Hugging Face's logo

gulaschnascher4000
/
lora_0-3_3B

PEFT
TensorBoard
Safetensors
llama-factory
lora
Generated from Trainer
Model card Files Metrics Community
lora_0-3_3B / README.md
gulaschnascher4000's picture
gulaschnascher4000
End of training
1a5aca6 verified
preview code
|
raw
history blame contribute delete
1.62 kB
metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-3B
tags:
  - llama-factory
  - lora
  - generated_from_trainer
model-index:
  - name: lora_0-3_3B
    results: []

lora_0-3_3B

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the gulaschnascher4000/stream-dataset-0-2 and the identity-chatgulaschpt datasets. It achieves the following results on the evaluation set:

  • Loss: 1.7561

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: 8
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • total_train_batch_size: 32
  • total_eval_batch_size: 4
  • optimizer: Use OptimizerNames.ADAFACTOR and the args are: scale_parameter=True, relative_step=True, warmup_init=True, lr=None
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 0.5

Training results

Training Loss Epoch Step Validation Loss
1.6649 0.4505 500 1.7574

Framework versions

  • PEFT 0.12.0
  • Transformers 4.46.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.1.0
  • Tokenizers 0.20.3