output
license: apache-2.0 base_model: unsloth/tinyllama-bnb-4bit tags: - generated_from_trainer datasets: - generator model-index: - name: tinyllama-bnb-4bit-ft-codeAlpaca results: []
tinyllama-bnb-4bit-ft-codeAlpaca
This model is a fine-tuned version of unsloth/tinyllama-bnb-4bit on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.7926
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: 8
- seed: 3407
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 5
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.7027 | 0.33 | 20 | 1.6844 |
1.2736 | 0.66 | 40 | 1.2825 |
1.091 | 0.99 | 60 | 1.0799 |
0.9683 | 1.32 | 80 | 0.9900 |
0.9431 | 1.65 | 100 | 0.9328 |
0.9352 | 1.98 | 120 | 0.8907 |
0.857 | 2.31 | 140 | 0.8580 |
0.8316 | 2.64 | 160 | 0.8346 |
0.8351 | 2.98 | 180 | 0.8203 |
0.8204 | 3.31 | 200 | 0.8103 |
0.7888 | 3.64 | 220 | 0.8035 |
0.7677 | 3.97 | 240 | 0.7985 |
0.7753 | 4.3 | 260 | 0.7952 |
0.7912 | 4.63 | 280 | 0.7931 |
0.7631 | 4.96 | 300 | 0.7926 |
Framework versions
- Transformers 4.37.0.dev0
- Pytorch 2.1.0+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0