Hugging Face's logo

oumaymaMb
/
Bert_Text_Classification_v4

Text Classification
Transformers
Safetensors
bert
Generated from Trainer
Inference Endpoints
Model card Files Community
Bert_Text_Classification_v4 / README.md
oumaymaMb's picture
oumaymaMb
End of training
2e4fb41 verified
preview code
|
raw
history blame contribute delete
9.05 kB
metadata
license: apache-2.0
base_model: bert-base-multilingual-uncased
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: Bert_Text_Classification_v4
    results: []

Bert_Text_Classification_v4

This model is a fine-tuned version of bert-base-multilingual-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0376
  • Accuracy: 0.9964
  • F1: 0.9963
  • Precision: 0.9963
  • Recall: 0.9963

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: 16
  • eval_batch_size: 32
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 30

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
0.0043 0.36 50 0.0399 0.9955 0.9953 0.9954 0.9951
0.0001 0.72 100 0.0226 0.9964 0.9961 0.9962 0.9961
0.0193 1.09 150 0.0668 0.9900 0.9893 0.9905 0.9884
0.0555 1.45 200 0.0504 0.9927 0.9927 0.9934 0.9922
0.0465 1.81 250 0.0017 0.9991 0.9990 0.9990 0.9991
0.048 2.17 300 0.0348 0.9936 0.9934 0.9937 0.9932
0.0513 2.54 350 0.0699 0.9873 0.9870 0.9878 0.9865
0.0213 2.9 400 0.0495 0.9927 0.9926 0.9925 0.9928
0.0427 3.26 450 0.0587 0.9936 0.9933 0.9939 0.9928
0.0097 3.62 500 0.0236 0.9964 0.9961 0.9963 0.9959
0.0001 3.99 550 0.0279 0.9964 0.9962 0.9964 0.9959
0.0001 4.35 600 0.0259 0.9973 0.9972 0.9975 0.9968
0.0 4.71 650 0.0260 0.9973 0.9972 0.9975 0.9968
0.0091 5.07 700 0.0216 0.9964 0.9962 0.9964 0.9959
0.0014 5.43 750 0.0268 0.9973 0.9972 0.9971 0.9972
0.0 5.8 800 0.0383 0.9955 0.9952 0.9957 0.9947
0.0 6.16 850 0.0362 0.9964 0.9962 0.9966 0.9958
0.0003 6.52 900 0.0956 0.9909 0.9904 0.9900 0.9910
0.0247 6.88 950 0.0285 0.9973 0.9972 0.9975 0.9968
0.0003 7.25 1000 0.0333 0.9964 0.9962 0.9967 0.9958
0.0001 7.61 1050 0.0334 0.9964 0.9962 0.9967 0.9958
0.0003 7.97 1100 0.0285 0.9973 0.9972 0.9971 0.9972
0.0001 8.33 1150 0.0294 0.9964 0.9962 0.9962 0.9962
0.0 8.7 1200 0.0298 0.9964 0.9962 0.9962 0.9962
0.0045 9.06 1250 0.0376 0.9955 0.9953 0.9954 0.9951
0.0004 9.42 1300 0.0450 0.9946 0.9943 0.9943 0.9942
0.0322 9.78 1350 0.0492 0.9936 0.9932 0.9939 0.9926
0.003 10.14 1400 0.0110 0.9991 0.9991 0.9992 0.9989
0.0001 10.51 1450 0.0112 0.9991 0.9991 0.9992 0.9989
0.0001 10.87 1500 0.0124 0.9982 0.9981 0.9981 0.9980
0.0 11.23 1550 0.0112 0.9982 0.9981 0.9981 0.9980
0.0 11.59 1600 0.0111 0.9991 0.9991 0.9992 0.9989
0.0 11.96 1650 0.0110 0.9991 0.9991 0.9992 0.9989
0.0 12.32 1700 0.0110 0.9991 0.9991 0.9992 0.9989
0.0 12.68 1750 0.0109 0.9991 0.9991 0.9992 0.9989
0.0 13.04 1800 0.0109 0.9991 0.9990 0.9991 0.9989
0.0 13.41 1850 0.0109 0.9991 0.9990 0.9991 0.9989
0.0 13.77 1900 0.0109 0.9991 0.9990 0.9991 0.9989
0.0 14.13 1950 0.0109 0.9991 0.9990 0.9991 0.9989
0.0 14.49 2000 0.0109 0.9991 0.9990 0.9991 0.9989
0.0 14.86 2050 0.0109 0.9991 0.9990 0.9991 0.9989
0.0 15.22 2100 0.0109 0.9991 0.9990 0.9991 0.9989
0.0 15.58 2150 0.0110 0.9991 0.9990 0.9991 0.9989
0.0 15.94 2200 0.0110 0.9991 0.9990 0.9991 0.9989
0.0 16.3 2250 0.0110 0.9991 0.9990 0.9991 0.9989
0.0 16.67 2300 0.0111 0.9991 0.9990 0.9991 0.9989
0.0 17.03 2350 0.0111 0.9991 0.9990 0.9991 0.9989
0.0 17.39 2400 0.0111 0.9991 0.9990 0.9991 0.9989
0.0 17.75 2450 0.0112 0.9991 0.9990 0.9991 0.9989
0.0 18.12 2500 0.0112 0.9991 0.9990 0.9991 0.9989
0.0 18.48 2550 0.0112 0.9991 0.9990 0.9991 0.9989
0.0099 18.84 2600 0.0175 0.9973 0.9973 0.9973 0.9973
0.0 19.2 2650 0.0133 0.9982 0.9981 0.9983 0.9979
0.0 19.57 2700 0.0135 0.9982 0.9981 0.9983 0.9979
0.0 19.93 2750 0.0135 0.9982 0.9981 0.9983 0.9979
0.0 20.29 2800 0.0135 0.9982 0.9981 0.9983 0.9979
0.0 20.65 2850 0.0132 0.9982 0.9981 0.9983 0.9979
0.0 21.01 2900 0.0133 0.9982 0.9981 0.9983 0.9979
0.0 21.38 2950 0.0133 0.9982 0.9981 0.9983 0.9979
0.0 21.74 3000 0.0124 0.9982 0.9981 0.9981 0.9980
0.0 22.1 3050 0.0125 0.9982 0.9981 0.9981 0.9980
0.0 22.46 3100 0.0125 0.9982 0.9981 0.9981 0.9980
0.0 22.83 3150 0.0125 0.9982 0.9981 0.9981 0.9980
0.0 23.19 3200 0.0125 0.9982 0.9981 0.9981 0.9980
0.0 23.55 3250 0.0126 0.9982 0.9981 0.9981 0.9980
0.0 23.91 3300 0.0126 0.9982 0.9981 0.9981 0.9980
0.0 24.28 3350 0.0126 0.9982 0.9981 0.9981 0.9980
0.0 24.64 3400 0.0126 0.9982 0.9981 0.9981 0.9980
0.0 25.0 3450 0.0126 0.9982 0.9981 0.9981 0.9980
0.0 25.36 3500 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 25.72 3550 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 26.09 3600 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 26.45 3650 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 26.81 3700 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 27.17 3750 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 27.54 3800 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 27.9 3850 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 28.26 3900 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 28.62 3950 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 28.99 4000 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 29.35 4050 0.0127 0.9982 0.9981 0.9981 0.9980
0.0 29.71 4100 0.0127 0.9982 0.9981 0.9981 0.9980

Framework versions

  • Transformers 4.37.2
  • Pytorch 2.3.0+cu121
  • Tokenizers 0.15.2