qa_en_ms_model_v3

This model is a fine-tuned version of mesolitica/finetune-qa-t5-small-standard-bahasa-cased on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8296

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: 2e-05
  • train_batch_size: 24
  • eval_batch_size: 24
  • seed: 42
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss
1.3752 1.0 1047 1.0868
1.1233 2.0 2094 0.9799
1.0295 3.0 3141 0.9326
0.9485 4.0 4188 0.9051
0.8883 5.0 5235 0.8748
0.8485 6.0 6282 0.8605
0.8243 7.0 7329 0.8485
0.7977 8.0 8376 0.8417
0.7597 9.0 9423 0.8286
0.7495 10.0 10470 0.8306
0.7211 11.0 11517 0.8255
0.7076 12.0 12564 0.8291
0.7012 13.0 13611 0.8350
0.6833 14.0 14658 0.8288
0.6687 15.0 15705 0.8230
0.6574 16.0 16752 0.8313
0.6342 17.0 17799 0.8239
0.6419 18.0 18846 0.8271
0.6451 19.0 19893 0.8302
0.6278 20.0 20940 0.8296

Framework versions

  • Transformers 4.52.4
  • Pytorch 2.5.1+cu121
  • Datasets 3.6.0
  • Tokenizers 0.21.1
Downloads last month
-
Safetensors
Model size
60.5M params
Tensor type
F32
Inference Providers NEW
This model isn't deployed by any Inference Provider. 馃檵 Ask for provider support

Model tree for yumiian/qa_en_ms_model_v3

Finetuned
(2)
this model