metadata
library_name: transformers
license: llama3
base_model: meta-llama/Meta-Llama-3-8B-Instruct
tags:
- alignment-handbook
- generated_from_trainer
datasets:
- >-
simonycl/Meta-Llama-3-8B-Instruct_metamath-Meta-Llama-3-8B-Instruct-annotate-judge-5
model-index:
- name: llama-3-8b-instruct-metamath-agg-judge
results: []
llama-3-8b-instruct-metamath-agg-judge
This model is a fine-tuned version of meta-llama/Meta-Llama-3-8B-Instruct on the simonycl/Meta-Llama-3-8B-Instruct_metamath-Meta-Llama-3-8B-Instruct-annotate-judge-5 dataset. It achieves the following results on the evaluation set:
- Loss: 0.7013
- Rewards/chosen: -4.0945
- Rewards/rejected: -5.8632
- Rewards/accuracies: 0.7060
- Rewards/margins: 1.7687
- Logps/rejected: -705.5204
- Logps/chosen: -502.4185
- Logits/rejected: -0.8140
- Logits/chosen: -1.0704
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: 5e-07
- train_batch_size: 1
- eval_batch_size: 2
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 32
- total_train_batch_size: 128
- total_eval_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.2753 | 0.7882 | 400 | 0.7013 | -4.0945 | -5.8632 | 0.7060 | 1.7687 | -705.5204 | -502.4185 | -0.8140 | -1.0704 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0+cu121
- Datasets 2.21.0
- Tokenizers 0.19.1