intfloat-multilingual-e5-large-english-fp16

This model is a fine-tuned version of intfloat/multilingual-e5-large on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.3003
• Accuracy: 0.8851
• Precision: 0.8857
• Recall: 0.8851
• F1: 0.8835

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: 2e-05
• train_batch_size: 64
• eval_batch_size: 64
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 128
• 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
• lr_scheduler_warmup_ratio: 0.3
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
1.0422	0.3922	50	0.8866	0.6081	0.6817	0.6081	0.5308
0.703	0.7843	100	0.4687	0.8266	0.8265	0.8266	0.8242
0.3701	1.1725	150	0.3189	0.8787	0.8783	0.8787	0.8784
0.3018	1.5647	200	0.3163	0.8861	0.8855	0.8861	0.8852
0.2988	1.9569	250	0.3223	0.8797	0.8828	0.8797	0.8770
0.2324	2.3451	300	0.3003	0.8851	0.8857	0.8851	0.8835
0.2337	2.7373	350	0.2901	0.8905	0.8909	0.8905	0.8904
0.2066	3.1255	400	0.3938	0.8851	0.8866	0.8851	0.8831
0.1711	3.5176	450	0.3373	0.8905	0.8910	0.8905	0.8907
0.1668	3.9098	500	0.3527	0.8861	0.8859	0.8861	0.8848

Framework versions

• Transformers 4.51.1
• Pytorch 2.6.0+cu124
• Datasets 3.5.0
• Tokenizers 0.21.1