CONTEXT_one

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

• Loss: 1.2483
• Precision: 0.8152
• Recall: 0.8158
• F1: 0.8141
• Accuracy: 0.8158

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
1.3127	0.62	30	1.1497	0.6818	0.5263	0.4785	0.5263
0.8414	1.25	60	0.8096	0.7479	0.75	0.7472	0.75
0.597	1.88	90	0.6579	0.7904	0.7895	0.7873	0.7895
0.4417	2.5	120	0.5761	0.8072	0.8026	0.8026	0.8026
0.3041	3.12	150	0.6691	0.7665	0.7632	0.7598	0.7632
0.2384	3.75	180	0.6736	0.7717	0.7632	0.7645	0.7632
0.28	4.38	210	0.7949	0.7602	0.7632	0.7574	0.7632
0.22	5.0	240	0.8305	0.7917	0.7895	0.7879	0.7895
0.1427	5.62	270	0.7339	0.8041	0.8026	0.8025	0.8026
0.1875	6.25	300	0.7198	0.8031	0.7895	0.7909	0.7895
0.1216	6.88	330	0.7462	0.8315	0.8289	0.8287	0.8289
0.0895	7.5	360	0.8646	0.8070	0.8026	0.8006	0.8026
0.0758	8.12	390	1.0129	0.7883	0.7632	0.7642	0.7632
0.0636	8.75	420	0.9161	0.7893	0.7895	0.7866	0.7895
0.0239	9.38	450	0.9354	0.7409	0.7368	0.7367	0.7368
0.0449	10.0	480	1.0156	0.7994	0.8026	0.7980	0.8026
0.0089	10.62	510	0.9735	0.8125	0.8158	0.8125	0.8158
0.0348	11.25	540	1.0077	0.7867	0.7895	0.7848	0.7895
0.0037	11.88	570	1.1631	0.7868	0.7895	0.7857	0.7895
0.0022	12.5	600	1.1037	0.7998	0.8026	0.7993	0.8026
0.026	13.12	630	1.0309	0.8152	0.8158	0.8141	0.8158
0.0118	13.75	660	1.0360	0.8152	0.8158	0.8141	0.8158
0.0125	14.38	690	1.2095	0.7867	0.7895	0.7848	0.7895
0.0158	15.0	720	1.0658	0.8152	0.8158	0.8141	0.8158
0.0072	15.62	750	1.1267	0.7708	0.7763	0.7688	0.7763
0.0015	16.25	780	1.1247	0.8152	0.8158	0.8141	0.8158
0.0018	16.88	810	1.1386	0.8152	0.8158	0.8141	0.8158
0.0013	17.5	840	1.1468	0.8152	0.8158	0.8141	0.8158
0.0011	18.12	870	1.1692	0.8152	0.8158	0.8141	0.8158
0.0013	18.75	900	1.1734	0.8152	0.8158	0.8141	0.8158
0.0011	19.38	930	1.1857	0.8152	0.8158	0.8141	0.8158
0.001	20.0	960	1.1890	0.8152	0.8158	0.8141	0.8158
0.001	20.62	990	1.1924	0.8152	0.8158	0.8141	0.8158
0.0009	21.25	1020	1.2005	0.8152	0.8158	0.8141	0.8158
0.0009	21.88	1050	1.2084	0.8152	0.8158	0.8141	0.8158
0.0009	22.5	1080	1.2216	0.8152	0.8158	0.8141	0.8158
0.0009	23.12	1110	1.2237	0.8152	0.8158	0.8141	0.8158
0.0008	23.75	1140	1.2231	0.8152	0.8158	0.8141	0.8158
0.0008	24.38	1170	1.2286	0.8152	0.8158	0.8141	0.8158
0.0008	25.0	1200	1.2312	0.8152	0.8158	0.8141	0.8158
0.0008	25.62	1230	1.2325	0.8152	0.8158	0.8141	0.8158
0.0008	26.25	1260	1.2362	0.8152	0.8158	0.8141	0.8158
0.0008	26.88	1290	1.2415	0.8152	0.8158	0.8141	0.8158
0.0007	27.5	1320	1.2462	0.8152	0.8158	0.8141	0.8158
0.0008	28.12	1350	1.2471	0.8152	0.8158	0.8141	0.8158
0.0007	28.75	1380	1.2466	0.8152	0.8158	0.8141	0.8158
0.0007	29.38	1410	1.2478	0.8152	0.8158	0.8141	0.8158
0.0007	30.0	1440	1.2483	0.8152	0.8158	0.8141	0.8158

Framework versions

• Transformers 4.37.1
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1