S02

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

• Loss: 0.5643
• Accuracy: 0.82
• F1: 0.9011

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: 20

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.0	50	0.5790	0.6	0.5992
No log	0.01	100	0.5691	0.65	0.6505
No log	0.01	150	0.5678	0.65	0.6505
No log	0.01	200	0.5621	0.68	0.6773
No log	0.02	250	0.5666	0.63	0.6303
No log	0.02	300	0.5721	0.65	0.6463
No log	0.02	350	0.5533	0.63	0.6260
No log	0.03	400	0.5614	0.62	0.6105
No log	0.03	450	0.5756	0.62	0.6181
0.5985	0.03	500	0.5666	0.6	0.5947
0.5985	0.04	550	0.5613	0.64	0.6406
0.5985	0.04	600	0.5541	0.63	0.6306
0.5985	0.04	650	0.5571	0.62	0.6192
0.5985	0.05	700	0.5536	0.62	0.6192
0.5985	0.05	750	0.5614	0.63	0.6306
0.5985	0.05	800	0.5667	0.63	0.6297
0.5985	0.06	850	0.5466	0.66	0.6600
0.5985	0.06	900	0.5532	0.66	0.6593
0.5985	0.06	950	0.5482	0.67	0.6630
0.5855	0.07	1000	0.5837	0.63	0.6220
0.5855	0.07	1050	0.5368	0.67	0.6705
0.5855	0.07	1100	0.5793	0.62	0.6167
0.5855	0.08	1150	0.5694	0.63	0.6276
0.5855	0.08	1200	0.5520	0.63	0.6306
0.5855	0.09	1250	0.5572	0.66	0.6593
0.5855	0.09	1300	0.5706	0.62	0.6150
0.5855	0.09	1350	0.5694	0.66	0.6593
0.5855	0.1	1400	0.5559	0.65	0.6497
0.5855	0.1	1450	0.5515	0.67	0.6705
0.5777	0.1	1500	0.5447	0.64	0.6393
0.5777	0.11	1550	0.5453	0.65	0.6502
0.5777	0.11	1600	0.5575	0.64	0.6400
0.5777	0.11	1650	0.5498	0.66	0.6584
0.5777	0.12	1700	0.5620	0.66	0.6604
0.5777	0.12	1750	0.5734	0.67	0.6702
0.5777	0.12	1800	0.5561	0.66	0.6593
0.5777	0.13	1850	0.5376	0.67	0.6649
0.5777	0.13	1900	0.5652	0.65	0.6505
0.5777	0.13	1950	0.5414	0.67	0.6689
0.575	0.14	2000	0.5340	0.67	0.6665
0.575	0.14	2050	0.5393	0.68	0.6794
0.575	0.14	2100	0.5253	0.7	0.6994
0.575	0.15	2150	0.5334	0.69	0.6834
0.575	0.15	2200	0.5395	0.68	0.6773
0.575	0.15	2250	0.5426	0.65	0.6446
0.575	0.16	2300	0.5523	0.64	0.6370
0.575	0.16	2350	0.5378	0.68	0.6804
0.575	0.16	2400	0.5375	0.67	0.6649
0.575	0.17	2450	0.5378	0.68	0.6742
0.556	0.17	2500	0.5491	0.69	0.6867
0.556	0.17	2550	0.5347	0.66	0.6517
0.556	0.18	2600	0.5325	0.69	0.6852
0.556	0.18	2650	0.5490	0.68	0.6794
0.556	0.18	2700	0.5313	0.7	0.7005
0.556	0.19	2750	0.5451	0.65	0.6314
0.556	0.19	2800	0.5506	0.64	0.6312
0.556	0.19	2850	0.5539	0.65	0.6497
0.556	0.2	2900	0.5601	0.66	0.6604
0.556	0.2	2950	0.5530	0.67	0.6705

Framework versions

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