andrewbai's picture
End of training
c72ac9d verified
metadata
license: apache-2.0
base_model: TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
  - trl
  - sft
  - generated_from_trainer
datasets:
  - ucla-cmllab/vicuna_sub_small_user_length_10k
model-index:
  - name: tinyllama-sft-vicuna-10k-small-user-length
    results: []

tinyllama-sft-vicuna-10k-small-user-length

This model is a fine-tuned version of TinyLlama/TinyLlama-1.1B-intermediate-step-1431k-3T on the ucla-cmllab/vicuna_sub_small_user_length_10k dataset. It achieves the following results on the evaluation set:

  • Loss: 0.8264

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: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 4
  • gradient_accumulation_steps: 2
  • 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
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 1

Training results

Training Loss Epoch Step Validation Loss
0.8347 0.9936 78 0.8264

Framework versions

  • Transformers 4.40.2
  • Pytorch 2.3.0+cu121
  • Datasets 2.19.1
  • Tokenizers 0.19.1