camembert_classification_tools

This model is a fine-tuned version of camembert-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.6969
• Accuracy: 0.775

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: 0.0001
• train_batch_size: 24
• eval_batch_size: 192
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 30

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
No log	1.0	5	2.0733	0.2
No log	2.0	10	2.0478	0.275
No log	3.0	15	1.9161	0.45
No log	4.0	20	1.7607	0.425
No log	5.0	25	1.5895	0.575
No log	6.0	30	1.4201	0.625
No log	7.0	35	1.2944	0.675
No log	8.0	40	1.2193	0.75
No log	9.0	45	1.0974	0.775
No log	10.0	50	1.0429	0.825
No log	11.0	55	0.9602	0.8
No log	12.0	60	0.9059	0.8
No log	13.0	65	0.8365	0.825
No log	14.0	70	0.9396	0.725
No log	15.0	75	0.8271	0.8
No log	16.0	80	0.7762	0.8
No log	17.0	85	0.7847	0.8
No log	18.0	90	0.7012	0.8
No log	19.0	95	0.6971	0.8
No log	20.0	100	0.7186	0.775
No log	21.0	105	0.7946	0.725
No log	22.0	110	0.7721	0.725
No log	23.0	115	0.7642	0.725
No log	24.0	120	0.7298	0.75
No log	25.0	125	0.7191	0.75
No log	26.0	130	0.6978	0.775
No log	27.0	135	0.6913	0.8
No log	28.0	140	0.6949	0.775
No log	29.0	145	0.6961	0.775
No log	30.0	150	0.6969	0.775

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.5
• Tokenizers 0.14.1