metadata
license: other
tags:
- alignment-handbook
- generated_from_trainer
base_model: deepseek-ai/deepseek-math-7b-base
datasets:
- AI-MO/numina-problems-sft-v1.7-preproc
model-index:
- name: sft_deepseek-math-7b_aimo_v31.24
results: []
sft_deepseek-math-7b_aimo_v31.24
This model is a fine-tuned version of deepseek-ai/deepseek-math-7b-base on the AI-MO/numina-problems-sft-v1.7-preproc dataset. It achieves the following results on the evaluation set:
- Loss: 0.4538
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: 2e-05
- train_batch_size: 4
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- total_train_batch_size: 32
- total_eval_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- num_epochs: 3.0
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4649 | 1.0 | 6954 | 0.4518 |
| 0.4026 | 2.0 | 13908 | 0.4403 |
| 0.3461 | 3.0 | 20862 | 0.4538 |
Framework versions
- Transformers 4.41.2
- Pytorch 2.1.2+cu121
- Datasets 2.18.0
- Tokenizers 0.19.1