<!-- 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. -->
base-plus-wiki-syn-2-14k
This model is a fine-tuned version of gpt2 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 4.3148
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 |
|---|---|---|---|
| 6.7031 | 0.28 | 500 | 5.6332 |
| 5.3191 | 0.55 | 1000 | 5.1964 |
| 4.964 | 0.83 | 1500 | 4.9440 |
| 4.6837 | 1.11 | 2000 | 4.7937 |
| 4.5015 | 1.39 | 2500 | 4.6709 |
| 4.4038 | 1.66 | 3000 | 4.5714 |
| 4.3088 | 1.94 | 3500 | 4.4814 |
| 4.0983 | 2.22 | 4000 | 4.4467 |
| 4.048 | 2.5 | 4500 | 4.4004 |
| 4.0159 | 2.77 | 5000 | 4.3475 |
| 3.927 | 3.05 | 5500 | 4.3214 |
| 3.7309 | 3.33 | 6000 | 4.3138 |
| 3.7299 | 3.61 | 6500 | 4.2814 |
| 3.7122 | 3.88 | 7000 | 4.2527 |
| 3.5488 | 4.16 | 7500 | 4.2687 |
| 3.4485 | 4.44 | 8000 | 4.2578 |
| 3.451 | 4.72 | 8500 | 4.2419 |
| 3.4356 | 4.99 | 9000 | 4.2303 |
| 3.2611 | 5.27 | 9500 | 4.2474 |
| 3.2644 | 5.55 | 10000 | 4.2456 |
| 3.2542 | 5.83 | 10500 | 4.2450 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.11.0+cu113
- Datasets 2.13.0
- Tokenizers 0.13.3
