metadata
license: other
base_model: lewtun/gemma-7b-sft-full-openhermes-v0
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
- trl
- dpo
- generated_from_trainer
datasets:
- argilla/dpo-mix-7k
model-index:
- name: gemma-7b-dpo-full-openhermes-mix1-beta-0.05
results: []
gemma-7b-dpo-full-openhermes-mix1-beta-0.05
This model is a fine-tuned version of lewtun/gemma-7b-sft-full-openhermes-v0 on the argilla/dpo-mix-7k dataset. It achieves the following results on the evaluation set:
- Loss: 0.5184
- Rewards/chosen: 0.5472
- Rewards/rejected: -0.7999
- Rewards/accuracies: 0.7604
- Rewards/margins: 1.3471
- Logps/rejected: -823.1282
- Logps/chosen: -781.3259
- Logits/rejected: 94.8342
- Logits/chosen: 103.4466
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-07
- train_batch_size: 2
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 8
- gradient_accumulation_steps: 8
- total_train_batch_size: 128
- total_eval_batch_size: 32
- 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
- Transformers 4.39.0.dev0
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.1