metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
- name: Mixtral_dolly_reverse_Inst
results: []
Mixtral_dolly_reverse_Inst
This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 1.4407
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: 2.5e-05
- train_batch_size: 32
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 0.03
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.8058 | 0.05 | 10 | 1.9081 |
| 1.7565 | 0.1 | 20 | 1.8383 |
| 1.7155 | 0.15 | 30 | 1.7551 |
| 1.6477 | 0.2 | 40 | 1.7002 |
| 1.5887 | 0.25 | 50 | 1.6647 |
| 1.5521 | 0.3 | 60 | 1.6351 |
| 1.5184 | 0.35 | 70 | 1.6105 |
| 1.5338 | 0.4 | 80 | 1.5860 |
| 1.4718 | 0.45 | 90 | 1.5600 |
| 1.4739 | 0.5 | 100 | 1.5341 |
| 1.4525 | 0.55 | 110 | 1.5110 |
| 1.4125 | 0.6 | 120 | 1.4896 |
| 1.4118 | 0.65 | 130 | 1.4735 |
| 1.3921 | 0.7 | 140 | 1.4631 |
| 1.3861 | 0.75 | 150 | 1.4553 |
| 1.3765 | 0.8 | 160 | 1.4497 |
| 1.3664 | 0.85 | 170 | 1.4460 |
| 1.3783 | 0.9 | 180 | 1.4429 |
| 1.3544 | 0.95 | 190 | 1.4413 |
| 1.3743 | 1.0 | 200 | 1.4407 |
Framework versions
- PEFT 0.7.1
- Transformers 4.36.2
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0