finetune_output
This model is a fine-tuned version of
meta-llama/Llama-3.2-1B-Instruct on the gnaf-2022-structured-training-1000000-v0-instruct-train dataset.
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: 5e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- 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_ratio: 0.1
- num_epochs: 2.0
- mixed_precision_training: Native AMP
Training results
Framework versions
- PEFT 0.17.1
- Transformers 4.57.1
- Pytorch 2.8.0+cu126
- Datasets 4.0.0
- Tokenizers 0.22.1
Full training details
model_version='v0.2'
aest_now='20251019-170453'
target_model_name='dylanhogg/gnaf-structured-address-v0.2-712c28b-20251019-170453'
train_args_hash='712c28b'
train_args=
{
"stage": "sft",
"do_train": true,
"model_name_or_path": "meta-llama/Llama-3.2-1B-Instruct",
"dataset": "gnaf-2022-structured-training-1000000-v0-instruct-train",
"eval_dataset": "gnaf-2022-structured-training-1000000-v0-instruct-test",
"template": "llama3",
"finetuning_type": "lora",
"lora_target": "all",
"output_dir": "finetune_output",
"plot_loss": true,
"per_device_train_batch_size": 2,
"gradient_accumulation_steps": 4,
"lr_scheduler_type": "cosine",
"logging_steps": 5,
"warmup_ratio": 0.1,
"save_steps": 1000,
"learning_rate": 5e-05,
"num_train_epochs": 2.0,
"max_samples": 10000,
"max_grad_norm": 1.0,
"loraplus_lr_ratio": 16.0,
"fp16": true,
"report_to": "none"
}
