idt5-base-qaqg-v2.42-SQuAD-id

This model is a fine-tuned version of muchad/idt5-base on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.4294
• Rouge1: 0.4081
• Rouge2: 0.2248
• Rougel: 0.3872
• Rougelsum: 0.3876
• Bleu: 0.1771
• Rouge All: {'rouge1': 0.4080957436925446, 'rouge2': 0.22480148208342282, 'rougeL': 0.3872231168699847, 'rougeLsum': 0.38764789209692174}
• Bleu All: {'bleu': 0.1770980316514973, 'precisions': [0.45895853899308986, 0.2570973348783314, 0.16511341053929968, 0.10789882314481856], 'brevity_penalty': 0.8270775126765066, 'length_ratio': 0.8404372264741875, 'translation_length': 81040, 'reference_length': 96426}

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: 4
• eval_batch_size: 4
• seed: 42
• optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Bleu	Rouge All	Bleu All
1.7449	1.0	12000	1.5397	0.3718	0.1965	0.3533	0.3535	0.1399	{'rouge1': 0.3718490946895444, 'rouge2': 0.1965156871711558, 'rougeL': 0.3532814746728979, 'rougeLsum': 0.35350493960191764}	{'bleu': 0.13990472949361535, 'precisions': [0.42520926536001336, 0.21737286209874113, 0.13068181818181818, 0.08154145077720207], 'brevity_penalty': 0.789736089247161, 'length_ratio': 0.8090245369506149, 'translation_length': 78011, 'reference_length': 96426}
1.4802	2.0	24000	1.4458	0.3903	0.2079	0.3715	0.3718	0.1499	{'rouge1': 0.390296728889544, 'rouge2': 0.2079388140702012, 'rougeL': 0.37146644580354204, 'rougeLsum': 0.37175821558659095}	{'bleu': 0.1499406165507238, 'precisions': [0.457939908398587, 0.24424767425103677, 0.1514562359236944, 0.09714871890518266], 'brevity_penalty': 0.7444379431558352, 'length_ratio': 0.7721257752058573, 'translation_length': 74453, 'reference_length': 96426}
1.3736	3.0	36000	1.4235	0.3994	0.2149	0.3794	0.3799	0.1595	{'rouge1': 0.39943581750724466, 'rouge2': 0.2149293515258604, 'rougeL': 0.37943997124432577, 'rougeLsum': 0.3798861838257821}	{'bleu': 0.15953274975691906, 'precisions': [0.46006610107739554, 0.2495990871522852, 0.15637413564808003, 0.09991388637417474], 'brevity_penalty': 0.7751510694188312, 'length_ratio': 0.7970049571692283, 'translation_length': 76852, 'reference_length': 96426}
1.2742	4.0	48000	1.4191	0.4027	0.2179	0.3830	0.3833	0.1627	{'rouge1': 0.4027028582003752, 'rouge2': 0.21790835565234015, 'rougeL': 0.38296077727467603, 'rougeLsum': 0.38328696528807565}	{'bleu': 0.16272036867527373, 'precisions': [0.46325611745513867, 0.2535860735009671, 0.16049405475159, 0.10453792646571712], 'brevity_penalty': 0.7722751692387979, 'length_ratio': 0.7946508203181715, 'translation_length': 76625, 'reference_length': 96426}
1.1521	5.0	60000	1.4294	0.4081	0.2248	0.3872	0.3876	0.1771	{'rouge1': 0.4080957436925446, 'rouge2': 0.22480148208342282, 'rougeL': 0.3872231168699847, 'rougeLsum': 0.38764789209692174}	{'bleu': 0.1770980316514973, 'precisions': [0.45895853899308986, 0.2570973348783314, 0.16511341053929968, 0.10789882314481856], 'brevity_penalty': 0.8270775126765066, 'length_ratio': 0.8404372264741875, 'translation_length': 81040, 'reference_length': 96426}

Framework versions

• Transformers 4.57.1
• Pytorch 2.9.0+cu129
• Datasets 4.2.0
• Tokenizers 0.22.1