Hugging Face's logo

gutsartificial
/
bge-small-en-v1.5-quality-weight-0.9

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
bge-small-en-v1.5-quality-weight-0.9 / README.md
gutsartificial's picture
gutsartificial
bge-small-en-v1.5-2024-12-28_04-50-16
65390ee verified
preview code
|
raw
history blame
5.79 kB
metadata
library_name: transformers
license: mit
base_model: BAAI/bge-small-en-v1.5
tags:
  - generated_from_trainer
model-index:
  - name: bge-small-en-v1.5-2024-12-28_04-50-16-quality-weight-0.9
    results: []

bge-small-en-v1.5-2024-12-28_04-50-16-quality-weight-0.9

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: 0.0182
  • Spearman: 0.9303
  • Pearson: 0.9235
  • Mse: 0.0182

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
  • gradient_accumulation_steps: 64
  • 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
0.0303 0.0997 263 0.0333 0.8642 0.8534 0.0333
0.0311 0.1994 526 0.0328 0.8847 0.8687 0.0328
0.0362 0.2990 789 0.0263 0.8952 0.8847 0.0263
0.0217 0.3987 1052 0.0251 0.9014 0.8929 0.0251
0.0277 0.4984 1315 0.0258 0.9037 0.8950 0.0258
0.02 0.5981 1578 0.0241 0.9086 0.8990 0.0241
0.0244 0.6978 1841 0.0221 0.9103 0.9028 0.0221
0.021 0.7975 2104 0.0217 0.9132 0.9050 0.0217
0.0255 0.8971 2367 0.0212 0.9137 0.9075 0.0212
0.0193 0.9968 2630 0.0209 0.9162 0.9107 0.0209
0.017 1.0963 2893 0.0204 0.9185 0.9120 0.0204
0.0213 1.1960 3156 0.0211 0.9186 0.9134 0.0211
0.0143 1.2956 3419 0.0206 0.9210 0.9144 0.0206
0.0153 1.3953 3682 0.0201 0.9214 0.9155 0.0201
0.0188 1.4950 3945 0.0203 0.9221 0.9166 0.0203
0.0173 1.5947 4208 0.0199 0.9217 0.9174 0.0199
0.0163 1.6944 4471 0.0192 0.9233 0.9178 0.0192
0.0131 1.7940 4734 0.0200 0.9230 0.9176 0.0200
0.0201 1.8937 4997 0.0194 0.9230 0.9188 0.0194
0.0176 1.9934 5260 0.0197 0.9244 0.9200 0.0197
0.0111 2.0929 5523 0.0189 0.9245 0.9194 0.0189
0.0126 2.1925 5786 0.0190 0.9257 0.9208 0.0190
0.0152 2.2922 6049 0.0185 0.9261 0.9203 0.0185
0.016 2.3919 6312 0.0184 0.9252 0.9208 0.0184
0.0167 2.4916 6575 0.0186 0.9270 0.9217 0.0186
0.0164 2.5913 6838 0.0183 0.9268 0.9226 0.0183
0.0126 2.6910 7101 0.0182 0.9272 0.9229 0.0182
0.0141 2.7906 7364 0.0186 0.9270 0.9221 0.0186
0.0193 2.8903 7627 0.0185 0.9276 0.9234 0.0185
0.0106 2.9900 7890 0.0182 0.9285 0.9242 0.0182
0.0128 3.0894 8153 0.0182 0.9282 0.9242 0.0182
0.0149 3.1891 8416 0.0184 0.9288 0.9233 0.0184
0.0146 3.2888 8679 0.0177 0.9286 0.9244 0.0177
0.0164 3.3885 8942 0.0179 0.9286 0.9237 0.0179
0.0111 3.4882 9205 0.0181 0.9293 0.9246 0.0181
0.0097 3.5879 9468 0.0189 0.9293 0.9243 0.0189
0.0153 3.6875 9731 0.0176 0.9298 0.9252 0.0176
0.0096 3.7872 9994 0.0178 0.9296 0.9249 0.0178
0.0126 3.8869 10257 0.0175 0.9297 0.9253 0.0175
0.0122 3.9866 10520 0.0177 0.9300 0.9253 0.0177
0.0105 4.0860 10783 0.0180 0.9301 0.9253 0.0180
0.0092 4.1857 11046 0.0179 0.9301 0.9251 0.0179
0.0116 4.2854 11309 0.0177 0.9301 0.9250 0.0177
0.014 4.3851 11572 0.0180 0.9299 0.9252 0.0180
0.0094 4.4848 11835 0.0178 0.9301 0.9255 0.0178
0.0106 4.5845 12098 0.0179 0.9300 0.9253 0.0179
0.0092 4.6841 12361 0.0179 0.9301 0.9253 0.0179
0.0096 4.7838 12624 0.0179 0.9301 0.9253 0.0179
0.0105 4.8835 12887 0.0178 0.9301 0.9253 0.0178
0.0106 4.9832 13150 0.0178 0.9301 0.9253 0.0178

Framework versions

  • Transformers 4.47.0
  • Pytorch 2.5.1+cu124
  • Datasets 2.19.2
  • Tokenizers 0.21.0