Merged-Server-praj

This model is a fine-tuned version of Anwaarma/BP-server02andinteger03 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6453
• Accuracy: 0.619
• F1: 0.7647

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: 4e-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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.0	50	0.6887	0.518	0.4747
No log	0.0	100	0.6872	0.539	0.4913
No log	0.01	150	0.6870	0.556	0.5124
No log	0.01	200	0.6845	0.554	0.5490
No log	0.01	250	0.6823	0.555	0.5509
No log	0.01	300	0.6818	0.545	0.5339
No log	0.02	350	0.6841	0.561	0.5207
No log	0.02	400	0.6845	0.566	0.5402
No log	0.02	450	0.6792	0.566	0.5650
0.6886	0.02	500	0.6808	0.532	0.4867
0.6886	0.02	550	0.6821	0.527	0.4643
0.6886	0.03	600	0.6777	0.577	0.5729
0.6886	0.03	650	0.6758	0.58	0.58
0.6886	0.03	700	0.6762	0.585	0.5793
0.6886	0.03	750	0.6743	0.577	0.5731
0.6886	0.04	800	0.6731	0.577	0.5762
0.6886	0.04	850	0.6762	0.582	0.5534
0.6886	0.04	900	0.6749	0.568	0.5458
0.6886	0.04	950	0.6739	0.578	0.5746
0.6819	0.04	1000	0.6715	0.588	0.588
0.6819	0.05	1050	0.6741	0.579	0.5524
0.6819	0.05	1100	0.6712	0.592	0.5894
0.6819	0.05	1150	0.6692	0.594	0.5905
0.6819	0.05	1200	0.6683	0.597	0.5957
0.6819	0.06	1250	0.6757	0.566	0.5209
0.6819	0.06	1300	0.6676	0.6	0.5882
0.6819	0.06	1350	0.6655	0.598	0.5943
0.6819	0.06	1400	0.6671	0.584	0.5724
0.6819	0.06	1450	0.6631	0.587	0.5812
0.6763	0.07	1500	0.6614	0.62	0.6140
0.6763	0.07	1550	0.6610	0.603	0.6018
0.6763	0.07	1600	0.6615	0.589	0.5843
0.6763	0.07	1650	0.6597	0.633	0.6326
0.6763	0.08	1700	0.6561	0.607	0.6025
0.6763	0.08	1750	0.6515	0.632	0.6318
0.6763	0.08	1800	0.6509	0.635	0.6323
0.6763	0.08	1850	0.6538	0.604	0.5903
0.6763	0.08	1900	0.6483	0.632	0.632
0.6763	0.09	1950	0.6513	0.616	0.6142
0.6659	0.09	2000	0.6475	0.618	0.6166
0.6659	0.09	2050	0.6443	0.613	0.6106
0.6659	0.09	2100	0.6482	0.629	0.6261
0.6659	0.1	2150	0.6552	0.604	0.5837
0.6659	0.1	2200	0.6492	0.618	0.6042
0.6659	0.1	2250	0.6441	0.63	0.6256
0.6659	0.1	2300	0.6447	0.63	0.6293
0.6659	0.1	2350	0.6429	0.633	0.6317
0.6659	0.11	2400	0.6450	0.62	0.6200
0.6659	0.11	2450	0.6480	0.639	0.6358
0.6577	0.11	2500	0.6480	0.601	0.5844
0.6577	0.11	2550	0.6422	0.641	0.6402
0.6577	0.11	2600	0.6407	0.623	0.6177
0.6577	0.12	2650	0.6393	0.634	0.6336
0.6577	0.12	2700	0.6405	0.635	0.6320
0.6577	0.12	2750	0.6422	0.642	0.6413
0.6577	0.12	2800	0.6355	0.632	0.6271
0.6577	0.13	2850	0.6351	0.622	0.6150
0.6577	0.13	2900	0.6331	0.658	0.6569
0.6577	0.13	2950	0.6352	0.656	0.6548
0.6569	0.13	3000	0.6385	0.609	0.5927
0.6569	0.13	3050	0.6307	0.645	0.6449
0.6569	0.14	3100	0.6304	0.639	0.6324
0.6569	0.14	3150	0.6268	0.654	0.6540
0.6569	0.14	3200	0.6297	0.641	0.6402
0.6569	0.14	3250	0.6293	0.651	0.6488
0.6569	0.15	3300	0.6251	0.66	0.66
0.6569	0.15	3350	0.6207	0.653	0.6513
0.6569	0.15	3400	0.6184	0.649	0.6470
0.6569	0.15	3450	0.6176	0.653	0.6523
0.6394	0.15	3500	0.6195	0.654	0.6527
0.6394	0.16	3550	0.6172	0.655	0.6535
0.6394	0.16	3600	0.6168	0.659	0.6590
0.6394	0.16	3650	0.6138	0.664	0.6631
0.6394	0.16	3700	0.6228	0.659	0.6478
0.6394	0.17	3750	0.6117	0.662	0.6608
0.6394	0.17	3800	0.6121	0.645	0.6443
0.6394	0.17	3850	0.6099	0.652	0.6515
0.6394	0.17	3900	0.6128	0.657	0.6515
0.6394	0.17	3950	0.6103	0.65	0.6499
0.6366	0.18	4000	0.6149	0.652	0.6447
0.6366	0.18	4050	0.6111	0.652	0.6518
0.6366	0.18	4100	0.6098	0.651	0.6502
0.6366	0.18	4150	0.6072	0.666	0.6640
0.6366	0.19	4200	0.6065	0.669	0.6646
0.6366	0.19	4250	0.6057	0.658	0.6531
0.6366	0.19	4300	0.6044	0.667	0.6634
0.6366	0.19	4350	0.6061	0.656	0.6451
0.6366	0.19	4400	0.5962	0.666	0.6660
0.6366	0.2	4450	0.5936	0.664	0.6637
0.6275	0.2	4500	0.5978	0.651	0.6508
0.6275	0.2	4550	0.5998	0.664	0.6601
0.6275	0.2	4600	0.5967	0.657	0.6560
0.6275	0.21	4650	0.5931	0.671	0.6708
0.6275	0.21	4700	0.5953	0.686	0.6856
0.6275	0.21	4750	0.6119	0.643	0.6331
0.6275	0.21	4800	0.6035	0.657	0.6497
0.6275	0.21	4850	0.5864	0.676	0.6756
0.6275	0.22	4900	0.5876	0.681	0.6809
0.6275	0.22	4950	0.5864	0.677	0.6762
0.6279	0.22	5000	0.5876	0.677	0.6770
0.6279	0.22	5050	0.5876	0.666	0.6636
0.6279	0.23	5100	0.5848	0.675	0.6745
0.6279	0.23	5150	0.5904	0.672	0.6719
0.6279	0.23	5200	0.5854	0.672	0.6718
0.6279	0.23	5250	0.5864	0.673	0.6709

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.0
• Tokenizers 0.15.0