test_trainer

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

• Loss: 0.4153
• Accuracy: 0.819

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 25

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	125	0.6959	0.451
No log	2.0	250	0.6876	0.561
No log	3.0	375	0.6825	0.543
0.6936	4.0	500	0.6629	0.617
0.6936	5.0	625	0.6337	0.661
0.6936	6.0	750	0.6049	0.674
0.6936	7.0	875	0.5729	0.706
0.6247	8.0	1000	0.5497	0.71
0.6247	9.0	1125	0.5248	0.733
0.6247	10.0	1250	0.5047	0.74
0.6247	11.0	1375	0.4837	0.765
0.5062	12.0	1500	0.4711	0.766
0.5062	13.0	1625	0.4593	0.784
0.5062	14.0	1750	0.4504	0.788
0.5062	15.0	1875	0.4430	0.793
0.4395	16.0	2000	0.4341	0.8
0.4395	17.0	2125	0.4310	0.8
0.4395	18.0	2250	0.4264	0.807
0.4395	19.0	2375	0.4214	0.807
0.3974	20.0	2500	0.4211	0.811
0.3974	21.0	2625	0.4168	0.812
0.3974	22.0	2750	0.4183	0.815
0.3974	23.0	2875	0.4155	0.815
0.3823	24.0	3000	0.4154	0.818
0.3823	25.0	3125	0.4153	0.819

Framework versions

• PEFT 0.7.1
• Transformers 4.36.2
• Pytorch 2.3.0.dev20231231
• Datasets 2.16.1
• Tokenizers 0.15.0