mT5-TextSimp-LT-BatchSize8

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

• Loss: 0.5250
• Rouge1: 0.0062
• Rouge2: 0.0
• Rougel: 0.0062
• Gen Len: 39.0501

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: 8
• eval_batch_size: 8
• seed: 42
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_steps: 500
• num_epochs: 8

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Gen Len
16.3791	0.96	200	11.2580	0.0041	0.0001	0.0041	512.0
1.4082	1.91	400	0.9502	0.0237	0.0002	0.0234	39.0501
0.7272	2.87	600	0.6131	0.0033	0.0	0.0032	39.0501
0.6517	3.83	800	0.5775	0.0019	0.0	0.0018	39.0501
0.6625	4.78	1000	0.5559	0.0014	0.0	0.0014	39.0501
0.5423	5.74	1200	0.5359	0.0016	0.0	0.0016	39.0501
0.7486	6.7	1400	0.5289	0.007	0.0	0.0069	39.0501
0.6712	7.66	1600	0.5250	0.0062	0.0	0.0062	39.0501

Framework versions

• Transformers 4.36.2
• Pytorch 2.1.1
• Datasets 2.16.1
• Tokenizers 0.15.0