<!-- 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-v5
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0162
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 |
---|---|---|---|
0.1893 | 21.37 | 5000 | 0.0961 |
0.0497 | 42.73 | 10000 | 0.0740 |
0.0486 | 64.1 | 15000 | 0.0601 |
0.0333 | 85.47 | 20000 | 0.0425 |
0.0251 | 106.84 | 25000 | 0.0226 |
0.0213 | 128.21 | 30000 | 0.0190 |
0.0198 | 149.57 | 35000 | 0.0185 |
0.0189 | 170.94 | 40000 | 0.0177 |
0.0183 | 192.31 | 45000 | 0.0175 |
0.0179 | 213.67 | 50000 | 0.0171 |
0.0175 | 235.04 | 55000 | 0.0168 |
0.0173 | 256.41 | 60000 | 0.0167 |
0.0171 | 277.78 | 65000 | 0.0166 |
0.0169 | 299.15 | 70000 | 0.0165 |
0.0168 | 320.51 | 75000 | 0.0165 |
0.0167 | 341.88 | 80000 | 0.0164 |
0.0166 | 363.25 | 85000 | 0.0163 |
0.0165 | 384.62 | 90000 | 0.0163 |
0.0164 | 405.98 | 95000 | 0.0163 |
0.0163 | 427.35 | 100000 | 0.0162 |
0.0163 | 448.72 | 105000 | 0.0162 |
0.0163 | 470.09 | 110000 | 0.0162 |
0.0162 | 491.45 | 115000 | 0.0162 |
Framework versions
- Transformers 4.26.1
- Pytorch 1.13.1.post200
- Datasets 2.9.0
- Tokenizers 0.13.2