metadata
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
library_name: peft
license: llama3.1
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: outputs
results: []
outputs
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8215
- Model Preparation Time: 0.0166
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: 1e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- 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: 20
- num_epochs: 10
- mixed_precision_training: Native AMP
Training results
Training Loss | Epoch | Step | Validation Loss | Model Preparation Time |
---|---|---|---|---|
2.1179 | 1.1765 | 20 | 2.0786 | 0.0166 |
1.1724 | 2.3529 | 40 | 1.2198 | 0.0166 |
0.9532 | 3.5294 | 60 | 0.9806 | 0.0166 |
0.851 | 4.7059 | 80 | 0.8941 | 0.0166 |
0.8294 | 5.8824 | 100 | 0.8571 | 0.0166 |
0.7754 | 7.0588 | 120 | 0.8378 | 0.0166 |
0.748 | 8.2353 | 140 | 0.8258 | 0.0166 |
0.7357 | 9.4118 | 160 | 0.8224 | 0.0166 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.1.2
- Datasets 2.21.0
- Tokenizers 0.19.1