Edit model card

flan-t5-small-ecommerce-text-classification

This model is a fine-tuned version of google/flan-t5-small on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 1.3475
  • Precision: 0.5168
  • Recall: 0.5168
  • F1: 0.5168
  • Precision Relaxed: 0.7526
  • Recall Relaxed: 0.7526
  • F1 Relaxed: 0.7526

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: 0.0003
  • train_batch_size: 16
  • eval_batch_size: 8
  • seed: 42
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 4

Training results

Training Loss Epoch Step Validation Loss Precision Recall F1 Precision Relaxed Recall Relaxed F1 Relaxed
1.3326 0.5865 4000 1.3469 0.4962 0.4962 0.4962 0.7181 0.7181 0.7181
1.2357 1.1730 8000 1.3094 0.5126 0.5126 0.5126 0.7321 0.7321 0.7321
1.2072 1.7595 12000 1.2919 0.5121 0.5121 0.5121 0.7459 0.7459 0.7459
1.1547 2.3460 16000 1.3003 0.5161 0.5161 0.5161 0.7453 0.7453 0.7453
1.1438 2.9326 20000 1.3029 0.5204 0.5204 0.5204 0.7476 0.7476 0.7476
1.0799 3.5191 24000 1.3393 0.5179 0.5179 0.5179 0.7506 0.7506 0.7506

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1
Downloads last month
7
Safetensors
Model size
60.8M params
Tensor type
F32
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Model tree for Terrasse/flan-t5-small-ecommerce-text-classification

Finetuned
(297)
this model