metadata

library_name: transformers
license: other
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: gemma-2-9b-control-4e-r2
    results: []

gemma-2-9b-control-4e-r2

This model is a fine-tuned version of /data/models/gemma-9b-compl on the ds1, the ds2, the ds3, the ds4, the kalo_opus_1, the claude_instruct, the claude_instruct_2 and the epic_synth_2 datasets.

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: 2
eval_batch_size: 8
seed: 42
distributed_type: multi-GPU
num_devices: 12
total_train_batch_size: 24
total_eval_batch_size: 96
optimizer: Use paged_adamw_8bit with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
lr_scheduler_type: cosine
lr_scheduler_warmup_ratio: 0.1
num_epochs: 4.0

Training results

Framework versions

Transformers 4.46.1
Pytorch 2.5.0a0+e000cf0ad9.nv24.10
Datasets 3.0.2
Tokenizers 0.20.1