summarization_model

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

• Loss: 2.3498
• Rouge1: 0.2026
• Rouge2: 0.0961
• Rougel: 0.1673
• Rougelsum: 0.167
• Gen Len: 20.0

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: 2e-05
• train_batch_size: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• 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	62	2.7994	0.1344	0.0398	0.1102	0.1104	20.0
No log	2.0	124	2.5713	0.154	0.0588	0.1246	0.1243	20.0
No log	3.0	186	2.4844	0.162	0.0621	0.1313	0.1311	20.0
No log	4.0	248	2.4358	0.1892	0.0847	0.1551	0.1549	20.0
No log	5.0	310	2.4020	0.1969	0.0947	0.1631	0.1628	20.0
No log	6.0	372	2.3818	0.1998	0.096	0.1653	0.1652	20.0
No log	7.0	434	2.3649	0.2014	0.0967	0.167	0.1668	20.0
No log	8.0	496	2.3570	0.2013	0.0959	0.1667	0.1665	20.0
2.7505	9.0	558	2.3518	0.2021	0.0962	0.1669	0.1668	20.0
2.7505	10.0	620	2.3498	0.2026	0.0961	0.1673	0.167	20.0

Framework versions

• Transformers 4.53.2
• Pytorch 2.11.0+cu128
• Datasets 4.0.0
• Tokenizers 0.21.4