<!-- 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. -->
guten-rarity-all-end-19k-ctx-512-finegrained-eval
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.2215
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: 64
- eval_batch_size: 64
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 6
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 8.9362 | 0.24 | 100 | 7.3168 |
| 6.5524 | 0.48 | 200 | 6.1279 |
| 5.9236 | 0.71 | 300 | 5.7874 |
| 5.6556 | 0.95 | 400 | 5.5952 |
| 5.4733 | 1.19 | 500 | 5.4416 |
| 5.2958 | 1.43 | 600 | 5.2824 |
| 5.1307 | 1.66 | 700 | 5.1223 |
| 4.9829 | 1.9 | 800 | 4.9860 |
| 4.8024 | 2.14 | 900 | 4.8963 |
| 4.6927 | 2.38 | 1000 | 4.7992 |
| 4.6095 | 2.61 | 1100 | 4.6988 |
| 4.516 | 2.85 | 1200 | 4.6015 |
| 4.3713 | 3.09 | 1300 | 4.5147 |
| 4.2277 | 3.33 | 1400 | 4.4417 |
| 4.1862 | 3.56 | 1500 | 4.3820 |
| 4.1371 | 3.8 | 1600 | 4.3342 |
| 4.059 | 4.04 | 1700 | 4.2893 |
| 3.8884 | 4.28 | 1800 | 4.2612 |
| 3.8665 | 4.51 | 1900 | 4.2299 |
| 3.8437 | 4.75 | 2000 | 4.1981 |
| 3.815 | 4.99 | 2100 | 4.1766 |
| 3.6574 | 5.23 | 2200 | 4.1724 |
| 3.6435 | 5.46 | 2300 | 4.1629 |
| 3.6348 | 5.7 | 2400 | 4.1584 |
| 3.6424 | 5.94 | 2500 | 4.1557 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
