best_model / README.md
hoangthethief's picture
End of training
3a89068 verified
|
raw
history blame
2.2 kB
metadata
license: mit
base_model: BAAI/bge-small-en-v1.5
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: best_model
    results: []

best_model

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: 0.2144
  • Accuracy: 1.0

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: 64
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 15

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 14 1.5615 0.7826
No log 2.0 28 1.2408 0.8913
No log 3.0 42 0.9712 0.9130
No log 4.0 56 0.7769 0.9783
No log 5.0 70 0.6251 1.0
No log 6.0 84 0.5102 1.0
No log 7.0 98 0.4342 1.0
No log 8.0 112 0.3669 1.0
No log 9.0 126 0.3205 1.0
No log 10.0 140 0.2853 1.0
No log 11.0 154 0.2599 1.0
No log 12.0 168 0.2426 1.0
No log 13.0 182 0.2309 1.0
No log 14.0 196 0.2245 1.0
No log 15.0 210 0.2224 1.0

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.1+cu117
  • Tokenizers 0.15.0