metadata
base_model: NousResearch/Meta-Llama-3.1-8B-Instruct
datasets:
- generator
library_name: peft
license: llama3.1
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: llama381binstruct_summarize_short
results: []
llama381binstruct_summarize_short
This model is a fine-tuned version of NousResearch/Meta-Llama-3.1-8B-Instruct on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 2.4987
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: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 500
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6561 | 1.3158 | 25 | 1.5733 |
| 0.7137 | 2.6316 | 50 | 1.6393 |
| 0.336 | 3.9474 | 75 | 1.8111 |
| 0.1344 | 5.2632 | 100 | 2.1297 |
| 0.0738 | 6.5789 | 125 | 2.0997 |
| 0.052 | 7.8947 | 150 | 2.1198 |
| 0.0333 | 9.2105 | 175 | 2.2542 |
| 0.015 | 10.5263 | 200 | 2.2692 |
| 0.0086 | 11.8421 | 225 | 2.3892 |
| 0.0052 | 13.1579 | 250 | 2.3374 |
| 0.008 | 14.4737 | 275 | 2.3392 |
| 0.0034 | 15.7895 | 300 | 2.3950 |
| 0.0025 | 17.1053 | 325 | 2.4337 |
| 0.0022 | 18.4211 | 350 | 2.4409 |
| 0.002 | 19.7368 | 375 | 2.4601 |
| 0.0024 | 21.0526 | 400 | 2.4790 |
| 0.0017 | 22.3684 | 425 | 2.4881 |
| 0.0017 | 23.6842 | 450 | 2.4939 |
| 0.0019 | 25.0 | 475 | 2.4977 |
| 0.0017 | 26.3158 | 500 | 2.4987 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1