<!-- 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-actions-kmeans-v2
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0165
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 |
|---|---|---|---|
| 0.1578 | 19.08 | 5000 | 0.0784 |
| 0.0432 | 38.17 | 10000 | 0.0289 |
| 0.1022 | 57.25 | 15000 | 0.0259 |
| 0.0257 | 76.34 | 20000 | 0.0203 |
| 0.0216 | 95.42 | 25000 | 0.0184 |
| 0.0196 | 114.5 | 30000 | 0.0177 |
| 0.0183 | 133.59 | 35000 | 0.0180 |
| 0.0178 | 152.67 | 40000 | 0.0171 |
| 0.0176 | 171.76 | 45000 | 0.0170 |
| 0.0174 | 190.84 | 50000 | 0.0169 |
| 0.0172 | 209.92 | 55000 | 0.0168 |
| 0.0171 | 229.01 | 60000 | 0.0168 |
| 0.017 | 248.09 | 65000 | 0.0167 |
| 0.0169 | 267.18 | 70000 | 0.0167 |
| 0.0169 | 286.26 | 75000 | 0.0166 |
| 0.0168 | 305.34 | 80000 | 0.0166 |
| 0.0168 | 324.43 | 85000 | 0.0166 |
| 0.0167 | 343.51 | 90000 | 0.0166 |
| 0.0167 | 362.6 | 95000 | 0.0165 |
| 0.0166 | 381.68 | 100000 | 0.0165 |
| 0.0166 | 400.76 | 105000 | 0.0165 |
| 0.0166 | 419.85 | 110000 | 0.0165 |
| 0.0165 | 438.93 | 115000 | 0.0165 |
| 0.0165 | 458.02 | 120000 | 0.0165 |
| 0.0165 | 477.1 | 125000 | 0.0165 |
| 0.0165 | 496.18 | 130000 | 0.0165 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2
