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.

mos-nllb-600M-mos2fr-latest

This model is a fine-tuned version of goaicorp/mos-nllb-600M-mos2fr on an unknown dataset. It achieves the following results on the evaluation set:

More information needed

More information needed

More information needed

The following hyperparameters were used during training:

learning_rate: 5e-05
train_batch_size: 32
eval_batch_size: 32
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 128
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: cosine
lr_scheduler_warmup_steps: 700
num_epochs: 5

Training Loss	Epoch	Step	Validation Loss	Bleu	Gen Len
6.1907	1.0	1431	1.4179	11.6587	67.3546
5.5986	2.0	2862	1.3201	16.2652	75.2126
5.2717	3.0	4293	1.2700	18.3915	78.3738
5.0063	4.0	5724	1.2509	19.1079	75.177
4.8846	5.0	7155	1.2489	19.4351	78.8268

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

Base model

Finetuned

(1)

this model