t5-small-finetuned-products-BestRe

This model is a fine-tuned version of t5-small on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9154
• Rouge1: 29.8465
• Rouge2: 9.5393
• Rougel: 29.7865
• Rougelsum: 29.7733
• Gen Len: 19.0

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: 3e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1235	0.9982	271	1.0141	26.5311	8.534	26.4863	26.4601	19.0
0.962	2.0	543	0.9526	28.4157	8.9587	28.3862	28.3715	19.0
0.9361	2.9982	814	0.9319	30.1712	9.7636	30.1159	30.1082	19.0
0.9879	4.0	1086	0.9181	29.7166	9.4117	29.6586	29.6496	19.0
0.9967	4.9908	1355	0.9154	29.8465	9.5393	29.7865	29.7733	19.0

Framework versions

• Transformers 4.44.0
• Pytorch 2.3.1+cpu
• Datasets 2.20.0
• Tokenizers 0.19.1