README.md

metadata

tags:
  - generated_from_trainer
metrics:
  - precision
  - recall
  - f1
  - accuracy
model-index:
  - name: tiny_focal_v2_label
    results: []

tiny_focal_v2_label

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

• Loss: 0.0558
• Precision: 0.6979
• Recall: 0.6747
• F1: 0.6861
• Accuracy: 0.9513

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: 3e-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	Precision	Recall	F1	Accuracy
0.0661	1.0	5561	0.0616	0.6850	0.6202	0.6510	0.9457
0.0613	2.0	11122	0.0587	0.6952	0.6351	0.6638	0.9480
0.0596	3.0	16683	0.0577	0.6814	0.6679	0.6746	0.9485
0.0555	4.0	22244	0.0567	0.6855	0.6693	0.6773	0.9492
0.0543	5.0	27805	0.0560	0.6966	0.6657	0.6808	0.9503
0.0529	6.0	33366	0.0558	0.7060	0.6587	0.6816	0.9510
0.052	7.0	38927	0.0552	0.7009	0.6662	0.6831	0.9510
0.0506	8.0	44488	0.0559	0.6921	0.6783	0.6852	0.9508
0.0501	9.0	50049	0.0556	0.6991	0.6716	0.6851	0.9512
0.0491	10.0	55610	0.0558	0.6979	0.6747	0.6861	0.9513

Framework versions

• Transformers 4.20.1
• Pytorch 1.11.0+cu113
• Datasets 2.3.2
• Tokenizers 0.12.1