Edit model card

multilingual_minilm-amazon_massive-intent_eu_noen

This model is a fine-tuned version of microsoft/Multilingual-MiniLM-L12-H384 on the MASSIVE1.1 dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7794
  • Accuracy: 0.8551
  • F1: 0.8551

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
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1
1.7624 1.0 4318 1.5462 0.6331 0.6331
0.9535 2.0 8636 0.9628 0.7698 0.7698
0.6849 3.0 12954 0.8034 0.8097 0.8097
0.5163 4.0 17272 0.7444 0.8290 0.8290
0.3973 5.0 21590 0.7346 0.8383 0.8383
0.331 6.0 25908 0.7369 0.8453 0.8453
0.2876 7.0 30226 0.7325 0.8510 0.8510
0.2319 8.0 34544 0.7726 0.8496 0.8496
0.2098 9.0 38862 0.7803 0.8543 0.8543
0.1863 10.0 43180 0.7794 0.8551 0.8551

Framework versions

  • Transformers 4.25.1
  • Pytorch 1.13.1+cu116
  • Datasets 2.8.0
  • Tokenizers 0.13.2
Downloads last month
23
Safetensors
Model size
118M params
Tensor type
I64
·
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for cartesinus/multilingual_minilm-amazon_massive-intent_eu6_noen

Finetuned
(20)
this model

Dataset used to train cartesinus/multilingual_minilm-amazon_massive-intent_eu6_noen

Evaluation results