categor_ai

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

• Loss: 0.6307
• Accuracy: 0.8901

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	Accuracy
No log	1.0	14	2.4323	0.4615
No log	2.0	28	2.0883	0.5495
No log	3.0	42	1.7465	0.7033
No log	4.0	56	1.4428	0.7363
No log	5.0	70	1.1838	0.8242
No log	6.0	84	0.9881	0.8132
No log	7.0	98	0.8446	0.8571
No log	8.0	112	0.7304	0.8791
No log	9.0	126	0.6456	0.8681
No log	10.0	140	0.6267	0.8352
No log	11.0	154	0.5656	0.8791
No log	12.0	168	0.5412	0.8901
No log	13.0	182	0.5301	0.8901
No log	14.0	196	0.5190	0.8791
No log	15.0	210	0.5175	0.8901
No log	16.0	224	0.5295	0.8681
No log	17.0	238	0.5147	0.8901
No log	18.0	252	0.5094	0.8901
No log	19.0	266	0.5130	0.8791
No log	20.0	280	0.5212	0.8901
No log	21.0	294	0.5421	0.8791
No log	22.0	308	0.5439	0.8791
No log	23.0	322	0.5516	0.8791
No log	24.0	336	0.5544	0.8791
No log	25.0	350	0.5441	0.8901
No log	26.0	364	0.5497	0.8901
No log	27.0	378	0.5502	0.8791
No log	28.0	392	0.5345	0.8901
No log	29.0	406	0.5444	0.8901
No log	30.0	420	0.5489	0.8901
No log	31.0	434	0.5838	0.8681
No log	32.0	448	0.5444	0.9011
No log	33.0	462	0.6005	0.8681
No log	34.0	476	0.5633	0.8901
No log	35.0	490	0.5701	0.8791
0.4178	36.0	504	0.5805	0.8901
0.4178	37.0	518	0.5919	0.8791
0.4178	38.0	532	0.5729	0.8901
0.4178	39.0	546	0.5805	0.8901
0.4178	40.0	560	0.5940	0.8901
0.4178	41.0	574	0.5816	0.8901
0.4178	42.0	588	0.5754	0.8901
0.4178	43.0	602	0.5838	0.8901
0.4178	44.0	616	0.5901	0.8901
0.4178	45.0	630	0.5942	0.8901
0.4178	46.0	644	0.5922	0.8901
0.4178	47.0	658	0.5908	0.8901
0.4178	48.0	672	0.5921	0.8901
0.4178	49.0	686	0.5916	0.8901
0.4178	50.0	700	0.6024	0.8901
0.4178	51.0	714	0.6012	0.8901
0.4178	52.0	728	0.5998	0.8901
0.4178	53.0	742	0.6031	0.8901
0.4178	54.0	756	0.5967	0.8901
0.4178	55.0	770	0.5950	0.8901
0.4178	56.0	784	0.6018	0.8901
0.4178	57.0	798	0.5989	0.8901
0.4178	58.0	812	0.5945	0.8901
0.4178	59.0	826	0.5948	0.8901
0.4178	60.0	840	0.5930	0.8901
0.4178	61.0	854	0.5961	0.8901
0.4178	62.0	868	0.6010	0.8901
0.4178	63.0	882	0.5973	0.8901
0.4178	64.0	896	0.5997	0.8901
0.4178	65.0	910	0.6016	0.8901
0.4178	66.0	924	0.6069	0.8901
0.4178	67.0	938	0.6095	0.8901
0.4178	68.0	952	0.6117	0.8901
0.4178	69.0	966	0.6160	0.8901
0.4178	70.0	980	0.6166	0.8901
0.4178	71.0	994	0.6177	0.8901
0.0153	72.0	1008	0.6172	0.8901
0.0153	73.0	1022	0.6190	0.8901
0.0153	74.0	1036	0.6213	0.8901
0.0153	75.0	1050	0.6220	0.8901
0.0153	76.0	1064	0.6204	0.8901
0.0153	77.0	1078	0.6193	0.8901
0.0153	78.0	1092	0.6198	0.8901
0.0153	79.0	1106	0.6235	0.8901
0.0153	80.0	1120	0.6260	0.8901
0.0153	81.0	1134	0.6271	0.8901
0.0153	82.0	1148	0.6290	0.8901
0.0153	83.0	1162	0.6288	0.8901
0.0153	84.0	1176	0.6298	0.8901
0.0153	85.0	1190	0.6301	0.8901
0.0153	86.0	1204	0.6324	0.8901
0.0153	87.0	1218	0.6332	0.8901
0.0153	88.0	1232	0.6333	0.8901
0.0153	89.0	1246	0.6347	0.8901
0.0153	90.0	1260	0.6337	0.8901
0.0153	91.0	1274	0.6332	0.8901
0.0153	92.0	1288	0.6329	0.8901
0.0153	93.0	1302	0.6316	0.8901
0.0153	94.0	1316	0.6315	0.8901
0.0153	95.0	1330	0.6312	0.8901
0.0153	96.0	1344	0.6310	0.8901
0.0153	97.0	1358	0.6305	0.8901
0.0153	98.0	1372	0.6306	0.8901
0.0153	99.0	1386	0.6307	0.8901
0.0153	100.0	1400	0.6307	0.8901

Framework versions

• Transformers 4.37.2
• Pytorch 2.3.1
• Datasets 2.19.1
• Tokenizers 0.15.1