metadata
base_model: google-bert/bert-base-uncased
datasets:
- wnut_17
library_name: peft
license: apache-2.0
metrics:
- precision
- recall
- f1
- accuracy
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: bert-base-uncased-wnut_17
results: []
bert-base-uncased-wnut_17
This model is a fine-tuned version of google-bert/bert-base-uncased on the wnut_17 dataset. It achieves the following results on the evaluation set:
- Loss: 0.2870
- Precision: 0.4802
- Recall: 0.2132
- F1: 0.2953
- Accuracy: 0.9366
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: 5e-05
- train_batch_size: 16
- eval_batch_size: 16
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 10
Training results
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|---|---|---|---|---|---|---|---|
| No log | 1.0 | 213 | 0.4305 | 1.0 | 0.0 | 0.0 | 0.9256 |
| No log | 2.0 | 426 | 0.3568 | 0.0 | 0.0 | 0.0 | 0.9256 |
| 0.496 | 3.0 | 639 | 0.3379 | 0.3495 | 0.0334 | 0.0609 | 0.9277 |
| 0.496 | 4.0 | 852 | 0.3166 | 0.3824 | 0.1205 | 0.1832 | 0.9321 |
| 0.1935 | 5.0 | 1065 | 0.3034 | 0.3907 | 0.1705 | 0.2374 | 0.9343 |
| 0.1935 | 6.0 | 1278 | 0.2956 | 0.4313 | 0.1863 | 0.2602 | 0.9353 |
| 0.1935 | 7.0 | 1491 | 0.2941 | 0.4700 | 0.1891 | 0.2697 | 0.9357 |
| 0.1717 | 8.0 | 1704 | 0.2960 | 0.4874 | 0.1965 | 0.2801 | 0.9363 |
| 0.1717 | 9.0 | 1917 | 0.2882 | 0.4797 | 0.2076 | 0.2898 | 0.9364 |
| 0.1594 | 10.0 | 2130 | 0.2870 | 0.4802 | 0.2132 | 0.2953 | 0.9366 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1