README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - accuracy
  - f1
  - precision
  - recall
model-index:
  - name: BertSeq
    results: []

BertSeq

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.2244
• Accuracy: 1.0
• F1: 1.0
• Precision: 1.0
• Recall: 1.0

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 32
• 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	F1	Precision	Recall
0.6468	2.5	5	0.5917	1.0	1.0	1.0	1.0
0.5888	5.0	10	0.5269	1.0	1.0	1.0	1.0
0.5427	7.5	15	0.4736	1.0	1.0	1.0	1.0
0.4919	10.0	20	0.4295	1.0	1.0	1.0	1.0
0.4872	12.5	25	0.3927	1.0	1.0	1.0	1.0
0.4447	15.0	30	0.3615	1.0	1.0	1.0	1.0
0.4242	17.5	35	0.3353	1.0	1.0	1.0	1.0
0.4133	20.0	40	0.3128	1.0	1.0	1.0	1.0
0.3889	22.5	45	0.2939	1.0	1.0	1.0	1.0
0.3736	25.0	50	0.2780	1.0	1.0	1.0	1.0
0.3736	27.5	55	0.2655	1.0	1.0	1.0	1.0
0.3847	30.0	60	0.2557	1.0	1.0	1.0	1.0
0.382	32.5	65	0.2483	1.0	1.0	1.0	1.0
0.3239	35.0	70	0.2418	1.0	1.0	1.0	1.0
0.3254	37.5	75	0.2361	1.0	1.0	1.0	1.0
0.3441	40.0	80	0.2316	1.0	1.0	1.0	1.0
0.3435	42.5	85	0.2284	1.0	1.0	1.0	1.0
0.3541	45.0	90	0.2262	1.0	1.0	1.0	1.0
0.2947	47.5	95	0.2248	1.0	1.0	1.0	1.0
0.3678	50.0	100	0.2244	1.0	1.0	1.0	1.0

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.1
• Tokenizers 0.15.0