metadata
license: mit
base_model: gpt2
tags:
- generated_from_keras_callback
model-index:
- name: deneme_linux
results: []
deneme_linux
This model is a fine-tuned version of gpt2 on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.6315
- Validation Loss: 7.0703
- Epoch: 99
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:
- optimizer: {'name': 'AdamWeightDecay', 'learning_rate': {'module': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 5e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 5e-05, 'decay_steps': -995, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 1000, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.01}
- training_precision: float32
Training results
| Train Loss | Validation Loss | Epoch |
|---|---|---|
| 0.6331 | 7.0703 | 0 |
| 0.6319 | 7.0703 | 1 |
| 0.6283 | 7.0703 | 2 |
| 0.6276 | 7.0703 | 3 |
| 0.6295 | 7.0703 | 4 |
| 0.6356 | 7.0703 | 5 |
| 0.6282 | 7.0703 | 6 |
| 0.6287 | 7.0703 | 7 |
| 0.6309 | 7.0703 | 8 |
| 0.6291 | 7.0703 | 9 |
| 0.6320 | 7.0703 | 10 |
| 0.6284 | 7.0703 | 11 |
| 0.6333 | 7.0703 | 12 |
| 0.6302 | 7.0703 | 13 |
| 0.6346 | 7.0703 | 14 |
| 0.6285 | 7.0703 | 15 |
| 0.6248 | 7.0703 | 16 |
| 0.6317 | 7.0703 | 17 |
| 0.6291 | 7.0703 | 18 |
| 0.6305 | 7.0703 | 19 |
| 0.6321 | 7.0703 | 20 |
| 0.6317 | 7.0703 | 21 |
| 0.6274 | 7.0703 | 22 |
| 0.6283 | 7.0703 | 23 |
| 0.6359 | 7.0703 | 24 |
| 0.6334 | 7.0703 | 25 |
| 0.6306 | 7.0703 | 26 |
| 0.6375 | 7.0703 | 27 |
| 0.6267 | 7.0703 | 28 |
| 0.6349 | 7.0703 | 29 |
| 0.6298 | 7.0703 | 30 |
| 0.6314 | 7.0703 | 31 |
| 0.6347 | 7.0703 | 32 |
| 0.6284 | 7.0703 | 33 |
| 0.6300 | 7.0703 | 34 |
| 0.6287 | 7.0703 | 35 |
| 0.6337 | 7.0703 | 36 |
| 0.6348 | 7.0703 | 37 |
| 0.6297 | 7.0703 | 38 |
| 0.6376 | 7.0703 | 39 |
| 0.6340 | 7.0703 | 40 |
| 0.6311 | 7.0703 | 41 |
| 0.6327 | 7.0703 | 42 |
| 0.6343 | 7.0703 | 43 |
| 0.6297 | 7.0703 | 44 |
| 0.6316 | 7.0703 | 45 |
| 0.6302 | 7.0703 | 46 |
| 0.6324 | 7.0703 | 47 |
| 0.6355 | 7.0703 | 48 |
| 0.6278 | 7.0703 | 49 |
| 0.6324 | 7.0703 | 50 |
| 0.6332 | 7.0703 | 51 |
| 0.6294 | 7.0703 | 52 |
| 0.6348 | 7.0703 | 53 |
| 0.6288 | 7.0703 | 54 |
| 0.6332 | 7.0703 | 55 |
| 0.6334 | 7.0703 | 56 |
| 0.6302 | 7.0703 | 57 |
| 0.6287 | 7.0703 | 58 |
| 0.6274 | 7.0703 | 59 |
| 0.6272 | 7.0703 | 60 |
| 0.6264 | 7.0703 | 61 |
| 0.6298 | 7.0703 | 62 |
| 0.6275 | 7.0703 | 63 |
| 0.6315 | 7.0703 | 64 |
| 0.6293 | 7.0703 | 65 |
| 0.6325 | 7.0703 | 66 |
| 0.6277 | 7.0703 | 67 |
| 0.6292 | 7.0703 | 68 |
| 0.6254 | 7.0703 | 69 |
| 0.6351 | 7.0703 | 70 |
| 0.6362 | 7.0703 | 71 |
| 0.6312 | 7.0703 | 72 |
| 0.6307 | 7.0703 | 73 |
| 0.6260 | 7.0703 | 74 |
| 0.6289 | 7.0703 | 75 |
| 0.6333 | 7.0703 | 76 |
| 0.6259 | 7.0703 | 77 |
| 0.6270 | 7.0703 | 78 |
| 0.6300 | 7.0703 | 79 |
| 0.6321 | 7.0703 | 80 |
| 0.6352 | 7.0703 | 81 |
| 0.6283 | 7.0703 | 82 |
| 0.6377 | 7.0703 | 83 |
| 0.6291 | 7.0703 | 84 |
| 0.6263 | 7.0703 | 85 |
| 0.6302 | 7.0703 | 86 |
| 0.6336 | 7.0703 | 87 |
| 0.6326 | 7.0703 | 88 |
| 0.6365 | 7.0703 | 89 |
| 0.6328 | 7.0703 | 90 |
| 0.6281 | 7.0703 | 91 |
| 0.6360 | 7.0703 | 92 |
| 0.6347 | 7.0703 | 93 |
| 0.6318 | 7.0703 | 94 |
| 0.6334 | 7.0703 | 95 |
| 0.6349 | 7.0703 | 96 |
| 0.6274 | 7.0703 | 97 |
| 0.6266 | 7.0703 | 98 |
| 0.6315 | 7.0703 | 99 |
Framework versions
- Transformers 4.38.2
- TensorFlow 2.15.0
- Datasets 2.18.0
- Tokenizers 0.15.2