flan-t5-base-dialoguSum_Solar_koen

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: 2.8520
• Rouge1: 11.9395
• Rouge2: 3.75
• Rougel: 10.3395
• Rougelsum: 11.9395
• Gen Len: 13.0

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• 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	5	2.9176	9.0824	3.75	9.0824	9.0824	11.6
No log	2.0	10	2.8520	11.9395	3.75	10.3395	11.9395	13.0
No log	3.0	15	2.8061	11.9395	3.75	10.3395	11.9395	13.0
No log	4.0	20	2.7792	7.3071	0.0	5.7	7.3071	16.2
No log	5.0	25	2.7691	10.1643	0.0	7.7381	10.1643	15.8

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0+cu121
• Datasets 2.21.0
• Tokenizers 0.19.1