flan-t5-small-gss

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

• Loss: 3.0813
• Rouge1: 7.7224
• Rouge2: 5.9202
• Rougel: 7.4878
• Rougelsum: 7.3009
• Gen Len: 9.1892

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: 5
• eval_batch_size: 5
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 10
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	33	8.4046	10.9442	6.6413	11.3804	11.0126	10.5946
No log	2.0	66	4.2661	5.3251	1.7316	5.3213	5.2358	7.9730
No log	3.0	99	3.5016	0.6359	0.0	0.318	0.318	3.7838
No log	4.0	132	3.1661	3.3576	2.3166	3.0259	3.0233	6.1351
No log	5.0	165	3.0813	7.7224	5.9202	7.4878	7.3009	9.1892

Framework versions

• Transformers 4.27.1
• Pytorch 1.13.1+cu116
• Datasets 2.10.1
• Tokenizers 0.13.2