flan_t5_small_finetuned_anirbanrc

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

• Loss: 1.5172
• Rouge1: 43.2639
• Rouge2: 20.726
• Rougel: 37.0774
• Rougelsum: 39.6232
• Gen Len: 16.92

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	7	1.6379	42.0058	18.6227	35.3019	38.6413	17.36
No log	2.0	14	1.5869	43.938	20.3595	36.876	40.0421	17.14
No log	3.0	21	1.5483	43.3723	20.3935	36.9286	39.6476	17.0
No log	4.0	28	1.5255	43.9774	21.5464	37.8954	40.5009	16.9
No log	5.0	35	1.5172	43.2639	20.726	37.0774	39.6232	16.92

Framework versions

• Transformers 4.30.2
• Pytorch 1.13.1+cpu
• Datasets 2.13.1
• Tokenizers 0.13.3