metadata
license: mit
base_model: indolem/indobert-base-uncased
tags:
- generated_from_keras_callback
model-index:
- name: Labira/LabiraEdu-v1.0x
results: []
Labira/LabiraEdu-v1.0x
This model is a fine-tuned version of indolem/indobert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:
- Train Loss: 0.0206
- Validation Loss: 4.5266
- Epoch: 98
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': 'Adam', 'weight_decay': None, 'clipnorm': None, 'global_clipnorm': None, 'clipvalue': None, 'use_ema': False, 'ema_momentum': 0.99, 'ema_overwrite_frequency': None, 'jit_compile': True, 'is_legacy_optimizer': False, 'learning_rate': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 1100, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False}
- training_precision: float32
Training results
Train Loss | Validation Loss | Epoch |
---|---|---|
5.0565 | 3.9761 | 0 |
3.6621 | 3.2932 | 1 |
3.0961 | 3.2587 | 2 |
2.7357 | 3.2031 | 3 |
2.3059 | 3.2519 | 4 |
1.8933 | 3.4772 | 5 |
1.9076 | 3.1664 | 6 |
1.5492 | 3.4201 | 7 |
1.2578 | 3.5190 | 8 |
1.0478 | 3.4076 | 9 |
1.0130 | 3.5961 | 10 |
0.9073 | 3.4919 | 11 |
0.7071 | 3.5013 | 12 |
0.5616 | 4.0259 | 13 |
0.4798 | 3.9766 | 14 |
0.5938 | 3.8146 | 15 |
0.6476 | 3.7065 | 16 |
0.4264 | 4.1631 | 17 |
0.5290 | 3.7455 | 18 |
0.4637 | 3.6362 | 19 |
0.3826 | 3.8389 | 20 |
0.2876 | 3.7611 | 21 |
0.2221 | 4.0540 | 22 |
0.1752 | 4.0683 | 23 |
0.1544 | 4.0452 | 24 |
0.1600 | 4.0417 | 25 |
0.1390 | 4.0668 | 26 |
0.1134 | 4.0659 | 27 |
0.0965 | 4.0700 | 28 |
0.0820 | 4.2026 | 29 |
0.0810 | 4.3008 | 30 |
0.1166 | 4.0835 | 31 |
0.0776 | 4.0886 | 32 |
0.1033 | 4.1303 | 33 |
0.0512 | 4.1014 | 34 |
0.0484 | 4.1462 | 35 |
0.0565 | 4.2404 | 36 |
0.0652 | 4.2064 | 37 |
0.0538 | 4.1032 | 38 |
0.0516 | 4.0948 | 39 |
0.0611 | 4.2563 | 40 |
0.0523 | 4.3629 | 41 |
0.0571 | 4.3032 | 42 |
0.0479 | 4.3147 | 43 |
0.0308 | 4.3639 | 44 |
0.0370 | 4.3490 | 45 |
0.0406 | 4.3471 | 46 |
0.0300 | 4.4078 | 47 |
0.0270 | 4.4253 | 48 |
0.0283 | 4.4177 | 49 |
0.0228 | 4.4394 | 50 |
0.0538 | 4.4019 | 51 |
0.0342 | 4.3553 | 52 |
0.0249 | 4.3161 | 53 |
0.0657 | 4.4426 | 54 |
0.0309 | 4.5678 | 55 |
0.0467 | 4.4247 | 56 |
0.0356 | 4.5058 | 57 |
0.0431 | 4.4563 | 58 |
0.0366 | 4.5242 | 59 |
0.0624 | 4.3149 | 60 |
0.0471 | 4.3177 | 61 |
0.0248 | 4.3159 | 62 |
0.0388 | 4.3554 | 63 |
0.0262 | 4.3888 | 64 |
0.0360 | 4.4544 | 65 |
0.0319 | 4.4608 | 66 |
0.0269 | 4.4676 | 67 |
0.0373 | 4.3847 | 68 |
0.0205 | 4.3560 | 69 |
0.0223 | 4.3715 | 70 |
0.0306 | 4.3894 | 71 |
0.0235 | 4.4409 | 72 |
0.0189 | 4.4767 | 73 |
0.0280 | 4.5137 | 74 |
0.0165 | 4.5471 | 75 |
0.0098 | 4.5553 | 76 |
0.0173 | 4.5465 | 77 |
0.0234 | 4.5461 | 78 |
0.0231 | 4.5485 | 79 |
0.0237 | 4.5326 | 80 |
0.0158 | 4.5293 | 81 |
0.0178 | 4.5309 | 82 |
0.0225 | 4.5306 | 83 |
0.0191 | 4.5213 | 84 |
0.0213 | 4.5231 | 85 |
0.0144 | 4.5332 | 86 |
0.0191 | 4.5365 | 87 |
0.0188 | 4.5487 | 88 |
0.0272 | 4.5426 | 89 |
0.0126 | 4.5390 | 90 |
0.0224 | 4.5384 | 91 |
0.0218 | 4.5389 | 92 |
0.0083 | 4.5394 | 93 |
0.0246 | 4.5326 | 94 |
0.0199 | 4.5284 | 95 |
0.0174 | 4.5264 | 96 |
0.0130 | 4.5259 | 97 |
0.0206 | 4.5266 | 98 |
Framework versions
- Transformers 4.41.2
- TensorFlow 2.15.0
- Datasets 2.19.2
- Tokenizers 0.19.1