2.3 KiB
2.3 KiB
license, tags, datasets, model-index
| license | tags | datasets | model-index | |||||||
|---|---|---|---|---|---|---|---|---|---|---|
| mit |
|
|
|
cbt-rarity-all-guten-rarity-all-end-19k-mixed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3203
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 |
|---|---|---|---|
| 6.7045 | 0.29 | 500 | 5.6303 |
| 5.3451 | 0.59 | 1000 | 5.2024 |
| 4.993 | 0.88 | 1500 | 4.9525 |
| 4.7145 | 1.17 | 2000 | 4.7988 |
| 4.5613 | 1.47 | 2500 | 4.6763 |
| 4.4489 | 1.76 | 3000 | 4.5785 |
| 4.3287 | 2.05 | 3500 | 4.4979 |
| 4.1353 | 2.35 | 4000 | 4.4492 |
| 4.1069 | 2.64 | 4500 | 4.3901 |
| 4.0676 | 2.93 | 5000 | 4.3409 |
| 3.8575 | 3.23 | 5500 | 4.3364 |
| 3.8071 | 3.52 | 6000 | 4.3043 |
| 3.7948 | 3.81 | 6500 | 4.2695 |
| 3.6747 | 4.11 | 7000 | 4.2699 |
| 3.5247 | 4.4 | 7500 | 4.2635 |
| 3.5208 | 4.69 | 8000 | 4.2499 |
| 3.5068 | 4.99 | 8500 | 4.2371 |
| 3.3383 | 5.28 | 9000 | 4.2509 |
| 3.332 | 5.58 | 9500 | 4.2494 |
| 3.3304 | 5.87 | 10000 | 4.2487 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3