--- tags: - generated_from_keras_callback model-index: - name: EricPeter/distilbert-base-cased results: [] --- # 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