Hugging Face's logo

gentilrenard
/
multi-e5-small_lmd-comments_v1

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
multi-e5-small_lmd-comments_v1 / README.md
gentilrenard's picture
gentilrenard
multi-e5-small_lmd-comments_v1
c2c3b95 verified
preview code
|
raw
history blame contribute delete
4.82 kB
metadata
license: mit
base_model: intfloat/multilingual-e5-small
tags:
  - generated_from_trainer
metrics:
  - f1
  - accuracy
model-index:
  - name: multi-e5-small_lmd-comments_v1
    results: []

multi-e5-small_lmd-comments_v1

This model is a fine-tuned version of intfloat/multilingual-e5-small on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.9808
  • F1: 0.7036
  • Accuracy: 0.7122

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: 2e-05
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 2

Training results

Training Loss Epoch Step Validation Loss F1 Accuracy
1.0969 0.04 100 1.0991 0.4109 0.4964
1.0764 0.08 200 1.0768 0.5217 0.5971
0.955 0.12 300 0.9313 0.5802 0.6691
0.8137 0.17 400 0.8927 0.5864 0.6475
0.7837 0.21 500 0.8711 0.6238 0.6475
0.7234 0.25 600 0.9953 0.5641 0.6475
0.6983 0.29 700 0.9111 0.6226 0.6475
0.6574 0.33 800 0.8557 0.6686 0.6835
0.6653 0.37 900 0.7925 0.7087 0.7122
0.6444 0.41 1000 0.8338 0.7056 0.7122
0.6155 0.46 1100 0.8339 0.7257 0.7338
0.5726 0.5 1200 0.8078 0.7140 0.7194
0.6279 0.54 1300 0.9534 0.6917 0.7050
0.6083 0.58 1400 0.9515 0.6914 0.7050
0.5525 0.62 1500 0.9281 0.6846 0.7050
0.6849 0.66 1600 0.8352 0.6917 0.7050
0.5924 0.7 1700 1.0702 0.6602 0.6906
0.5614 0.75 1800 0.9689 0.6801 0.6978
0.5936 0.79 1900 1.0179 0.6896 0.7050
0.5582 0.83 2000 0.8858 0.7320 0.7410
0.5479 0.87 2100 0.9373 0.7030 0.7122
0.6278 0.91 2200 0.8694 0.6858 0.6978
0.4819 0.95 2300 0.9440 0.7074 0.7194
0.5425 0.99 2400 1.0661 0.6765 0.6906
0.5804 1.04 2500 0.8904 0.7189 0.7266
0.5025 1.08 2600 1.0105 0.6886 0.7050
0.5148 1.12 2700 0.9934 0.7076 0.7194
0.5359 1.16 2800 0.9249 0.7291 0.7410
0.5002 1.2 2900 0.7503 0.7047 0.7050
0.4563 1.24 3000 0.8149 0.7230 0.7266
0.4837 1.28 3100 0.8956 0.7125 0.7194
0.4486 1.33 3200 0.9013 0.7110 0.7194
0.4721 1.37 3300 1.0545 0.7142 0.7266
0.5482 1.41 3400 1.0139 0.7014 0.7122
0.4488 1.45 3500 0.9427 0.7162 0.7266
0.4859 1.49 3600 1.1337 0.7074 0.7194
0.504 1.53 3700 1.0299 0.7178 0.7266
0.4555 1.57 3800 0.8830 0.7273 0.7338
0.502 1.62 3900 1.0340 0.7142 0.7266
0.5131 1.66 4000 1.0997 0.7031 0.7194
0.5208 1.7 4100 1.0845 0.7025 0.7194
0.4329 1.74 4200 1.0553 0.7132 0.7266
0.4612 1.78 4300 1.0458 0.7074 0.7194
0.4857 1.82 4400 0.9425 0.7120 0.7194
0.4986 1.86 4500 0.9965 0.7237 0.7338
0.4066 1.91 4600 0.9520 0.7041 0.7122
0.4638 1.95 4700 0.9558 0.6979 0.7050
0.4541 1.99 4800 0.9808 0.7036 0.7122

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.2
  • Datasets 2.1.0
  • Tokenizers 0.15.2