e5_Sentiment_Dechets_v1

This model is a fine-tuned version of intfloat/multilingual-e5-large-instruct on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.0251
• Accuracy: 0.9937
• F1: 0.9936

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: 5e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 64
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 100
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1
0.5101	0.9748	29	0.2217	0.9482	0.9489
0.2405	1.9748	58	0.1395	0.9694	0.9695
0.1653	2.9748	87	0.0717	0.9831	0.9833
0.1304	3.9748	116	0.0611	0.9794	0.9798
0.1021	4.9748	145	0.0412	0.9889	0.9890
0.0864	5.9748	174	0.0206	0.9942	0.9942
0.0612	6.9748	203	0.0396	0.9900	0.9900
0.0542	7.9748	232	0.0317	0.9926	0.9927
0.0551	8.9748	261	0.0251	0.9937	0.9936

Framework versions

• Transformers 4.50.3
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1