Hugging Face's logo

AntoineD
/
camembert_ccnet_classification_tools_qlora_fr

Generated from Trainer
Model card Files Community
camembert_ccnet_classification_tools_qlora_fr / README.md
AntoineD's picture
AntoineD
End of training
c409a95
preview code
|
raw
history blame
No virus
4.66 kB
metadata
base_model: camembert/camembert-base-ccnet
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: camembert_ccnet_classification_tools_qlora_fr
    results: []

camembert_ccnet_classification_tools_qlora_fr

This model is a fine-tuned version of camembert/camembert-base-ccnet on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.4958
  • Accuracy: 0.45

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: 0.0001
  • train_batch_size: 24
  • eval_batch_size: 192
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 60

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 5 2.0916 0.075
No log 2.0 10 2.1165 0.075
No log 3.0 15 2.1285 0.075
No log 4.0 20 2.1210 0.075
No log 5.0 25 2.1182 0.125
No log 6.0 30 2.0984 0.125
No log 7.0 35 2.0764 0.15
No log 8.0 40 2.0390 0.2
No log 9.0 45 2.0085 0.2
No log 10.0 50 1.9749 0.175
No log 11.0 55 1.9474 0.15
No log 12.0 60 1.9271 0.225
No log 13.0 65 1.9089 0.225
No log 14.0 70 1.8945 0.225
No log 15.0 75 1.8847 0.2
No log 16.0 80 1.8638 0.25
No log 17.0 85 1.8387 0.3
No log 18.0 90 1.8156 0.275
No log 19.0 95 1.8003 0.3
No log 20.0 100 1.7827 0.275
No log 21.0 105 1.7688 0.3
No log 22.0 110 1.7467 0.275
No log 23.0 115 1.7255 0.275
No log 24.0 120 1.7132 0.325
No log 25.0 125 1.7007 0.35
No log 26.0 130 1.6881 0.35
No log 27.0 135 1.6801 0.35
No log 28.0 140 1.6642 0.375
No log 29.0 145 1.6450 0.325
No log 30.0 150 1.6425 0.35
No log 31.0 155 1.6305 0.375
No log 32.0 160 1.6193 0.4
No log 33.0 165 1.6128 0.4
No log 34.0 170 1.6027 0.4
No log 35.0 175 1.5915 0.425
No log 36.0 180 1.5837 0.45
No log 37.0 185 1.5721 0.45
No log 38.0 190 1.5605 0.425
No log 39.0 195 1.5555 0.425
No log 40.0 200 1.5521 0.425
No log 41.0 205 1.5480 0.425
No log 42.0 210 1.5399 0.45
No log 43.0 215 1.5276 0.45
No log 44.0 220 1.5282 0.45
No log 45.0 225 1.5197 0.45
No log 46.0 230 1.5175 0.45
No log 47.0 235 1.5065 0.45
No log 48.0 240 1.5043 0.45
No log 49.0 245 1.5019 0.45
No log 50.0 250 1.4975 0.45
No log 51.0 255 1.4949 0.45
No log 52.0 260 1.4969 0.45
No log 53.0 265 1.4958 0.45

Framework versions

  • Transformers 4.34.0
  • Pytorch 2.0.1+cu117
  • Datasets 2.14.5
  • Tokenizers 0.14.1