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: >-
l3.1-8b-inst-lora64-induction-gpt4wmini100k-mini100k-gpt4wmini20k-gpt4wllama20k-lr2e-4-ep3
results: []
l3.1-8b-inst-lora64-induction-gpt4wmini100k-mini100k-gpt4wmini20k-gpt4wllama20k-lr2e-4-ep3
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: 0.2684
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: 8
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.2882 | 1.0 | 1784 | 0.2852 |
| 0.257 | 2.0 | 3568 | 0.2705 |
| 0.2329 | 3.0 | 5352 | 0.2684 |
Framework versions
- PEFT 0.13.0
- Transformers 4.45.0.dev0
- Pytorch 2.4.1+cu121
- Datasets 3.0.0
- Tokenizers 0.19.1