training

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: 2.3256
• Accuracy: 0.6768
• F1: 0.6764
• Precision: 0.6772
• Recall: 0.6768

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: 40
• eval_batch_size: 20
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 40

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall
No log	1.0	66	0.7029	0.4939	0.3623	0.4289	0.4939
No log	2.0	132	0.6985	0.4726	0.4074	0.4429	0.4726
No log	3.0	198	0.7052	0.5091	0.5079	0.5101	0.5091
No log	4.0	264	0.7277	0.5732	0.5687	0.5746	0.5732
No log	5.0	330	0.8226	0.5747	0.5711	0.5791	0.5747
No log	6.0	396	0.9070	0.6098	0.6084	0.6126	0.6098
No log	7.0	462	0.9877	0.6296	0.6288	0.6299	0.6296
0.4904	8.0	528	1.2868	0.5976	0.5814	0.6198	0.5976
0.4904	9.0	594	1.2709	0.6433	0.6396	0.6517	0.6433
0.4904	10.0	660	1.3541	0.6494	0.6494	0.6494	0.6494
0.4904	11.0	726	1.4138	0.6631	0.6572	0.6724	0.6631
0.4904	12.0	792	1.5116	0.6631	0.6616	0.6676	0.6631
0.4904	13.0	858	1.5349	0.6738	0.6687	0.6825	0.6738
0.4904	14.0	924	1.5437	0.6845	0.6845	0.6845	0.6845
0.4904	15.0	990	1.8465	0.6585	0.6581	0.6588	0.6585
0.0493	16.0	1056	1.8186	0.6662	0.6661	0.6667	0.6662
0.0493	17.0	1122	1.9234	0.6601	0.6589	0.6635	0.6601
0.0493	18.0	1188	1.9517	0.6707	0.6689	0.6763	0.6707
0.0493	19.0	1254	1.9673	0.6616	0.6609	0.6639	0.6616
0.0493	20.0	1320	2.0034	0.6768	0.6768	0.6769	0.6768
0.0493	21.0	1386	2.0452	0.6707	0.6707	0.6707	0.6707
0.0493	22.0	1452	2.1151	0.6570	0.6569	0.6578	0.6570
0.0085	23.0	1518	2.0888	0.6631	0.6627	0.6633	0.6631
0.0085	24.0	1584	2.1101	0.6646	0.6646	0.6649	0.6646
0.0085	25.0	1650	2.1330	0.6662	0.6661	0.6666	0.6662
0.0085	26.0	1716	2.1890	0.6662	0.6659	0.6663	0.6662
0.0085	27.0	1782	2.2275	0.6601	0.6598	0.6602	0.6601
0.0085	28.0	1848	2.2380	0.6662	0.6648	0.6704	0.6662
0.0085	29.0	1914	2.2606	0.6646	0.6646	0.6650	0.6646
0.0085	30.0	1980	2.2708	0.6738	0.6734	0.6755	0.6738
0.0029	31.0	2046	2.2827	0.6677	0.6675	0.6677	0.6677
0.0029	32.0	2112	2.2992	0.6738	0.6738	0.6738	0.6738
0.0029	33.0	2178	2.2926	0.6768	0.6757	0.6782	0.6768
0.0029	34.0	2244	2.3100	0.6738	0.6738	0.6740	0.6738
0.0029	35.0	2310	2.3081	0.6768	0.6767	0.6768	0.6768
0.0029	36.0	2376	2.3080	0.6768	0.6764	0.6772	0.6768
0.0029	37.0	2442	2.3242	0.6784	0.6783	0.6787	0.6784
0.0004	38.0	2508	2.3252	0.6799	0.6799	0.6799	0.6799
0.0004	39.0	2574	2.3228	0.6784	0.6782	0.6784	0.6784
0.0004	40.0	2640	2.3256	0.6768	0.6764	0.6772	0.6768

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0