metadata
library_name: transformers
base_model: ai-forever/rugpt3small_based_on_gpt2
tags:
- generated_from_trainer
model-index:
- name: aristotle_csv2
results: []
aristotle_csv2
This model is a fine-tuned version of ai-forever/rugpt3small_based_on_gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.3083
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: 5e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Use OptimizerNames.ADAFACTOR and the args are: No additional optimizer arguments
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 500
- num_epochs: 30
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.1893 | 1.0 | 129 | 3.9908 |
| 3.6923 | 2.0 | 258 | 3.4627 |
| 3.4284 | 3.0 | 387 | 3.3217 |
| 3.146 | 4.0 | 516 | 3.2514 |
| 2.86 | 5.0 | 645 | 3.2055 |
| 2.6066 | 6.0 | 774 | 3.2279 |
| 2.3943 | 7.0 | 903 | 3.2737 |
| 2.1619 | 8.0 | 1032 | 3.3083 |
Framework versions
- Transformers 4.48.3
- Pytorch 2.5.1+cu124
- Datasets 3.3.0
- Tokenizers 0.21.0