metadata
license: llama3
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3-8B-Instruct
model-index:
- name: experiments
results: []
experiments
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 3.1279
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: 1
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.05
- num_epochs: 70
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3621 | 3.4964 | 420 | 1.4379 |
| 1.1954 | 6.9927 | 840 | 1.4208 |
| 0.8507 | 10.4891 | 1260 | 1.5712 |
| 0.789 | 13.9854 | 1680 | 1.6759 |
| 0.5388 | 17.4818 | 2100 | 1.9153 |
| 0.4013 | 20.9781 | 2520 | 2.0319 |
| 0.2933 | 24.4745 | 2940 | 2.2094 |
| 0.207 | 27.9709 | 3360 | 2.3547 |
| 0.1604 | 31.4672 | 3780 | 2.5483 |
| 0.1154 | 34.9636 | 4200 | 2.5953 |
| 0.0982 | 38.4599 | 4620 | 2.7355 |
| 0.0954 | 41.9563 | 5040 | 2.8220 |
| 0.0677 | 45.4527 | 5460 | 2.8909 |
| 0.0613 | 48.9490 | 5880 | 2.9654 |
| 0.0482 | 52.4454 | 6300 | 3.0125 |
| 0.0415 | 55.9417 | 6720 | 3.0390 |
| 0.0477 | 59.4381 | 7140 | 3.0992 |
| 0.0412 | 62.9344 | 7560 | 3.1126 |
| 0.0327 | 66.4308 | 7980 | 3.1262 |
| 0.0391 | 69.9272 | 8400 | 3.1279 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.2
- Pytorch 1.13.1+cu117
- Datasets 2.19.2
- Tokenizers 0.19.1