metadata
library_name: transformers
license: mit
base_model: BAAI/bge-small-en-v1.5
tags:
- generated_from_trainer
model-index:
- name: bge-small-en-v1.5-2024-12-06_21-55-53-quality-weight-0.1
results: []
bge-small-en-v1.5-2024-12-06_21-55-53-quality-weight-0.1
This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.0214
- Spearman: 0.9268
- Pearson: 0.9311
- Mse: 0.0214
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: 64
- eval_batch_size: 16
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 256
- optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss | Spearman | Pearson | Mse |
|---|---|---|---|---|---|---|
| 0.0325 | 0.3998 | 1055 | 0.0286 | 0.8985 | 0.9051 | 0.0286 |
| 0.0278 | 0.7997 | 2110 | 0.0255 | 0.9081 | 0.9158 | 0.0255 |
| 0.0238 | 1.1995 | 3165 | 0.0249 | 0.9123 | 0.9200 | 0.0249 |
| 0.0235 | 1.5994 | 4220 | 0.0224 | 0.9199 | 0.9262 | 0.0224 |
| 0.0211 | 1.9992 | 5275 | 0.0230 | 0.9212 | 0.9286 | 0.0230 |
| 0.0182 | 2.3991 | 6330 | 0.0222 | 0.9218 | 0.9299 | 0.0222 |
| 0.0172 | 2.7989 | 7385 | 0.0211 | 0.9240 | 0.9318 | 0.0211 |
| 0.0136 | 3.1988 | 8440 | 0.0212 | 0.9253 | 0.9312 | 0.0212 |
| 0.014 | 3.5986 | 9495 | 0.0210 | 0.9263 | 0.9326 | 0.0210 |
| 0.0144 | 3.9985 | 10550 | 0.0208 | 0.9264 | 0.9330 | 0.0208 |
| 0.0109 | 4.3983 | 11605 | 0.0210 | 0.9264 | 0.9329 | 0.0210 |
| 0.0123 | 4.7982 | 12660 | 0.0210 | 0.9267 | 0.9331 | 0.0210 |
Framework versions
- Transformers 4.46.3
- Pytorch 2.4.1+cu121
- Datasets 2.19.2
- Tokenizers 0.20.3