INT03

This model is a fine-tuned version of prajjwal1/bert-tiny on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0169
• Accuracy: 1.0
• F1: 1.0

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: 5e-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	0.6888	0.62	0.5657
No log	0.01	100	0.6817	0.66	0.5965
No log	0.01	150	0.6004	0.86	0.8553
No log	0.02	200	0.4136	0.87	0.8651
No log	0.02	250	0.3550	0.89	0.8889
No log	0.03	300	0.3241	0.89	0.8889
No log	0.03	350	0.3144	0.89	0.8889
No log	0.04	400	0.3146	0.89	0.8889
No log	0.04	450	0.2985	0.89	0.8889
0.5219	0.05	500	0.2604	0.92	0.92
0.5219	0.05	550	0.2242	0.92	0.9202
0.5219	0.06	600	0.1976	0.92	0.9197
0.5219	0.06	650	0.1800	0.93	0.9302
0.5219	0.07	700	0.1685	0.93	0.9302
0.5219	0.07	750	0.1706	0.93	0.9303
0.5219	0.08	800	0.1532	0.93	0.9303
0.5219	0.08	850	0.1411	0.93	0.9303
0.5219	0.09	900	0.1070	0.98	0.9799
0.5219	0.09	950	0.0970	0.96	0.9601
0.2869	0.1	1000	0.0775	0.96	0.9601
0.2869	0.1	1050	0.0789	0.97	0.9701
0.2869	0.11	1100	0.0546	0.98	0.98
0.2869	0.11	1150	0.0789	0.98	0.9800
0.2869	0.12	1200	0.0425	0.99	0.9900
0.2869	0.12	1250	0.0443	0.99	0.9900
0.2869	0.13	1300	0.0340	0.99	0.9900
0.2869	0.13	1350	0.0649	0.97	0.9700
0.2869	0.14	1400	0.0241	1.0	1.0
0.2869	0.14	1450	0.0215	1.0	1.0
0.1754	0.15	1500	0.0146	1.0	1.0
0.1754	0.15	1550	0.0125	1.0	1.0
0.1754	0.16	1600	0.0122	1.0	1.0
0.1754	0.16	1650	0.0110	1.0	1.0
0.1754	0.17	1700	0.0092	1.0	1.0
0.1754	0.17	1750	0.0117	1.0	1.0

Framework versions

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