metadata
library_name: peft
tags:
- llama-factory
- lora
- generated_from_trainer
base_model: google/gemma-7b
model-index:
- name: Gemma_AAID_mixed_train_final_last
results: []
Gemma_AAID_mixed_train_final_last
This model is a fine-tuned version of google/gemma-7b on the AAID_mixed dataset. It achieves the following results on the evaluation set:
- Loss: 0.6802
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 256
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1593 | 0.2188 | 200 | 0.6802 |
| 0.3301 | 0.4375 | 400 | 0.8198 |
| 0.1942 | 0.6563 | 600 | 0.9700 |
| 0.0992 | 0.8750 | 800 | 1.0706 |
| 0.0496 | 1.0938 | 1000 | 1.3044 |
| 0.0263 | 1.3126 | 1200 | 1.4879 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.1
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1