metadata

license: apache-2.0
tags:
  - generated_from_trainer
datasets:
  - imdb
metrics:
  - accuracy
  - f1
model-index:
  - name: bert_uncased_L-2_H-128_A-2-finetuned-emotion-finetuned-tweet
    results:
      - task:
          name: Text Classification
          type: text-classification
        dataset:
          name: imdb
          type: imdb
          config: plain_text
          split: train
          args: plain_text
        metrics:
          - name: Accuracy
            type: accuracy
            value: 0.87168
          - name: F1
            type: f1
            value: 0.8716747437975058

bert_uncased_L-2_H-128_A-2-finetuned-emotion-finetuned-tweet

This model is a fine-tuned version of muhtasham/bert_uncased_L-2_H-128_A-2-finetuned-emotion on the imdb dataset. It achieves the following results on the evaluation set:

Loss: 0.4004
Accuracy: 0.8717
F1: 0.8717

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: 3e-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: constant
num_epochs: 200

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.4751	1.28	500	0.3880	0.828	0.8277
0.3453	2.56	1000	0.3282	0.8608	0.8607
0.2973	3.84	1500	0.3140	0.8695	0.8695
0.26	5.12	2000	0.3154	0.8736	0.8735
0.2218	6.39	2500	0.3144	0.8756	0.8756
0.1977	7.67	3000	0.3197	0.876	0.8760
0.1656	8.95	3500	0.3526	0.8737	0.8735
0.1404	10.23	4000	0.3865	0.8691	0.8689
0.121	11.51	4500	0.4004	0.8717	0.8717

Framework versions

Transformers 4.24.0
Pytorch 1.12.1+cu113
Datasets 2.7.0
Tokenizers 0.13.2