qa-persian-xlm-roberta-large

This model is a fine-tuned version of makhataei/qa-persian-xlm-roberta-large on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 5.7315

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: 1e-08
  • train_batch_size: 14
  • eval_batch_size: 14
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 40

Training results

Training Loss Epoch Step Validation Loss
5.2629 1.0 202 5.7315
5.2091 2.0 404 5.7315
5.3101 3.0 606 5.7315
5.4071 4.0 808 5.7315
5.4292 5.0 1010 5.7315
5.4351 6.0 1212 5.7315
5.4477 7.0 1414 5.7315
5.436 8.0 1616 5.7315
5.4652 9.0 1818 5.7315
5.4464 10.0 2020 5.7315
5.435 11.0 2222 5.7315
5.4423 12.0 2424 5.7315
5.451 13.0 2626 5.7315
5.4455 14.0 2828 5.7315
5.4703 15.0 3030 5.7315
5.4351 16.0 3232 5.7315
5.4895 17.0 3434 5.7315
5.4439 18.0 3636 5.7315
5.4662 19.0 3838 5.7315
5.454 20.0 4040 5.7315
5.4645 21.0 4242 5.7315
5.4453 22.0 4444 5.7315
5.4659 23.0 4646 5.7315
5.4628 24.0 4848 5.7315
5.4349 25.0 5050 5.7315
5.4345 26.0 5252 5.7315
5.4228 27.0 5454 5.7315
5.4492 28.0 5656 5.7315
5.4358 29.0 5858 5.7315
5.461 30.0 6060 5.7315
5.4304 31.0 6262 5.7315
5.4376 32.0 6464 5.7315
5.4526 33.0 6666 5.7315
5.4687 34.0 6868 5.7315
5.44 35.0 7070 5.7315
5.4491 36.0 7272 5.7315
5.4379 37.0 7474 5.7315
5.4596 38.0 7676 5.7315
5.4663 39.0 7878 5.7315
5.4487 40.0 8080 5.7315

Framework versions

  • Transformers 4.38.2
  • Pytorch 2.2.1+cu121
  • Datasets 2.18.0
  • Tokenizers 0.15.2
Downloads last month
29
Safetensors
Model size
559M 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 makhataei/qa-persian-xlm-roberta-large

Unable to build the model tree, the base model loops to the model itself. Learn more.