conversation_kelantan

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

• Loss: 0.0000
• Rouge1: 49.8162
• Rouge2: 48.8893
• Rougel: 50.2619
• Rougelsum: 50.2497
• Gen Len: 18.3889

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
0.003	1.0	1875	0.0000	49.8162	48.8893	50.2619	50.2497	18.3889
0.0009	2.0	3750	0.0000	49.8162	48.8893	50.2619	50.2497	18.3889
0.0003	3.0	5625	0.0000	49.8162	48.8893	50.2619	50.2497	18.3889
0.0002	4.0	7500	0.0000	49.8162	48.8893	50.2619	50.2497	18.3889
0.0001	5.0	9375	0.0000	49.8162	48.8893	50.2619	50.2497	18.3889

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3