Edit model card

RoBERTa-large-PM-M3-Voc-hf-finetuned-ner

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3493
  • Precision: 0.6836
  • Recall: 0.8494
  • F1: 0.7575
  • Accuracy: 0.9116

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: cosine
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
No log 1.0 23 1.2145 0.1762 0.0340 0.0569 0.7236
No log 2.0 46 0.8308 0.4435 0.3547 0.3942 0.7735
No log 3.0 69 0.7051 0.4419 0.6091 0.5122 0.7842
No log 4.0 92 0.6051 0.4989 0.6416 0.5613 0.8085
No log 5.0 115 0.5500 0.5501 0.6449 0.5937 0.8243
No log 6.0 138 0.5272 0.5351 0.6892 0.6025 0.8277
No log 7.0 161 0.5256 0.5426 0.7143 0.6167 0.8316
No log 8.0 184 0.4943 0.5583 0.7582 0.6431 0.8479
No log 9.0 207 0.4196 0.6217 0.7475 0.6788 0.8773
No log 10.0 230 0.4065 0.6270 0.7789 0.6948 0.8850
No log 11.0 253 0.4367 0.6012 0.8062 0.6887 0.8776
No log 12.0 276 0.3917 0.6301 0.8125 0.7098 0.8915
No log 13.0 299 0.3563 0.6736 0.8191 0.7393 0.9042
No log 14.0 322 0.3654 0.6653 0.8335 0.7400 0.9040
No log 15.0 345 0.3637 0.6611 0.8439 0.7414 0.9057
No log 16.0 368 0.3522 0.6785 0.8453 0.7528 0.9100
No log 17.0 391 0.3469 0.6841 0.8472 0.7569 0.9115
No log 18.0 414 0.3520 0.6821 0.8490 0.7565 0.9110
No log 19.0 437 0.3485 0.6848 0.8494 0.7583 0.9121
No log 20.0 460 0.3493 0.6836 0.8494 0.7575 0.9116

Framework versions

  • Transformers 4.33.1
  • Pytorch 2.0.1+cu118
  • Datasets 2.14.5
  • Tokenizers 0.13.3
Downloads last month
7
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.

Space using abymmathew/RoBERTa-large-PM-M3-Voc-hf-finetuned-ner 1