GaetanMichelet's picture
End of training
803ee30 verified
metadata
base_model: google/gemma-2-2b-it
datasets:
  - GaetanMichelet/chat-60_ft_task-2_auto
  - GaetanMichelet/chat-120_ft_task-2_auto
  - GaetanMichelet/chat-180_ft_task-2_auto
library_name: peft
license: gemma
tags:
  - alignment-handbook
  - trl
  - sft
  - generated_from_trainer
model-index:
  - name: Gemma-2-2B_task-2_180-samples_config-2_auto
    results: []

Gemma-2-2B_task-2_180-samples_config-2_auto

This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-2_auto, the GaetanMichelet/chat-120_ft_task-2_auto and the GaetanMichelet/chat-180_ft_task-2_auto datasets. It achieves the following results on the evaluation set:

  • Loss: 0.6109

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: 0.0001
  • train_batch_size: 1
  • eval_batch_size: 1
  • seed: 42
  • distributed_type: multi-GPU
  • gradient_accumulation_steps: 16
  • total_train_batch_size: 16
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: cosine
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 50

Training results

Training Loss Epoch Step Validation Loss
0.9786 0.9412 8 1.0015
0.8258 2.0 17 0.8337
0.7427 2.9412 25 0.7353
0.6073 4.0 34 0.6722
0.5792 4.9412 42 0.6399
0.5866 6.0 51 0.6176
0.4814 6.9412 59 0.6109
0.4326 8.0 68 0.6347
0.3304 8.9412 76 0.6800
0.271 10.0 85 0.7600
0.198 10.9412 93 0.9147
0.0956 12.0 102 1.0827
0.0691 12.9412 110 1.2139
0.0451 14.0 119 1.3165

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1