metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: finetuned_token_2e-05_16_02_2022-14_15_41
    results: []

finetuned_token_2e-05_16_02_2022-14_15_41

This model is a fine-tuned version of distilbert-base-uncased-finetuned-sst-2-english on the None dataset. It achieves the following results on the evaluation set:

Loss: 0.1746
Precision: 0.3191
Recall: 0.3382
F1: 0.3284
Accuracy: 0.9439

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: 32
eval_batch_size: 32
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	38	0.2908	0.1104	0.1905	0.1398	0.8731
No log	2.0	76	0.2253	0.1682	0.3206	0.2206	0.9114
No log	3.0	114	0.2041	0.2069	0.3444	0.2585	0.9249
No log	4.0	152	0.1974	0.2417	0.3603	0.2894	0.9269
No log	5.0	190	0.1958	0.2707	0.3683	0.3120	0.9299

Framework versions

Transformers 4.15.0
Pytorch 1.10.1+cu113
Datasets 1.18.0
Tokenizers 0.10.3