metadata
license: apache-2.0
library_name: peft
tags:
- trl
- dpo
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: zephyr-7b-dpo-qlora-fsdp
results: []
zephyr-7b-dpo-qlora-fsdp
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.6865
- Rewards/chosen: 0.0331
- Rewards/rejected: 0.0188
- Rewards/accuracies: 0.5935
- Rewards/margins: 0.0143
- Logps/rejected: -257.1393
- Logps/chosen: -276.4896
- Logits/rejected: -2.3640
- Logits/chosen: -2.4104
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: 5
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- gradient_accumulation_steps: 4
- total_train_batch_size: 20
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 0.01
Training results
Framework versions
- PEFT 0.9.0
- Transformers 4.38.1
- Pytorch 2.2.0+cu118
- Datasets 2.17.1
- Tokenizers 0.15.2