howanching-clara's picture
Upload tokenizer
a3d50ae verified
|
raw
history blame
3.5 kB
metadata
tags:
  - generated_from_trainer
base_model: sentence-transformers/multi-qa-MiniLM-L6-cos-v1
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: all_keywords_multi-qa-MiniLM-L6-cos-v1_another
    results: []

all_keywords_multi-qa-MiniLM-L6-cos-v1_another

This model is a fine-tuned version of sentence-transformers/multi-qa-MiniLM-L6-cos-v1 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.6836
  • Accuracy: 0.5091
  • Precision: 0.5091
  • Recall: 0.5091
  • F1: 0.5091

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
2.3001 1.0 712 1.9740 0.4306 0.4306 0.4306 0.4306
2.0028 2.0 1424 1.9084 0.4418 0.4418 0.4418 0.4418
1.7335 3.0 2136 1.8073 0.4642 0.4642 0.4642 0.4642
1.6116 4.0 2848 1.8696 0.4853 0.4853 0.4853 0.4853
1.2663 5.0 3560 1.8992 0.4783 0.4783 0.4783 0.4783
1.0998 6.0 4272 2.0148 0.4923 0.4923 0.4923 0.4923
1.0126 7.0 4984 2.3935 0.4684 0.4684 0.4684 0.4684
0.7917 8.0 5696 2.5295 0.5035 0.5035 0.5035 0.5035
0.7038 9.0 6408 2.9043 0.4909 0.4909 0.4909 0.4909
0.601 10.0 7120 2.9520 0.5021 0.5021 0.5021 0.5021
0.5927 11.0 7832 3.0934 0.5175 0.5175 0.5175 0.5175
0.5112 12.0 8544 3.2217 0.5021 0.5021 0.5021 0.5021
0.4325 13.0 9256 3.3412 0.5119 0.5119 0.5119 0.5119
0.4005 14.0 9968 3.4485 0.5161 0.5161 0.5161 0.5161
0.3646 15.0 10680 3.6021 0.4825 0.4825 0.4825 0.4825
0.3385 16.0 11392 3.4522 0.5203 0.5203 0.5203 0.5203
0.316 17.0 12104 3.5701 0.5175 0.5175 0.5175 0.5175
0.266 18.0 12816 3.6202 0.5063 0.5063 0.5063 0.5063
0.2518 19.0 13528 3.6250 0.5175 0.5175 0.5175 0.5175
0.254 20.0 14240 3.6836 0.5091 0.5091 0.5091 0.5091

Framework versions

  • Transformers 4.39.3
  • Pytorch 2.2.1+cu118
  • Datasets 2.14.7
  • Tokenizers 0.15.2