phi-2-gpo-test-longest-iter-random2-3
This model is a fine-tuned version of DUAL-GPO/phi-2-gpo-test-longest-iter-random2-2 on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:
- Loss: 0.0018
- Rewards/chosen: -0.0061
- Rewards/rejected: -0.0056
- Rewards/accuracies: 0.5015
- Rewards/margins: -0.0005
- Logps/rejected: -279.5969
- Logps/chosen: -307.4853
- Logits/rejected: 0.0326
- Logits/chosen: -0.0650
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
- gradient_accumulation_steps: 4
- total_train_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: 4
Training results
Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
---|---|---|---|---|---|---|---|---|---|---|---|
0.0011 | 1.6 | 100 | 0.0018 | -0.0031 | -0.0021 | 0.4800 | -0.0009 | -279.2489 | -307.1817 | 0.0509 | -0.0480 |
0.001 | 3.2 | 200 | 0.0019 | -0.0055 | -0.0043 | 0.4765 | -0.0012 | -279.4667 | -307.4276 | 0.0323 | -0.0664 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.2.1+cu121
- Datasets 2.14.6
- Tokenizers 0.15.2
- Downloads last month
- 2
Model tree for DUAL-GPO/phi-2-gpo-test-longest-iter-random2-3
Base model
microsoft/phi-2
Adapter
this model