mt5-base

This model was trained from scratch on the None dataset. It achieves the following results on the evaluation set:

• Loss: 1.2760
• Bleu: 8.6707
• Gen Len: 16.9319

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: 0.001
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 256
• total_train_batch_size: 2048
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 5

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
No log	1.0	183	1.4997	6.2141	17.0073
No log	2.0	366	1.3718	7.4647	16.9205
1.9408	3.0	549	1.3184	8.1938	16.8962
1.9408	4.0	732	1.2857	8.5265	16.9167
1.9408	5.0	915	1.2760	8.6707	16.9319

Framework versions

• Transformers 4.18.0
• Pytorch 1.11.0+cu113
• Datasets 2.1.0
• Tokenizers 0.12.1