flan_t5_small_finetuned

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

• Loss: 1.3412
• Rouge1: 44.9038
• Rouge2: 22.7667
• Rougel: 38.8789
• Rougelsum: 41.7196
• Gen Len: 16.92

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	7	1.4537	43.8958	21.4426	37.7876	41.0621	17.4
No log	2.0	14	1.4025	44.291	21.7752	37.6394	41.0092	17.1
No log	3.0	21	1.3687	44.5803	22.5489	38.5959	41.6202	17.0
No log	4.0	28	1.3487	44.6139	22.5884	38.6786	41.5311	16.94
No log	5.0	35	1.3412	44.9038	22.7667	38.8789	41.7196	16.92

Framework versions

• Transformers 4.30.2
• Pytorch 1.13.1+cpu
• Datasets 2.13.1
• Tokenizers 0.13.3