UNIST-Eunchan/flan-t5-Prompting-NLP-Paper-to-QA-Generation

Prompting-NLP-Paper-to-QA-Generation-abstract-only

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

• Loss: 21.0330

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: 1e-05
• train_batch_size: 1
• eval_batch_size: 1
• seed: 42
• gradient_accumulation_steps: 16
• total_train_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 184
• num_epochs: 15

Training results

Training Loss	Epoch	Step	Validation Loss
No log	0.99	46	42.8265
36.8265	1.99	92	41.8626
36.8265	2.98	138	39.9479
35.1011	3.97	184	37.2276
35.1011	4.97	230	33.5552
28.7673	5.96	276	25.3570
28.7673	6.95	322	22.8463
20.3737	7.95	368	22.0063
20.3737	8.94	414	21.5694
19.2477	9.93	460	21.3303
19.2477	10.93	506	21.1698
18.9724	11.92	552	21.0922
18.9724	12.91	598	21.0487
18.9072	13.91	644	21.0365
18.9072	14.9	690	21.0330

Framework versions

• Transformers 4.35.2
• Pytorch 2.1.0+cu118
• Datasets 2.15.0
• Tokenizers 0.15.0