dpo-lora-2
This model is a fine-tuned version of hatakeyama-llm-team/with_halcination_little_codes_ck5200 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.2400
- Rewards/chosen: 1.0314
- Rewards/rejected: -3.3152
- Rewards/accuracies: 0.7485
- Rewards/margins: 4.3466
- Logps/rejected: -324.0153
- Logps/chosen: -225.2345
- Logits/rejected: -0.1042
- Logits/chosen: 0.2104
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-06
- train_batch_size: 2
- eval_batch_size: 2
- 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: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 1
Training results
Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
---|---|---|---|---|---|---|---|---|---|---|---|
0.2789 | 0.32 | 100 | 0.2862 | 0.7314 | -2.0185 | 0.7407 | 2.7499 | -311.0483 | -228.2343 | 0.1715 | 0.3351 |
0.2351 | 0.64 | 200 | 0.2444 | 1.0416 | -3.0321 | 0.7534 | 4.0737 | -321.1842 | -225.1324 | -0.1048 | 0.1873 |
0.2457 | 0.96 | 300 | 0.2400 | 1.0314 | -3.3152 | 0.7485 | 4.3466 | -324.0153 | -225.2345 | -0.1042 | 0.2104 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0