You can deploy this model and start earning money today!

xummer/
mistral-7b-belebele-lora-ell-grek

Name: mistral-7b-belebele-lora-ell-grek
Availability: InStock

mistralai/Mistral-7B-Instruct-v0.3

other

Views

No views yet

belebele_ell_Grek

This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the belebele_ell_Grek_train dataset. It achieves the following results on the evaluation set:

Loss: 0.1772
Accuracy: 0.9538
Mcq Accuracy: 0.5114

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: 0.0002
train_batch_size: 16
eval_batch_size: 16
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: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Mcq Accuracy
0.2988	1.0256	40	0.1741	0.9510	0.375
0.0889	2.0513	80	0.1497	0.9500	0.5341
0.0419	3.0769	120	0.1673	0.9555	0.5568
0.0029	4.1026	160	0.1727	0.9521	0.5

Framework versions

PEFT 0.18.1
Transformers 5.2.0
Pytorch 2.10.0+cu128
Datasets 4.0.0
Tokenizers 0.22.2

xummer/mistral-7b-belebele-lora-ell-grek

belebele_ell_Grek

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

xummer/
mistral-7b-belebele-lora-ell-grek