metadata
license: mit
library_name: peft
tags:
- trl
- kto
- generated_from_trainer
base_model: HuggingFaceH4/zephyr-7b-beta
model-index:
- name: WeniGPT-Agents-Zephyr-1.0.1-KTO
results: []
WeniGPT-Agents-Zephyr-1.0.1-KTO
This model is a fine-tuned version of HuggingFaceH4/zephyr-7b-beta on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.4733
- Rewards/chosen: -188.7491
- Logps/chosen: -2394.6819
- Rewards/rejected: -176.6560
- Logps/rejected: -2418.2639
- Kl: 0.0
- Rewards/margins: -12.4013
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: 0.0002
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 145
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss | Rewards/chosen | Logps/chosen | Rewards/rejected | Logps/rejected | Kl | Rewards/margins |
|---|---|---|---|---|---|---|---|---|---|
| 0.5465 | 0.34 | 50 | 0.5112 | -20.3414 | -710.6042 | -4.1466 | -693.1708 | 45.8506 | -17.1827 |
| 0.4745 | 0.68 | 100 | 0.4733 | -188.7491 | -2394.6819 | -176.6560 | -2418.2639 | 0.0 | -12.4013 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2