Metrics.

TrainOutput(global_step=1390,
  training_loss=1.0502444919064748,
  metrics={
    'train_runtime': 22700.8355,
    'train_samples_per_second': 2.449,
    'train_steps_per_second': 0.061,
    'total_flos': 1.2395973405265306e+18,
    'train_loss': 1.0502444919064748,
    'epoch': 4.05
})

Take dataset.

OpenAssistant/oasst2

Dataset format gemma fine tune.

NickyNicky/oasst2_clusters

colab examples.

https://colab.research.google.com/drive/16qS7NMSu20LzcwvYCrBGVI7rd9Hr-vpN?usp=sharing
Downloads last month
25
Safetensors
Model size
2.51B params
Tensor type
BF16
·
Inference Examples
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social visibility and check back later, or deploy to Inference Endpoints (dedicated) instead.

Datasets used to train NickyNicky/gemma-1.1-2b-it_oasst_format_chatML_unsloth_V1