<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
Timelist_large_GPT_from_sber1
This model is a fine-tuned version of sberbank-ai/rugpt3small_based_on_gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.4887
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: 3e-05
- train_batch_size: 3
- eval_batch_size: 3
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 6
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.97 | 16 | 3.5658 |
| No log | 2.0 | 33 | 3.5069 |
| No log | 2.97 | 49 | 3.4860 |
| No log | 4.0 | 66 | 3.4713 |
| No log | 4.97 | 82 | 3.4724 |
| No log | 6.0 | 99 | 3.4769 |
| No log | 6.97 | 115 | 3.4814 |
| No log | 8.0 | 132 | 3.4879 |
| No log | 8.97 | 148 | 3.4869 |
| No log | 9.7 | 160 | 3.4887 |
Framework versions
- Transformers 4.33.3
- Pytorch 2.0.1+cu117
- Datasets 2.14.5
- Tokenizers 0.13.3
