flan-t5-base-finetuned-xsum

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

• Loss: nan
• Rouge1: 37.215
• Rouge2: 20.5293
• Rougel: 34.9978
• Rougelsum: 35.1065
• Gen Len: 14.4

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: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	17	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	2.0	34	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	3.0	51	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	4.0	68	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	5.0	85	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	6.0	102	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	7.0	119	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	8.0	136	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	9.0	153	nan	37.215	20.5293	34.9978	35.1065	14.4
No log	10.0	170	nan	37.215	20.5293	34.9978	35.1065	14.4

Framework versions

• Transformers 4.34.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.14.1