README.md

metadata

license: gemma
library_name: peft
tags:
  - trl
  - sft
  - generated_from_trainer
  - ipex
  - GPU Max 1100
datasets:
  - generator
base_model: google/gemma-2b
model-index:
  - name: GemmaDoll-2b-dolly-LORA-Tune
    results: []

GemmaDoll-2b-dolly-LORA-Tune

This model is a fine-tuned version of google/gemma-2b on the generator dataset. It achieves the following results on the evaluation set:

• Loss: 2.1517

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: 1e-05
• train_batch_size: 2
• eval_batch_size: 8
• seed: 42
• gradient_accumulation_steps: 4
• total_train_batch_size: 8
• optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
• lr_scheduler_type: linear
• lr_scheduler_warmup_ratio: 0.05
• training_steps: 593

Training results

Training Loss	Epoch	Step	Validation Loss
2.8667	0.82	100	2.5298
2.4504	1.64	200	2.3277
2.2982	2.46	300	2.2235
2.2202	3.28	400	2.1739
2.2001	4.1	500	2.1517

Framework versions

• PEFT 0.10.0
• Transformers 4.39.3
• Pytorch 2.0.1a0+cxx11.abi
• Datasets 2.18.0
• Tokenizers 0.15.2