Edit model card

ppo_beta1

This model is a fine-tuned version of wandb/gemma-2b-zephyr-sft on an unknown dataset.

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: 3e-06
  • train_batch_size: 14
  • eval_batch_size: 8
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 8
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 448
  • total_eval_batch_size: 64
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • num_epochs: 3.0

Framework versions

  • Transformers 4.42.4
  • Pytorch 2.2.1
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
0
Safetensors
Model size
2.51B params
Tensor type
BF16
·
Inference API
Unable to determine this model's library. Check the docs .

Model tree for Nevali/ppo_beta1

Base model

google/gemma-2b
Finetuned
(7)
this model