LLama3-1B-finetuning

This model is a fine-tuned version of meta-llama/Llama-3.2-1B on the None dataset. It achieves the following results on the evaluation set:

  • Loss: 0.3472
  • Accuracy: 0.8694
  • F1 Macro: 0.8692

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: 2e-05
  • train_batch_size: 16
  • eval_batch_size: 16
  • seed: 42
  • gradient_accumulation_steps: 2
  • total_train_batch_size: 32
  • optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 10
  • mixed_precision_training: Native AMP

Training results

Training Loss Epoch Step Validation Loss Accuracy F1 Macro
1.3459 1.0 360 0.7530 0.6667 0.6615
0.8291 2.0 720 0.4807 0.8021 0.7951
0.8198 3.0 1080 0.4037 0.8306 0.8255
0.6597 4.0 1440 0.4082 0.8292 0.8270
0.5621 5.0 1800 0.3817 0.8438 0.8410
0.5646 6.0 2160 0.3784 0.8472 0.8453
0.4532 7.0 2520 0.3879 0.8431 0.8401

Framework versions

  • PEFT 0.14.0
  • Transformers 4.47.1
  • Pytorch 2.5.1+cu121
  • Datasets 3.2.0
  • Tokenizers 0.21.0
Downloads last month
24
Inference Providers NEW
This model is not currently available via any of the supported third-party Inference Providers, and HF Inference API was unable to determine this model’s pipeline type.

Model tree for msab97/LLama3-1B-finetuning

Adapter
(231)
this model