metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: distilBERT_token_itr0_1e-05_webDiscourse_01_03_2022-15_10_39
    results: []

distilBERT_token_itr0_1e-05_webDiscourse_01_03_2022-15_10_39

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: 0.5867
Precision: 0.0119
Recall: 0.0116
F1: 0.0118
Accuracy: 0.6976

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: 1e-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	10	0.5730	0.0952	0.0270	0.0421	0.7381
No log	2.0	20	0.5755	0.0213	0.0135	0.0165	0.7388
No log	3.0	30	0.5635	0.0196	0.0135	0.016	0.7416
No log	4.0	40	0.5549	0.0392	0.0270	0.032	0.7429
No log	5.0	50	0.5530	0.0357	0.0270	0.0308	0.7438

Framework versions

Transformers 4.15.0
Pytorch 1.10.1+cu113
Datasets 1.18.0
Tokenizers 0.10.3