metadata
base_model: unsloth/llama-3.2-1b-instruct-bnb-4bit
library_name: peft
license: llama3.2
tags:
- trl
- sft
- unsloth
- generated_from_trainer
model-index:
- name: Llama-3.2-1B-Instruct
results: []
Llama-3.2-1B-Instruct
This model is a fine-tuned version of unsloth/llama-3.2-1b-instruct-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.8254
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: 4
- eval_batch_size: 8
- seed: 3407
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 100
- num_epochs: 1
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8725 | 0.1594 | 50 | 1.9015 |
| 1.8203 | 0.3187 | 100 | 1.8936 |
| 1.766 | 0.4781 | 150 | 1.8729 |
| 1.8071 | 0.6375 | 200 | 1.8494 |
| 1.7771 | 0.7968 | 250 | 1.8358 |
| 1.8222 | 0.9562 | 300 | 1.8254 |
Framework versions
- PEFT 0.13.2
- Transformers 4.44.2
- Pytorch 2.4.1+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1