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.

malagasy-to-betsim-t5-base-v2

This model is a fine-tuned version of t5-base on the None 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: 3e-05
train_batch_size: 8
eval_batch_size: 8
seed: 42
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
num_epochs: 50
mixed_precision_training: Native AMP

Training Loss	Epoch	Step	Validation Loss
1.4493	3.3333	500	1.1330
1.0069	6.6667	1000	0.9316
0.8069	10.0	1500	0.8125
0.6822	13.3333	2000	0.7414
0.5971	16.6667	2500	0.7125
0.5318	20.0	3000	0.6861
0.4788	23.3333	3500	0.6627
0.442	26.6667	4000	0.6569
0.4048	30.0	4500	0.6473
0.3801	33.3333	5000	0.6444
0.3633	36.6667	5500	0.6372
0.3446	40.0	6000	0.6347
0.3301	43.3333	6500	0.6296
0.3274	46.6667	7000	0.6292
0.3192	50.0	7500	0.6292

Safetensors

Model size

0.2B params

Tensor type

F32

Inference Providers NEW

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

Base model

Finetuned

(713)

this model