You can deploy this model and start earning money today!

xummer/
deepseek-r1-8b-belebele-lora-amh-ethi

Name: deepseek-r1-8b-belebele-lora-amh-ethi
Availability: InStock

deepseek-ai/DeepSeek-R1-Distill-Llama-8B

other

Views

No views yet

belebele_amh_Ethi

This model is a fine-tuned version of deepseek-ai/DeepSeek-R1-Distill-Llama-8B on the belebele_amh_Ethi_train dataset. It achieves the following results on the evaluation set:

Loss: 0.7536
Accuracy: 0.8320
Mcq Accuracy: 0.2444

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
0.5234	1.0	40	0.6309	0.8065	0.1333
0.4403	2.0	80	0.5251	0.8291	0.1778
0.2811	3.0	120	0.5499	0.8313	0.2444
0.1551	4.0	160	0.6583	0.8287	0.2222
0.1034	5.0	200	0.7536	0.8320	0.2444

Framework versions

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

xummer/deepseek-r1-8b-belebele-lora-amh-ethi

belebele_amh_Ethi

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

xummer/
deepseek-r1-8b-belebele-lora-amh-ethi