result

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

• Loss: 0.0181
• Precision: 0.0
• Recall: 0.0
• F1: 0.0
• Accuracy: 0.9960

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: 0.00025
• train_batch_size: 32
• eval_batch_size: 32
• 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	Precision	Recall	F1	Accuracy
No log	1.0	25	0.0900	0.0	0.0	0.0	0.9818
No log	2.0	50	0.0557	0.0	0.0	0.0	0.9822
No log	3.0	75	0.0546	0.0	0.0	0.0	0.9889
No log	4.0	100	0.0287	0.0	0.0	0.0	0.9945
No log	5.0	125	0.0240	0.0	0.0	0.0	0.9941
No log	6.0	150	0.0179	0.0	0.0	0.0	0.9956
No log	7.0	175	0.0163	0.0	0.0	0.0	0.9964
No log	8.0	200	0.0189	0.0	0.0	0.0	0.9952
No log	9.0	225	0.0169	0.0	0.0	0.0	0.9960
No log	10.0	250	0.0145	0.0	0.0	0.0	0.9968
No log	11.0	275	0.0164	0.0	0.0	0.0	0.9964
No log	12.0	300	0.0153	0.0	0.0	0.0	0.9964
No log	13.0	325	0.0153	0.0	0.0	0.0	0.9964
No log	14.0	350	0.0161	0.0	0.0	0.0	0.9964
No log	15.0	375	0.0164	0.0	0.0	0.0	0.9964
No log	16.0	400	0.0166	0.0	0.0	0.0	0.9964
No log	17.0	425	0.0161	0.0	0.0	0.0	0.9964
No log	18.0	450	0.0166	0.0	0.0	0.0	0.9956
No log	19.0	475	0.0182	0.0	0.0	0.0	0.9960
0.0262	20.0	500	0.0181	0.0	0.0	0.0	0.9960

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.0