T5-3B-ch

This model is a fine-tuned version of google-t5/t5-3b on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.4411
• Bleu: 0.2953

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: 32
• eval_batch_size: 32
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 128
• optimizer: Use adamw_torch_fused with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu
0.5699	2.3258	1000	0.5428	0.1328
0.5037	4.6515	2000	0.4777	0.3525
0.476	6.9773	3000	0.4515	0.1759
0.4616	9.3025	4000	0.4411	0.2953

Framework versions

• PEFT 0.18.0
• Transformers 4.57.2
• Pytorch 2.9.1+cu128
• Datasets 4.4.1
• Tokenizers 0.22.1