metadata
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- alignment-handbook
- trl
- dpo
- generated_from_trainer
- trl
- dpo
- alignment-handbook
- generated_from_trainer
datasets:
- HuggingFaceH4/ultrafeedback_binarized
model-index:
- name: zephyr-7b-dpo-full-ultrabin-high-bleu
results: []
zephyr-7b-dpo-full-ultrabin-high-bleu
This model is a fine-tuned version of alignment-handbook/zephyr-7b-sft-full on the HuggingFaceH4/ultrafeedback_binarized dataset. It achieves the following results on the evaluation set:
- Loss: 0.6250
- Rewards/chosen: -0.3165
- Rewards/rejected: -0.5606
- Rewards/accuracies: 0.6953
- Rewards/margins: 0.2441
- Logps/rejected: -318.7193
- Logps/chosen: -294.2789
- Logits/rejected: -2.3036
- Logits/chosen: -2.3509
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: 55
- 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 |
---|---|---|---|---|---|---|---|---|---|---|---|
0.6597 | 0.3484 | 50 | 0.6513 | -0.1047 | -0.2299 | 0.6641 | 0.1252 | -285.6537 | -273.1035 | -2.4969 | -2.5355 |
0.6383 | 0.6969 | 100 | 0.6311 | -0.3272 | -0.5547 | 0.6875 | 0.2276 | -318.1367 | -295.3459 | -2.3484 | -2.3932 |
Framework versions
- Transformers 4.44.0.dev0
- Pytorch 2.1.2
- Datasets 2.20.0
- Tokenizers 0.19.1