metadata
license: mit
base_model: tinkoff-ai/ruDialoGPT-medium
tags:
- generated_from_trainer
model-index:
- name: model
results: []
model
This model is a fine-tuned version of tinkoff-ai/ruDialoGPT-medium on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.9686
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: 32
- 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
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.0471 | 1.0 | 1978 | 1.0083 |
| 0.9815 | 2.0 | 3956 | 0.9772 |
| 0.9378 | 3.0 | 5934 | 0.9686 |
Framework versions
- Transformers 4.32.1
- Pytorch 1.13.1+cu117
- Datasets 2.10.1
- Tokenizers 0.13.3