Hugging Face's logo

kajamo
/
model_16

PEFT
TensorBoard
Safetensors
Generated from Trainer
Model card Files Metrics Community
model_16 / README.md
kajamo's picture
kajamo
Model save
c3328c8 verified
preview code
|
raw
history blame contribute delete
1.38 kB
metadata
license: apache-2.0
library_name: peft
tags:
  - generated_from_trainer
base_model: distilbert-base-uncased
model-index:
  - name: model_16
    results: []

model_16

This model is a fine-tuned version of distilbert-base-uncased on an unknown dataset. It achieves the following results on the evaluation set:

  • eval_loss: 0.6194
  • eval_accuracy: 0.7624
  • eval_precision: 0.7632
  • eval_recall: 0.7624
  • eval_f1: 0.7621
  • eval_runtime: 42.8182
  • eval_samples_per_second: 285.977
  • eval_steps_per_second: 17.89
  • epoch: 14.0
  • step: 42868

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: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_steps: 100
  • num_epochs: 20

Framework versions

  • PEFT 0.11.1
  • Transformers 4.41.2
  • Pytorch 2.1.2
  • Datasets 2.19.2
  • Tokenizers 0.19.1