metadata
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- trl
- dpo
- generated_from_trainer
model-index:
- name: zephyr-7b-dpo-full
results: []
zephyr-7b-dpo-full
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.5028
- Rewards/chosen: -0.9469
- Rewards/rejected: -1.8932
- Rewards/accuracies: 0.7656
- Rewards/margins: 0.9463
- Logps/rejected: -451.4661
- Logps/chosen: -357.2325
- Logits/rejected: 1.5731
- Logits/chosen: 0.6530
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: 8
- gradient_accumulation_steps: 2
- total_train_batch_size: 128
- total_eval_batch_size: 64
- 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
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Rewards/rejected | Rewards/accuracies | Rewards/margins | Logps/rejected | Logps/chosen | Logits/rejected | Logits/chosen |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5545 | 0.21 | 100 | 0.5658 | -0.4953 | -1.1217 | 0.7188 | 0.6264 | -374.3159 | -312.0799 | -1.0287 | -1.3212 |
| 0.5026 | 0.42 | 200 | 0.5202 | -0.8995 | -1.7718 | 0.7461 | 0.8723 | -439.3264 | -352.4985 | 0.5190 | -0.1773 |
| 0.5106 | 0.63 | 300 | 0.5104 | -0.7946 | -1.6285 | 0.7656 | 0.8339 | -424.9976 | -342.0043 | 0.9099 | 0.0862 |
| 0.4859 | 0.84 | 400 | 0.5031 | -0.9777 | -1.9580 | 0.7578 | 0.9803 | -457.9452 | -360.3139 | 1.7438 | 0.7818 |
Framework versions
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.14.6
- Tokenizers 0.15.0