kto2
This model is a fine-tuned version of deepseek-ai/deepseek-coder-1.3b-base on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5
- Eval/rewards/chosen: -1151.2938
- Eval/logps/chosen: -11550.3197
- Eval/rewards/rejected: -1115.2082
- Eval/logps/rejected: -11226.5358
- Eval/rewards/margins: -36.0856
- Eval/kl: 0.0
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: 0.07
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 128
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.1
- lr_scheduler_warmup_steps: 200
- num_epochs: 5
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | |
|---|---|---|---|---|
| 0.498 | 1.1552 | 100 | 0.5 | 0.0 |
| 0.4992 | 2.3105 | 200 | 0.5 | 0.0 |
| 0.4982 | 3.4657 | 300 | 0.5 | 0.0 |
| 0.5001 | 4.6209 | 400 | 0.5 | 0.0 |
Framework versions
- Transformers 4.45.0
- Pytorch 2.5.1+cu124
- Datasets 2.19.2
- Tokenizers 0.20.3
- Downloads last month
- 7
Model tree for stojchet/kto2
Base model
deepseek-ai/deepseek-coder-1.3b-base