metadata
license: apache-2.0
library_name: peft
tags:
- trl
- kto
- KTO
- WeniGPT
- generated_from_trainer
base_model: mistralai/Mixtral-8x7B-Instruct-v0.1
model-index:
- name: WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
results: []
WeniGPT-Agents-Mixstral-Instruct-2.0.0-KTO
This model is a fine-tuned version of mistralai/Mixtral-8x7B-Instruct-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.3856
- Rewards/chosen: -2.7129
- Logps/chosen: -263.7560
- Rewards/rejected: -6.5728
- Logps/rejected: -282.9854
- Kl: 0.0
- Rewards/margins: 3.9057
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 |
|---|---|---|---|---|---|---|---|---|---|
| 0.4403 | 0.34 | 50 | 0.4195 | -1.1683 | -248.3103 | -3.6153 | -253.4100 | 0.5120 | 2.6137 |
| 0.3518 | 0.68 | 100 | 0.3856 | -2.7129 | -263.7560 | -6.5728 | -282.9854 | 0.0 | 3.9057 |
Framework versions
- PEFT 0.10.0
- Transformers 4.39.1
- Pytorch 2.1.0+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2