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