flan-t5-base-dialogsum-summarization

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: 1.2095
• Rouge1: 39.3212
• Rouge2: 15.6335
• Rougel: 33.4773
• Rougelsum: 35.1795
• Gen Len: 18.872

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: 16
• eval_batch_size: 16
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.1318	1.0	1558	1.2331	39.1301	15.2555	33.1115	35.0288	18.868
1.0483	2.0	3116	1.2095	39.3212	15.6335	33.4773	35.1795	18.872
0.9969	3.0	4674	1.2104	40.0115	16.029	34.0364	35.8358	18.852
0.9601	4.0	6232	1.2161	39.7403	15.9708	33.8644	35.5952	18.868

Framework versions

• Transformers 4.38.1
• Pytorch 2.1.2
• Datasets 2.17.1
• Tokenizers 0.15.1