This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the gsm8k_bn_train dataset. It achieves the following results on the evaluation set:

Loss: 0.2219
Accuracy: 0.9297
Mcq Accuracy: 0.9113

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: 0.0001
train_batch_size: 1
eval_batch_size: 1
seed: 42
gradient_accumulation_steps: 16
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: cosine
lr_scheduler_warmup_steps: 0.1
num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy	Mcq Accuracy
0.2139	0.64	200	0.2189	0.9281	0.9021
0.1775	1.2784	400	0.2170	0.9289	0.9052
0.1770	1.9184	600	0.2111	0.9310	0.9113
0.1448	2.5568	800	0.2221	0.9296	0.9098

Framework versions

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

xummer/llama3-1-8b-gsm8k-fromEn-n5000-seed42-lora-bn

bn

Model description

Intended uses & limitations

Training and evaluation data

Training procedure

Training hyperparameters

Training results

Framework versions

xummer/
llama3-1-8b-gsm8k-fromEn-n5000-seed42-lora-bn