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_Alpace_v3
results: []
Mixtral_Alpace_v3
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: 0.7454
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
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9971 | 0.02 | 10 | 0.9638 |
| 0.9418 | 0.03 | 20 | 0.8981 |
| 0.8833 | 0.05 | 30 | 0.8468 |
| 0.8358 | 0.06 | 40 | 0.8169 |
| 0.7959 | 0.08 | 50 | 0.7940 |
| 0.7839 | 0.09 | 60 | 0.7762 |
| 0.7749 | 0.11 | 70 | 0.7630 |
| 0.7442 | 0.12 | 80 | 0.7535 |
| 0.7554 | 0.14 | 90 | 0.7476 |
| 0.749 | 0.16 | 100 | 0.7454 |
Framework versions
- PEFT 0.8.2
- Transformers 4.39.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.17.1
- Tokenizers 0.15.2