metadata
base_model: barc0/Llama-3.1-ARC-Potpourri-Transduction-8B
datasets:
- barc0/transduction_formatted_test_time_finetune_for_evaluation
- barc0/transduction_formatted_rearc_dataset_100k
- barc0/transduction_heavy_100k_jsonl
library_name: peft
license: llama3.1
tags:
- alignment-handbook
- trl
- sft
- generated_from_trainer
model-index:
- name: engineer1-heavy-barc-llama3.1-8b-instruct-lora64-testtime-finetuning
results: []
engineer1-heavy-barc-llama3.1-8b-instruct-lora64-testtime-finetuning
This model is a fine-tuned version of barc0/Llama-3.1-ARC-Potpourri-Transduction-8B on the barc0/transduction_formatted_test_time_finetune_for_evaluation, the barc0/transduction_formatted_rearc_dataset_100k and the barc0/transduction_heavy_100k_jsonl datasets. It achieves the following results on the evaluation set:
- Loss: 0.0337
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: 2
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- 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 |
|---|---|---|---|
| 0.032 | 1.0 | 667 | 0.0307 |
| 0.0169 | 2.0 | 1334 | 0.0286 |
| 0.0019 | 3.0 | 2001 | 0.0337 |
Framework versions
- PEFT 0.13.2
- Transformers 4.45.0.dev0
- Pytorch 2.4.0+cu121
- Datasets 3.1.0
- Tokenizers 0.19.1