baseline_3-seed_2025

This model is a fine-tuned version of google/flan-t5-base on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 3.5377
  • Precision: 0.3859
  • Recall: 0.4167
  • F1: 0.4007

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: 0.0003
  • train_batch_size: 8
  • eval_batch_size: 8
  • seed: 2025
  • 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: 15

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1
0.6258 1.0 447 0.8530 0.4362 0.5942 0.5031
0.6041 2.0 894 1.0887 0.4151 0.3188 0.3607
0.5717 3.0 1341 1.0252 0.4206 0.5761 0.4862
0.5455 4.0 1788 1.2918 0.4265 0.6304 0.5088
0.4904 5.0 2235 1.9671 0.4 0.4565 0.4264
0.4739 6.0 2682 1.7556 0.4039 0.5254 0.4567
0.4421 7.0 3129 2.4087 0.3928 0.5109 0.4441
0.4086 8.0 3576 2.2270 0.3970 0.4746 0.4323
0.427 9.0 4023 2.3055 0.3668 0.3841 0.3752
0.4233 10.0 4470 2.5657 0.3969 0.4674 0.4293
0.3891 11.0 4917 2.6900 0.3724 0.3913 0.3816
0.2841 12.0 5364 2.9719 0.3811 0.4239 0.4014
0.3323 13.0 5811 3.1814 0.3905 0.4457 0.4162
0.3462 14.0 6258 3.3791 0.3838 0.4130 0.3979
0.3005 15.0 6705 3.5377 0.3859 0.4167 0.4007

Framework versions

  • Transformers 4.52.0.dev0
  • Pytorch 2.7.0+cu126
  • Datasets 3.6.0
  • Tokenizers 0.21.1
Downloads last month
226
Safetensors
Model size
223M params
Tensor type
F32
ยท
Inference Providers NEW
This model isn't deployed by any Inference Provider. ๐Ÿ™‹ Ask for provider support

Model tree for maud-dr/baseline_3-seed_2025

Finetuned
(791)
this model