ops_subcate

This model is a fine-tuned version of microsoft/deberta-v3-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1575
  • Accuracy: 0.7428
  • F1: 0.7647
  • Precision: 0.7715
  • Recall: 0.7581

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: 5e-05
  • train_batch_size: 64
  • eval_batch_size: 128
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_steps: 500
  • num_epochs: 10

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
No log 1.0 49 0.1300 0.7291 0.7604 0.7883 0.7345
No log 2.0 98 0.1272 0.7391 0.7707 0.7989 0.7444
No log 3.0 147 0.1294 0.7391 0.7654 0.7918 0.7407
No log 4.0 196 0.1388 0.7341 0.7567 0.7733 0.7407
No log 5.0 245 0.1326 0.7541 0.7791 0.8026 0.7568
No log 6.0 294 0.1407 0.7478 0.7743 0.7940 0.7556
No log 7.0 343 0.1445 0.7341 0.7576 0.7712 0.7444
No log 8.0 392 0.1533 0.7528 0.7684 0.7776 0.7593
No log 9.0 441 0.1573 0.7628 0.7747 0.7816 0.7680
No log 10.0 490 0.1575 0.7428 0.7647 0.7715 0.7581

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.3.1+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
10
Safetensors
Model size
142M 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 tangminhanh/ops_subcate

Finetuned
(133)
this model