|
--- |
|
license: apache-2.0 |
|
base_model: bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- f1 |
|
model-index: |
|
- name: boss-sentiment-1500-bert-base-uncased |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# boss-sentiment-1500-bert-base-uncased |
|
|
|
This model is a fine-tuned version of [bert-base-uncased](https://huggingface.co/bert-base-uncased) on the None dataset. |
|
It achieves the following results on the evaluation set: |
|
- F1: 0.6639 |
|
- Acc: 0.8128 |
|
- Loss: 0.9879 |
|
|
|
## 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 | 94 | 0.4638 | 0.6355 | 1.0296 | |
|
| No log | 2.0 | 188 | 0.6014 | 0.8005 | 0.5842 | |
|
| No log | 3.0 | 282 | 0.6925 | 0.8577 | 0.3928 | |
|
| No log | 4.0 | 376 | 0.6529 | 0.7895 | 0.6497 | |
|
| No log | 5.0 | 470 | 0.6965 | 0.8595 | 0.5122 | |
|
| 0.5499 | 6.0 | 564 | 0.6758 | 0.8256 | 0.7653 | |
|
| 0.5499 | 7.0 | 658 | 0.6720 | 0.8277 | 0.8562 | |
|
| 0.5499 | 8.0 | 752 | 0.6639 | 0.8128 | 0.9879 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.0 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.14.6 |
|
- Tokenizers 0.14.1 |
|
|
