Hugging Face's logo

JunxiongWang
/
Llama3.1-Mamba2-8B-distill

PyTorch
llama
alignment-handbook
Generated from Trainer
Model card Files Community
Llama3.1-Mamba2-8B-distill / README.md
Junxiong Wang
add models
9224e3e
preview code
|
raw
history blame contribute delete
1.88 kB
metadata
license: llama3.1
base_model: meta-llama/Llama-3.1-8B-Instruct
tags:
  - alignment-handbook
  - generated_from_trainer
datasets:
  - JunxiongWang/sftdatasetv3
model-index:
  - name: Llama-Mamba2-3.1-8B-teacher-Llama-3.1-70B-Instruct-kl1.0-ce0.0
    results: []

Visualize in Weights & Biases

Llama-Mamba2-3.1-8B-teacher-Llama-3.1-70B-Instruct-kl1.0-ce0.0

This model is a fine-tuned version of meta-llama/Llama-3.1-8B-Instruct on the JunxiongWang/sftdatasetv3 dataset. It achieves the following results on the evaluation set:

  • Loss: 268.4026

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: 2
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 64
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.01
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
236.7 1.0000 51995 268.4026

Framework versions

  • Transformers 4.43.1
  • Pytorch 2.1.1+cu118
  • Datasets 2.20.0
  • Tokenizers 0.19.1