disc5 / README.md
yyyjwang's picture
Upload model weights
fd20b0f verified
metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-3B
tags:
  - generated_from_trainer
datasets:
  - TIGER-Lab/MathInstruct
metrics:
  - accuracy
model-index:
  - name: 1e-6_noniid_disc5
    results:
      - task:
          type: text-generation
          name: Causal Language Modeling
        dataset:
          name: TIGER-Lab/MathInstruct default
          type: TIGER-Lab/MathInstruct
          args: default
        metrics:
          - type: accuracy
            value: 0.34
            name: Accuracy

1e-6_noniid_disc5

This model is a fine-tuned version of meta-llama/Llama-3.2-3B on the TIGER-Lab/MathInstruct default dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8627
  • Accuracy: 0.34

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: 1.8825509907063326e-07
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 4
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 1.0

Training results

Framework versions

  • PEFT 0.11.1
  • Transformers 4.45.2
  • Pytorch 2.5.1+cu124
  • Datasets 2.19.0
  • Tokenizers 0.20.3