classify-bluesky-1000-v2

This model is a fine-tuned version of sentence-transformers/all-mpnet-base-v2 on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.0055
• Accuracy: 0.9994
• F1: 0.9994
• Precision: 0.9994
• Recall: 0.9994
• Accuracy Label Bluesky: 1.0
• Accuracy Label Non bluesky: 0.9992

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: 16
• eval_batch_size: 16
• 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
• lr_scheduler_warmup_steps: 500
• num_epochs: 3

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	F1	Precision	Recall	Accuracy Label Bluesky	Accuracy Label Non bluesky
0.514	0.4292	100	0.4462	0.8747	0.8577	0.8925	0.8747	0.4832	1.0
0.095	0.8584	200	0.0717	0.9984	0.9984	0.9984	0.9984	0.9948	0.9996
0.031	1.2876	300	0.0230	1.0	1.0	1.0	1.0	1.0	1.0
0.0139	1.7167	400	0.0099	1.0	1.0	1.0	1.0	1.0	1.0
0.007	2.1459	500	0.0259	0.9947	0.9947	0.9948	0.9947	1.0	0.9930
0.0045	2.5751	600	0.0060	0.9994	0.9994	0.9994	0.9994	1.0	0.9992

Framework versions

• Transformers 4.49.0
• Pytorch 2.5.1+cu124
• Datasets 3.3.2
• Tokenizers 0.21.0