<!-- 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. -->
aochildes-rarity-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1164
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 |
---|---|---|---|
6.3514 | 0.29 | 500 | 5.3390 |
5.0369 | 0.59 | 1000 | 4.9222 |
4.7211 | 0.88 | 1500 | 4.6884 |
4.4532 | 1.17 | 2000 | 4.5398 |
4.3029 | 1.47 | 2500 | 4.4318 |
4.2095 | 1.76 | 3000 | 4.3295 |
4.0772 | 2.05 | 3500 | 4.2615 |
3.9042 | 2.35 | 4000 | 4.2130 |
3.8732 | 2.64 | 4500 | 4.1604 |
3.8358 | 2.93 | 5000 | 4.1110 |
3.641 | 3.23 | 5500 | 4.1105 |
3.5952 | 3.52 | 6000 | 4.0799 |
3.5797 | 3.81 | 6500 | 4.0466 |
3.465 | 4.11 | 7000 | 4.0458 |
3.3242 | 4.4 | 7500 | 4.0451 |
3.3146 | 4.69 | 8000 | 4.0309 |
3.3112 | 4.99 | 8500 | 4.0183 |
3.1524 | 5.28 | 9000 | 4.0325 |
3.1343 | 5.57 | 9500 | 4.0319 |
3.1354 | 5.87 | 10000 | 4.0309 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3