sizhkhy/ftni-sample

llm3br256

This model is a fine-tuned version of meta-llama/Llama-3.2-3B-Instruct on the ftni-oneshot-train dataset. It achieves the following results on the evaluation set:

• Loss: 0.0169

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: 4
• eval_batch_size: 4
• seed: 42
• gradient_accumulation_steps: 8
• total_train_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: cosine
• lr_scheduler_warmup_ratio: 0.1
• num_epochs: 5.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.0269	1.5385	5	0.0240
0.0264	3.0769	10	0.0179
0.0123	4.6154	15	0.0169

Framework versions

• PEFT 0.12.0
• Transformers 4.46.1
• Pytorch 2.4.0+cu121
• Datasets 3.1.0
• Tokenizers 0.20.3