flan-t5-base-hai

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: 0.6881
• Rouge1: 39.7841
• Rouge2: 29.2031
• Rougel: 36.6883
• Rougelsum: 37.533
• Gen Len: 17.5106

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: 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: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	118	0.9586	35.7723	22.9975	32.3447	33.2069	17.4894
No log	2.0	236	0.8239	36.2962	24.2274	33.1222	33.8173	17.5447
No log	3.0	354	0.7414	38.4245	27.3598	35.4793	36.3822	17.6596
No log	4.0	472	0.6988	39.386	28.7308	36.4217	37.2752	17.5277
0.8817	5.0	590	0.6881	39.7841	29.2031	36.6883	37.533	17.5106

Framework versions

• Transformers 4.30.2
• Pytorch 2.0.1+cu118
• Datasets 2.13.1
• Tokenizers 0.13.3