roberta-polymarket-sentiment-lora-context-gemini-distilled

This model is a fine-tuned version of roberta-base on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.7342
  • Accuracy: 0.6772
  • F1: 0.7091
  • Precision: 0.7089
  • Recall: 0.7093

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: 0.0002
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 20

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Precision Recall
1.0408 0.1880 50 1.0508 0.3333 0.3085 0.2278 0.4773
1.0667 0.3759 100 1.0405 0.3333 0.3085 0.2278 0.4773
1.0304 0.5639 150 1.0115 0.3682 0.3757 0.3619 0.496
0.9777 0.7519 200 0.8976 0.4721 0.4843 0.5427 0.5587
0.8738 0.9398 250 0.8267 0.5554 0.5920 0.6295 0.6267
0.8935 1.1278 300 0.8106 0.5768 0.6136 0.6343 0.6333
0.7933 1.3158 350 0.8309 0.6353 0.6589 0.6756 0.6507
0.8031 1.5038 400 0.7636 0.6260 0.6686 0.6656 0.6773
0.8065 1.6917 450 0.7501 0.6390 0.6762 0.6744 0.6787
0.8551 1.8797 500 0.7634 0.6534 0.6783 0.6936 0.6813
0.708 2.0677 550 0.7611 0.6620 0.6888 0.6946 0.6853
0.7281 2.2556 600 0.7342 0.6760 0.7087 0.7086 0.7093
0.7763 2.4436 650 0.7429 0.6630 0.6994 0.6988 0.704
0.704 2.6316 700 0.7782 0.6265 0.6698 0.6764 0.6853
0.7218 2.8195 750 0.7455 0.6849 0.7149 0.7197 0.7187
0.7099 3.0075 800 0.7552 0.6703 0.6956 0.7041 0.6933

Framework versions

  • PEFT 0.18.0
  • Transformers 4.57.1
  • Pytorch 2.9.1+cu128
  • Datasets 4.4.1
  • Tokenizers 0.22.1
Downloads last month
27
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for levente-murgas/roberta-polymarket-sentiment-lora-context-gemini-distilled

Adapter
(329)
this model