cellate-tapt_base-LR_1e-05

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

  • Loss: 6.1339
  • Accuracy: 0.2568

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-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 3407
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-06 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.06
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
10.1673 1.0 6 11.0601 0.0
9.7047 2.0 12 10.0083 0.0
8.7667 3.0 18 9.2391 0.0025
8.0493 4.0 24 8.5184 0.0256
7.555 5.0 30 7.9435 0.0637
7.1487 6.0 36 7.7096 0.0716
6.8066 7.0 42 7.3534 0.0997
6.5712 8.0 48 7.2085 0.1537
6.3437 9.0 54 6.9363 0.1856
6.1888 10.0 60 6.8290 0.1927
5.9906 11.0 66 6.6097 0.2204
5.8675 12.0 72 6.4388 0.2308
5.7465 13.0 78 6.2943 0.2438
5.7011 14.0 84 6.2983 0.2472
5.5803 15.0 90 6.4921 0.2250
5.598 16.0 96 6.2085 0.2488
5.9767 16.7273 100 6.1339 0.2568

Framework versions

  • Transformers 4.48.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.2
  • Tokenizers 0.21.0
Downloads last month
-
Safetensors
Model size
0.1B params
Tensor type
F32
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Mardiyyah/cellate-tapt_base-LR_1e-05

Finetuned
(5)
this model