metadata
base_model: ai-forever/rugpt3medium_based_on_gpt2
tags:
- generated_from_trainer
model-index:
- name: my_rugpt3medium_finetune
results: []
my_rugpt3medium_finetune
This model is a fine-tuned version of ai-forever/rugpt3medium_based_on_gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.2471
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: cosine
- lr_scheduler_warmup_steps: 500
- num_epochs: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 9.9269 | 0.61 | 100 | 9.4224 |
| 9.1428 | 1.23 | 200 | 8.6591 |
| 8.3563 | 1.84 | 300 | 7.8627 |
| 7.665 | 2.45 | 400 | 7.2471 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu121
- Datasets 2.16.0
- Tokenizers 0.15.0