metadata
license: other
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: google/gemma-2b-it
model-index:
- name: gemma-2b-it-dolly-finetune
results: []
gemma-2b-it-dolly-finetune
This model is a fine-tuned version of google/gemma-2b-it on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 3.1625
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-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 5.2432 | 0.96 | 3 | 3.1625 |
Framework versions
- Transformers 4.38.1
- Pytorch 2.2.1+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2