metadata
base_model: /cpfs01/user/zhangyiqun/models/gemma-2-2b-it
library_name: peft
license: other
tags:
- llama-factory
- lora
- generated_from_trainer
model-index:
- name: open_orca
results: []
open_orca
This model is a fine-tuned version of /cpfs01/user/zhangyiqun/models/gemma-2-2b-it on the open_orca dataset. It achieves the following results on the evaluation set:
- Loss: 1.0459
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: 0.0002
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- 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: 5.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9091 | 1.1344 | 1000 | 0.8941 |
| 0.7524 | 2.2689 | 2000 | 0.9067 |
| 0.7148 | 3.4033 | 3000 | 0.9693 |
| 0.5743 | 4.5377 | 4000 | 1.0443 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.3.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1