You need to agree to share your contact information to access this model

This repository is publicly accessible, but you have to accept the conditions to access its files and content.

mimba/mbart50-fra2ngiemboon

This model is a fine-tuned version of facebook/mbart-large-50 on the mimba/text2text dataset. It achieves the following results on the evaluation set:

Loss: 1.7816
Chrf: 31.5016
Chrf Plus Plus: 31.5016

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: 1e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
gradient_accumulation_steps: 2
total_train_batch_size: 16
optimizer: Use OptimizerNames.ADAMW_TORCH_FUSED with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: linear
lr_scheduler_warmup_steps: 500
num_epochs: 6
mixed_precision_training: Native AMP

Training results

Training Loss	Epoch	Step	Validation Loss	Chrf	Chrf Plus Plus
2.1721	1.0	2405	2.0448	26.7525	26.7525
1.8762	2.0	4810	1.8418	29.7621	29.7621
1.6973	3.0	7215	1.7565	32.2489	32.2489
1.5754	4.0	9620	1.7212	33.2755	33.2755
1.8376	5.0	12025	1.9832	28.8290	28.8290
1.553	6.0	14430	1.7816	31.5016	31.5016

Framework versions

Transformers 4.57.6
Pytorch 2.10.0+cu126
Datasets 4.5.0
Tokenizers 0.22.2

Downloads last month: 15

Safetensors

Model size

0.6B params

Tensor type

F32

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for mimba/mbart50-ngiemboon2fra

Base model

facebook/mbart-large-50

Finetuned

(343)

this model