categor_ai_23_cats

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: 1.6794
• Accuracy: 0.7426

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	58	2.7413	0.2970
No log	2.0	116	2.2790	0.4208
No log	3.0	174	1.9305	0.5718
No log	4.0	232	1.6436	0.6238
No log	5.0	290	1.4104	0.6708
No log	6.0	348	1.2412	0.6931
No log	7.0	406	1.1342	0.7376
No log	8.0	464	1.0672	0.7302
1.5793	9.0	522	1.0224	0.7228
1.5793	10.0	580	1.0148	0.7302
1.5793	11.0	638	1.0117	0.7351
1.5793	12.0	696	1.0580	0.7153
1.5793	13.0	754	1.1021	0.7104
1.5793	14.0	812	1.1037	0.7327
1.5793	15.0	870	1.1391	0.7351
1.5793	16.0	928	1.1627	0.7252
1.5793	17.0	986	1.1568	0.7450
0.1406	18.0	1044	1.2121	0.7203
0.1406	19.0	1102	1.2466	0.7302
0.1406	20.0	1160	1.2464	0.7327
0.1406	21.0	1218	1.2832	0.7302
0.1406	22.0	1276	1.2930	0.7277
0.1406	23.0	1334	1.3046	0.7351
0.1406	24.0	1392	1.3081	0.7376
0.1406	25.0	1450	1.3347	0.7351
0.0133	26.0	1508	1.3463	0.7376
0.0133	27.0	1566	1.3575	0.7351
0.0133	28.0	1624	1.3602	0.7401
0.0133	29.0	1682	1.3803	0.7327
0.0133	30.0	1740	1.4009	0.7302
0.0133	31.0	1798	1.3954	0.7351
0.0133	32.0	1856	1.4164	0.7277
0.0133	33.0	1914	1.3861	0.7401
0.0133	34.0	1972	1.4193	0.7376
0.0067	35.0	2030	1.4369	0.7327
0.0067	36.0	2088	1.4436	0.7327
0.0067	37.0	2146	1.4609	0.7327
0.0067	38.0	2204	1.4718	0.7302
0.0067	39.0	2262	1.4617	0.7302
0.0067	40.0	2320	1.4766	0.7401
0.0067	41.0	2378	1.4664	0.7327
0.0067	42.0	2436	1.5111	0.7351
0.0067	43.0	2494	1.5158	0.7401
0.0046	44.0	2552	1.5137	0.7327
0.0046	45.0	2610	1.5083	0.7327
0.0046	46.0	2668	1.5127	0.7302
0.0046	47.0	2726	1.5264	0.7302
0.0046	48.0	2784	1.5365	0.7327
0.0046	49.0	2842	1.5398	0.7351
0.0046	50.0	2900	1.5535	0.7302
0.0046	51.0	2958	1.5396	0.7401
0.0033	52.0	3016	1.5432	0.7376
0.0033	53.0	3074	1.6068	0.7228
0.0033	54.0	3132	1.5997	0.7277
0.0033	55.0	3190	1.5685	0.7401
0.0033	56.0	3248	1.5744	0.7302
0.0033	57.0	3306	1.5825	0.7327
0.0033	58.0	3364	1.5790	0.7351
0.0033	59.0	3422	1.5820	0.7327
0.0033	60.0	3480	1.5835	0.7327
0.0029	61.0	3538	1.5778	0.7351
0.0029	62.0	3596	1.5949	0.7302
0.0029	63.0	3654	1.5996	0.7376
0.0029	64.0	3712	1.6261	0.7302
0.0029	65.0	3770	1.5951	0.7351
0.0029	66.0	3828	1.6197	0.7426
0.0029	67.0	3886	1.6085	0.7376
0.0029	68.0	3944	1.6186	0.7351
0.0027	69.0	4002	1.6241	0.7376
0.0027	70.0	4060	1.6297	0.7351
0.0027	71.0	4118	1.6347	0.7327
0.0027	72.0	4176	1.6333	0.7327
0.0027	73.0	4234	1.6320	0.7327
0.0027	74.0	4292	1.6335	0.7302
0.0027	75.0	4350	1.6304	0.7351
0.0027	76.0	4408	1.6387	0.7351
0.0027	77.0	4466	1.6369	0.7376
0.0026	78.0	4524	1.6383	0.7376
0.0026	79.0	4582	1.6404	0.7376
0.0026	80.0	4640	1.6351	0.7351
0.0026	81.0	4698	1.6708	0.7277
0.0026	82.0	4756	1.6695	0.7302
0.0026	83.0	4814	1.6668	0.7277
0.0026	84.0	4872	1.6695	0.7277
0.0026	85.0	4930	1.6804	0.7277
0.0026	86.0	4988	1.6801	0.7277
0.0024	87.0	5046	1.6762	0.7327
0.0024	88.0	5104	1.6796	0.7302
0.0024	89.0	5162	1.6846	0.7302
0.0024	90.0	5220	1.6797	0.7277
0.0024	91.0	5278	1.6864	0.7302
0.0024	92.0	5336	1.6906	0.7302
0.0024	93.0	5394	1.6849	0.7302
0.0024	94.0	5452	1.6792	0.7351
0.0019	95.0	5510	1.6780	0.7351
0.0019	96.0	5568	1.6780	0.7302
0.0019	97.0	5626	1.6786	0.7351
0.0019	98.0	5684	1.6795	0.7351
0.0019	99.0	5742	1.6795	0.7401
0.0019	100.0	5800	1.6794	0.7426

Framework versions

• Transformers 4.44.1
• Pytorch 2.3.1
• Datasets 2.19.1
• Tokenizers 0.19.1