summarise_cy

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

• Loss: nan
• Rouge1: 0.1434
• Rouge2: 0.0535
• Rougel: 0.1286
• Rougelsum: 0.1287
• Gen Len: 20.0

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: 2e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	410	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	2.0	820	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	3.0	1230	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	4.0	1640	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	5.0	2050	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	6.0	2460	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	7.0	2870	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	8.0	3280	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	9.0	3690	nan	0.1434	0.0535	0.1286	0.1287	20.0
0.0	10.0	4100	nan	0.1434	0.0535	0.1286	0.1287	20.0

Framework versions

• Transformers 4.52.4
• Pytorch 2.6.0+cu124
• Datasets 3.6.0
• Tokenizers 0.21.1