relatives_labels-cbert_finetuned

This model is a fine-tuned version of camembert/camembert-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.6900
  • Accuracy: 0.5859
  • Precision: 0.7929
  • Recall: 0.5
  • F1: 0.3694

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
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1
No log 1.0 49 0.7593 0.5859 0.5447 0.5071 0.4105
No log 2.0 98 0.7108 0.5859 0.7929 0.5 0.3694
No log 3.0 147 0.6904 0.5859 0.7929 0.5 0.3694
No log 4.0 196 0.6891 0.5859 0.7929 0.5 0.3694
No log 5.0 245 0.6900 0.5859 0.7929 0.5 0.3694

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
15
Safetensors
Model size
337M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for djamina/relatives_labels-cbert_finetuned

Finetuned
(10)
this model