Edit model card

BERT_BIOMAT_NER_1000

This model is a fine-tuned version of google-bert/bert-base-uncased on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3920
  • Precision: 0.9495
  • Recall: 0.9444
  • F1: 0.9470
  • Accuracy: 0.9380

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
No log 1.0 211 0.2669 0.9407 0.9352 0.9380 0.9275
No log 2.0 422 0.2809 0.9457 0.9432 0.9444 0.9343
0.2064 3.0 633 0.3114 0.9472 0.9454 0.9463 0.9353
0.2064 4.0 844 0.3323 0.9491 0.9422 0.9456 0.9358
0.0481 5.0 1055 0.3478 0.9493 0.9441 0.9467 0.9382
0.0481 6.0 1266 0.3731 0.9486 0.9438 0.9462 0.9374
0.0481 7.0 1477 0.3723 0.9491 0.9445 0.9468 0.9379
0.0201 8.0 1688 0.3830 0.9489 0.9443 0.9466 0.9369
0.0201 9.0 1899 0.3873 0.9503 0.9448 0.9475 0.9378
0.0106 10.0 2110 0.3920 0.9495 0.9444 0.9470 0.9380

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.4.0+cu121
  • Datasets 2.21.0
  • Tokenizers 0.19.1
Downloads last month
4
Safetensors
Model size
109M params
Tensor type
F32
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for judithrosell/BERT_BIOMAT_NER_1000

Finetuned
(2085)
this model