metadata
license: apache-2.0
base_model: bert-base-uncased
tags:
- generated_from_trainer
metrics:
- f1
model-index:
- name: boss-sentiment-6000-bert-base-uncased
results: []
boss-sentiment-6000-bert-base-uncased
This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:
- F1: 0.6808
- Acc: 0.8249
- Loss: 1.1523
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: 16
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 20
Training results
| Training Loss | Epoch | Step | F1 | Acc | Validation Loss |
|---|---|---|---|---|---|
| No log | 1.0 | 375 | 0.6519 | 0.8092 | 0.5142 |
| 0.8417 | 2.0 | 750 | 0.6644 | 0.8447 | 0.4261 |
| 0.4234 | 3.0 | 1125 | 0.7150 | 0.8582 | 0.4002 |
| 0.234 | 4.0 | 1500 | 0.7360 | 0.8883 | 0.4355 |
| 0.234 | 5.0 | 1875 | 0.7408 | 0.8848 | 0.5524 |
| 0.1203 | 6.0 | 2250 | 0.7118 | 0.8484 | 0.8452 |
| 0.0738 | 7.0 | 2625 | 0.7201 | 0.8680 | 0.8452 |
| 0.0416 | 8.0 | 3000 | 0.6808 | 0.8249 | 1.1523 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.0+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1