camembert_ccnet_classification_analyse_visage_classifier-only_fr_lr1e-3

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

• Loss: 0.0117
• Accuracy: 1.0
• Learning Rate: 0.0

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: 0.001
• 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	Rate
0.9997	1.0	4	0.6869	0.8333	0.0010
0.6989	2.0	8	0.4634	1.0	0.0009
0.4979	3.0	12	0.3029	1.0	0.0009
0.3335	4.0	16	0.2251	1.0	0.0009
0.2709	5.0	20	0.1619	1.0	0.0008
0.2246	6.0	24	0.1013	1.0	0.0008
0.1836	7.0	28	0.0968	1.0	0.0008
0.1711	8.0	32	0.0767	1.0	0.0007
0.2015	9.0	36	0.0548	1.0	0.0007
0.1353	10.0	40	0.0463	1.0	0.0007
0.081	11.0	44	0.0307	1.0	0.0006
0.1331	12.0	48	0.0519	1.0	0.0006
0.11	13.0	52	0.0393	1.0	0.0006
0.0737	14.0	56	0.0289	1.0	0.0005
0.0627	15.0	60	0.0251	1.0	0.0005
0.0477	16.0	64	0.0174	1.0	0.0005
0.0564	17.0	68	0.0155	1.0	0.0004
0.054	18.0	72	0.0128	1.0	0.0004
0.0486	19.0	76	0.0154	1.0	0.0004
0.0444	20.0	80	0.0122	1.0	0.0003
0.0394	21.0	84	0.0166	1.0	0.0003
0.0522	22.0	88	0.0146	1.0	0.0003
0.0416	23.0	92	0.0092	1.0	0.0002
0.0553	24.0	96	0.0074	1.0	0.0002
0.0791	25.0	100	0.0074	1.0	0.0002
0.0798	26.0	104	0.0083	1.0	0.0001
0.0412	27.0	108	0.0107	1.0	0.0001
0.0406	28.0	112	0.0127	1.0	0.0001
0.0407	29.0	116	0.0123	1.0	0.0000
0.0534	30.0	120	0.0117	1.0	0.0

Framework versions

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