metadata
license: mit
tags:
- generated_from_trainer
base_model: BAAI/bge-m3-retromae
metrics:
- accuracy
model-index:
- name: bge-m3-retromae-zeroshot-v2.0-2024-04-02-09-26
results: []
bge-m3-retromae-zeroshot-v2.0-2024-04-02-09-26
This model is a fine-tuned version of BAAI/bge-m3-retromae on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1873
- F1 Macro: 0.6439
- F1 Micro: 0.7032
- Accuracy Balanced: 0.6808
- Accuracy: 0.7032
- Precision Macro: 0.6635
- Recall Macro: 0.6808
- Precision Micro: 0.7032
- Recall Micro: 0.7032
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 |
---|---|---|---|---|---|---|---|---|---|---|---|
0.2461 | 1.0 | 33914 | 0.3735 | 0.8313 | 0.8456 | 0.8329 | 0.8456 | 0.8298 | 0.8329 | 0.8456 | 0.8456 |
0.1947 | 2.0 | 67828 | 0.3949 | 0.8370 | 0.8515 | 0.8371 | 0.8515 | 0.8370 | 0.8371 | 0.8515 | 0.8515 |
Framework versions
- Transformers 4.37.2
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2