results2

This model is a fine-tuned version of UBC-NLP/AraT5v2-base-1024 on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.1539
  • F1: 0.9682

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: 4
  • eval_batch_size: 16
  • 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 F1
3.1612 1.0 574 2.9806 0.0625
2.7788 2.0 1148 1.6246 0.4172
1.0397 3.0 1722 0.3903 0.8539
0.3532 4.0 2296 0.2816 0.9261
0.1624 5.0 2870 0.2199 0.9512
0.0984 6.0 3444 0.1321 0.9720
0.0581 7.0 4018 0.1576 0.9682
0.0369 8.0 4592 0.1243 0.9760
0.0351 9.0 5166 0.1539 0.9721
0.0338 10.0 5740 0.1539 0.9682

Framework versions

  • Transformers 4.36.2
  • Pytorch 2.0.1
  • Datasets 2.16.1
  • Tokenizers 0.15.0
Downloads last month
17
Safetensors
Model size
283M 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 Salama1429/results2

Finetuned
(11)
this model