|
|
--- |
|
|
tags: |
|
|
- generated_from_trainer |
|
|
metrics: |
|
|
- accuracy |
|
|
model-index: |
|
|
- name: mamba_text_classification |
|
|
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. --> |
|
|
|
|
|
# mamba_text_classification |
|
|
|
|
|
This model was trained from scratch on an unknown dataset. |
|
|
It achieves the following results on the evaluation set: |
|
|
- Loss: 0.3710 |
|
|
- Accuracy: 0.8993 |
|
|
|
|
|
## 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: 5e-05 |
|
|
- train_batch_size: 4 |
|
|
- eval_batch_size: 16 |
|
|
- seed: 42 |
|
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
|
- lr_scheduler_type: cosine |
|
|
- lr_scheduler_warmup_ratio: 0.01 |
|
|
- num_epochs: 1 |
|
|
|
|
|
### Training results |
|
|
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Accuracy | |
|
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:| |
|
|
| 0.0072 | 0.1 | 1487 | 0.4826 | 0.8833 | |
|
|
| 0.9742 | 0.2 | 2974 | 0.4212 | 0.8689 | |
|
|
| 1.9626 | 0.3 | 4461 | 0.4013 | 0.8949 | |
|
|
| 0.0048 | 0.4 | 5948 | 0.4107 | 0.8954 | |
|
|
| 0.9199 | 0.5 | 7435 | 0.3877 | 0.8938 | |
|
|
| 1.3472 | 0.6 | 8922 | 0.4172 | 0.8949 | |
|
|
| 0.1115 | 0.7 | 10409 | 0.3733 | 0.8971 | |
|
|
| 0.1208 | 0.8 | 11896 | 0.3935 | 0.8998 | |
|
|
| 0.0072 | 0.9 | 13383 | 0.3710 | 0.8993 | |
|
|
|
|
|
|
|
|
### Framework versions |
|
|
|
|
|
- Transformers 4.37.2 |
|
|
- Pytorch 2.1.0+cu121 |
|
|
- Datasets 2.17.1 |
|
|
- Tokenizers 0.15.2 |
|
|
|
