metadata
license: mit
tags:
- generated_from_trainer
model-index:
- name: ms-16maps_nonalpha-ds
results: []
ms-16maps_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: 6.3569
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 |
|---|---|---|---|
| 6.6897 | 0.06 | 100 | 6.5741 |
| 6.5747 | 0.11 | 200 | 6.5529 |
| 6.5287 | 0.17 | 300 | 6.5047 |
| 6.4802 | 0.22 | 400 | 6.4695 |
| 6.4668 | 0.28 | 500 | 6.4435 |
| 6.4468 | 0.33 | 600 | 6.4283 |
| 6.4378 | 0.39 | 700 | 6.4119 |
| 6.4183 | 0.44 | 800 | 6.4043 |
| 6.4172 | 0.5 | 900 | 6.3952 |
| 6.3946 | 0.55 | 1000 | 6.3870 |
| 6.3888 | 0.61 | 1100 | 6.3795 |
| 6.3756 | 0.66 | 1200 | 6.3749 |
| 6.3738 | 0.72 | 1300 | 6.3690 |
| 6.3771 | 0.77 | 1400 | 6.3644 |
| 6.3709 | 0.83 | 1500 | 6.3600 |
| 6.3706 | 0.88 | 1600 | 6.3578 |
| 6.3652 | 0.94 | 1700 | 6.3571 |
| 6.3767 | 1.0 | 1800 | 6.3569 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.0.1+cu117
- Datasets 2.13.1
- Tokenizers 0.13.3