|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert_base_uncased_amazon |
|
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. --> |
|
|
|
# bert_base_uncased_amazon |
|
|
|
This model is a fine-tuned version of [google-bert/bert-base-uncased](https://huggingface.co/google-bert/bert-base-uncased) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.7916 |
|
- Accuracy: 0.7879 |
|
- F1 Macro: 0.7308 |
|
- F1 Micro: 0.7879 |
|
|
|
## 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: 32 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- distributed_type: multi-GPU |
|
- num_devices: 2 |
|
- total_train_batch_size: 64 |
|
- total_eval_batch_size: 64 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 Macro | F1 Micro | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 2.5476 | 0.26 | 50 | 2.4071 | 0.4967 | 0.3546 | 0.4967 | |
|
| 1.7401 | 0.53 | 100 | 1.6470 | 0.6337 | 0.4899 | 0.6337 | |
|
| 1.3223 | 0.79 | 150 | 1.2889 | 0.6897 | 0.5665 | 0.6897 | |
|
| 1.1317 | 1.05 | 200 | 1.1047 | 0.7358 | 0.6577 | 0.7358 | |
|
| 0.9137 | 1.32 | 250 | 0.9907 | 0.7536 | 0.6820 | 0.7536 | |
|
| 0.9434 | 1.58 | 300 | 0.9264 | 0.7602 | 0.6896 | 0.7602 | |
|
| 0.86 | 1.84 | 350 | 0.8729 | 0.7780 | 0.7135 | 0.7780 | |
|
| 0.7567 | 2.11 | 400 | 0.8322 | 0.7859 | 0.7244 | 0.7859 | |
|
| 0.7028 | 2.37 | 450 | 0.8130 | 0.7892 | 0.7339 | 0.7892 | |
|
| 0.6842 | 2.63 | 500 | 0.8005 | 0.7892 | 0.7284 | 0.7892 | |
|
| 0.6784 | 2.89 | 550 | 0.7916 | 0.7879 | 0.7308 | 0.7879 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|