README.md

metadata

library_name: transformers
license: gemma
base_model: google/gemma-2-9b
tags:
  - llama-factory
  - full
  - generated_from_trainer
model-index:
  - name: hp_ablations_gemma_lr2e-6_dcftv1.2
    results: []

hp_ablations_gemma_lr2e-6_dcftv1.2

This model is a fine-tuned version of google/gemma-2-9b on the mlfoundations-dev/oh-dcft-v1.2_no-curation_gpt-4o-mini dataset. It achieves the following results on the evaluation set:

• Loss: 0.6160

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-06
• train_batch_size: 4
• eval_batch_size: 4
• seed: 42
• distributed_type: multi-GPU
• num_devices: 8
• gradient_accumulation_steps: 16
• total_train_batch_size: 512
• total_eval_batch_size: 32
• optimizer: Use OptimizerNames.ADAMW_TORCH with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
• lr_scheduler_type: constant
• lr_scheduler_warmup_ratio: 0.1
• lr_scheduler_warmup_steps: 1738
• num_epochs: 3.0

Training results

Training Loss	Epoch	Step	Validation Loss
0.6157	0.9998	334	0.6271
0.5868	1.9996	668	0.6163
0.5572	2.9994	1002	0.6160

Framework versions

• Transformers 4.46.1
• Pytorch 2.3.0
• Datasets 3.0.2
• Tokenizers 0.20.3