metadata

license: apache-2.0
base_model: distilbert-base-uncased
tags:
  - generated_from_trainer
datasets:
  - emotion
metrics:
  - accuracy
  - f1
model-index:
  - name: distilbert-base-uncased-finetuned-emotion
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: emotion
          type: emotion
          config: split
          split: train[:2000]
          args: split
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.89
          - name: F1
            type: f1
            value: 0.8909727258350819

distilbert-base-uncased-finetuned-emotion

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

Loss: 0.6248
Accuracy: 0.89
Balanced accuracy: 0.8764
F1: 0.8910

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: 64
eval_batch_size: 64
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Balanced accuracy	F1
0.0269	1.0	25	0.4880	0.905	0.8890	0.9058
0.0204	2.0	50	0.5177	0.89	0.8934	0.8896
0.009	3.0	75	0.4983	0.89	0.8787	0.8911
0.0089	4.0	100	0.5681	0.895	0.8724	0.8947
0.0048	5.0	125	0.5800	0.88	0.8662	0.8819
0.0023	6.0	150	0.5706	0.89	0.8959	0.8917
0.0035	7.0	175	0.6086	0.895	0.8760	0.8955
0.006	8.0	200	0.6522	0.88	0.9011	0.8811
0.0017	9.0	225	0.5806	0.89	0.8715	0.8907
0.0014	10.0	250	0.5809	0.885	0.9001	0.8868
0.0011	11.0	275	0.5942	0.885	0.8729	0.8864
0.001	12.0	300	0.5997	0.895	0.8826	0.8963
0.0009	13.0	325	0.6006	0.89	0.8791	0.8912
0.001	14.0	350	0.6135	0.885	0.9013	0.8857
0.0009	15.0	375	0.6199	0.885	0.8740	0.8858
0.0008	16.0	400	0.6257	0.885	0.8740	0.8858
0.0007	17.0	425	0.6254	0.885	0.8740	0.8858
0.0007	18.0	450	0.6273	0.885	0.8740	0.8858
0.0007	19.0	475	0.6248	0.885	0.8740	0.8858
0.0007	20.0	500	0.6248	0.89	0.8764	0.8910

Framework versions

Transformers 4.38.1
Pytorch 2.1.0+cu121
Datasets 2.18.0
Tokenizers 0.15.2