OTE-DAPT-CAMEL-MSA-HARD-4248-SUBSAMPLE-run3

This model is a fine-tuned version of salohnana2018/HARD_without_dp_4248_camel_prepocessed_OTE on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1685
  • Precision: 0.7509
  • Recall: 0.7962
  • F1: 0.7729
  • Accuracy: 0.9548

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: 32
  • eval_batch_size: 8
  • seed: 23
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Accuracy
0.1495 1.0 121 0.1123 0.7811 0.7573 0.7690 0.9567
0.0847 2.0 242 0.1201 0.7505 0.7972 0.7731 0.9540
0.0581 3.0 363 0.1314 0.7610 0.7853 0.7729 0.9560
0.0363 4.0 484 0.1529 0.7649 0.7798 0.7723 0.9551
0.0242 5.0 605 0.1685 0.7509 0.7962 0.7729 0.9548

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
21
Safetensors
Model size
108M 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 salohnana2018/OTE-DAPT-CAMEL-MSA-HARD-4248-SUBSAMPLE-run3