metadata
license: llama3.1
library_name: peft
tags:
- generated_from_trainer
base_model: meta-llama/Meta-Llama-3.1-8B-Instruct
model-index:
- name: llama3_8b_instruct_BWRM
results: []
llama3_8b_instruct_BWRM
This model is a fine-tuned version of meta-llama/Meta-Llama-3.1-8B-Instruct on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3034
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: 0.0003
- train_batch_size: 32
- eval_batch_size: 32
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 1024
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.7965 | 0.1840 | 20 | 0.5969 |
| 0.6001 | 0.3680 | 40 | 0.5778 |
| 0.5739 | 0.5520 | 60 | 0.5419 |
| 0.5411 | 0.7361 | 80 | 0.4995 |
| 0.5147 | 0.9201 | 100 | 0.4758 |
| 0.45 | 1.1041 | 120 | 0.4148 |
| 0.4145 | 1.2881 | 140 | 0.4171 |
| 0.4011 | 1.4721 | 160 | 0.3753 |
| 0.371 | 1.6561 | 180 | 0.4154 |
| 0.3702 | 1.8401 | 200 | 0.3424 |
| 0.3438 | 2.0242 | 220 | 0.3332 |
| 0.3298 | 2.2082 | 240 | 0.3231 |
| 0.3185 | 2.3922 | 260 | 0.3174 |
| 0.3127 | 2.5762 | 280 | 0.3130 |
| 0.3073 | 2.7602 | 300 | 0.3060 |
| 0.3033 | 2.9442 | 320 | 0.3034 |
Framework versions
- PEFT 0.10.0
- Transformers 4.44.0
- Pytorch 2.3.0+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1