584_32_2

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: 1.0716
• Accuracy: 0.7375

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: 64
• 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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	121	1.3762	0.3167
No log	2.0	242	1.2997	0.4354
No log	3.0	363	1.0788	0.5646
No log	4.0	484	0.9368	0.6042
1.2396	5.0	605	0.8875	0.6667
1.2396	6.0	726	0.8721	0.6521
1.2396	7.0	847	0.8031	0.6813
1.2396	8.0	968	0.7952	0.7
0.6439	9.0	1089	0.7813	0.7042
0.6439	10.0	1210	0.8157	0.7167
0.6439	11.0	1331	0.8293	0.7333
0.6439	12.0	1452	0.8892	0.7063
0.2849	13.0	1573	0.9220	0.7167
0.2849	14.0	1694	0.9649	0.725
0.2849	15.0	1815	1.0061	0.7312
0.2849	16.0	1936	1.0530	0.725
0.1251	17.0	2057	1.0418	0.7292
0.1251	18.0	2178	1.0583	0.7354
0.1251	19.0	2299	1.0761	0.7375
0.1251	20.0	2420	1.0716	0.7375

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.1+cu121
• Datasets 3.0.1
• Tokenizers 0.19.1