mt5_base-silver-standard-lora

This model is a fine-tuned version of google/mt5-base on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 2.0014
• Rouge1: 37.7941
• Rouge2: 22.0953
• Rougel: 36.8509
• Rougelsum: 36.9714

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: 0.0003
• train_batch_size: 8
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 2
• total_train_batch_size: 16
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: linear
• num_epochs: 3
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
35.0066	1.0	149	3.0369	15.5109	5.2653	15.0068	15.042
12.4424	2.0	298	2.0791	33.6692	19.2782	32.7224	32.7674
11.1139	3.0	447	2.0014	37.7941	22.0953	36.8509	36.9714

Framework versions

• PEFT 0.18.1
• Transformers 5.0.0
• Pytorch 2.10.0+cu128
• Datasets 4.8.3
• Tokenizers 0.22.2