584_test3_metrics

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: 1.5861
• Accuracy: 0.7562
• Precision: 0.7607
• Recall: 0.7562
• F1: 0.7575

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	Precision	Recall	F1
No log	1.0	121	1.2523	0.4604	0.4677	0.4604	0.4289
No log	2.0	242	0.9115	0.6125	0.6287	0.6125	0.5964
No log	3.0	363	0.7587	0.6875	0.6886	0.6875	0.6766
No log	4.0	484	0.7560	0.7333	0.7386	0.7333	0.7305
0.9506	5.0	605	0.9259	0.6896	0.7131	0.6896	0.6851
0.9506	6.0	726	0.9248	0.7271	0.7481	0.7271	0.7248
0.9506	7.0	847	1.0145	0.7354	0.7390	0.7354	0.7362
0.9506	8.0	968	1.1566	0.7354	0.7481	0.7354	0.7357
0.2213	9.0	1089	1.3256	0.7104	0.7337	0.7104	0.7126
0.2213	10.0	1210	1.3571	0.7333	0.7352	0.7333	0.7334
0.2213	11.0	1331	1.4365	0.7417	0.7550	0.7417	0.7429
0.2213	12.0	1452	1.4358	0.7562	0.7688	0.7562	0.7577
0.0549	13.0	1573	1.3191	0.7625	0.7683	0.7625	0.7620
0.0549	14.0	1694	1.5765	0.7312	0.7460	0.7312	0.7338
0.0549	15.0	1815	1.5070	0.7479	0.7537	0.7479	0.7494
0.0549	16.0	1936	1.6250	0.7312	0.7454	0.7312	0.7331
0.0221	17.0	2057	1.6765	0.7375	0.7569	0.7375	0.7410
0.0221	18.0	2178	1.6002	0.7479	0.7513	0.7479	0.7492
0.0221	19.0	2299	1.5772	0.7521	0.7576	0.7521	0.7531
0.0221	20.0	2420	1.5861	0.7562	0.7607	0.7562	0.7575

Framework versions

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