Hugging Face's logo

Realgon
/
left_padding90model

Text Classification
Transformers
TensorBoard
Safetensors
distilbert
Generated from Trainer
Eval Results (legacy)
text-embeddings-inference
Model card Files
xet
 Metrics Community
How to use from the
Use from the
Transformers library
# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-classification", model="Realgon/left_padding90model")
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSequenceClassification

tokenizer = AutoTokenizer.from_pretrained("Realgon/left_padding90model")
model = AutoModelForSequenceClassification.from_pretrained("Realgon/left_padding90model", device_map="auto")
Quick Links

left_padding90model

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

  • Accuracy: 0.9290
  • Loss: 0.7641

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: linear
  • num_epochs: 10

Training results

Training Loss Epoch Step Accuracy Validation Loss
0.0369 1.0 1563 0.9254 0.5650
0.0118 2.0 3126 0.9295 0.6178
0.0314 3.0 4689 0.9216 0.5877
0.0093 4.0 6252 0.9212 0.6736
0.0043 5.0 7815 0.9216 0.7475
0.0144 6.0 9378 0.9297 0.6278
0.0034 7.0 10941 0.9258 0.6739
0.0059 8.0 12504 0.9310 0.6986
0.0 9.0 14067 0.9277 0.7724
0.0038 10.0 15630 0.9290 0.7641

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.0.0+cu117
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
5
Safetensors
Model size
67M params
Tensor type
F32
·
Inference Providers NEW
Text Classification
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for Realgon/left_padding90model

Base model

distilbert/distilbert-base-uncased
Finetuned
(12691)
this model

Dataset used to train Realgon/left_padding90model

Evaluation results