Edit model card

distilbert-base-uncased_3epoch10

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

  • Loss: 2.5208
  • Accuracy: 0.6988
  • F1: 0.3192
  • Precision: 0.4537
  • Recall: 0.2462
  • Precision Sarcastic: 0.4537
  • Recall Sarcastic: 0.2462
  • F1 Sarcastic: 0.3192

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: 16
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall Precision Sarcastic Recall Sarcastic F1 Sarcastic
No log 1.0 174 2.6411 0.7017 0.1481 0.4091 0.0905 0.4091 0.0905 0.1481
No log 2.0 348 2.0172 0.7104 0.3045 0.4889 0.2211 0.4889 0.2211 0.3045
0.0495 3.0 522 1.9688 0.6844 0.4097 0.4419 0.3819 0.4419 0.3819 0.4097
0.0495 4.0 696 2.1007 0.7075 0.2671 0.4744 0.1859 0.4744 0.1859 0.2671
0.0495 5.0 870 2.4142 0.7104 0.2744 0.4872 0.1910 0.4872 0.1910 0.2744
0.032 6.0 1044 2.3684 0.6931 0.4132 0.4573 0.3769 0.4573 0.3769 0.4132
0.032 7.0 1218 2.5365 0.7118 0.2754 0.4935 0.1910 0.4935 0.1910 0.2754
0.032 8.0 1392 2.5712 0.7046 0.2756 0.4643 0.1960 0.4643 0.1960 0.2756
0.0112 9.0 1566 2.4974 0.6960 0.3127 0.4444 0.2412 0.4444 0.2412 0.3127
0.0112 10.0 1740 2.5208 0.6988 0.3192 0.4537 0.2462 0.4537 0.2462 0.3192

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
67M 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 dianamihalache27/distilbert-base-uncased_3epoch10

Finetuned
(6713)
this model