t5-small-canadaWildfireKP

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

• Loss: 0.9108
• Rouge1: 45.9651
• Rouge2: 39.4386
• Rougel: 45.9311
• Rougelsum: 45.9452
• Gen Len: 8.7484

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
1.2141	1.0	6015	1.0340	43.8621	37.4812	43.7904	43.7672	9.4331
1.0575	2.0	12030	1.0058	46.0317	39.5737	46.0188	46.032	9.3363
0.9392	3.0	18045	0.9552	44.3467	37.8118	44.3349	44.3262	8.9630
0.8959	4.0	24060	0.9384	45.3347	38.7573	45.313	45.3346	8.9434
0.8197	5.0	30075	0.9164	45.3703	38.8341	45.3714	45.3623	8.7409
0.8302	6.0	36090	0.9161	45.5709	39.1509	45.5322	45.53	8.7904
0.7883	7.0	42105	0.9108	45.9651	39.4386	45.9311	45.9452	8.7484
0.7381	8.0	48120	0.9142	45.4087	38.9851	45.4047	45.4117	8.6583

Framework versions

• Transformers 4.39.3
• Pytorch 2.2.1+cu121
• Datasets 2.18.0
• Tokenizers 0.15.2