e5_EC_MultiLabel_12082025

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: 0.1220
• F1 Weighted: 0.9559

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 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
0.9125	1.0	324	0.5410	0.7120
0.4462	2.0	648	0.2934	0.8546
0.2895	3.0	972	0.2372	0.8833
0.2172	4.0	1296	0.1978	0.9065
0.171	5.0	1620	0.1744	0.9182
0.1389	6.0	1944	0.1505	0.9325
0.116	7.0	2268	0.1402	0.9418
0.0985	8.0	2592	0.1410	0.9412
0.0849	9.0	2916	0.1341	0.9480
0.0707	10.0	3240	0.1276	0.9529
0.063	11.0	3564	0.1239	0.9531
0.0567	12.0	3888	0.1220	0.9559

Framework versions

• Transformers 4.55.0
• Pytorch 2.6.0+cu124
• Datasets 4.0.0
• Tokenizers 0.21.4