metadata
library_name: peft
license: llama3.2
base_model: meta-llama/Llama-3.2-1B-Instruct
tags:
- generated_from_trainer
model-index:
- name: Llama-3.2-1B-Instruct-tuned
results: []
datasets:
- TuringGame/TuringChat-chats
language:
- en
- de
Llama-3.2-1B-Instruct-tuned
This model is a fine-tuned version of meta-llama/Llama-3.2-1B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 2.2766
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: 0.01
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 64
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: linear
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0 | 0 | 12.3951 |
| No log | 0.2004 | 27 | 5.5223 |
| No log | 0.4007 | 54 | 3.8031 |
| No log | 0.6011 | 81 | 3.1578 |
| No log | 0.8015 | 108 | 2.8569 |
| No log | 1.0 | 135 | 2.6538 |
| No log | 1.2004 | 162 | 2.4921 |
| No log | 1.4007 | 189 | 2.3860 |
| No log | 1.6011 | 216 | 2.3240 |
| No log | 1.8015 | 243 | 2.2894 |
| No log | 2.0 | 270 | 2.2766 |
Framework versions
- PEFT 0.15.2
- Transformers 4.52.4
- Pytorch 2.6.0+cu124
- Datasets 3.6.0
- Tokenizers 0.21.1