flan-t5-base_twon-generative-agent

This model was trained from scratch on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 3.4169
• Rouge1: 10.2333
• Rouge2: 3.5054
• Rougel: 9.3072
• Rougelsum: 9.5746
• 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: 4e-05
• train_batch_size: 24
• eval_batch_size: 24
• 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
3.8525	1.19	100	3.5675	9.3174	3.159	8.733	8.9542	19.0
3.7039	2.38	200	3.5041	9.3909	2.9968	8.7403	8.9773	19.0
3.5969	3.57	300	3.4671	9.3084	2.9709	8.5531	8.8267	19.0
3.5688	4.76	400	3.4485	9.7453	3.2357	8.9905	9.2249	19.0
3.5208	5.95	500	3.4338	10.0439	3.2804	9.2699	9.5649	19.0
3.4951	7.14	600	3.4240	9.9809	3.4881	9.1725	9.4274	19.0
3.4748	8.33	700	3.4196	10.1212	3.5683	9.2865	9.5681	19.0
3.4427	9.52	800	3.4169	10.2333	3.5054	9.3072	9.5746	19.0

Framework versions

• Transformers 4.31.0
• Pytorch 2.0.1+cu117
• Datasets 2.14.3
• Tokenizers 0.13.3