A model to predict if a text string is an Autobot or Decepticon motto!

bert-base-uncased-finetuned-TF-mottos

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

• Loss: 0.6088
• Accuracy: 0.7241
• F1: 0.7241

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: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.7065	1.0	16	0.6716	0.6897	0.6855
0.6407	2.0	32	0.6404	0.6552	0.6446
0.5087	3.0	48	0.6088	0.7241	0.7241
0.3035	4.0	64	0.7323	0.6552	0.6636
0.1443	5.0	80	0.9169	0.5862	0.5952
0.0619	6.0	96	1.3918	0.5517	0.5517
0.0494	7.0	112	1.5762	0.6207	0.6207
0.0154	8.0	128	1.4311	0.6552	0.6636
0.0052	9.0	144	1.8390	0.5862	0.5901
0.0031	10.0	160	1.8705	0.6207	0.6270
0.0021	11.0	176	1.9632	0.6207	0.6270
0.0018	12.0	192	2.0319	0.6207	0.6270
0.0115	13.0	208	2.0895	0.6207	0.6270
0.0014	14.0	224	2.2048	0.5862	0.5901
0.0012	15.0	240	2.2127	0.6207	0.6270
0.0011	16.0	256	2.2382	0.6207	0.6270
0.0011	17.0	272	2.2513	0.6207	0.6270
0.001	18.0	288	2.2649	0.6207	0.6270
0.001	19.0	304	2.2752	0.6207	0.6270
0.001	20.0	320	2.2845	0.5862	0.5901

Framework versions

• Transformers 4.48.2
• Pytorch 2.5.1+cu124
• Datasets 3.2.0
• Tokenizers 0.21.0