Edit model card

fine_tuned_copa_sloberta

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

  • Loss: 0.6931
  • Accuracy: 0.48
  • F1: 0.4615

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: 0.003
  • 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
  • training_steps: 400

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
0.7241 1.0 50 0.6931 0.52 0.5188
0.7129 2.0 100 0.6931 0.42 0.4167
0.7115 3.0 150 0.6931 0.46 0.4547
0.7135 4.0 200 0.6931 0.54 0.5304
0.7109 5.0 250 0.6931 0.51 0.5013
0.7121 6.0 300 0.6931 0.5 0.4670
0.7224 7.0 350 0.6931 0.51 0.4982
0.7109 8.0 400 0.6931 0.48 0.4615

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
111M params
Tensor type
F32
·
Inference API
Inference API (serverless) does not yet support transformers models for this pipeline type.

Model tree for lenatr99/fine_tuned_copa_sloberta

Base model

EMBEDDIA/sloberta
Finetuned
(8)
this model