my_awesome_wnut_Place

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: 0.0871
• Precision: 0.7
• Recall: 0.8077
• F1: 0.75
• Accuracy: 0.9909

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	0.0618	0.0	0.0	0.0	0.9748
No log	2.0	92	0.0324	0.6129	0.7308	0.6667	0.9884
No log	3.0	138	0.0326	0.6452	0.7692	0.7018	0.9909
No log	4.0	184	0.0364	0.6825	0.8269	0.7478	0.9906
No log	5.0	230	0.0409	0.7455	0.7885	0.7664	0.9918
No log	6.0	276	0.0462	0.7213	0.8462	0.7788	0.9924
No log	7.0	322	0.0486	0.7368	0.8077	0.7706	0.9921
No log	8.0	368	0.0547	0.7143	0.7692	0.7407	0.9912
No log	9.0	414	0.0532	0.65	0.75	0.6964	0.9894
No log	10.0	460	0.0501	0.6667	0.7692	0.7143	0.9912
0.0249	11.0	506	0.0571	0.7018	0.7692	0.7339	0.9909
0.0249	12.0	552	0.0628	0.6667	0.8077	0.7304	0.9894
0.0249	13.0	598	0.0693	0.6418	0.8269	0.7227	0.9887
0.0249	14.0	644	0.0589	0.6833	0.7885	0.7321	0.9912
0.0249	15.0	690	0.0569	0.7321	0.7885	0.7593	0.9915
0.0249	16.0	736	0.0599	0.6885	0.8077	0.7434	0.9918
0.0249	17.0	782	0.0625	0.6885	0.8077	0.7434	0.9912
0.0249	18.0	828	0.0620	0.7193	0.7885	0.7523	0.9918
0.0249	19.0	874	0.0621	0.6935	0.8269	0.7544	0.9906
0.0249	20.0	920	0.0671	0.6364	0.8077	0.7119	0.9894
0.0249	21.0	966	0.0657	0.6719	0.8269	0.7414	0.9903
0.0006	22.0	1012	0.0685	0.6949	0.7885	0.7387	0.9903
0.0006	23.0	1058	0.0696	0.6833	0.7885	0.7321	0.9900
0.0006	24.0	1104	0.0709	0.6833	0.7885	0.7321	0.9900
0.0006	25.0	1150	0.0719	0.6949	0.7885	0.7387	0.9903
0.0006	26.0	1196	0.0736	0.7069	0.7885	0.7455	0.9909
0.0006	27.0	1242	0.0733	0.6780	0.7692	0.7207	0.9897
0.0006	28.0	1288	0.0743	0.6949	0.7885	0.7387	0.9903
0.0006	29.0	1334	0.0784	0.7143	0.7692	0.7407	0.9906
0.0006	30.0	1380	0.0766	0.7069	0.7885	0.7455	0.9906
0.0006	31.0	1426	0.0753	0.6949	0.7885	0.7387	0.9909
0.0006	32.0	1472	0.0809	0.6462	0.8077	0.7179	0.9891
0.0002	33.0	1518	0.0690	0.6613	0.7885	0.7193	0.9906
0.0002	34.0	1564	0.0674	0.7069	0.7885	0.7455	0.9912
0.0002	35.0	1610	0.0692	0.6949	0.7885	0.7387	0.9909
0.0002	36.0	1656	0.0712	0.6949	0.7885	0.7387	0.9909
0.0002	37.0	1702	0.0743	0.6721	0.7885	0.7257	0.9909
0.0002	38.0	1748	0.0746	0.6833	0.7885	0.7321	0.9912
0.0002	39.0	1794	0.0748	0.6833	0.7885	0.7321	0.9912
0.0002	40.0	1840	0.0750	0.6833	0.7885	0.7321	0.9912
0.0002	41.0	1886	0.0760	0.6833	0.7885	0.7321	0.9912
0.0002	42.0	1932	0.0765	0.6833	0.7885	0.7321	0.9912
0.0002	43.0	1978	0.0774	0.6833	0.7885	0.7321	0.9912
0.0001	44.0	2024	0.0778	0.6833	0.7885	0.7321	0.9912
0.0001	45.0	2070	0.0830	0.6308	0.7885	0.7009	0.9900
0.0001	46.0	2116	0.0709	0.7222	0.75	0.7358	0.9912
0.0001	47.0	2162	0.0711	0.6949	0.7885	0.7387	0.9915
0.0001	48.0	2208	0.0779	0.7091	0.75	0.7290	0.9909
0.0001	49.0	2254	0.0792	0.6667	0.8077	0.7304	0.9909
0.0001	50.0	2300	0.0766	0.6842	0.75	0.7156	0.9909
0.0001	51.0	2346	0.0773	0.6897	0.7692	0.7273	0.9906
0.0001	52.0	2392	0.0766	0.7018	0.7692	0.7339	0.9909
0.0001	53.0	2438	0.0803	0.6508	0.7885	0.7130	0.9906
0.0001	54.0	2484	0.0783	0.6462	0.8077	0.7179	0.9903
0.0003	55.0	2530	0.0849	0.6364	0.8077	0.7119	0.9900
0.0003	56.0	2576	0.0843	0.6406	0.7885	0.7069	0.9900
0.0003	57.0	2622	0.0833	0.6613	0.7885	0.7193	0.9906
0.0003	58.0	2668	0.0837	0.6613	0.7885	0.7193	0.9906
0.0003	59.0	2714	0.0842	0.6613	0.7885	0.7193	0.9906
0.0003	60.0	2760	0.0846	0.6613	0.7885	0.7193	0.9906
0.0003	61.0	2806	0.0855	0.6508	0.7885	0.7130	0.9903
0.0003	62.0	2852	0.0866	0.6406	0.7885	0.7069	0.9900
0.0003	63.0	2898	0.0868	0.6406	0.7885	0.7069	0.9900
0.0003	64.0	2944	0.0870	0.6406	0.7885	0.7069	0.9900
0.0003	65.0	2990	0.0872	0.6406	0.7885	0.7069	0.9900
0.0	66.0	3036	0.0879	0.6406	0.7885	0.7069	0.9900
0.0	67.0	3082	0.0881	0.6406	0.7885	0.7069	0.9900
0.0	68.0	3128	0.0884	0.6406	0.7885	0.7069	0.9900
0.0	69.0	3174	0.0885	0.6508	0.7885	0.7130	0.9903
0.0	70.0	3220	0.0887	0.6508	0.7885	0.7130	0.9903
0.0	71.0	3266	0.0889	0.6508	0.7885	0.7130	0.9903
0.0	72.0	3312	0.0890	0.6508	0.7885	0.7130	0.9903
0.0	73.0	3358	0.0892	0.6508	0.7885	0.7130	0.9903
0.0	74.0	3404	0.0893	0.6508	0.7885	0.7130	0.9903
0.0	75.0	3450	0.0894	0.6508	0.7885	0.7130	0.9903
0.0	76.0	3496	0.0896	0.6508	0.7885	0.7130	0.9903
0.0	77.0	3542	0.0897	0.6508	0.7885	0.7130	0.9903
0.0	78.0	3588	0.0898	0.6508	0.7885	0.7130	0.9903
0.0	79.0	3634	0.0899	0.6508	0.7885	0.7130	0.9903
0.0	80.0	3680	0.0900	0.6508	0.7885	0.7130	0.9903
0.0	81.0	3726	0.0902	0.6508	0.7885	0.7130	0.9903
0.0	82.0	3772	0.0895	0.6508	0.7885	0.7130	0.9903
0.0	83.0	3818	0.0881	0.6613	0.7885	0.7193	0.9906
0.0	84.0	3864	0.0861	0.6613	0.7885	0.7193	0.9906
0.0	85.0	3910	0.0862	0.6613	0.7885	0.7193	0.9906
0.0	86.0	3956	0.0865	0.6613	0.7885	0.7193	0.9906
0.0001	87.0	4002	0.0862	0.6721	0.7885	0.7257	0.9909
0.0001	88.0	4048	0.0863	0.7	0.8077	0.75	0.9909
0.0001	89.0	4094	0.0864	0.7	0.8077	0.75	0.9909
0.0001	90.0	4140	0.0865	0.7	0.8077	0.75	0.9909
0.0001	91.0	4186	0.0866	0.7	0.8077	0.75	0.9909
0.0001	92.0	4232	0.0867	0.7	0.8077	0.75	0.9909
0.0001	93.0	4278	0.0868	0.7	0.8077	0.75	0.9909
0.0001	94.0	4324	0.0869	0.7	0.8077	0.75	0.9909
0.0001	95.0	4370	0.0870	0.7	0.8077	0.75	0.9909
0.0001	96.0	4416	0.0870	0.7	0.8077	0.75	0.9909
0.0001	97.0	4462	0.0871	0.7	0.8077	0.75	0.9909
0.0	98.0	4508	0.0871	0.7	0.8077	0.75	0.9909
0.0	99.0	4554	0.0871	0.7	0.8077	0.75	0.9909
0.0	100.0	4600	0.0871	0.7	0.8077	0.75	0.9909

Framework versions

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