mt5-base-qaqg-finetuned-SQuAD-id-sentence

This model is a fine-tuned version of google/mt5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4176
• Rouge: {'rouge1': 0.431906438503008, 'rouge2': 0.25499026452104945, 'rougeL': 0.39204274842839615, 'rougeLsum': 0.39456014504144676}
• Rouge1: 0.4319
• Rouge2: 0.2550
• Rougel: 0.3920
• Rougelsum: 0.3946
• Bleu: 0.2255

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: 0.0001
• 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	Rouge	Rouge1	Rouge2	Rougel	Rougelsum	Bleu
1.8092	1.0	2000	1.5726	{'rouge1': 0.38857764947308354, 'rouge2': 0.2144816356866815, 'rougeL': 0.34718290508264066, 'rougeLsum': 0.3491704618702567}	0.3886	0.2145	0.3472	0.3492	0.2027
1.448	2.0	4000	1.4578	{'rouge1': 0.4201425066563658, 'rouge2': 0.24245589461633016, 'rougeL': 0.3801327577125928, 'rougeLsum': 0.38306624507182285}	0.4201	0.2425	0.3801	0.3831	0.2179
1.2703	3.0	6000	1.4241	{'rouge1': 0.42984982575843933, 'rouge2': 0.2542816232928319, 'rougeL': 0.38888435744081745, 'rougeLsum': 0.39130709798526525}	0.4298	0.2543	0.3889	0.3913	0.2251
1.2228	4.0	8000	1.4314	{'rouge1': 0.4293519247279466, 'rouge2': 0.2525711759038574, 'rougeL': 0.3885634471147471, 'rougeLsum': 0.3910623048069688}	0.4294	0.2526	0.3886	0.3911	0.2240
1.1391	5.0	10000	1.4176	{'rouge1': 0.431906438503008, 'rouge2': 0.25499026452104945, 'rougeL': 0.39204274842839615, 'rougeLsum': 0.39456014504144676}	0.4319	0.2550	0.3920	0.3946	0.2255

Framework versions

• Transformers 4.44.2
• Pytorch 2.4.0a0+f70bd71a48.nv24.06
• Datasets 2.21.0
• Tokenizers 0.19.1