metadata
license: llama3.1
base_model: NousResearch/Meta-Llama-3.1-8B-Instruct
tags:
- generated_from_trainer
model-index:
- name: Llama-3.1-8B-Instruct-EI1-120K-fix-32gpus-08
results: []
Llama-3.1-8B-Instruct-EI1-120K-fix-32gpus-08
This model is a fine-tuned version of NousResearch/Meta-Llama-3.1-8B-Instruct on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4171
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: 6e-06
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 32
- total_train_batch_size: 64
- total_eval_batch_size: 256
- optimizer: Adam with betas=(0.9,0.95) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 2.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.3650 | 100 | 0.5246 |
| No log | 0.7299 | 200 | 0.4631 |
| No log | 1.0949 | 300 | 0.4346 |
| No log | 1.4599 | 400 | 0.4217 |
| 0.4699 | 1.8248 | 500 | 0.4171 |
Framework versions
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 3.0.1
- Tokenizers 0.19.1