metadata
license: mit
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: microsoft/phi-2
model-index:
- name: phi-2-dpo-ultrachat-lora
results: []
phi-2-dpo-ultrachat-lora
This model is a fine-tuned version of microsoft/phi-2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6932
- Rewards/chosen: -0.0003
- Rewards/rejected: -0.0002
- Rewards/accuracies: 0.2480
- Rewards/margins: -0.0000
- Logps/rejected: -94.2209
- Logps/chosen: -91.7559
- Logits/rejected: 0.8201
- Logits/chosen: 0.8023
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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- 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
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu118
- Datasets 2.14.6
- Tokenizers 0.15.2