flan-t5-small-samsum

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: 1.6307
• Rouge1: 43.9705
• Rouge2: 19.625
• Rougel: 36.5169
• Rougelsum: 39.991
• Gen Len: 16.8034

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
1.8232	1.0	1842	1.6649	42.84	18.7134	35.4575	39.1611	16.9060
1.7366	2.0	3684	1.6412	43.3041	18.979	35.8757	39.4089	16.9121
1.6958	3.0	5526	1.6357	43.4414	19.1581	36.0299	39.5906	16.7937
1.6619	4.0	7368	1.6327	43.7014	19.441	36.3343	39.8082	16.8449
1.6362	5.0	9210	1.6307	43.9705	19.625	36.5169	39.991	16.8034

Framework versions

• Transformers 4.37.2
• Pytorch 2.1.0+cu121
• Datasets 2.16.1
• Tokenizers 0.15.1