gpt2_mini_baby_10M_32768_53
This model was trained from scratch on an unknown dataset.
It achieves the following results on the evaluation set:
- Loss: 4.3898
- Accuracy: 0.2987
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: 0.0001
- train_batch_size: 32
- eval_batch_size: 32
- seed: 53
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 40000
- training_steps: 100000
Training results
| Training Loss | Epoch | Step | Validation Loss | Accuracy |
|---|
| 5.9484 | 2.19 | 2000 | 6.5412 | 0.1714 |
| 4.3433 | 4.39 | 4000 | 5.7143 | 0.2059 |
| 4.0404 | 6.58 | 6000 | 5.3750 | 0.2163 |
| 3.9014 | 8.77 | 8000 | 5.2082 | 0.2245 |
| 3.7307 | 10.96 | 10000 | 5.0188 | 0.2458 |
| 3.5978 | 13.16 | 12000 | 4.8811 | 0.2579 |
| 3.4913 | 15.35 | 14000 | 4.7592 | 0.2677 |
| 3.411 | 17.54 | 16000 | 4.6640 | 0.2752 |
| 3.3402 | 19.74 | 18000 | 4.5972 | 0.2822 |
| 3.2797 | 21.93 | 20000 | 4.5349 | 0.2876 |
| 3.2206 | 24.12 | 22000 | 4.4976 | 0.2917 |
| 3.1719 | 26.32 | 24000 | 4.4646 | 0.2940 |
| 3.1314 | 28.51 | 26000 | 4.4208 | 0.2990 |
| 3.0906 | 30.7 | 28000 | 4.3898 | 0.2987 |
| 3.0572 | 32.89 | 30000 | 4.3934 | 0.3009 |
| 3.0177 | 35.09 | 32000 | 4.3996 | 0.3010 |
| 2.9895 | 37.28 | 34000 | 4.3958 | 0.3026 |
Framework versions
- Transformers 4.30.2
- Pytorch 2.9.0+cu128
- Datasets 4.1.1
- Tokenizers 0.13.3
