question-context-random-to10-p

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

• Loss: 8.7664
• Rouge1: 0.0054
• Rouge2: 0.0
• Rougel: 0.0054
• Rougelsum: 0.0054
• Gen Len: 12.3333

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

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
No log	1.0	43	16.1624	0.0054	0.0019	0.0054	0.0054	4.2667
No log	2.0	86	13.0632	0.0054	0.0	0.0054	0.0054	4.4667
No log	3.0	129	11.7471	0.0054	0.0	0.0054	0.0054	5.4667
No log	4.0	172	9.8950	0.0054	0.0	0.0054	0.0054	6.2667
No log	5.0	215	9.2587	0.0054	0.0	0.0054	0.0054	7.7333
No log	6.0	258	8.3778	0.0054	0.0	0.0054	0.0054	8.0
No log	7.0	301	8.9698	0.0054	0.0	0.0054	0.0054	10.1333
No log	8.0	344	8.9596	0.0054	0.0	0.0054	0.0054	10.2667
No log	9.0	387	8.7883	0.0054	0.0	0.0054	0.0054	11.4667
No log	10.0	430	8.7664	0.0054	0.0	0.0054	0.0054	12.3333

Framework versions

• Transformers 4.28.0
• Pytorch 2.0.1+cu118
• Datasets 2.12.0
• Tokenizers 0.13.3