Hugging Face's logo

adriansanz
/
te-zsc-synthetic

Text Classification
Transformers
TensorBoard
Safetensors
roberta
Generated from Trainer
Inference Endpoints
Model card Files Metrics Community
te-zsc-synthetic / README.md
adriansanz's picture
adriansanz
End of training
3147d3d verified
preview code
|
raw
history blame
3.51 kB
metadata
license: apache-2.0
base_model: projecte-aina/roberta-base-ca-v2-cased-te
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: SYN_300524_epoch_1
    results: []

SYN_300524_epoch_1

This model is a fine-tuned version of projecte-aina/roberta-base-ca-v2-cased-te on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3748
  • Accuracy: 0.961
  • Precision: 0.9615
  • Recall: 0.961
  • F1: 0.9610
  • Ratio: 0.483

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: 16
  • eval_batch_size: 16
  • seed: 47
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.06
  • lr_scheduler_warmup_steps: 4
  • num_epochs: 1
  • label_smoothing_factor: 0.1

Training results

Training Loss Epoch Step Validation Loss Accuracy Precision Recall F1 Ratio
2.9367 0.0533 10 1.4668 0.65 0.7117 0.65 0.6225 0.77
1.1009 0.1067 20 0.6674 0.856 0.8560 0.856 0.8560 0.502
0.6993 0.16 30 0.5583 0.908 0.9095 0.9080 0.9079 0.53
0.6377 0.2133 40 0.4923 0.934 0.9343 0.9340 0.9340 0.486
0.5192 0.2667 50 0.4930 0.926 0.9282 0.9260 0.9259 0.464
0.5189 0.32 60 0.4687 0.937 0.9383 0.937 0.9370 0.527
0.5083 0.3733 70 0.4321 0.944 0.9445 0.944 0.9440 0.484
0.4645 0.4267 80 0.4026 0.949 0.9490 0.949 0.9490 0.495
0.4268 0.48 90 0.3990 0.949 0.9498 0.9490 0.9490 0.479
0.4327 0.5333 100 0.3949 0.952 0.9524 0.952 0.9520 0.486
0.4283 0.5867 110 0.3894 0.954 0.9540 0.954 0.9540 0.496
0.4263 0.64 120 0.3829 0.957 0.9572 0.957 0.9570 0.489
0.4205 0.6933 130 0.3800 0.962 0.9620 0.962 0.9620 0.496
0.4291 0.7467 140 0.3760 0.962 0.9620 0.962 0.9620 0.502
0.4124 0.8 150 0.3723 0.964 0.9641 0.964 0.9640 0.494
0.4142 0.8533 160 0.3720 0.964 0.9641 0.964 0.9640 0.492
0.4209 0.9067 170 0.3767 0.96 0.9605 0.96 0.9600 0.484
0.3908 0.96 180 0.3748 0.96 0.9605 0.96 0.9600 0.484

Framework versions

  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1