<!-- 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. -->
all-base-rarity-all-bnc-rarity-iorder-est-5p5k-mostf
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3552
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 |
|---|---|---|---|
| 6.7751 | 0.31 | 500 | 5.6534 |
| 5.4091 | 0.63 | 1000 | 5.2238 |
| 5.0666 | 0.94 | 1500 | 4.9739 |
| 4.7773 | 1.25 | 2000 | 4.8259 |
| 4.6406 | 1.56 | 2500 | 4.7086 |
| 4.5289 | 1.88 | 3000 | 4.6001 |
| 4.3302 | 2.19 | 3500 | 4.5391 |
| 4.2295 | 2.5 | 4000 | 4.4722 |
| 4.1833 | 2.82 | 4500 | 4.4085 |
| 4.0396 | 3.13 | 5000 | 4.3880 |
| 3.9019 | 3.44 | 5500 | 4.3625 |
| 3.8912 | 3.75 | 6000 | 4.3198 |
| 3.8042 | 4.07 | 6500 | 4.3143 |
| 3.6122 | 4.38 | 7000 | 4.3069 |
| 3.6013 | 4.69 | 7500 | 4.2897 |
| 3.5881 | 5.01 | 8000 | 4.2790 |
| 3.4114 | 5.32 | 8500 | 4.2918 |
| 3.4083 | 5.63 | 9000 | 4.2889 |
| 3.4077 | 5.94 | 9500 | 4.2889 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
