ndpo1
This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.0465
- Rewards/chosen: 1.3306
- Rewards/rejected: -5.9771
- Rewards/accuracies: 0.9934
- Rewards/margins: 7.3077
- Logps/rejected: -232.7393
- Logps/chosen: -155.1493
- Logits/rejected: -16.8463
- Logits/chosen: -16.6346
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: 1e-05
- train_batch_size: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 64
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 200
- num_epochs: 2
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.1691 | 1.7149 | 100 | 0.0465 | 1.3306 | -5.9771 | 0.9934 | 7.3077 | -232.7393 | -155.1493 | -16.8463 | -16.6346 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1