metadata
base_model: ai-forever/rugpt3small_based_on_gpt2
tags:
- generated_from_trainer
metrics:
- accuracy
model-index:
- name: output
results: []
output
This model is a fine-tuned version of ai-forever/rugpt3small_based_on_gpt2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.7083
- Accuracy: 0.5209
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: 1.41e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 24
- total_train_batch_size: 192
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|---|---|---|---|
| 0.7676 | 0.13 | 50 | 0.7502 | 0.4717 |
| 0.7482 | 0.25 | 100 | 0.7369 | 0.4830 |
| 0.7414 | 0.38 | 150 | 0.7276 | 0.4915 |
| 0.7261 | 0.5 | 200 | 0.7205 | 0.5062 |
| 0.7272 | 0.63 | 250 | 0.7143 | 0.5132 |
| 0.7209 | 0.76 | 300 | 0.7106 | 0.5148 |
| 0.7218 | 0.88 | 350 | 0.7083 | 0.5209 |
Framework versions
- Transformers 4.35.2
- Pytorch 2.1.0+cu118
- Datasets 2.15.0
- Tokenizers 0.15.0