|
--- |
|
library_name: transformers |
|
license: mit |
|
base_model: Labira/LabiraPJOK_2_100_Full |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: Labira/LabiraPJOK_3_100_Full |
|
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. --> |
|
|
|
# Labira/LabiraPJOK_3_100_Full |
|
|
|
This model is a fine-tuned version of [Labira/LabiraPJOK_2_100_Full](https://huggingface.co/Labira/LabiraPJOK_2_100_Full) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.0026 |
|
- Validation Loss: 0.0007 |
|
- Epoch: 76 |
|
|
|
## 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 | |
|
|:----------:|:---------------:|:-----:| |
|
| 2.7614 | 1.1522 | 0 | |
|
| 1.5531 | 0.5524 | 1 | |
|
| 1.0482 | 0.2232 | 2 | |
|
| 0.5443 | 0.0847 | 3 | |
|
| 0.5227 | 0.0529 | 4 | |
|
| 0.2873 | 0.0412 | 5 | |
|
| 0.2568 | 0.0330 | 6 | |
|
| 0.1310 | 0.0190 | 7 | |
|
| 0.1108 | 0.0067 | 8 | |
|
| 0.1252 | 0.0117 | 9 | |
|
| 0.0740 | 0.0071 | 10 | |
|
| 0.0507 | 0.0059 | 11 | |
|
| 0.0790 | 0.0058 | 12 | |
|
| 0.0282 | 0.0036 | 13 | |
|
| 0.0562 | 0.0070 | 14 | |
|
| 0.0850 | 0.0047 | 15 | |
|
| 0.0715 | 0.0176 | 16 | |
|
| 0.0724 | 0.0077 | 17 | |
|
| 0.0361 | 0.0024 | 18 | |
|
| 0.0266 | 0.0029 | 19 | |
|
| 0.0207 | 0.0026 | 20 | |
|
| 0.0158 | 0.0023 | 21 | |
|
| 0.0086 | 0.0016 | 22 | |
|
| 0.0214 | 0.0093 | 23 | |
|
| 0.0327 | 0.0063 | 24 | |
|
| 0.0102 | 0.0016 | 25 | |
|
| 0.0072 | 0.0012 | 26 | |
|
| 0.0273 | 0.0024 | 27 | |
|
| 0.0185 | 0.0034 | 28 | |
|
| 0.0091 | 0.0018 | 29 | |
|
| 0.0144 | 0.0021 | 30 | |
|
| 0.0107 | 0.0032 | 31 | |
|
| 0.0632 | 0.0037 | 32 | |
|
| 0.0149 | 0.0034 | 33 | |
|
| 0.0151 | 0.0103 | 34 | |
|
| 0.0195 | 0.0081 | 35 | |
|
| 0.0145 | 0.0023 | 36 | |
|
| 0.0150 | 0.0012 | 37 | |
|
| 0.0126 | 0.0018 | 38 | |
|
| 0.0068 | 0.0017 | 39 | |
|
| 0.0057 | 0.0014 | 40 | |
|
| 0.0075 | 0.0015 | 41 | |
|
| 0.0035 | 0.0015 | 42 | |
|
| 0.0059 | 0.0013 | 43 | |
|
| 0.0040 | 0.0010 | 44 | |
|
| 0.0036 | 0.0009 | 45 | |
|
| 0.0040 | 0.0011 | 46 | |
|
| 0.0058 | 0.0020 | 47 | |
|
| 0.0801 | 0.0013 | 48 | |
|
| 0.0062 | 0.0014 | 49 | |
|
| 0.0049 | 0.0011 | 50 | |
|
| 0.0057 | 0.0012 | 51 | |
|
| 0.0023 | 0.0011 | 52 | |
|
| 0.0047 | 0.0007 | 53 | |
|
| 0.0041 | 0.0006 | 54 | |
|
| 0.0056 | 0.0012 | 55 | |
|
| 0.0035 | 0.0016 | 56 | |
|
| 0.0042 | 0.0011 | 57 | |
|
| 0.0029 | 0.0006 | 58 | |
|
| 0.0025 | 0.0004 | 59 | |
|
| 0.0229 | 0.0085 | 60 | |
|
| 0.0057 | 0.0075 | 61 | |
|
| 0.0038 | 0.0050 | 62 | |
|
| 0.0047 | 0.0014 | 63 | |
|
| 0.0024 | 0.0006 | 64 | |
|
| 0.0021 | 0.0005 | 65 | |
|
| 0.0480 | 0.0008 | 66 | |
|
| 0.0041 | 0.0010 | 67 | |
|
| 0.0038 | 0.0010 | 68 | |
|
| 0.0032 | 0.0010 | 69 | |
|
| 0.0037 | 0.0009 | 70 | |
|
| 0.0027 | 0.0007 | 71 | |
|
| 0.0041 | 0.0007 | 72 | |
|
| 0.0039 | 0.0006 | 73 | |
|
| 0.0024 | 0.0007 | 74 | |
|
| 0.0020 | 0.0007 | 75 | |
|
| 0.0026 | 0.0007 | 76 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.46.2 |
|
- TensorFlow 2.17.0 |
|
- Datasets 3.1.0 |
|
- Tokenizers 0.20.3 |
|
|
