idt5-base-qaqg-v1.42-TydiQA-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: 0.9428
• Rouge1: 0.5070
• Rouge2: 0.3356
• Rougel: 0.5058
• Rougelsum: 0.5053
• Bleu: 0.3365
• Rouge All: {'rouge1': 0.5069689942297999, 'rouge2': 0.3355793165915669, 'rougeL': 0.5057816918103952, 'rougeLsum': 0.5053098172718404}
• Bleu All: {'bleu': 0.3365275223783402, 'precisions': [0.5604608139926001, 0.40582726326742974, 0.3292315748134573, 0.2938678444029217], 'brevity_penalty': 0.8737467700098572, 'length_ratio': 0.8810846854856634, 'translation_length': 11892, 'reference_length': 13497}

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
1.4002	1.0	2281	1.0726	0.4478	0.2807	0.4459	0.4463	0.2862	{'rouge1': 0.447773549455706, 'rouge2': 0.28070445946002587, 'rougeL': 0.44589098575657504, 'rougeLsum': 0.4463217785523249}	{'bleu': 0.286219603516708, 'precisions': [0.5052074584243239, 0.3477763923524522, 0.273892012027716, 0.23800580501963461], 'brevity_penalty': 0.8749136331484815, 'length_ratio': 0.8821219530265985, 'translation_length': 11906, 'reference_length': 13497}
1.042	2.0	4562	0.9795	0.4753	0.3047	0.4742	0.4733	0.2976	{'rouge1': 0.47531258513760055, 'rouge2': 0.30465751815947567, 'rougeL': 0.4741518702456516, 'rougeLsum': 0.4732901991716333}	{'bleu': 0.29761996416765446, 'precisions': [0.5385757972913936, 0.3755320309942159, 0.2982284837494769, 0.2664819944598338], 'brevity_penalty': 0.8358615686350978, 'length_ratio': 0.8479662147143809, 'translation_length': 11445, 'reference_length': 13497}
0.9046	3.0	6843	0.9351	0.4944	0.3293	0.4930	0.4924	0.3200	{'rouge1': 0.49440043058754596, 'rouge2': 0.3292538082318104, 'rougeL': 0.4929970255290347, 'rougeLsum': 0.4923957884790322}	{'bleu': 0.3200344552486096, 'precisions': [0.5424468889075489, 0.38630933831931025, 0.31129476584022037, 0.27413587604290823], 'brevity_penalty': 0.8751635206448749, 'length_ratio': 0.8823442246425132, 'translation_length': 11909, 'reference_length': 13497}
0.7298	4.0	9124	0.9297	0.5094	0.3354	0.5079	0.5077	0.3322	{'rouge1': 0.509448548447027, 'rouge2': 0.3353960376629344, 'rougeL': 0.5078926563315382, 'rougeLsum': 0.5077352111892346}	{'bleu': 0.33218064336126607, 'precisions': [0.5631167063627084, 0.40489761452396034, 0.3286190793862575, 0.29385124542762586], 'brevity_penalty': 0.8623495414438967, 'length_ratio': 0.8710083722308661, 'translation_length': 11756, 'reference_length': 13497}
0.6602	5.0	11405	0.9428	0.5070	0.3356	0.5058	0.5053	0.3365	{'rouge1': 0.5069689942297999, 'rouge2': 0.3355793165915669, 'rougeL': 0.5057816918103952, 'rougeLsum': 0.5053098172718404}	{'bleu': 0.3365275223783402, 'precisions': [0.5604608139926001, 0.40582726326742974, 0.3292315748134573, 0.2938678444029217], 'brevity_penalty': 0.8737467700098572, 'length_ratio': 0.8810846854856634, 'translation_length': 11892, 'reference_length': 13497}

Framework versions

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