|
--- |
|
license: mit |
|
base_model: prajjwal1/bert-tiny |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- f1 |
|
model-index: |
|
- name: MM05 |
|
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. --> |
|
|
|
# MM05 |
|
|
|
This model is a fine-tuned version of [prajjwal1/bert-tiny](https://huggingface.co/prajjwal1/bert-tiny) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.3184 |
|
- Accuracy: 0.99 |
|
- F1: 0.9950 |
|
|
|
## 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: 3e-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: 7 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | F1 | |
|
|:-------------:|:-----:|:----:|:---------------:|:--------:|:------:| |
|
| No log | 0.0 | 50 | 0.6884 | 0.58 | 0.4258 | |
|
| No log | 0.01 | 100 | 0.6988 | 0.42 | 0.2485 | |
|
| No log | 0.01 | 150 | 0.6952 | 0.42 | 0.2485 | |
|
| No log | 0.02 | 200 | 0.6886 | 0.58 | 0.4258 | |
|
| No log | 0.02 | 250 | 0.6889 | 0.59 | 0.4481 | |
|
| No log | 0.02 | 300 | 0.6920 | 0.59 | 0.5916 | |
|
| No log | 0.03 | 350 | 0.6917 | 0.57 | 0.5535 | |
|
| No log | 0.03 | 400 | 0.6947 | 0.45 | 0.3250 | |
|
| No log | 0.04 | 450 | 0.6541 | 0.69 | 0.6866 | |
|
| 0.6877 | 0.04 | 500 | 0.6117 | 0.7 | 0.6829 | |
|
| 0.6877 | 0.04 | 550 | 0.5938 | 0.71 | 0.7030 | |
|
| 0.6877 | 0.05 | 600 | 0.5851 | 0.74 | 0.7390 | |
|
| 0.6877 | 0.05 | 650 | 0.5721 | 0.77 | 0.7645 | |
|
| 0.6877 | 0.06 | 700 | 0.5612 | 0.77 | 0.7704 | |
|
| 0.6877 | 0.06 | 750 | 0.5368 | 0.76 | 0.7612 | |
|
| 0.6877 | 0.06 | 800 | 0.5013 | 0.77 | 0.7696 | |
|
| 0.6877 | 0.07 | 850 | 0.4831 | 0.78 | 0.7792 | |
|
| 0.6877 | 0.07 | 900 | 0.4831 | 0.78 | 0.7792 | |
|
| 0.6877 | 0.08 | 950 | 0.4573 | 0.8 | 0.7886 | |
|
| 0.5813 | 0.08 | 1000 | 0.4576 | 0.79 | 0.7792 | |
|
| 0.5813 | 0.08 | 1050 | 0.4483 | 0.81 | 0.7956 | |
|
| 0.5813 | 0.09 | 1100 | 0.4377 | 0.8 | 0.7886 | |
|
| 0.5813 | 0.09 | 1150 | 0.4297 | 0.81 | 0.7956 | |
|
| 0.5813 | 0.1 | 1200 | 0.4287 | 0.81 | 0.7956 | |
|
| 0.5813 | 0.1 | 1250 | 0.4301 | 0.81 | 0.7956 | |
|
| 0.5813 | 0.1 | 1300 | 0.4286 | 0.81 | 0.7956 | |
|
| 0.5813 | 0.11 | 1350 | 0.4193 | 0.81 | 0.7956 | |
|
| 0.5813 | 0.11 | 1400 | 0.4088 | 0.81 | 0.7956 | |
|
| 0.5813 | 0.12 | 1450 | 0.4107 | 0.81 | 0.7956 | |
|
| 0.4699 | 0.12 | 1500 | 0.4016 | 0.81 | 0.7956 | |
|
| 0.4699 | 0.12 | 1550 | 0.4056 | 0.81 | 0.7956 | |
|
| 0.4699 | 0.13 | 1600 | 0.4095 | 0.81 | 0.7956 | |
|
| 0.4699 | 0.13 | 1650 | 0.3973 | 0.81 | 0.7956 | |
|
| 0.4699 | 0.14 | 1700 | 0.3907 | 0.81 | 0.7956 | |
|
| 0.4699 | 0.14 | 1750 | 0.3907 | 0.81 | 0.7956 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.35.2 |
|
- Pytorch 2.1.0+cu121 |
|
- Datasets 2.16.0 |
|
- Tokenizers 0.15.0 |
|
|
