meditron-7b-dpo-full-sft-wo-kqa_silver_wogold
This model is a fine-tuned version of Minbyul/meditron-7b-wo-kqa_silver_wogold-sft on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:
- Loss: 0.6249
- Rewards/chosen: -0.0145
- Rewards/rejected: -0.1983
- Rewards/accuracies: 0.875
- Rewards/margins: 0.1839
- Logps/rejected: -653.1394
- Logps/chosen: -150.2214
- Logits/rejected: -1.0337
- Logits/chosen: -1.4037
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: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 2
- total_train_batch_size: 64
- 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
- Datasets 2.14.6
- Tokenizers 0.15.2