zephyr-7b-align-scan-0.0-0.0-polynomial-2
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: 0.6385
- Rewards/chosen: -0.2230
- Rewards/rejected: -0.5393
- Rewards/accuracies: 0.3333
- Rewards/margins: 0.3162
- Logps/rejected: -96.4576
- Logps/chosen: -80.8310
- Logits/rejected: -2.3598
- Logits/chosen: -2.3790
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: 2.9843836387024965e-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: polynomial
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 2
Training results
| Training Loss | Epoch | Step | Logits/chosen | Logits/rejected | Logps/chosen | Logps/rejected | Validation Loss | Rewards/accuracies | Rewards/chosen | Rewards/margins | Rewards/rejected |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 0.5735 | 1.0417 | 100 | -2.4166 | -2.3982 | -79.0868 | -91.3032 | 0.6444 | 0.3234 | -0.1722 | 0.2091 | -0.3813 |
Framework versions
- Transformers 4.44.2
- Pytorch 2.4.0
- Datasets 2.21.0
- Tokenizers 0.19.1
- Downloads last month
- 5
Inference Providers
NEW
This model is not currently available via any of the supported third-party Inference Providers, and
the model is not deployed on the HF Inference API.
Model tree for taicheng/zephyr-7b-align-scan-0.0-0.0-polynomial-2
Base model
mistralai/Mistral-7B-v0.1
Finetuned
alignment-handbook/zephyr-7b-sft-full