Hugging Face's logo

mlfoundations-dev
/
hp_ablations_gemma_bsz1024

Text Generation
Transformers
Safetensors
gemma2
llama-factory
full
Generated from Trainer
conversational
text-generation-inference
Inference Endpoints
Model card Files Community
hp_ablations_gemma_bsz1024 / README.md
sedrickkeh's picture
sedrickkeh
End of training
20025c5 verified
preview code
|
raw
history blame
1.77 kB
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_bsz1024
    results: []

hp_ablations_gemma_bsz1024

This model is a fine-tuned version of google/gemma-2-9b on the mlfoundations-dev/oh-dcft-v3.1-gpt-4o-mini dataset. It achieves the following results on the evaluation set:

  • Loss: 0.5917

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: 5e-06
  • train_batch_size: 4
  • eval_batch_size: 4
  • seed: 42
  • distributed_type: multi-GPU
  • num_devices: 16
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 1024
  • total_eval_batch_size: 64
  • 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
0.5944 0.9975 221 0.5953
0.5591 1.9961 442 0.5867
0.5153 2.9946 663 0.5917

Framework versions

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