bert-base-phia-secondhandDescription-100

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: 2.2601
• Precision: 0.3167
• Recall: 0.3333
• Accuracy: 0.3333
• F1: 0.2933

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: 10
• eval_batch_size: 10
• 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	Accuracy	F1
No log	1.0	9	2.4405	0.0	0.0	0.0	0.0
No log	2.0	18	2.3760	0.0833	0.2	0.2	0.1156
No log	3.0	27	2.3655	0.0148	0.0667	0.0667	0.0242
No log	4.0	36	2.4138	0.0467	0.1333	0.1333	0.0667
No log	5.0	45	2.3539	0.2833	0.3333	0.3333	0.2933
No log	6.0	54	2.3328	0.075	0.1333	0.1333	0.0815
No log	7.0	63	2.3062	0.1095	0.2	0.2	0.1278
No log	8.0	72	2.3072	0.3111	0.3333	0.3333	0.2857
No log	9.0	81	2.2739	0.2611	0.3333	0.3333	0.2800
No log	10.0	90	2.2601	0.3167	0.3333	0.3333	0.2933

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1
• Datasets 2.20.0
• Tokenizers 0.19.1