metadata

license: apache-2.0
base_model: google-t5/t5-base
tags:
  - generated_from_trainer
metrics:
  - rouge
model-index:
  - name: pep_summarization
    results: []

pep_summarization

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

Loss: 0.0564
Rouge1: 89.1468
Rouge2: 88.6354
Rougel: 89.0016
Rougelsum: 89.0138
Gen Len: 63.7246

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: 5e-05
train_batch_size: 4
eval_batch_size: 4
seed: 42
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
num_epochs: 30.0

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	69	0.0463	84.7175	84.1187	84.7778	84.4607	74.1884
No log	2.0	138	0.0312	87.2197	86.9176	87.1927	87.1243	70.0
No log	3.0	207	0.0357	87.3839	87.2143	87.4316	87.3834	68.0580
No log	4.0	276	0.0334	87.8426	87.5124	87.8504	87.7767	68.0580
No log	5.0	345	0.0330	89.2541	88.8329	89.2476	89.1951	65.8551
No log	6.0	414	0.0352	89.8437	89.6094	90.0088	89.8354	67.9565
No log	7.0	483	0.0351	87.6113	87.1275	87.5987	87.4656	68.8841
0.0508	8.0	552	0.0346	90.0332	89.523	89.93	89.9648	64.9275
0.0508	9.0	621	0.0341	90.2056	89.7318	90.0764	90.1856	60.2174
0.0508	10.0	690	0.0405	90.2441	89.7403	90.1241	90.1975	62.4928
0.0508	11.0	759	0.0422	89.9563	89.3932	89.8517	89.919	62.6232
0.0508	12.0	828	0.0462	88.9553	88.5149	88.8596	88.8863	64.5507
0.0508	13.0	897	0.0462	88.3505	87.8014	88.2999	88.1348	68.6087
0.0508	14.0	966	0.0453	89.2841	88.7915	89.0835	89.1838	63.7971
0.0047	15.0	1035	0.0475	89.207	88.8346	89.1459	89.1182	65.4348
0.0047	16.0	1104	0.0526	89.7978	89.3703	89.7601	89.7866	65.9275
0.0047	17.0	1173	0.0517	88.0891	87.7321	88.1064	88.0137	66.4058
0.0047	18.0	1242	0.0503	90.3002	89.7609	90.1585	90.218	62.1014
0.0047	19.0	1311	0.0545	88.9807	88.5391	88.8142	88.8417	65.6957
0.0047	20.0	1380	0.0547	89.2547	88.8381	89.1517	89.158	65.1739
0.0047	21.0	1449	0.0560	88.2792	87.9155	88.2849	88.1559	66.0870
0.0019	22.0	1518	0.0575	88.0891	87.7321	88.1064	88.0137	66.4058
0.0019	23.0	1587	0.0576	87.7192	87.309	87.7299	87.5507	66.0435
0.0019	24.0	1656	0.0558	89.0175	88.5301	88.8811	88.906	64.1594
0.0019	25.0	1725	0.0561	89.0175	88.5301	88.8811	88.906	64.1594
0.0019	26.0	1794	0.0559	90.1169	89.6101	89.9618	90.0139	62.4203
0.0019	27.0	1863	0.0569	89.1468	88.6354	89.0016	89.0138	63.7246
0.0019	28.0	1932	0.0562	89.1468	88.6354	89.0016	89.0138	63.7246
0.0013	29.0	2001	0.0563	89.1468	88.6354	89.0016	89.0138	63.7246
0.0013	30.0	2070	0.0564	89.1468	88.6354	89.0016	89.0138	63.7246

Framework versions

Transformers 4.38.0.dev0
Pytorch 2.1.2+cu121
Datasets 2.16.1
Tokenizers 0.15.0