Anwaarma/BP-MM05

BP-S02andInt03

This model is a fine-tuned version of Anwaarma/BP-test4 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.4031
• Accuracy: 0.82
• F1: 0.8097

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: 13

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
No log	0.0	50	1.1241	0.54	0.4220
No log	0.01	100	0.8697	0.51	0.4402
No log	0.01	150	0.7063	0.37	0.3740
No log	0.02	200	0.6895	0.51	0.4184
No log	0.02	250	0.6880	0.52	0.4467
No log	0.02	300	0.6874	0.52	0.4778
No log	0.03	350	0.6842	0.52	0.4778
No log	0.03	400	0.6889	0.5	0.4491
No log	0.04	450	0.6727	0.55	0.5398
0.7977	0.04	500	0.6617	0.59	0.5877
0.7977	0.04	550	0.6514	0.59	0.5877
0.7977	0.05	600	0.6597	0.59	0.5877
0.7977	0.05	650	0.6322	0.59	0.5877
0.7977	0.06	700	0.5898	0.57	0.5655
0.7977	0.06	750	0.5406	0.7	0.7015
0.7977	0.06	800	0.4813	0.8	0.7862
0.7977	0.07	850	0.4706	0.8	0.7862
0.7977	0.07	900	0.4743	0.79	0.7768
0.7977	0.08	950	0.4578	0.8	0.7862
0.5646	0.08	1000	0.4571	0.8	0.7862
0.5646	0.08	1050	0.4536	0.8	0.7862
0.5646	0.09	1100	0.4461	0.8	0.7862
0.5646	0.09	1150	0.4451	0.8	0.7862
0.5646	0.1	1200	0.4398	0.81	0.7956
0.5646	0.1	1250	0.4360	0.8	0.7862
0.5646	0.1	1300	0.4325	0.81	0.7956
0.5646	0.11	1350	0.4316	0.81	0.7956
0.5646	0.11	1400	0.4310	0.81	0.7956
0.5646	0.12	1450	0.4301	0.81	0.7956
0.4672	0.12	1500	0.4275	0.81	0.7956
0.4672	0.12	1550	0.4271	0.8	0.7862
0.4672	0.13	1600	0.4258	0.81	0.7956
0.4672	0.13	1650	0.4211	0.81	0.7956
0.4672	0.14	1700	0.4154	0.82	0.8097
0.4672	0.14	1750	0.4153	0.81	0.7956
0.4672	0.14	1800	0.4120	0.81	0.7956
0.4672	0.15	1850	0.4134	0.8	0.7862
0.4672	0.15	1900	0.4119	0.8	0.7862
0.4672	0.16	1950	0.4119	0.82	0.8097
0.4371	0.16	2000	0.4094	0.82	0.8097
0.4371	0.16	2050	0.4113	0.82	0.8097
0.4371	0.17	2100	0.4136	0.83	0.8259
0.4371	0.17	2150	0.4096	0.82	0.8097
0.4371	0.18	2200	0.4116	0.82	0.8097
0.4371	0.18	2250	0.4039	0.82	0.8097
0.4371	0.18	2300	0.4044	0.82	0.8097
0.4371	0.19	2350	0.4031	0.82	0.8097

Framework versions

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