my_awesome_wnut_NEG

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: 0.0164
• Precision: 0.9412
• Recall: 0.8889
• F1: 0.9143
• Accuracy: 0.9979

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	0.0377	0.9375	0.2778	0.4286	0.9878
No log	2.0	92	0.0142	0.9535	0.7593	0.8454	0.9960
No log	3.0	138	0.0100	0.9184	0.8333	0.8738	0.9967
No log	4.0	184	0.0104	0.875	0.9074	0.8909	0.9967
No log	5.0	230	0.0108	0.9074	0.9074	0.9074	0.9976
No log	6.0	276	0.0128	0.8596	0.9074	0.8829	0.9967
No log	7.0	322	0.0145	0.8448	0.9074	0.875	0.9964
No log	8.0	368	0.0136	0.9074	0.9074	0.9074	0.9976
No log	9.0	414	0.0180	0.9375	0.8333	0.8824	0.9970
No log	10.0	460	0.0184	0.8868	0.8704	0.8785	0.9964
0.0166	11.0	506	0.0186	0.8519	0.8519	0.8519	0.9960
0.0166	12.0	552	0.0191	0.9020	0.8519	0.8762	0.9970
0.0166	13.0	598	0.0193	0.9020	0.8519	0.8762	0.9970
0.0166	14.0	644	0.0195	0.9020	0.8519	0.8762	0.9970
0.0166	15.0	690	0.0199	0.9020	0.8519	0.8762	0.9970
0.0166	16.0	736	0.0202	0.9020	0.8519	0.8762	0.9970
0.0166	17.0	782	0.0206	0.9020	0.8519	0.8762	0.9970
0.0166	18.0	828	0.0207	0.9020	0.8519	0.8762	0.9970
0.0166	19.0	874	0.0208	0.9020	0.8519	0.8762	0.9970
0.0166	20.0	920	0.0211	0.9020	0.8519	0.8762	0.9970
0.0166	21.0	966	0.0214	0.9020	0.8519	0.8762	0.9970
0.0	22.0	1012	0.0216	0.9020	0.8519	0.8762	0.9970
0.0	23.0	1058	0.0218	0.9020	0.8519	0.8762	0.9970
0.0	24.0	1104	0.0219	0.9020	0.8519	0.8762	0.9970
0.0	25.0	1150	0.0219	0.9020	0.8519	0.8762	0.9970
0.0	26.0	1196	0.0223	0.9020	0.8519	0.8762	0.9970
0.0	27.0	1242	0.0225	0.9020	0.8519	0.8762	0.9970
0.0	28.0	1288	0.0227	0.9020	0.8519	0.8762	0.9970
0.0	29.0	1334	0.0229	0.9020	0.8519	0.8762	0.9970
0.0	30.0	1380	0.0229	0.9020	0.8519	0.8762	0.9970
0.0	31.0	1426	0.0231	0.9020	0.8519	0.8762	0.9970
0.0	32.0	1472	0.0233	0.9020	0.8519	0.8762	0.9970
0.0	33.0	1518	0.0234	0.9020	0.8519	0.8762	0.9970
0.0	34.0	1564	0.0235	0.9020	0.8519	0.8762	0.9970
0.0	35.0	1610	0.0237	0.9020	0.8519	0.8762	0.9970
0.0	36.0	1656	0.0238	0.9020	0.8519	0.8762	0.9970
0.0	37.0	1702	0.0252	0.94	0.8704	0.9038	0.9976
0.0	38.0	1748	0.0250	0.94	0.8704	0.9038	0.9976
0.0	39.0	1794	0.0251	0.94	0.8704	0.9038	0.9976
0.0	40.0	1840	0.0249	0.9020	0.8519	0.8762	0.9970
0.0	41.0	1886	0.0249	0.9020	0.8519	0.8762	0.9970
0.0	42.0	1932	0.0250	0.9020	0.8519	0.8762	0.9970
0.0	43.0	1978	0.0251	0.9020	0.8519	0.8762	0.9970
0.0	44.0	2024	0.0252	0.9020	0.8519	0.8762	0.9970
0.0	45.0	2070	0.0253	0.9020	0.8519	0.8762	0.9970
0.0	46.0	2116	0.0255	0.9020	0.8519	0.8762	0.9970
0.0	47.0	2162	0.0259	0.875	0.9074	0.8909	0.9967
0.0	48.0	2208	0.0264	0.8727	0.8889	0.8807	0.9964
0.0	49.0	2254	0.0170	0.94	0.8704	0.9038	0.9976
0.0	50.0	2300	0.0177	0.94	0.8704	0.9038	0.9976
0.0	51.0	2346	0.0180	0.94	0.8704	0.9038	0.9976
0.0	52.0	2392	0.0175	0.9412	0.8889	0.9143	0.9979
0.0	53.0	2438	0.0176	0.9245	0.9074	0.9159	0.9979
0.0	54.0	2484	0.0178	0.9245	0.9074	0.9159	0.9979
0.0001	55.0	2530	0.0179	0.9245	0.9074	0.9159	0.9979
0.0001	56.0	2576	0.0181	0.9245	0.9074	0.9159	0.9979
0.0001	57.0	2622	0.0183	0.9245	0.9074	0.9159	0.9979
0.0001	58.0	2668	0.0186	0.9592	0.8704	0.9126	0.9979
0.0001	59.0	2714	0.0159	0.9434	0.9259	0.9346	0.9982
0.0001	60.0	2760	0.0160	0.9434	0.9259	0.9346	0.9982
0.0001	61.0	2806	0.0160	0.9434	0.9259	0.9346	0.9982
0.0001	62.0	2852	0.0161	0.9434	0.9259	0.9346	0.9982
0.0001	63.0	2898	0.0161	0.9245	0.9074	0.9159	0.9979
0.0001	64.0	2944	0.0162	0.9245	0.9074	0.9159	0.9979
0.0001	65.0	2990	0.0162	0.9245	0.9074	0.9159	0.9979
0.0	66.0	3036	0.0163	0.9245	0.9074	0.9159	0.9979
0.0	67.0	3082	0.0164	0.9245	0.9074	0.9159	0.9979
0.0	68.0	3128	0.0164	0.9245	0.9074	0.9159	0.9979
0.0	69.0	3174	0.0164	0.9245	0.9074	0.9159	0.9979
0.0	70.0	3220	0.0165	0.9245	0.9074	0.9159	0.9979
0.0	71.0	3266	0.0165	0.9245	0.9074	0.9159	0.9979
0.0	72.0	3312	0.0165	0.9245	0.9074	0.9159	0.9979
0.0	73.0	3358	0.0166	0.9245	0.9074	0.9159	0.9979
0.0	74.0	3404	0.0166	0.9245	0.9074	0.9159	0.9979
0.0	75.0	3450	0.0166	0.9245	0.9074	0.9159	0.9979
0.0	76.0	3496	0.0167	0.9245	0.9074	0.9159	0.9979
0.0	77.0	3542	0.0167	0.9245	0.9074	0.9159	0.9979
0.0	78.0	3588	0.0168	0.9245	0.9074	0.9159	0.9979
0.0	79.0	3634	0.0168	0.9245	0.9074	0.9159	0.9979
0.0	80.0	3680	0.0168	0.9245	0.9074	0.9159	0.9979
0.0	81.0	3726	0.0168	0.9245	0.9074	0.9159	0.9979
0.0	82.0	3772	0.0169	0.9245	0.9074	0.9159	0.9979
0.0	83.0	3818	0.0169	0.9245	0.9074	0.9159	0.9979
0.0	84.0	3864	0.0170	0.9245	0.9074	0.9159	0.9979
0.0	85.0	3910	0.0162	0.9412	0.8889	0.9143	0.9979
0.0	86.0	3956	0.0162	0.9412	0.8889	0.9143	0.9979
0.0	87.0	4002	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	88.0	4048	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	89.0	4094	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	90.0	4140	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	91.0	4186	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	92.0	4232	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	93.0	4278	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	94.0	4324	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	95.0	4370	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	96.0	4416	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	97.0	4462	0.0163	0.9412	0.8889	0.9143	0.9979
0.0	98.0	4508	0.0164	0.9412	0.8889	0.9143	0.9979
0.0	99.0	4554	0.0164	0.9412	0.8889	0.9143	0.9979
0.0	100.0	4600	0.0164	0.9412	0.8889	0.9143	0.9979

Framework versions

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