bmd1905's picture
Training complete
ad43750 verified
metadata
tags:
  - generated_from_trainer
metrics:
  - accuracy
model-index:
  - name: mamba_text_classification
    results: []

mamba_text_classification

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 0.2351
  • Accuracy: 0.9406

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: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss Accuracy
0.0061 0.1 625 0.2807 0.9074
1.7561 0.2 1250 0.2201 0.9252
0.0296 0.3 1875 0.3153 0.9184
0.0057 0.4 2500 0.2213 0.9342
0.0002 0.5 3125 0.2311 0.935
2.8004 0.6 3750 0.2264 0.9378
0.0143 0.7 4375 0.2599 0.9348
0.0021 0.8 5000 0.2267 0.939
0.2814 0.9 5625 0.2343 0.942
0.069 1.0 6250 0.2351 0.9406

Framework versions

  • Transformers 4.38.1
  • Pytorch 2.1.1+cu118
  • Datasets 2.17.1
  • Tokenizers 0.15.2