flan-t5-small-code_de_travail

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: 1.8644
• Rouge1: 25.4859
• Rouge2: 9.5703
• Rougel: 20.373
• Rougelsum: 22.7081
• Gen Len: 19.0

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	100	1.9280	25.07	8.9144	19.6643	22.1851	19.0
No log	2.0	200	1.8979	25.3572	9.3844	20.223	22.645	19.0
No log	3.0	300	1.8786	25.3392	9.4074	20.2737	22.6969	19.0
No log	4.0	400	1.8671	25.2214	9.3115	20.2123	22.5665	19.0
2.1021	5.0	500	1.8644	25.4859	9.5703	20.373	22.7081	19.0

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.2+cu121
• Datasets 2.16.1
• Tokenizers 0.15.2