<!-- 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-miss-children_stories-seed
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.1052
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 |
|---|---|---|---|
| 6.3409 | 0.3 | 500 | 5.3419 |
| 5.0286 | 0.6 | 1000 | 4.9295 |
| 4.7037 | 0.9 | 1500 | 4.6832 |
| 4.4246 | 1.2 | 2000 | 4.5359 |
| 4.2918 | 1.5 | 2500 | 4.4200 |
| 4.1862 | 1.8 | 3000 | 4.3170 |
| 4.0317 | 2.1 | 3500 | 4.2468 |
| 3.8811 | 2.4 | 4000 | 4.1944 |
| 3.8583 | 2.7 | 4500 | 4.1408 |
| 3.8126 | 3.0 | 5000 | 4.0981 |
| 3.5694 | 3.31 | 5500 | 4.0926 |
| 3.5839 | 3.61 | 6000 | 4.0590 |
| 3.5599 | 3.91 | 6500 | 4.0275 |
| 3.3793 | 4.21 | 7000 | 4.0365 |
| 3.3133 | 4.51 | 7500 | 4.0243 |
| 3.2975 | 4.81 | 8000 | 4.0125 |
| 3.2367 | 5.11 | 8500 | 4.0151 |
| 3.1249 | 5.41 | 9000 | 4.0169 |
| 3.1267 | 5.71 | 9500 | 4.0142 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
