e5_Sentiment_Biodiversite_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: 0.0069
• Accuracy: 0.9976
• F1: 0.9976

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
0.5305	1.0	26	0.3177	0.9391	0.9393
0.2891	2.0	52	0.2367	0.9650	0.9650
0.2232	3.0	78	0.1235	0.9819	0.9818
0.1577	4.0	104	0.0844	0.9771	0.9773
0.1522	5.0	130	0.1118	0.9922	0.9921
0.1047	6.0	156	0.0379	0.9892	0.9893
0.0531	7.0	182	0.0607	0.9910	0.9909
0.1136	8.0	208	0.0563	0.9922	0.9922
0.0709	9.0	234	0.0174	0.9964	0.9964
0.0229	10.0	260	0.0142	0.9976	0.9976
0.0347	11.0	286	0.0196	0.9952	0.9952
0.0341	12.0	312	0.0069	0.9976	0.9976

Framework versions

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