
- name: DialoGPT-medium-FinalFantasyDialogue
results: []
DialoGPT-medium-FinalFantasyDialogue
This model is a fine-tuned version of microsoft/DialoGPT-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3830
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: 0.005
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 1000
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.5572 | 1.0 | 282 | 2.2660 |
| 1.9013 | 2.0 | 565 | 1.7536 |
| 1.6648 | 3.0 | 847 | 1.5819 |
| 1.3933 | 4.0 | 1130 | 1.2777 |
| 0.8024 | 5.0 | 1413 | 0.8038 |
| 0.5416 | 6.0 | 1695 | 0.5897 |
| 0.3418 | 7.0 | 1978 | 0.4679 |
| 0.224 | 8.0 | 2261 | 0.4045 |
| 0.1648 | 9.0 | 2543 | 0.3789 |
| 0.1342 | 9.98 | 2820 | 0.3830 |
Framework versions
- Transformers 4.33.2
- Pytorch 2.0.1+cu118
- Datasets 2.14.5
- Tokenizers 0.13.3