peft_ft_fl_mod_ind / README.md
ishikaibm's picture
Model save
f0ba4f0 verified
|
raw
history blame
1.8 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: google-bert/bert-base-uncased
metrics:
  - accuracy
model-index:
  - name: peft_ft_fl_mod_ind
    results: []

peft_ft_fl_mod_ind

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

  • Loss: 11.2143
  • Accuracy: -5278.2032

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: 0.005
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 5
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy
No log 1.0 1 11.2884 13619.4675
No log 2.0 2 12.4142 -34586.9665
No log 3.0 3 12.0917 -36170.8404
No log 4.0 4 11.3609 -34348.1929
No log 5.0 5 11.2143 -5278.2032

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.1
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1