all_mini_lm_text_classifier_330h

This model is a fine-tuned version of KasuleTrevor/all-MiniLM-L6-v2_intents on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.2633
• Accuracy: 0.943
• Precision: 0.946
• Recall: 0.943
• F1: 0.943

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
2.7003	1.0	263	1.8368	0.642	0.633	0.642	0.582
1.3435	2.0	526	0.6806	0.8	0.848	0.8	0.754
0.5577	3.0	789	0.2745	0.94	0.928	0.94	0.931
0.2935	4.0	1052	0.2084	0.944	0.932	0.944	0.936
0.2122	5.0	1315	0.1717	0.97	0.971	0.97	0.97
0.1596	6.0	1578	0.1608	0.967	0.968	0.967	0.967
0.1394	7.0	1841	0.1911	0.967	0.968	0.967	0.967
0.107	8.0	2104	0.1624	0.968	0.969	0.968	0.968
0.0952	9.0	2367	0.1836	0.965	0.966	0.965	0.965
0.08	10.0	2630	0.1889	0.965	0.967	0.965	0.965
0.0724	11.0	2893	0.2068	0.955	0.957	0.955	0.955
0.0643	12.0	3156	0.2027	0.961	0.962	0.961	0.961
0.0553	13.0	3419	0.2172	0.961	0.962	0.961	0.961
0.0474	14.0	3682	0.2170	0.961	0.962	0.961	0.961
0.038	15.0	3945	0.2225	0.959	0.961	0.959	0.959
0.0303	16.0	4208	0.2427	0.95	0.952	0.95	0.95
0.0254	17.0	4471	0.2529	0.946	0.948	0.946	0.946
0.0228	18.0	4734	0.2571	0.946	0.949	0.946	0.946
0.02	19.0	4997	0.2627	0.943	0.946	0.943	0.943
0.019	20.0	5260	0.2633	0.943	0.946	0.943	0.943

Framework versions

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