TestForColab

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: 0.6515
• Accuracy: 0.56
• F1: 0.5579

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	0.6897	0.54	0.3787
No log	0.01	100	0.6899	0.6	0.5926
No log	0.01	150	0.6952	0.46	0.2899
No log	0.01	200	0.6874	0.63	0.6194
No log	0.02	250	0.6849	0.64	0.6092
No log	0.02	300	0.6929	0.46	0.2899
No log	0.02	350	0.6830	0.6	0.5390
No log	0.03	400	0.6821	0.54	0.3787
No log	0.03	450	0.6812	0.63	0.6095
0.6924	0.03	500	0.6806	0.62	0.6077
0.6924	0.04	550	0.6770	0.62	0.5969
0.6924	0.04	600	0.6805	0.58	0.5746
0.6924	0.04	650	0.6800	0.59	0.5857
0.6924	0.05	700	0.6732	0.63	0.6008
0.6924	0.05	750	0.6820	0.56	0.5387
0.6924	0.05	800	0.6652	0.64	0.6253
0.6924	0.06	850	0.6634	0.59	0.5896
0.6924	0.06	900	0.6604	0.61	0.6103
0.6924	0.06	950	0.6733	0.62	0.5936
0.6842	0.07	1000	0.6590	0.65	0.6176
0.6842	0.07	1050	0.6549	0.6	0.6005
0.6842	0.07	1100	0.6521	0.63	0.6242
0.6842	0.08	1150	0.6524	0.61	0.6015
0.6842	0.08	1200	0.6587	0.57	0.5634
0.6842	0.09	1250	0.6515	0.56	0.5579

Framework versions

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