koja_mbartLarge_55p_run2

This model is a fine-tuned version of facebook/mbart-large-50-many-to-many-mmt on an unknown dataset. It achieves the following results on the evaluation set:

• Loss: 0.9303
• Bleu: 57.3778
• Gen Len: 16.682

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: 5e-05
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 4
• gradient_accumulation_steps: 2
• total_train_batch_size: 32
• total_eval_batch_size: 16
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• num_epochs: 10

Training results

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
1.0633	0.48	8000	1.0419	52.4575	17.4003
0.9731	0.97	16000	0.9550	55.7136	16.9686
0.7608	1.45	24000	0.9372	56.8788	16.7537
0.7213	1.93	32000	0.9303	57.4421	16.6742
0.5702	2.42	40000	0.9622	56.774	16.4703
0.5416	2.9	48000	0.9697	57.4192	16.6763
0.4226	3.38	56000	1.0399	56.5425	16.4626

Framework versions

• Transformers 4.34.1
• Pytorch 2.1.0+cu121
• Datasets 2.14.6
• Tokenizers 0.14.1