T5-based-Masked-keywords-to-Sentence-Epoch-10

This model is a fine-tuned version of mrm8488/t5-base-finetuned-common_gen on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.3073
• Bleu: 6.3322
• Gen Len: 13.3221

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: 128
• eval_batch_size: 128
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
2.255	1.0	527	2.2946	6.3492	13.0607
2.2177	2.0	1054	2.2913	6.3936	13.0821
2.2031	3.0	1581	2.2970	6.3451	13.1381
2.1827	4.0	2108	2.2992	6.4297	13.1899
2.1762	5.0	2635	2.3026	6.3671	13.3084
2.1623	6.0	3162	2.3047	6.3458	13.343
2.1572	7.0	3689	2.3061	6.3492	13.3079
2.1461	8.0	4216	2.3054	6.3986	13.3081
2.1466	9.0	4743	2.3075	6.3311	13.2982
2.1402	10.0	5270	2.3073	6.3322	13.3221

Framework versions

• Transformers 4.37.2
• Pytorch 2.2.2+cu118
• Datasets 2.18.0
• Tokenizers 0.15.1