my_awesome_wnut_JGTg

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

• Loss: 0.0866
• Precision: 0.5778
• Recall: 0.6842
• F1: 0.6265
• Accuracy: 0.9887

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 100

Training results

Training Loss	Epoch	Step	Validation Loss	Precision	Recall	F1	Accuracy
No log	1.0	46	0.0728	0.0	0.0	0.0	0.9838
No log	2.0	92	0.0419	0.7143	0.1316	0.2222	0.9862
No log	3.0	138	0.0390	0.55	0.5789	0.5641	0.9891
No log	4.0	184	0.0372	0.5652	0.6842	0.6190	0.9887
No log	5.0	230	0.0431	0.5532	0.6842	0.6118	0.9887
No log	6.0	276	0.0435	0.6667	0.5263	0.5882	0.9898
No log	7.0	322	0.0459	0.6047	0.6842	0.6420	0.9894
No log	8.0	368	0.0519	0.6190	0.6842	0.6500	0.9901
No log	9.0	414	0.0477	0.5870	0.7105	0.6429	0.9894
No log	10.0	460	0.0526	0.675	0.7105	0.6923	0.9915
0.0283	11.0	506	0.0532	0.6222	0.7368	0.6747	0.9905
0.0283	12.0	552	0.0550	0.6364	0.7368	0.6829	0.9905
0.0283	13.0	598	0.0578	0.5870	0.7105	0.6429	0.9887
0.0283	14.0	644	0.0642	0.5909	0.6842	0.6341	0.9891
0.0283	15.0	690	0.0615	0.625	0.6579	0.6410	0.9901
0.0283	16.0	736	0.0707	0.56	0.7368	0.6364	0.9880
0.0283	17.0	782	0.0683	0.5870	0.7105	0.6429	0.9884
0.0283	18.0	828	0.0656	0.625	0.6579	0.6410	0.9901
0.0283	19.0	874	0.0646	0.7188	0.6053	0.6571	0.9912
0.0283	20.0	920	0.0660	0.6098	0.6579	0.6329	0.9898
0.0283	21.0	966	0.0679	0.625	0.6579	0.6410	0.9901
0.0006	22.0	1012	0.0677	0.6190	0.6842	0.6500	0.9901
0.0006	23.0	1058	0.0683	0.625	0.6579	0.6410	0.9901
0.0006	24.0	1104	0.0706	0.6136	0.7105	0.6585	0.9901
0.0006	25.0	1150	0.0714	0.5952	0.6579	0.625	0.9891
0.0006	26.0	1196	0.0713	0.5094	0.7105	0.5934	0.9862
0.0006	27.0	1242	0.0667	0.6154	0.6316	0.6234	0.9905
0.0006	28.0	1288	0.0649	0.6786	0.5	0.5758	0.9905
0.0006	29.0	1334	0.0636	0.6216	0.6053	0.6133	0.9901
0.0006	30.0	1380	0.0635	0.6429	0.4737	0.5455	0.9898
0.0006	31.0	1426	0.0744	0.52	0.6842	0.5909	0.9873
0.0006	32.0	1472	0.0694	0.5909	0.6842	0.6341	0.9891
0.001	33.0	1518	0.0695	0.6098	0.6579	0.6329	0.9894
0.001	34.0	1564	0.0746	0.6047	0.6842	0.6420	0.9894
0.001	35.0	1610	0.0741	0.6047	0.6842	0.6420	0.9894
0.001	36.0	1656	0.0732	0.6279	0.7105	0.6667	0.9901
0.001	37.0	1702	0.0736	0.6279	0.7105	0.6667	0.9901
0.001	38.0	1748	0.0757	0.6	0.7105	0.6506	0.9894
0.001	39.0	1794	0.0762	0.5745	0.7105	0.6353	0.9887
0.001	40.0	1840	0.0762	0.5870	0.7105	0.6429	0.9891
0.001	41.0	1886	0.0753	0.5870	0.7105	0.6429	0.9891
0.001	42.0	1932	0.0856	0.5294	0.7105	0.6067	0.9873
0.001	43.0	1978	0.0809	0.5510	0.7105	0.6207	0.9880
0.0003	44.0	2024	0.0733	0.5745	0.7105	0.6353	0.9887
0.0003	45.0	2070	0.0748	0.5745	0.7105	0.6353	0.9887
0.0003	46.0	2116	0.0767	0.5745	0.7105	0.6353	0.9887
0.0003	47.0	2162	0.0768	0.5745	0.7105	0.6353	0.9887
0.0003	48.0	2208	0.0791	0.5745	0.7105	0.6353	0.9887
0.0003	49.0	2254	0.0790	0.5745	0.7105	0.6353	0.9887
0.0003	50.0	2300	0.0795	0.5745	0.7105	0.6353	0.9887
0.0003	51.0	2346	0.0823	0.5745	0.7105	0.6353	0.9887
0.0003	52.0	2392	0.0823	0.5745	0.7105	0.6353	0.9887
0.0003	53.0	2438	0.0903	0.5094	0.7105	0.5934	0.9866
0.0003	54.0	2484	0.0726	0.6047	0.6842	0.6420	0.9898
0.0003	55.0	2530	0.0742	0.6136	0.7105	0.6585	0.9901
0.0003	56.0	2576	0.0762	0.6136	0.7105	0.6585	0.9901
0.0003	57.0	2622	0.0801	0.5745	0.7105	0.6353	0.9887
0.0003	58.0	2668	0.0803	0.5745	0.7105	0.6353	0.9887
0.0003	59.0	2714	0.0806	0.5745	0.7105	0.6353	0.9887
0.0003	60.0	2760	0.0818	0.5625	0.7105	0.6279	0.9884
0.0003	61.0	2806	0.0820	0.5625	0.7105	0.6279	0.9884
0.0003	62.0	2852	0.0819	0.5745	0.7105	0.6353	0.9887
0.0003	63.0	2898	0.0818	0.5745	0.7105	0.6353	0.9887
0.0003	64.0	2944	0.0819	0.5870	0.7105	0.6429	0.9891
0.0003	65.0	2990	0.0818	0.6	0.7105	0.6506	0.9894
0.0003	66.0	3036	0.0808	0.6136	0.7105	0.6585	0.9898
0.0003	67.0	3082	0.0814	0.5814	0.6579	0.6173	0.9887
0.0003	68.0	3128	0.0812	0.5814	0.6579	0.6173	0.9887
0.0003	69.0	3174	0.0815	0.5814	0.6579	0.6173	0.9887
0.0003	70.0	3220	0.0820	0.5814	0.6579	0.6173	0.9887
0.0003	71.0	3266	0.0828	0.5909	0.6842	0.6341	0.9891
0.0003	72.0	3312	0.0837	0.6	0.7105	0.6506	0.9894
0.0003	73.0	3358	0.0843	0.6	0.7105	0.6506	0.9894
0.0003	74.0	3404	0.0846	0.6	0.7105	0.6506	0.9894
0.0003	75.0	3450	0.0856	0.6	0.7105	0.6506	0.9894
0.0003	76.0	3496	0.0849	0.6	0.7105	0.6506	0.9894
0.0002	77.0	3542	0.0911	0.5625	0.7105	0.6279	0.9884
0.0002	78.0	3588	0.0972	0.4909	0.7105	0.5806	0.9859
0.0002	79.0	3634	0.0906	0.5294	0.7105	0.6067	0.9873
0.0002	80.0	3680	0.0897	0.54	0.7105	0.6136	0.9876
0.0002	81.0	3726	0.0906	0.54	0.7105	0.6136	0.9876
0.0002	82.0	3772	0.0905	0.54	0.7105	0.6136	0.9876
0.0002	83.0	3818	0.0909	0.54	0.7105	0.6136	0.9876
0.0002	84.0	3864	0.0904	0.54	0.7105	0.6136	0.9876
0.0002	85.0	3910	0.0898	0.5510	0.7105	0.6207	0.9880
0.0002	86.0	3956	0.0903	0.54	0.7105	0.6136	0.9876
0.0003	87.0	4002	0.0844	0.5778	0.6842	0.6265	0.9887
0.0003	88.0	4048	0.0833	0.5909	0.6842	0.6341	0.9894
0.0003	89.0	4094	0.0836	0.5909	0.6842	0.6341	0.9891
0.0003	90.0	4140	0.0841	0.5909	0.6842	0.6341	0.9891
0.0003	91.0	4186	0.0845	0.5909	0.6842	0.6341	0.9891
0.0003	92.0	4232	0.0858	0.5778	0.6842	0.6265	0.9887
0.0003	93.0	4278	0.0857	0.5778	0.6842	0.6265	0.9887
0.0003	94.0	4324	0.0861	0.5778	0.6842	0.6265	0.9887
0.0003	95.0	4370	0.0862	0.5778	0.6842	0.6265	0.9887
0.0003	96.0	4416	0.0865	0.5778	0.6842	0.6265	0.9887
0.0003	97.0	4462	0.0866	0.5778	0.6842	0.6265	0.9887
0.0002	98.0	4508	0.0866	0.5778	0.6842	0.6265	0.9887
0.0002	99.0	4554	0.0866	0.5778	0.6842	0.6265	0.9887
0.0002	100.0	4600	0.0866	0.5778	0.6842	0.6265	0.9887

Framework versions

• Transformers 4.39.1
• Pytorch 2.2.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.2