mt5-large_V8901_V89881

This model is a fine-tuned version of emilstabil/mt5-large_V8901 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.7699
• Rouge1: 27.4218
• Rouge2: 9.9757
• Rougel: 15.034
• Rougelsum: 25.6557
• Gen Len: 542.2616

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: 3e-05
• train_batch_size: 2
• eval_batch_size: 2
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 11

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum	Gen Len
3.5194	2.11	500	2.0126	26.5426	9.1387	14.0294	24.8851	547.0
2.5168	4.21	1000	1.8798	27.1959	9.8737	14.6794	25.5359	547.0
2.1275	6.32	1500	1.8062	27.3601	9.9172	14.9859	25.5846	543.2152
1.9746	8.42	2000	1.7772	27.1321	9.8267	15.0547	25.4467	542.2278
1.9195	10.53	2500	1.7699	27.4218	9.9757	15.034	25.6557	542.2616

Framework versions

• Transformers 4.30.2
• Pytorch 1.12.1+git7548e2f
• Datasets 2.13.2
• Tokenizers 0.13.3