t5-finetuned-NYT

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

• Loss: 2.2519
• Rouge1: 45.692
• Rouge2: 32.1167
• Rougel: 44.3548
• Rougelsum: 44.3959

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: 5.6e-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: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
No log	1.0	2516	2.4293	38.1445	25.9377	36.5758	36.6165
No log	2.0	5032	2.3661	40.356	27.7563	38.993	39.036
No log	3.0	7548	2.3225	43.6557	30.2246	42.2529	42.2804
No log	4.0	10064	2.2852	43.7584	30.4744	42.3437	42.3871
No log	5.0	12580	2.2677	45.6522	32.0921	44.311	44.3587
No log	6.0	15096	2.2598	45.4426	31.7845	44.1273	44.1394
No log	7.0	17612	2.2529	45.6841	32.1469	44.3355	44.37
3.2998	8.0	20128	2.2519	45.692	32.1167	44.3548	44.3959

Framework versions

• Transformers 4.25.1
• Pytorch 1.12.1+cu113
• Datasets 2.7.1
• Tokenizers 0.13.2