metadata
license: gemma
base_model: google/gemma-2b-it
tags:
- generated_from_trainer
model-index:
- name: gemma-2b-it-lora-math
results: []
gemma-2b-it-lora-math
This model is a fine-tuned version of google/gemma-2b-it on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4824
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 100
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.5108 | 0.5131 | 200 | 0.5543 |
| 0.4467 | 1.0263 | 400 | 0.5035 |
| 0.4167 | 1.5394 | 600 | 0.4929 |
| 0.3823 | 2.0526 | 800 | 0.4840 |
| 0.379 | 2.5657 | 1000 | 0.4824 |
Framework versions
- Transformers 4.42.3
- Pytorch 2.3.1+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1