e5_Energie_MultiLabel_08092025

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: 0.1473
• F1 Weighted: 0.9406

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-06
• train_batch_size: 16
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• 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: linear
• num_epochs: 15
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	F1 Weighted
0.8088	1.0	402	0.4611	0.7347
0.4222	2.0	804	0.3283	0.8228
0.3117	3.0	1206	0.2786	0.8490
0.2502	4.0	1608	0.2368	0.8758
0.2054	5.0	2010	0.2167	0.8865
0.17	6.0	2412	0.1851	0.9109
0.1448	7.0	2814	0.1787	0.9166
0.1262	8.0	3216	0.1673	0.9235
0.1099	9.0	3618	0.1679	0.9220
0.0961	10.0	4020	0.1564	0.9334
0.0871	11.0	4422	0.1538	0.9331
0.0773	12.0	4824	0.1482	0.9390
0.0712	13.0	5226	0.1549	0.9334
0.0654	14.0	5628	0.1482	0.9410
0.0637	15.0	6030	0.1473	0.9406

Framework versions

• Transformers 4.56.0
• Pytorch 2.8.0+cu126
• Datasets 4.0.0
• Tokenizers 0.22.0