seven_epoch

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

• Loss: 2.6967
• Rouge1: 0.2471
• Rouge2: 0.1156
• Rougel: 0.221
• Rougelsum: 0.2214
• Gen Len: 17.57

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 7

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	107	3.2445	0.1098	0.0185	0.0968	0.0967	18.47
No log	2.0	214	2.9257	0.1353	0.0337	0.119	0.1191	17.94
No log	3.0	321	2.8182	0.2021	0.0797	0.1801	0.1795	17.45
No log	4.0	428	2.7577	0.2358	0.1081	0.2096	0.2089	17.53
3.0898	5.0	535	2.7202	0.2347	0.1059	0.211	0.2094	17.31
3.0898	6.0	642	2.7035	0.2429	0.1124	0.2191	0.2188	17.58
3.0898	7.0	749	2.6967	0.2471	0.1156	0.221	0.2214	17.57

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0