results

This model is a fine-tuned version of bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6829
• Accuracy: 0.6045
• Precision: [0.7241379310338585, 0.50549450549395, 0.6101694915243895]
• Recall: [0.6829268292677374, 0.6388888888880015, 0.44444444444389575]
• Micro F1: 0.6125
• Macro F1: 0.5939
• Confusion Matrix: [[155, 100], [110, 166]]

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	Micro F1	Macro F1	Confusion Matrix
0.6005	1.0	138	0.6847	0.5729	[0.8235294117634948, 0.642857142852551, 0.5434782608683837]	[0.6153846153839391, 0.11999999999984, 0.49999999999899997]	0.5233	0.4758	[[130, 38], [126, 90]]
0.5435	2.0	276	0.6608	0.6276	[0.790123456789148, 0.6779661016937661, 0.5531914893605251]	[0.7032967032959304, 0.5333333333326222, 0.51999999999896]	0.6452	0.6258	[[111, 57], [86, 130]]
0.5863	3.0	414	0.6713	0.6354	[0.8260869565205419, 0.7272727272714049, 0.5535714285704401]	[0.626373626372938, 0.5333333333326222, 0.61999999999876]	0.6465	0.6376	[[116, 52], [88, 128]]

Framework versions

• Transformers 4.42.3
• Pytorch 2.3.1+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1