results

This model is a fine-tuned version of on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4920
• Accuracy: 0.9437

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: 0.001
• train_batch_size: 32
• eval_batch_size: 32
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 150
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	143	0.8632	0.8707
No log	2.0	286	0.8353	0.8619
No log	3.0	429	1.0302	0.8452
0.3082	4.0	572	0.7561	0.8760
0.3082	5.0	715	0.6557	0.8804
0.3082	6.0	858	0.6932	0.8716
0.2777	7.0	1001	1.0559	0.8329
0.2777	8.0	1144	0.6415	0.8804
0.2777	9.0	1287	0.9046	0.8478
0.2777	10.0	1430	0.7140	0.8575
0.2421	11.0	1573	0.6330	0.8813
0.2421	12.0	1716	0.5947	0.8681
0.2421	13.0	1859	1.5674	0.7546
0.2146	14.0	2002	0.7706	0.8584
0.2146	15.0	2145	0.6218	0.8857
0.2146	16.0	2288	0.6246	0.8901
0.2146	17.0	2431	0.5434	0.8795
0.1904	18.0	2574	0.4420	0.9006
0.1904	19.0	2717	0.6535	0.8839
0.1904	20.0	2860	0.7375	0.8558
0.1803	21.0	3003	0.6950	0.8593
0.1803	22.0	3146	0.6608	0.8734
0.1803	23.0	3289	0.5115	0.8962
0.1803	24.0	3432	0.6611	0.8821
0.1649	25.0	3575	0.6603	0.8654
0.1649	26.0	3718	0.4735	0.9077
0.1649	27.0	3861	0.6741	0.8690
0.1443	28.0	4004	0.5726	0.8857
0.1443	29.0	4147	0.6853	0.8874
0.1443	30.0	4290	0.7509	0.8769
0.1443	31.0	4433	0.7393	0.8637
0.1586	32.0	4576	0.5145	0.9024
0.1586	33.0	4719	0.6831	0.8786
0.1586	34.0	4862	0.5655	0.8971
0.1502	35.0	5005	0.4671	0.9147
0.1502	36.0	5148	0.5472	0.8989
0.1502	37.0	5291	0.6309	0.8839
0.1502	38.0	5434	0.4712	0.9006
0.1442	39.0	5577	0.7001	0.8795
0.1442	40.0	5720	0.4912	0.8945
0.1442	41.0	5863	0.5469	0.9068
0.1067	42.0	6006	0.6218	0.8883
0.1067	43.0	6149	0.6146	0.8918
0.1067	44.0	6292	0.4521	0.9173
0.1067	45.0	6435	0.4191	0.9244
0.1080	46.0	6578	0.6703	0.8874
0.1080	47.0	6721	0.6333	0.8857
0.1080	48.0	6864	0.5952	0.9059
0.0972	49.0	7007	0.5189	0.9173
0.0972	50.0	7150	0.4723	0.9077
0.0972	51.0	7293	0.6105	0.9015
0.0972	52.0	7436	0.5164	0.9103
0.1084	53.0	7579	0.6370	0.8901
0.1084	54.0	7722	0.5392	0.9077
0.1084	55.0	7865	0.5462	0.9120
0.0945	56.0	8008	0.6324	0.8980
0.0945	57.0	8151	0.5393	0.9077
0.0945	58.0	8294	0.6138	0.9041
0.0945	59.0	8437	0.5659	0.9112
0.0713	60.0	8580	0.6440	0.9050
0.0713	61.0	8723	0.6189	0.8989
0.0713	62.0	8866	0.5161	0.9041
0.0858	63.0	9009	0.6661	0.9006
0.0858	64.0	9152	0.4703	0.9147
0.0858	65.0	9295	0.5455	0.9024
0.0858	66.0	9438	0.4444	0.9200
0.0859	67.0	9581	0.4706	0.9208
0.0859	68.0	9724	0.5447	0.9077
0.0859	69.0	9867	0.4518	0.9244
0.0658	70.0	10010	0.5719	0.9085
0.0658	71.0	10153	0.5937	0.9147
0.0658	72.0	10296	0.6555	0.9050
0.0658	73.0	10439	0.5324	0.9103
0.0616	74.0	10582	0.4328	0.9296
0.0616	75.0	10725	0.5411	0.9173
0.0616	76.0	10868	0.5422	0.9033
0.0546	77.0	11011	0.4701	0.9244
0.0546	78.0	11154	0.5527	0.9112
0.0546	79.0	11297	0.5769	0.9138
0.0546	80.0	11440	0.5977	0.9112
0.0512	81.0	11583	0.4879	0.9208
0.0512	82.0	11726	0.4947	0.9261
0.0512	83.0	11869	0.5727	0.9208
0.0439	84.0	12012	0.6155	0.9164
0.0439	85.0	12155	0.5573	0.9208
0.0439	86.0	12298	0.5852	0.9103
0.0439	87.0	12441	0.6440	0.9077
0.0456	88.0	12584	0.5488	0.9208
0.0456	89.0	12727	0.5731	0.9182
0.0456	90.0	12870	0.5297	0.9279
0.0336	91.0	13013	0.4989	0.9252
0.0336	92.0	13156	0.5171	0.9235
0.0336	93.0	13299	0.5451	0.9200
0.0336	94.0	13442	0.6079	0.9129
0.0294	95.0	13585	0.5456	0.9182
0.0294	96.0	13728	0.6461	0.9120
0.0294	97.0	13871	0.5759	0.9191
0.0286	98.0	14014	0.5699	0.9252
0.0286	99.0	14157	0.5818	0.9244
0.0286	100.0	14300	0.5410	0.9261
0.0286	101.0	14443	0.4661	0.9323
0.0275	102.0	14586	0.5415	0.9314
0.0275	103.0	14729	0.6667	0.9173
0.0275	104.0	14872	0.5280	0.9279
0.0403	105.0	15015	0.5211	0.9296
0.0403	106.0	15158	0.5350	0.9340
0.0403	107.0	15301	0.6051	0.9208
0.0403	108.0	15444	0.5091	0.9261
0.0224	109.0	15587	0.6498	0.9217
0.0224	110.0	15730	0.5658	0.9182
0.0224	111.0	15873	0.5365	0.9235
0.0154	112.0	16016	0.5798	0.9200
0.0154	113.0	16159	0.5772	0.9296
0.0154	114.0	16302	0.5040	0.9323
0.0154	115.0	16445	0.5339	0.9305
0.0208	116.0	16588	0.5409	0.9252
0.0208	117.0	16731	0.5635	0.9270
0.0208	118.0	16874	0.5262	0.9288
0.0212	119.0	17017	0.5195	0.9349
0.0212	120.0	17160	0.5011	0.9376
0.0212	121.0	17303	0.5140	0.9305
0.0212	122.0	17446	0.5398	0.9296
0.0165	123.0	17589	0.5441	0.9340
0.0165	124.0	17732	0.5013	0.9323
0.0165	125.0	17875	0.5013	0.9358
0.0087	126.0	18018	0.4601	0.9420
0.0087	127.0	18161	0.5191	0.9402
0.0087	128.0	18304	0.5713	0.9279
0.0087	129.0	18447	0.4783	0.9393
0.0072	130.0	18590	0.4957	0.9367
0.0072	131.0	18733	0.5092	0.9376
0.0072	132.0	18876	0.5512	0.9332
0.0065	133.0	19019	0.5053	0.9367
0.0065	134.0	19162	0.4775	0.9428
0.0065	135.0	19305	0.5195	0.9358
0.0065	136.0	19448	0.4970	0.9376
0.0183	137.0	19591	0.5058	0.9332
0.0183	138.0	19734	0.5133	0.9340
0.0183	139.0	19877	0.4766	0.9358
0.0172	140.0	20020	0.4806	0.9402
0.0172	141.0	20163	0.5278	0.9376
0.0172	142.0	20306	0.4747	0.9428
0.0172	143.0	20449	0.5242	0.9349
0.0158	144.0	20592	0.4927	0.9411
0.0158	145.0	20735	0.4873	0.9402
0.0158	146.0	20878	0.4989	0.9340
0.0036	147.0	21021	0.5063	0.9384
0.0036	148.0	21164	0.4955	0.9393
0.0036	149.0	21307	0.4920	0.9437
0.0036	150.0	21450	0.4912	0.9393

Framework versions

• Transformers 5.0.0.dev0
• Pytorch 2.9.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.1