Hugging Face's logo

amazingvince
/
zephyr-1.1b-sft-full

Text Generation
Transformers
TensorBoard
Safetensors
llama
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Metrics Community
zephyr-1.1b-sft-full / README.md
amazingvince's picture
amazingvince
Model save
40291a8
preview code
|
raw
history blame
1.54 kB
metadata
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T
tags:
  - generated_from_trainer
model-index:
  - name: zephyr-1.1b-sft-full
    results: []

zephyr-1.1b-sft-full

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-955k-token-2T on an unknown dataset. It achieves the following results on the evaluation set:

  • Loss: 1.1737

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: 2
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 2
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 64
  • total_eval_batch_size: 4
  • 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
1.1826 0.7 2282 1.1737

Framework versions

  • Transformers 4.35.0
  • Pytorch 2.1.0
  • Datasets 2.14.6
  • Tokenizers 0.14.1