flan-t5-s

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

• Loss: 0.2736
• Rouge1: 40.152
• Rouge2: 15.8816
• Rougel: 33.4399
• Rougelsum: 35.9029
• Gen Len: 19.886

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: 1e-05
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
0.347	1.0	2307	0.2918	38.3203	14.7065	31.7739	34.536	19.904
0.2765	2.0	4615	0.2817	38.9417	15.3147	32.5082	35.1789	19.884
0.2683	3.0	6922	0.2776	39.3458	15.3133	32.7661	35.2993	19.878
0.2635	4.0	9230	0.2751	39.7671	15.7051	33.1173	35.6438	19.884
0.2611	5.0	11537	0.2738	39.8607	15.5855	33.1643	35.6319	19.882
0.2592	6.0	13842	0.2736	40.152	15.8816	33.4399	35.9029	19.886

Framework versions

• Transformers 4.36.1
• Pytorch 2.1.2
• Datasets 2.20.0
• Tokenizers 0.15.2