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_mix_2
results: []
mixtral_mix_2
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: 0.2832
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: 0.0001
- train_batch_size: 2
- eval_batch_size: 1
- seed: 42
- gradient_accumulation_steps: 32
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 200
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.686 | 0.36 | 10 | 1.1952 |
| 1.0961 | 0.71 | 20 | 0.9786 |
| 0.9359 | 1.07 | 30 | 0.8352 |
| 0.7603 | 1.42 | 40 | 0.6454 |
| 0.5832 | 1.78 | 50 | 0.4951 |
| 0.4764 | 2.14 | 60 | 0.4361 |
| 0.4172 | 2.49 | 70 | 0.3998 |
| 0.3911 | 2.85 | 80 | 0.3735 |
| 0.37 | 3.2 | 90 | 0.3564 |
| 0.3408 | 3.56 | 100 | 0.3407 |
| 0.3454 | 3.92 | 110 | 0.3270 |
| 0.3153 | 4.27 | 120 | 0.3142 |
| 0.3025 | 4.63 | 130 | 0.3046 |
| 0.3076 | 4.98 | 140 | 0.2963 |
| 0.2791 | 5.34 | 150 | 0.2903 |
| 0.2907 | 5.7 | 160 | 0.2863 |
| 0.2787 | 6.05 | 170 | 0.2840 |
| 0.284 | 6.41 | 180 | 0.2832 |
| 0.264 | 6.76 | 190 | 0.2832 |
| 0.2734 | 7.12 | 200 | 0.2832 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.38.1
- Pytorch 2.1.2+cu121
- Datasets 2.16.1
- Tokenizers 0.15.0