gutsartificial/bge-small-en-v1.5-relevancy-1

bge-small-en-v1.5-2024-12-06_14-23-52-relevancy-1

This model is a fine-tuned version of BAAI/bge-small-en-v1.5 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0219
• Spearman: 0.9313
• Pearson: 0.9323
• Mse: 0.0219

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: 64
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 256
• 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: cosine
• lr_scheduler_warmup_ratio: 0.05
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Spearman	Pearson	Mse
0.0334	0.3998	1055	0.0291	0.9039	0.9070	0.0291
0.0276	0.7997	2110	0.0264	0.9129	0.9165	0.0264
0.0244	1.1995	3165	0.0253	0.9185	0.9215	0.0253
0.0239	1.5994	4220	0.0230	0.9235	0.9271	0.0230
0.0217	1.9992	5275	0.0234	0.9252	0.9294	0.0234
0.0186	2.3991	6330	0.0228	0.9272	0.9304	0.0228
0.0174	2.7989	7385	0.0219	0.9286	0.9320	0.0219
0.0136	3.1988	8440	0.0221	0.9290	0.9314	0.0221
0.014	3.5986	9495	0.0218	0.9304	0.9329	0.0218
0.0149	3.9985	10550	0.0215	0.9305	0.9332	0.0215
0.0112	4.3983	11605	0.0217	0.9305	0.9332	0.0217
0.0127	4.7982	12660	0.0217	0.9306	0.9333	0.0217

Framework versions

• Transformers 4.46.3
• Pytorch 2.4.1+cu121
• Datasets 2.19.2
• Tokenizers 0.20.3