metadata

license: mit
base_model: prajjwal1/bert-tiny
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
model-index:
  - name: model_INT03
    results: []

model_INT03

This model is a fine-tuned version of prajjwal1/bert-tiny on an unknown dataset. It achieves the following results on the evaluation set:

Loss: 0.3220
Accuracy: 0.89
F1: 0.8889

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: 16
eval_batch_size: 16
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.0	50	0.6958	0.43	0.2586
No log	0.01	100	0.6890	0.67	0.6043
No log	0.01	150	0.6814	0.57	0.4139
No log	0.02	200	0.6723	0.57	0.4139
No log	0.02	250	0.6289	0.81	0.8103
No log	0.03	300	0.5298	0.82	0.8207
No log	0.03	350	0.4480	0.88	0.8796
No log	0.04	400	0.4042	0.89	0.8889
No log	0.04	450	0.3688	0.9	0.8988
0.6099	0.05	500	0.3615	0.89	0.8889
0.6099	0.05	550	0.3542	0.89	0.8889
0.6099	0.06	600	0.3443	0.89	0.8889
0.6099	0.06	650	0.3300	0.89	0.8889
0.6099	0.07	700	0.3196	0.89	0.8889
0.6099	0.07	750	0.3220	0.89	0.8889

Framework versions

Transformers 4.35.2
Pytorch 2.1.0+cu118
Datasets 2.15.0
Tokenizers 0.15.0