flan-t5-base-samsum

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: 1.4179
• Rouge1: 47.0205
• Rouge2: 22.1222
• Rougel: 39.632
• Rougelsum: 43.699
• Gen Len: 17.58

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	38	1.4191	47.4088	23.3573	40.3184	44.0528	17.18
No log	2.0	76	1.4179	47.0205	22.1222	39.632	43.699	17.58
No log	3.0	114	1.4206	47.5761	22.5403	39.8967	44.3589	17.46
No log	4.0	152	1.4283	47.2004	22.2872	39.3765	43.9613	17.58
No log	5.0	190	1.4301	47.2497	22.1798	39.6196	43.9584	17.61

Framework versions

• Transformers 4.33.1
• Pytorch 2.0.1+cu118
• Datasets 2.14.5
• Tokenizers 0.13.3