flan_t5_summarization

This model is a fine-tuned version of google/flan-t5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.6162
• Rouge1: 15.9418
• Rouge2: 7.4447
• Rougel: 15.5655
• Rougelsum: 15.5835
• Gen Len: 18.7313

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: 5e-05
• train_batch_size: 12
• eval_batch_size: 12
• 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	272	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7405	2.0	544	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7405	3.0	816	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7453	4.0	1088	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7453	5.0	1360	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7372	6.0	1632	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7372	7.0	1904	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7436	8.0	2176	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7436	9.0	2448	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313
0.7425	10.0	2720	0.6162	15.9418	7.4447	15.5655	15.5835	18.7313

Framework versions

• Transformers 4.26.0
• Pytorch 1.13.1+cu116
• Datasets 2.9.0
• Tokenizers 0.13.2