Dagobert42/mobilebert-uncased-biored-finetuned

This model is a fine-tuned version of mobilebert-uncased on the bigbio/biored dataset. It achieves the following results on the evaluation set:

• Loss: 1.0264
• Accuracy: 0.7163
• Precision: 0.1023
• Recall: 0.1429
• F1: 0.1192
• Weighted F1: 0.5979

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1	Weighted F1
No log	1.0	13	1.6911	0.7114	0.1016	0.1429	0.1188	0.5914
No log	2.0	26	1.2080	0.7114	0.1016	0.1429	0.1188	0.5914
No log	3.0	39	1.0905	0.7114	0.1016	0.1429	0.1188	0.5914
No log	4.0	52	1.0400	0.7114	0.1016	0.1429	0.1188	0.5914
No log	5.0	65	1.0439	0.7114	0.1016	0.1429	0.1188	0.5914
No log	6.0	78	1.0288	0.7114	0.1016	0.1429	0.1188	0.5914
No log	7.0	91	1.0259	0.7114	0.1016	0.1429	0.1188	0.5914
No log	8.0	104	1.0180	0.7114	0.1016	0.1429	0.1188	0.5914
No log	9.0	117	1.0229	0.7114	0.1016	0.1429	0.1188	0.5914
No log	10.0	130	1.0186	0.7114	0.1016	0.1429	0.1188	0.5914

Framework versions

• Transformers 4.35.2
• Pytorch 2.0.1+cu117
• Datasets 2.12.0
• Tokenizers 0.15.0