|
--- |
|
license: mit |
|
tags: |
|
- generated_from_trainer |
|
base_model: BAAI/bge-m3-retromae |
|
metrics: |
|
- accuracy |
|
model-index: |
|
- name: bge-m3-retromae-zeroshot-v2.0-2024-04-01-10-20 |
|
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. --> |
|
|
|
# bge-m3-retromae-zeroshot-v2.0-2024-04-01-10-20 |
|
|
|
This model is a fine-tuned version of [BAAI/bge-m3-retromae](https://huggingface.co/BAAI/bge-m3-retromae) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.1287 |
|
- F1 Macro: 0.4725 |
|
- F1 Micro: 0.4848 |
|
- Accuracy Balanced: 0.5093 |
|
- Accuracy: 0.4848 |
|
- Precision Macro: 0.5943 |
|
- Recall Macro: 0.5093 |
|
- Precision Micro: 0.4848 |
|
- Recall Micro: 0.4848 |
|
|
|
## 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: 9e-06 |
|
- train_batch_size: 4 |
|
- eval_batch_size: 32 |
|
- seed: 42 |
|
- gradient_accumulation_steps: 8 |
|
- total_train_batch_size: 32 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- lr_scheduler_warmup_ratio: 0.06 |
|
- num_epochs: 2 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | F1 Macro | F1 Micro | Accuracy Balanced | Accuracy | Precision Macro | Recall Macro | Precision Micro | Recall Micro | |
|
|:-------------:|:-----:|:-----:|:---------------:|:--------:|:--------:|:-----------------:|:--------:|:---------------:|:------------:|:---------------:|:------------:| |
|
| 0.2548 | 1.0 | 20813 | 0.6014 | 0.7561 | 0.7717 | 0.7643 | 0.7717 | 0.7516 | 0.7643 | 0.7717 | 0.7717 | |
|
| 0.1972 | 2.0 | 41626 | 0.6154 | 0.7666 | 0.7827 | 0.7732 | 0.7827 | 0.7623 | 0.7732 | 0.7827 | 0.7827 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.37.2 |
|
- Pytorch 2.2.1+cu121 |
|
- Datasets 2.17.1 |
|
- Tokenizers 0.15.2 |
|
|
