<!-- 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-aochildes-mod-no-repeating-sub-5p9k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1910
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 |
|---|---|---|---|
| 6.7322 | 0.29 | 500 | 5.6333 |
| 5.3729 | 0.59 | 1000 | 5.1988 |
| 5.0349 | 0.88 | 1500 | 4.9538 |
| 4.7493 | 1.17 | 2000 | 4.8018 |
| 4.5927 | 1.46 | 2500 | 4.6743 |
| 4.486 | 1.76 | 3000 | 4.5692 |
| 4.3597 | 2.05 | 3500 | 4.4925 |
| 4.1596 | 2.34 | 4000 | 4.4409 |
| 4.1333 | 2.64 | 4500 | 4.3870 |
| 4.0953 | 2.93 | 5000 | 4.3292 |
| 3.8828 | 3.22 | 5500 | 4.3239 |
| 3.8324 | 3.51 | 6000 | 4.2936 |
| 3.8143 | 3.81 | 6500 | 4.2607 |
| 3.7021 | 4.1 | 7000 | 4.2580 |
| 3.536 | 4.39 | 7500 | 4.2492 |
| 3.5371 | 4.69 | 8000 | 4.2342 |
| 3.5223 | 4.98 | 8500 | 4.2215 |
| 3.3541 | 5.27 | 9000 | 4.2356 |
| 3.3407 | 5.57 | 9500 | 4.2346 |
| 3.3399 | 5.86 | 10000 | 4.2341 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
