README.md

metadata

license: apache-2.0
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: product_description_generator
    results: []

product_description_generator

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

• Loss: 3.3303
• Rouge1: 0.1597
• Rouge2: 0.0
• Rougel: 0.1349
• Rougelsum: 0.1334
• Gen Len: 18.7

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
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	6	3.5039	0.185	0.0105	0.1573	0.1576	15.7
No log	2.0	12	3.4680	0.1915	0.0105	0.1747	0.174	16.9
No log	3.0	18	3.4331	0.1579	0.0105	0.1308	0.1282	17.4
No log	4.0	24	3.4049	0.1579	0.0105	0.1308	0.1282	17.8
No log	5.0	30	3.3817	0.1716	0.0091	0.1476	0.1434	18.5
No log	6.0	36	3.3638	0.1323	0.0	0.1176	0.116	17.1
No log	7.0	42	3.3497	0.1597	0.0	0.1349	0.1334	18.7
No log	8.0	48	3.3394	0.1597	0.0	0.1349	0.1334	18.7
No log	9.0	54	3.3332	0.1597	0.0	0.1349	0.1334	18.7
No log	10.0	60	3.3303	0.1597	0.0	0.1349	0.1334	18.7

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.0+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3