bert-intent-eva

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

• Loss: 0.0237
• Accuracy: 0.9967
• Precision: 0.9968
• Recall: 0.9967
• F1: 0.9968

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: 1e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• num_epochs: 50

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
0.8092	1.0	612	0.1544	0.9739	0.9744	0.9739	0.9739
0.0672	2.0	1224	0.0732	0.9869	0.9872	0.9869	0.9870
0.0387	3.0	1836	0.0641	0.9918	0.9921	0.9918	0.9918
0.0384	4.0	2448	0.0592	0.9902	0.9906	0.9902	0.9902
0.0291	5.0	3060	0.0987	0.9886	0.9890	0.9886	0.9886
0.0697	6.0	3672	0.0816	0.9821	0.9825	0.9821	0.9819
0.0684	7.0	4284	0.0501	0.9918	0.9920	0.9918	0.9919
0.0182	8.0	4896	0.0268	0.9951	0.9952	0.9951	0.9951
0.0222	9.0	5508	0.0419	0.9935	0.9936	0.9935	0.9935
0.025	10.0	6120	0.0238	0.9967	0.9968	0.9967	0.9968
0.0101	11.0	6732	0.0263	0.9967	0.9968	0.9967	0.9968
0.0171	12.0	7344	0.0237	0.9967	0.9968	0.9967	0.9968
0.0177	13.0	7956	0.0270	0.9967	0.9968	0.9967	0.9968
0.0199	14.0	8568	0.0481	0.9935	0.9936	0.9935	0.9935
0.0001	15.0	9180	0.0350	0.9951	0.9952	0.9951	0.9951
0.0197	16.0	9792	0.0294	0.9951	0.9952	0.9951	0.9951
0.1381	17.0	10404	0.0405	0.9951	0.9952	0.9951	0.9951

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.1
• Datasets 4.4.1
• Tokenizers 0.22.1