| --- |
| tags: |
| - generated_from_keras_callback |
| model-index: |
| - name: EricPeter/distilbert-base-cased |
| results: [] |
| --- |
| |
| <!-- This model card has been generated automatically according to the information Keras had access to. You should |
| probably proofread and complete it, then remove this comment. --> |
|
|
| # EricPeter/distilbert-base-cased |
|
|
| This model was trained from scratch on an unknown dataset. |
| It achieves the following results on the evaluation set: |
| - Train Loss: 0.2356 |
| - Epoch: 49 |
|
|
| ## 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: {'inner_optimizer': {'class_name': 'AdamWeightDecay', 'config': {'name': 'AdamWeightDecay', 'learning_rate': {'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 2846, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, '__passive_serialization__': True}, 'warmup_steps': 4, 'power': 1.0, 'name': None}}, 'decay': 0.0, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False, 'weight_decay_rate': 0.06}}, 'dynamic': True, 'initial_scale': 32768.0, 'dynamic_growth_steps': 2000} |
| - training_precision: mixed_float16 |
| |
| ### Training results |
| |
| | Train Loss | Epoch | |
| |:----------:|:-----:| |
| | 0.3158 | 0 | |
| | 0.3561 | 1 | |
| | 0.2694 | 2 | |
| | 0.2718 | 3 | |
| | 0.2687 | 4 | |
| | 0.2844 | 5 | |
| | 0.2824 | 6 | |
| | 0.2698 | 7 | |
| | 0.2882 | 8 | |
| | 0.2808 | 9 | |
| | 0.2710 | 10 | |
| | 0.2663 | 11 | |
| | 0.2574 | 12 | |
| | 0.2417 | 13 | |
| | 0.2581 | 14 | |
| | 0.2581 | 15 | |
| | 0.2625 | 16 | |
| | 0.2443 | 17 | |
| | 0.2360 | 18 | |
| | 0.2478 | 19 | |
| | 0.2431 | 20 | |
| | 0.2454 | 21 | |
| | 0.2409 | 22 | |
| | 0.2359 | 23 | |
| | 0.2428 | 24 | |
| | 0.2374 | 25 | |
| | 0.2419 | 26 | |
| | 0.2371 | 27 | |
| | 0.2392 | 28 | |
| | 0.2393 | 29 | |
| | 0.2378 | 30 | |
| | 0.2399 | 31 | |
| | 0.2381 | 32 | |
| | 0.2347 | 33 | |
| | 0.2414 | 34 | |
| | 0.2352 | 35 | |
| | 0.2361 | 36 | |
| | 0.2407 | 37 | |
| | 0.2397 | 38 | |
| | 0.2314 | 39 | |
| | 0.2370 | 40 | |
| | 0.2338 | 41 | |
| | 0.2360 | 42 | |
| | 0.2356 | 43 | |
| | 0.2375 | 44 | |
| | 0.2343 | 45 | |
| | 0.2366 | 46 | |
| | 0.2377 | 47 | |
| | 0.2369 | 48 | |
| | 0.2356 | 49 | |
| |
| |
| ### Framework versions |
| |
| - Transformers 4.32.0 |
| - TensorFlow 2.12.0 |
| - Datasets 2.14.4 |
| - Tokenizers 0.13.3 |
| |
