metadata
license: apache-2.0
base_model: google-bert/bert-base-cased
tags:
- generated_from_trainer
metrics:
- f1
- recall
model-index:
- name: bert-base-cased
results: []
bert-base-cased
This model is a fine-tuned version of google-bert/bert-base-cased on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4627
- F1 Macro: 0.8506
- F1: 0.9044
- F1 Neg: 0.7969
- Acc: 0.87
- Prec: 0.8945
- Recall: 0.9145
- Mcc: 0.7018
- Millor Epoca: 7
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:
- learning_rate: 1e-06
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 7
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc | Millor Epoca |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.4818 | 1.0 | 1698 | 0.4294 | 0.8184 | 0.8810 | 0.7557 | 0.84 | 0.8810 | 0.8810 | 0.6368 | 1 |
| 0.396 | 2.0 | 3396 | 0.4083 | 0.8364 | 0.8986 | 0.7742 | 0.86 | 0.8763 | 0.9219 | 0.6755 | 2 |
| 0.3536 | 3.0 | 5094 | 0.4110 | 0.8455 | 0.9038 | 0.7871 | 0.8675 | 0.8830 | 0.9257 | 0.6933 | 3 |
| 0.3171 | 4.0 | 6792 | 0.4451 | 0.8408 | 0.9029 | 0.7787 | 0.865 | 0.8746 | 0.9331 | 0.6862 | 3 |
| 0.3195 | 5.0 | 8490 | 0.4440 | 0.8475 | 0.9028 | 0.7922 | 0.8675 | 0.8913 | 0.9145 | 0.6956 | 5 |
| 0.2994 | 6.0 | 10188 | 0.4627 | 0.8403 | 0.8998 | 0.7809 | 0.8625 | 0.8821 | 0.9182 | 0.6824 | 5 |
| 0.3216 | 7.0 | 11886 | 0.4627 | 0.8506 | 0.9044 | 0.7969 | 0.87 | 0.8945 | 0.9145 | 0.7018 | 7 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2