metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- unsloth
- generated_from_trainer
base_model: unsloth/tinyllama-chat-bnb-4bit
datasets:
- generator
model-index:
- name: MunicipalPredictionModel-TinyLlama
results: []
MunicipalPredictionModel-TinyLlama
This model is a fine-tuned version of unsloth/tinyllama-chat-bnb-4bit on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.6823
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
- gradient_accumulation_steps: 4
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
4.5606 | 0.0377 | 10 | 4.0606 |
3.7693 | 0.0753 | 20 | 3.5539 |
3.3915 | 0.1130 | 30 | 3.2022 |
3.0938 | 0.1507 | 40 | 2.9560 |
2.8692 | 0.1883 | 50 | 2.7576 |
2.6774 | 0.2260 | 60 | 2.5706 |
2.5012 | 0.2637 | 70 | 2.3805 |
2.3332 | 0.3013 | 80 | 2.2277 |
2.159 | 0.3390 | 90 | 2.1030 |
2.0806 | 0.3766 | 100 | 2.0125 |
1.9781 | 0.4143 | 110 | 1.9497 |
1.9683 | 0.4520 | 120 | 1.9005 |
1.917 | 0.4896 | 130 | 1.8584 |
1.8551 | 0.5273 | 140 | 1.8224 |
1.8121 | 0.5650 | 150 | 1.7910 |
1.7998 | 0.6026 | 160 | 1.7673 |
1.7484 | 0.6403 | 170 | 1.7486 |
1.7221 | 0.6780 | 180 | 1.7331 |
1.7171 | 0.7156 | 190 | 1.7207 |
1.7103 | 0.7533 | 200 | 1.7108 |
1.7086 | 0.7910 | 210 | 1.7025 |
1.7083 | 0.8286 | 220 | 1.6955 |
1.7065 | 0.8663 | 230 | 1.6907 |
1.6829 | 0.9040 | 240 | 1.6864 |
1.6892 | 0.9416 | 250 | 1.6838 |
1.6985 | 0.9793 | 260 | 1.6823 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.4
- Pytorch 2.2.0+cu121
- Datasets 2.18.0
- Tokenizers 0.19.0