Edit model card

XLMRoberta-base-amazon-massive-NER

This model is a fine-tuned version of xlm-roberta-base on the MASSIVE dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2907
  • Precision: 0.6189
  • Recall: 0.6243
  • F1: 0.6123
  • Accuracy: 0.9200

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: 32
  • eval_batch_size: 32
  • 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 Precision Recall F1 Accuracy
0.9645 1.0 720 0.4148 0.4631 0.4177 0.4154 0.8950
0.4421 2.0 1440 0.3181 0.5808 0.6001 0.5780 0.9154
0.2514 3.0 2160 0.2907 0.6189 0.6243 0.6123 0.9200
0.2117 4.0 2880 0.2967 0.6522 0.6351 0.6352 0.9252
0.1592 5.0 3600 0.3090 0.6288 0.6923 0.6520 0.9233
0.131 6.0 4320 0.2961 0.6619 0.6693 0.6546 0.9282
0.1054 7.0 5040 0.3147 0.6424 0.6762 0.6498 0.9260
0.0923 8.0 5760 0.3171 0.6447 0.6945 0.6614 0.9257
0.0845 9.0 6480 0.3328 0.6434 0.6791 0.6539 0.9256
0.0691 10.0 7200 0.3314 0.6628 0.6834 0.6635 0.9264

Framework versions

  • Transformers 4.41.0
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
277M params
Tensor type
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 stepanom/XLMRoberta-base-amazon-massive-NER

Finetuned
(2589)
this model

Dataset used to train stepanom/XLMRoberta-base-amazon-massive-NER