|
--- |
|
license: bigscience-bloom-rail-1.0 |
|
base_model: bigscience/bloomz-560m |
|
tags: |
|
- generated_from_trainer |
|
metrics: |
|
- accuracy |
|
- precision |
|
- recall |
|
model-index: |
|
- name: BLOOM-Meta4Types-ft-ES |
|
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. --> |
|
|
|
# BLOOM-Meta4Types-ft-ES |
|
|
|
This model is a fine-tuned version of [bigscience/bloomz-560m](https://huggingface.co/bigscience/bloomz-560m) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 1.6658 |
|
- Roc Auc: 0.6521 |
|
- Hamming Loss: 0.2255 |
|
- F1 Score: 0.5792 |
|
- Accuracy: 0.5098 |
|
- Precision: 0.5611 |
|
- Recall: 0.6085 |
|
|
|
## 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: 4 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_steps: 500 |
|
- num_epochs: 10 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | Roc Auc | Hamming Loss | F1 Score | Accuracy | Precision | Recall | |
|
|:-------------:|:-----:|:----:|:---------------:|:-------:|:------------:|:--------:|:--------:|:---------:|:------:| |
|
| No log | 1.0 | 204 | 1.4085 | 0.5227 | 0.3775 | 0.0874 | 0.0490 | 0.9333 | 0.0500 | |
|
| No log | 2.0 | 408 | 1.3092 | 0.5569 | 0.4036 | 0.3425 | 0.2353 | 0.7464 | 0.4360 | |
|
| 1.9965 | 3.0 | 612 | 1.2200 | 0.5497 | 0.2304 | 0.4634 | 0.4510 | 0.7327 | 0.5574 | |
|
| 1.9965 | 4.0 | 816 | 1.4996 | 0.5843 | 0.3235 | 0.3965 | 0.3922 | 0.4177 | 0.4519 | |
|
| 0.6193 | 5.0 | 1020 | 1.0759 | 0.5823 | 0.2271 | 0.4488 | 0.5098 | 0.6180 | 0.4070 | |
|
| 0.6193 | 6.0 | 1224 | 1.8243 | 0.5808 | 0.2614 | 0.4892 | 0.3775 | 0.5688 | 0.5824 | |
|
| 0.6193 | 7.0 | 1428 | 1.6658 | 0.6521 | 0.2255 | 0.5792 | 0.5098 | 0.5611 | 0.6085 | |
|
| 0.202 | 8.0 | 1632 | 2.0491 | 0.5856 | 0.2075 | 0.4864 | 0.5441 | 0.5844 | 0.4447 | |
|
| 0.202 | 9.0 | 1836 | 2.2174 | 0.6241 | 0.1944 | 0.5733 | 0.5588 | 0.6183 | 0.5504 | |
|
| 0.0338 | 10.0 | 2040 | 2.1754 | 0.6265 | 0.1993 | 0.5693 | 0.5539 | 0.6197 | 0.5399 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.43.3 |
|
- Pytorch 2.3.1+cu121 |
|
- Datasets 2.20.0 |
|
- Tokenizers 0.19.1 |
|
|
