metadata
license: apache-2.0
base_model: alignment-handbook/zephyr-7b-sft-full
tags:
- generated_from_trainer
model-index:
- name: zephyr-ds
results: []
zephyr-ds
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: 0.6636
- Rewards/chosen: 0.0135
- Rewards/rejected: -0.0160
- Rewards/accuracies: 0.6280
- Rewards/margins: 0.0295
- Logps/rejected: -259.4594
- Logps/chosen: -284.1223
- Logits/rejected: -2.8462
- Logits/chosen: -2.8424
- Use Label: 11234.4961
- Pred Label: 4797.5039
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: 4
- eval_batch_size: 4
- seed: 42
- distributed_type: multi-GPU
- num_devices: 4
- gradient_accumulation_steps: 4
- total_train_batch_size: 64
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- 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 | Use Label | Pred Label |
---|---|---|---|---|---|---|---|---|---|---|---|---|---|
0.6641 | 1.0 | 955 | 0.6636 | 0.0135 | -0.0160 | 0.6280 | 0.0295 | -259.4594 | -284.1223 | -2.8462 | -2.8424 | 10931.4961 | 4600.5039 |
Framework versions
- Transformers 4.35.0
- Pytorch 2.1.1+cu121
- Datasets 2.14.6
- Tokenizers 0.14.1