<!-- 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. -->
gpt2-concat-all-mod-datasets1-rarity-all-iorder-c13k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3983
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 |
|---|---|---|---|
| 6.7811 | 0.32 | 500 | 5.6598 |
| 5.4368 | 0.63 | 1000 | 5.2297 |
| 5.0819 | 0.95 | 1500 | 4.9819 |
| 4.8064 | 1.27 | 2000 | 4.8391 |
| 4.6653 | 1.58 | 2500 | 4.7273 |
| 4.5682 | 1.9 | 3000 | 4.6197 |
| 4.3541 | 2.22 | 3500 | 4.5701 |
| 4.2704 | 2.53 | 4000 | 4.5079 |
| 4.2264 | 2.85 | 4500 | 4.4351 |
| 4.051 | 3.17 | 5000 | 4.4290 |
| 3.9415 | 3.49 | 5500 | 4.3896 |
| 3.9311 | 3.8 | 6000 | 4.3596 |
| 3.8035 | 4.12 | 6500 | 4.3598 |
| 3.6487 | 4.44 | 7000 | 4.3523 |
| 3.6387 | 4.75 | 7500 | 4.3363 |
| 3.5857 | 5.07 | 8000 | 4.3408 |
| 3.4463 | 5.39 | 8500 | 4.3415 |
| 3.4459 | 5.7 | 9000 | 4.3420 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
