t5-small-greeceWildfireKP

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

• Loss: 1.0172
• Rouge1: 42.4498
• Rouge2: 32.029
• Rougel: 42.3347
• Rougelsum: 42.4464
• Gen Len: 7.0250

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
1.1637	1.0	6255	1.1113	39.9978	28.5698	39.7044	39.7788	6.8378
1.0009	2.0	12510	1.1041	39.7716	28.1562	39.486	39.5699	6.7668
0.9468	3.0	18765	1.0590	41.5251	30.4922	41.3609	41.4653	7.0351
0.8608	4.0	25020	1.0279	43.1567	32.6989	43.0861	43.1628	7.2114
0.8378	5.0	31275	1.0172	42.4498	32.029	42.3347	42.4464	7.0250
0.8076	6.0	37530	1.0351	42.8131	31.9118	42.7036	42.802	7.1778
0.7264	7.0	43785	1.0319	43.4766	32.7878	43.3806	43.4906	7.2527
0.7472	8.0	50040	1.0472	43.012	32.2029	42.9432	42.9966	7.0562

Framework versions

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