<!-- 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-mod-datatsets-rarity-all-iorder-e13k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1226
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: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 6.7718 | 0.32 | 500 | 5.7281 |
| 5.4474 | 0.65 | 1000 | 5.2933 |
| 5.0982 | 0.97 | 1500 | 5.0449 |
| 4.8151 | 1.29 | 2000 | 4.8885 |
| 4.6938 | 1.61 | 2500 | 4.7536 |
| 4.5789 | 1.94 | 3000 | 4.6584 |
| 4.3616 | 2.26 | 3500 | 4.6069 |
| 4.2969 | 2.58 | 4000 | 4.5367 |
| 4.2577 | 2.91 | 4500 | 4.4728 |
| 4.0523 | 3.23 | 5000 | 4.4717 |
| 3.9978 | 3.55 | 5500 | 4.4424 |
| 3.9769 | 3.87 | 6000 | 4.3959 |
| 3.7984 | 4.2 | 6500 | 4.4148 |
| 3.7049 | 4.52 | 7000 | 4.4053 |
| 3.7033 | 4.84 | 7500 | 4.3793 |
| 3.5633 | 5.16 | 8000 | 4.3989 |
| 3.4447 | 5.49 | 8500 | 4.4027 |
| 3.4427 | 5.81 | 9000 | 4.3926 |
| 3.3719 | 6.13 | 9500 | 4.4064 |
| 3.2863 | 6.46 | 10000 | 4.4103 |
| 3.2858 | 6.78 | 10500 | 4.4118 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
