Edit model card

Gemma-2-2B_task-1_120-samples_config-1_full_auto

This model is a fine-tuned version of google/gemma-2-2b-it on the GaetanMichelet/chat-60_ft_task-1_auto and the GaetanMichelet/chat-120_ft_task-1_auto datasets. It achieves the following results on the evaluation set:

  • Loss: 0.9272

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: 8
  • total_train_batch_size: 8
  • 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
2.3294 1.0 11 2.2008
1.6286 2.0 22 1.6358
1.2359 3.0 33 1.1649
0.9635 4.0 44 0.9962
0.8326 5.0 55 0.9411
0.7894 6.0 66 0.9272
0.6386 7.0 77 0.9589
0.5299 8.0 88 1.0148
0.4425 9.0 99 1.1574
0.306 10.0 110 1.3965
0.2155 11.0 121 1.5442
0.1928 12.0 132 1.7250
0.1191 13.0 143 1.8248

Framework versions

  • PEFT 0.12.0
  • Transformers 4.44.0
  • Pytorch 2.1.2+cu121
  • Datasets 2.20.0
  • Tokenizers 0.19.1
Downloads last month
2
Inference API
Unable to determine this model’s pipeline type. Check the docs .

Model tree for GaetanMichelet/Gemma-2-2B_task-1_120-samples_config-1_full_auto

Base model

google/gemma-2-2b
Adapter
(154)
this model

Collection including GaetanMichelet/Gemma-2-2B_task-1_120-samples_config-1_full_auto