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: 0.4068
- F1 Macro: 0.8879
- F1: 0.9207
- F1 Neg: 0.8551
- Acc: 0.8975
- Prec: 0.9119
- Recall: 0.9297
- Mcc: 0.7761
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: 2e-05
- 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: 3
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 | F1 Neg | Acc | Prec | Recall | Mcc |
|---|---|---|---|---|---|---|---|---|---|---|
| No log | 1.0 | 455 | 0.3953 | 0.8401 | 0.8681 | 0.8121 | 0.845 | 0.9533 | 0.7969 | 0.7001 |
| 0.4578 | 2.0 | 910 | 0.3415 | 0.8924 | 0.9209 | 0.8639 | 0.9 | 0.932 | 0.9102 | 0.7854 |
| 0.2713 | 3.0 | 1365 | 0.4068 | 0.8879 | 0.9207 | 0.8551 | 0.8975 | 0.9119 | 0.9297 | 0.7761 |
Framework versions
- Transformers 4.38.2
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2