README.md

metadata

library_name: transformers
base_model: KasuleTrevor/all-MiniLM-L12-v2-rny-intents
tags:
  - generated_from_trainer
metrics:
  - accuracy
  - precision
  - recall
  - f1
model-index:
  - name: all_mini_lm_text_classifier_nyn
    results: []

all_mini_lm_text_classifier_nyn

This model is a fine-tuned version of KasuleTrevor/all-MiniLM-L12-v2-rny-intents on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.3562
• Accuracy: 0.943
• Precision: 0.945
• Recall: 0.943
• F1: 0.942

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: 0.0001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• 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_steps: 500
• num_epochs: 20
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Precision	Recall	F1
2.5968	1.0	293	1.7473	0.633	0.535	0.633	0.555
1.2106	2.0	586	0.6798	0.828	0.82	0.828	0.804
0.5287	3.0	879	0.4751	0.896	0.894	0.896	0.891
0.3188	4.0	1172	0.3477	0.904	0.916	0.904	0.901
0.2335	5.0	1465	0.2991	0.936	0.94	0.936	0.936
0.1855	6.0	1758	0.3184	0.932	0.937	0.932	0.932
0.1609	7.0	2051	0.3253	0.934	0.939	0.934	0.933
0.1398	8.0	2344	0.2569	0.949	0.952	0.949	0.949
0.1151	9.0	2637	0.3135	0.943	0.946	0.943	0.943
0.0997	10.0	2930	0.3000	0.951	0.953	0.951	0.951
0.0866	11.0	3223	0.3140	0.945	0.948	0.945	0.945
0.0615	12.0	3516	0.3165	0.945	0.948	0.945	0.945
0.0574	13.0	3809	0.3870	0.934	0.94	0.934	0.935
0.0459	14.0	4102	0.3428	0.947	0.951	0.947	0.947
0.0423	15.0	4395	0.3565	0.945	0.948	0.945	0.945
0.0412	16.0	4688	0.3655	0.945	0.948	0.945	0.945
0.0343	17.0	4981	0.3528	0.947	0.95	0.947	0.947
0.0289	18.0	5274	0.3567	0.943	0.945	0.943	0.942
0.0297	19.0	5567	0.3565	0.943	0.945	0.943	0.942
0.0286	20.0	5860	0.3562	0.943	0.945	0.943	0.942

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1