|
--- |
|
license: apache-2.0 |
|
base_model: google-bert/bert-base-uncased |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bert_base_uncased_ledgar |
|
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_ledgar |
|
|
|
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: 0.6676 |
|
- Accuracy: 0.8349 |
|
- F1 Macro: 0.7127 |
|
- F1 Micro: 0.8349 |
|
|
|
## 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 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:--------:|:--------:| |
|
| 3.6919 | 0.11 | 100 | 3.4439 | 0.4049 | 0.1512 | 0.4049 | |
|
| 2.7312 | 0.21 | 200 | 2.5762 | 0.5766 | 0.3025 | 0.5766 | |
|
| 2.1872 | 0.32 | 300 | 2.0346 | 0.656 | 0.3994 | 0.656 | |
|
| 1.7869 | 0.43 | 400 | 1.6759 | 0.7075 | 0.4796 | 0.7075 | |
|
| 1.5593 | 0.53 | 500 | 1.4354 | 0.7454 | 0.5447 | 0.7454 | |
|
| 1.388 | 0.64 | 600 | 1.2759 | 0.7695 | 0.5778 | 0.7695 | |
|
| 1.214 | 0.75 | 700 | 1.1428 | 0.7806 | 0.5891 | 0.7806 | |
|
| 1.158 | 0.85 | 800 | 1.0531 | 0.784 | 0.5955 | 0.784 | |
|
| 1.0284 | 0.96 | 900 | 0.9726 | 0.7944 | 0.6182 | 0.7944 | |
|
| 0.9249 | 1.07 | 1000 | 0.9276 | 0.8009 | 0.6295 | 0.8009 | |
|
| 0.9046 | 1.17 | 1100 | 0.8824 | 0.8058 | 0.6413 | 0.8058 | |
|
| 0.9312 | 1.28 | 1200 | 0.8425 | 0.8081 | 0.6450 | 0.8081 | |
|
| 0.8329 | 1.39 | 1300 | 0.8096 | 0.8135 | 0.6585 | 0.8135 | |
|
| 0.7601 | 1.49 | 1400 | 0.7946 | 0.8148 | 0.6646 | 0.8148 | |
|
| 0.7812 | 1.6 | 1500 | 0.7766 | 0.8192 | 0.6739 | 0.8192 | |
|
| 0.7944 | 1.71 | 1600 | 0.7585 | 0.8221 | 0.6800 | 0.8221 | |
|
| 0.7632 | 1.81 | 1700 | 0.7363 | 0.8269 | 0.6902 | 0.8269 | |
|
| 0.7027 | 1.92 | 1800 | 0.7229 | 0.8227 | 0.6793 | 0.8227 | |
|
| 0.671 | 2.03 | 1900 | 0.7145 | 0.8263 | 0.6870 | 0.8263 | |
|
| 0.6361 | 2.13 | 2000 | 0.7067 | 0.8277 | 0.6952 | 0.8277 | |
|
| 0.6615 | 2.24 | 2100 | 0.6969 | 0.8281 | 0.6974 | 0.8281 | |
|
| 0.6432 | 2.35 | 2200 | 0.6908 | 0.8311 | 0.7054 | 0.8311 | |
|
| 0.648 | 2.45 | 2300 | 0.6850 | 0.8304 | 0.7011 | 0.8304 | |
|
| 0.631 | 2.56 | 2400 | 0.6750 | 0.8323 | 0.7063 | 0.8323 | |
|
| 0.575 | 2.67 | 2500 | 0.6718 | 0.8337 | 0.7094 | 0.8337 | |
|
| 0.6444 | 2.77 | 2600 | 0.6701 | 0.8332 | 0.7102 | 0.8332 | |
|
| 0.6054 | 2.88 | 2700 | 0.6690 | 0.8346 | 0.7122 | 0.8346 | |
|
| 0.6123 | 2.99 | 2800 | 0.6676 | 0.8349 | 0.7127 | 0.8349 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.39.0.dev0 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.18.0 |
|
- Tokenizers 0.15.2 |
|
|