cellate-tapt_base-LR_2e-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: 4.9618
  • Accuracy: 0.3431

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: 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: 0.1
  • num_epochs: 20
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
10.1666 1.0 6 11.0374 0.0
9.6209 2.0 12 9.6987 0.0
8.2654 3.0 18 8.4261 0.0281
7.3452 4.0 24 7.7401 0.0637
6.7638 5.0 30 7.0736 0.1537
6.2231 6.0 36 6.6987 0.1956
5.7561 7.0 42 6.2060 0.2480
5.4166 8.0 48 5.9637 0.2752
5.1312 9.0 54 5.7060 0.2832
4.9182 10.0 60 5.5990 0.2995
4.6794 11.0 66 5.3070 0.3117
4.5745 12.0 72 5.2026 0.3180
4.4439 13.0 78 5.0539 0.3331
4.412 14.0 84 5.0538 0.3469
4.2761 15.0 90 5.2681 0.3167
4.3235 16.0 96 4.9841 0.3259
4.5983 16.7273 100 4.9618 0.3431

Framework versions

  • Transformers 4.48.2
  • Pytorch 2.4.1+cu121
  • Datasets 3.0.2
  • Tokenizers 0.21.0
Downloads last month
12
Safetensors
Model size
0.1B 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 Mardiyyah/cellate-tapt_base-LR_2e-05

Finetuned
(5)
this model

Evaluation results