metadata
license: mit
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: phi2-lora-distilabel-intel-orca-dpo-pairs
results: []
phi2-lora-distilabel-intel-orca-dpo-pairs
This model is a fine-tuned version of microsoft/phi-2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.4547
- Rewards/chosen: -0.0932
- Rewards/rejected: -1.3103
- Rewards/accuracies: 0.8386
- Rewards/margins: 1.2171
- Logps/rejected: -222.2418
- Logps/chosen: -199.7473
- Logits/rejected: 0.5130
- Logits/chosen: 0.3441
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: 2
- seed: 42
- gradient_accumulation_steps: 16
- total_train_batch_size: 32
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 250
- 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 |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5579 | 0.78 | 250 | 0.4547 | -0.0932 | -1.3103 | 0.8386 | 1.2171 | -222.2418 | -199.7473 | 0.5130 | 0.3441 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2