Edit model card

zephyr-smol_llama-100m-sft-full

This model is a fine-tuned version of BEE-spoke-data/smol_llama-101M-GQA on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.9579

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
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 128
  • total_eval_batch_size: 32
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
1.9642 0.7 1141 1.9578

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0
  • Datasets 2.14.6
  • Tokenizers 0.14.1
Downloads last month
1,428
Safetensors
Model size
101M 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.

Model tree for amazingvince/zephyr-smol_llama-100m-sft-full

Finetuned
(3)
this model
Finetunes
2 models
Quantizations
1 model