camembert_ccnet_classification_tools_NEFTune_fr_lr1e-3_V2

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: 2.0965
• Accuracy: 0.1042
• Learning Rate: 0.0008

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: 60

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Rate
2.1119	1.0	15	2.1246	0.1042	0.0010
2.0909	2.0	30	2.1521	0.0938	0.0010
2.1043	3.0	45	2.0959	0.0938	0.0009
2.0866	4.0	60	2.1143	0.0938	0.0009
2.0746	5.0	75	2.1063	0.1354	0.0009
2.0753	6.0	90	2.1266	0.0938	0.0009
2.0793	7.0	105	2.1177	0.1146	0.0009
2.0844	8.0	120	2.0959	0.1354	0.0009
2.0855	9.0	135	2.1072	0.0938	0.0008
2.0805	10.0	150	2.1128	0.0938	0.0008
2.079	11.0	165	2.1027	0.1354	0.0008
2.0855	12.0	180	2.1164	0.0938	0.0008
2.0745	13.0	195	2.0965	0.1042	0.0008

Framework versions

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