metadata
library_name: transformers
license: gemma
base_model: google/gemma-2-2b-it
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: gemma2b-b
results: []
gemma2b-b
This model is a fine-tuned version of google/gemma-2-2b-it on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.9842
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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- total_eval_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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3036 | 0.9180 | 7 | 1.2136 |
| 0.9604 | 1.9672 | 15 | 0.9997 |
| 0.8292 | 2.7541 | 21 | 0.9842 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1