first_sentences_based_model

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

• Loss: 2.2821
• Rouge1: 0.2693
• Rouge2: 0.1679
• Rougel: 0.2565
• Rougelsum: 0.2559
• 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: 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	106	3.0079	0.1316	0.0477	0.1134	0.1133	19.0
No log	2.0	212	2.6733	0.2296	0.1302	0.2121	0.2121	19.0
No log	3.0	318	2.5159	0.2535	0.1472	0.2367	0.2371	19.0
No log	4.0	424	2.4352	0.2588	0.153	0.244	0.2438	19.0
3.0707	5.0	530	2.3773	0.2654	0.1624	0.2515	0.2515	19.0
3.0707	6.0	636	2.3391	0.2624	0.1607	0.2499	0.2495	19.0
3.0707	7.0	742	2.3124	0.2672	0.1662	0.2542	0.2538	19.0
3.0707	8.0	848	2.2952	0.2688	0.1677	0.2557	0.255	19.0
3.0707	9.0	954	2.2854	0.2692	0.1689	0.2567	0.2562	19.0
2.5484	10.0	1060	2.2821	0.2693	0.1679	0.2565	0.2559	19.0

Framework versions

• Transformers 4.41.2
• Pytorch 2.3.0+cu121
• Datasets 2.20.0
• Tokenizers 0.19.1