Edit model card

my_awesome_ner-token_classification_v1.0.7-4

This model is a fine-tuned version of lilyyellow/my_awesome_ner-token_classification_v1.0.7-4 on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5084
  • Precision: 0.6376
  • Recall: 0.6915
  • F1: 0.6634
  • Accuracy: 0.8858

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: cosine
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.1297 1.9965 1156 0.4660 0.6384 0.6812 0.6591 0.8855
0.0986 3.9931 2312 0.5084 0.6376 0.6915 0.6634 0.8858

Framework versions

  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.19.2
  • Tokenizers 0.19.1
Downloads last month
6
Safetensors
Model size
133M params
Tensor type
F32
·
Inference API
This model can be loaded on Inference API (serverless).

Finetuned from