<!-- 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. -->
gpt-expt-sp-v3-K-600-MA-Mac-actions-kmeans-v3
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0160
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
- gradient_accumulation_steps: 8
- total_train_batch_size: 512
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 1000
- num_epochs: 500
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.1609 | 25.38 | 5000 | 0.0690 |
| 0.0733 | 50.76 | 10000 | 0.0576 |
| 0.0365 | 76.14 | 15000 | 0.0392 |
| 0.0324 | 101.52 | 20000 | 0.0456 |
| 0.0267 | 126.9 | 25000 | 0.0406 |
| 0.0249 | 152.28 | 30000 | 0.0311 |
| 0.0234 | 177.66 | 35000 | 0.0271 |
| 0.0215 | 203.05 | 40000 | 0.0221 |
| 0.0203 | 228.42 | 45000 | 0.0243 |
| 0.0189 | 253.8 | 50000 | 0.0192 |
| 0.0181 | 279.19 | 55000 | 0.0175 |
| 0.0174 | 304.57 | 60000 | 0.0167 |
| 0.017 | 329.95 | 65000 | 0.0165 |
| 0.0167 | 355.33 | 70000 | 0.0162 |
| 0.0165 | 380.71 | 75000 | 0.0161 |
| 0.0163 | 406.09 | 80000 | 0.0160 |
| 0.0162 | 431.47 | 85000 | 0.0160 |
| 0.0161 | 456.85 | 90000 | 0.0160 |
| 0.0161 | 482.23 | 95000 | 0.0160 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
