584_test3

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: 1.5385
• Accuracy: 0.7646

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: 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	1.2841	0.4896
No log	2.0	242	0.9163	0.6208
No log	3.0	363	0.7371	0.6937
No log	4.0	484	0.7564	0.7354
0.929	5.0	605	0.8983	0.7063
0.929	6.0	726	0.9534	0.7188
0.929	7.0	847	1.1081	0.7125
0.929	8.0	968	1.1693	0.7312
0.2157	9.0	1089	1.2048	0.7354
0.2157	10.0	1210	1.3441	0.7271
0.2157	11.0	1331	1.4214	0.7417
0.2157	12.0	1452	1.3565	0.7479
0.0627	13.0	1573	1.3894	0.7479
0.0627	14.0	1694	1.4546	0.7625
0.0627	15.0	1815	1.4636	0.7583
0.0627	16.0	1936	1.4862	0.7667
0.0229	17.0	2057	1.5382	0.7604
0.0229	18.0	2178	1.5487	0.7667
0.0229	19.0	2299	1.5400	0.7667
0.0229	20.0	2420	1.5385	0.7646

Framework versions

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