RuTaskFlow-mBART-T26-200K

This model is a fine-tuned version of facebook/mbart-large-50 on the None dataset. It achieves the following results on the evaluation set:

• Loss: 0.5087
• Rouge1: 85.72
• Rouge2: 63.57
• Rougel: 83.99
• Rougelsum: 83.99

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: 6
• eval_batch_size: 6
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 24
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 4
• mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Rouge1	Rouge2	Rougel	Rougelsum
0.5496	0.9999	6803	0.5541	81.99	59.63	80.24	80.22
0.4657	2.0	13607	0.5035	84.21	62.28	82.5	82.48
0.307	2.9999	20410	0.4942	85.26	62.93	83.5	83.5
0.2345	3.9997	27212	0.5087	85.72	63.57	83.99	83.99

Framework versions

• Transformers 4.45.2
• Pytorch 2.5.1+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3