VOOZH about

URL: https://huggingface.co/lapp0/distily_modelcard_try

⇱ lapp0/distily_modelcard_try · Hugging Face


Summary

Distilled with Distily library using teacher model gpt2 on dataset wikimedia/wikipedia.

Model Architecture:

  • Architecture: GPT2LMHeadModel
  • Total Parameters: 124,439,808
  • Data Type (dtype): torch.bfloat16
  • Model Size: 0.24 GB

Evaluation Metrics Comparison

step epoch enwikippl frwikippl loss runtime samples_per_second steps_per_second tinystoriesppl zhwikippl
teacher eval 43.75 61.75 11.8125 19.125
0 0 949187772416.0 76416058130432.0 21.75 0.1221 16.381 8.191 3556769792.0 13950053777408.0
20 1.0 13248.0 64000.0 5.6562 0.0646 30.969 15.485 7712.0 181248.0

Resource Usage Comparison

  • VRAM Use: 7.9388 GB

`# Distillation (Teacher -> Student) Architecture Difference:

  • Architecture: GPT2LMHeadModel -> GPT2LMHeadModel
  • Total Parameters: 124,439,808 -> 124,439,808
  • Data Type (dtype): 124439808 -> torch.bfloat16
  • Model Size: 0.16 GB -> 0.24 GB

Train Dataset

Trained on 149,632 tokens from the wikimedia/wikipedia dataset.

  • Num Samples: 158
  • Subset: 20231101.en
  • Split: train

Training Objective

DistillationObjective(logits_loss_component=LossComponent(label=logits, weight=1, loss_fn=kl))

Hyperparameters

The following hyperparameters were used during training:


Framework Versions

  • Distily 0.2.0
  • Transformers 4.44.0
  • Pytorch 2.3.0
  • Datasets 2.21.0
Downloads last month
7
Safetensors
Model size
0.1B params
Tensor type
BF16
·
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support

Model tree for lapp0/distily_modelcard_try

Quantized
(92)
this model

Dataset used to train lapp0/distily_modelcard_try