Anwaarma/BP-SERVER

BP-S02andInt03andMM05

This model is a fine-tuned version of Anwaarma/BP-S02andInt03 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.5994
• Accuracy: 0.64
• F1: 0.6335

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.0	50	0.7057	0.5	0.4909
No log	0.01	100	0.6936	0.52	0.5206
No log	0.01	150	0.6981	0.48	0.4673
No log	0.01	200	0.6958	0.51	0.5107
No log	0.02	250	0.6921	0.54	0.5378
No log	0.02	300	0.6981	0.45	0.4150
No log	0.02	350	0.6895	0.53	0.5226
No log	0.03	400	0.6876	0.54	0.4112
No log	0.03	450	0.6900	0.53	0.5284
0.7105	0.03	500	0.6903	0.52	0.52
0.7105	0.04	550	0.6892	0.52	0.52
0.7105	0.04	600	0.6920	0.5	0.4990
0.7105	0.04	650	0.6912	0.5	0.5
0.7105	0.05	700	0.6874	0.53	0.5250
0.7105	0.05	750	0.6893	0.5	0.4990
0.7105	0.05	800	0.6814	0.58	0.5441
0.7105	0.06	850	0.6827	0.52	0.5206
0.7105	0.06	900	0.6791	0.55	0.5429
0.7105	0.06	950	0.6855	0.53	0.5169
0.692	0.07	1000	0.6745	0.56	0.4930
0.692	0.07	1050	0.6668	0.55	0.5503
0.692	0.07	1100	0.6601	0.59	0.5673
0.692	0.08	1150	0.6514	0.59	0.5714
0.692	0.08	1200	0.6679	0.59	0.5813
0.692	0.09	1250	0.6513	0.62	0.6181
0.692	0.09	1300	0.6462	0.6	0.5947
0.692	0.09	1350	0.6492	0.63	0.6243
0.692	0.1	1400	0.6375	0.58	0.5664
0.692	0.1	1450	0.6302	0.62	0.6192
0.6793	0.1	1500	0.6233	0.57	0.5654
0.6793	0.11	1550	0.6308	0.6	0.5992
0.6793	0.11	1600	0.6336	0.62	0.6205
0.6793	0.11	1650	0.6205	0.68	0.68
0.6793	0.12	1700	0.6061	0.66	0.6605
0.6793	0.12	1750	0.6197	0.65	0.6488
0.6793	0.12	1800	0.6090	0.66	0.6593
0.6793	0.13	1850	0.5986	0.59	0.5886
0.6793	0.13	1900	0.5990	0.66	0.6593
0.6793	0.13	1950	0.5995	0.66	0.6600
0.6632	0.14	2000	0.6033	0.6	0.5966
0.6632	0.14	2050	0.6003	0.66	0.6604
0.6632	0.14	2100	0.6088	0.62	0.6206
0.6632	0.15	2150	0.6178	0.65	0.6463
0.6632	0.15	2200	0.6003	0.63	0.6303
0.6632	0.15	2250	0.6072	0.61	0.6103
0.6632	0.16	2300	0.6160	0.68	0.6742
0.6632	0.16	2350	0.6056	0.62	0.6192
0.6632	0.16	2400	0.6100	0.62	0.6192
0.6632	0.17	2450	0.6175	0.67	0.6630
0.6485	0.17	2500	0.6070	0.66	0.6584
0.6485	0.17	2550	0.6090	0.66	0.6556
0.6485	0.18	2600	0.6123	0.59	0.5906
0.6485	0.18	2650	0.6245	0.64	0.6393
0.6485	0.18	2700	0.6049	0.66	0.6593
0.6485	0.19	2750	0.5994	0.64	0.6335

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0