jndpo2
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: 0.0001
- Rewards/chosen: 0.2169
- Rewards/rejected: -18.5283
- Rewards/accuracies: 1.0
- Rewards/margins: 18.7452
- Logps/rejected: -314.1786
- Logps/chosen: -108.3139
- Logits/rejected: -19.7908
- Logits/chosen: -19.2399
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-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 |
---|---|---|---|---|---|---|---|---|---|---|---|
0.0629 | 1.7067 | 100 | 0.0001 | 0.2169 | -18.5283 | 1.0 | 18.7452 | -314.1786 | -108.3139 | -19.7908 | -19.2399 |
Framework versions
- Transformers 4.43.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.19.2
- Tokenizers 0.19.1
- Downloads last month
- 2
Inference API (serverless) is not available, repository is disabled.