<!-- 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_cbt_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: 4.1220
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 |
---|---|---|---|
6.365 | 0.29 | 500 | 5.3408 |
5.0483 | 0.59 | 1000 | 4.9282 |
4.7186 | 0.88 | 1500 | 4.6933 |
4.4606 | 1.17 | 2000 | 4.5590 |
4.315 | 1.47 | 2500 | 4.4381 |
4.2073 | 1.76 | 3000 | 4.3375 |
4.0917 | 2.05 | 3500 | 4.2624 |
3.9138 | 2.35 | 4000 | 4.2183 |
3.8813 | 2.64 | 4500 | 4.1641 |
3.8464 | 2.93 | 5000 | 4.1152 |
3.6477 | 3.23 | 5500 | 4.1130 |
3.6014 | 3.52 | 6000 | 4.0847 |
3.5838 | 3.81 | 6500 | 4.0509 |
3.4799 | 4.11 | 7000 | 4.0527 |
3.3288 | 4.4 | 7500 | 4.0486 |
3.328 | 4.69 | 8000 | 4.0350 |
3.3186 | 4.99 | 8500 | 4.0239 |
3.1615 | 5.28 | 9000 | 4.0374 |
3.1453 | 5.58 | 9500 | 4.0360 |
3.1478 | 5.87 | 10000 | 4.0353 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3