|
--- |
|
base_model: dccuchile/bert-base-spanish-wwm-uncased |
|
tags: |
|
- generated_from_keras_callback |
|
model-index: |
|
- name: lulygavri/sub1-trans |
|
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. --> |
|
|
|
# lulygavri/sub1-trans |
|
|
|
This model is a fine-tuned version of [dccuchile/bert-base-spanish-wwm-uncased](https://huggingface.co/dccuchile/bert-base-spanish-wwm-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Train Loss: 0.0428 |
|
- Validation Loss: 0.4923 |
|
- Train Accuracy: 0.9 |
|
- Train Precision: [0.90909091 0. ] |
|
- Train Precision W: 0.8273 |
|
- Train Recall: [0.98901099 0. ] |
|
- Train Recall W: 0.9 |
|
- Train F1: [0.94736842 0. ] |
|
- Train F1 W: 0.8621 |
|
- Epoch: 5 |
|
|
|
## 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': 'transformers.optimization_tf', 'class_name': 'WarmUp', 'config': {'initial_learning_rate': 2e-05, 'decay_schedule_fn': {'module': 'keras.optimizers.schedules', 'class_name': 'PolynomialDecay', 'config': {'initial_learning_rate': 2e-05, 'decay_steps': 34, 'end_learning_rate': 0.0, 'power': 1.0, 'cycle': False, 'name': None}, 'registered_name': None}, 'warmup_steps': 500, 'power': 1.0, 'name': None}, 'registered_name': 'WarmUp'}, 'beta_1': 0.9, 'beta_2': 0.999, 'epsilon': 1e-08, 'amsgrad': False} |
|
- training_precision: float32 |
|
|
|
### Training results |
|
|
|
| Train Loss | Validation Loss | Train Accuracy | Train Precision | Train Precision W | Train Recall | Train Recall W | Train F1 | Train F1 W | Epoch | |
|
|:----------:|:---------------:|:--------------:|:-----------------------:|:-----------------:|:-----------------------:|:--------------:|:-----------------------:|:----------:|:-----:| |
|
| 0.6479 | 0.4942 | 0.91 | [0.91 0. ] | 0.8281 | [1. 0.] | 0.91 | [0.95287958 0. ] | 0.8671 | 1 | |
|
| 0.4492 | 0.4305 | 0.8 | [0.9382716 0.21052632] | 0.8728 | [0.83516484 0.44444444] | 0.8 | [0.88372093 0.28571429] | 0.8299 | 2 | |
|
| 0.1358 | 0.3080 | 0.88 | [0.90721649 0. ] | 0.8256 | [0.96703297 0. ] | 0.88 | [0.93617021 0. ] | 0.8519 | 3 | |
|
| 0.0545 | 0.3801 | 0.9 | [0.90909091 0. ] | 0.8273 | [0.98901099 0. ] | 0.9 | [0.94736842 0. ] | 0.8621 | 4 | |
|
| 0.0428 | 0.4923 | 0.9 | [0.90909091 0. ] | 0.8273 | [0.98901099 0. ] | 0.9 | [0.94736842 0. ] | 0.8621 | 5 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.38.2 |
|
- TensorFlow 2.15.0 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|
