<!-- 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. -->
ms-4maps_nonalpha-ds
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 6.0690
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: 0.0005
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.3876 | 0.1 | 100 | 6.3259 |
| 6.3259 | 0.2 | 200 | 6.3044 |
| 6.3008 | 0.3 | 300 | 6.2929 |
| 6.2811 | 0.39 | 400 | 6.2448 |
| 6.2072 | 0.49 | 500 | 6.1656 |
| 6.1554 | 0.59 | 600 | 6.1266 |
| 6.1135 | 0.69 | 700 | 6.0980 |
| 6.1011 | 0.79 | 800 | 6.0825 |
| 6.0908 | 0.89 | 900 | 6.0715 |
| 6.0836 | 0.99 | 1000 | 6.0690 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3
