metadata
library_name: peft
license: other
base_model: deepseek-ai/deepseek-coder-1.3b-base
tags:
- trl
- kto
- generated_from_trainer
model-index:
- name: kto4
results: []
kto4
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: nan
- Eval/rewards/chosen: 0.0
- Eval/logps/chosen: 0.0
- Eval/rewards/rejected: 0.0
- Eval/logps/rejected: 0.0
- Eval/rewards/margins: 0.0
- Eval/kl: nan
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: 0.1
- 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: 4
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | |
|---|---|---|---|---|
| 0.4759 | 1.1552 | 100 | 0.5000 | 0.0 |
| 0.5018 | 2.3105 | 200 | 0.5000 | 0.0 |
| 4.6568 | 3.4657 | 300 | nan | nan |
Framework versions
- PEFT 0.10.0
- Transformers 4.45.0
- Pytorch 2.5.1+cu124
- Datasets 2.19.2
- Tokenizers 0.20.3