metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
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 an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.8556
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: 16
- 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 |
|---|---|---|---|
| 1.1522 | 0.03 | 10 | 1.1246 |
| 1.0849 | 0.07 | 20 | 1.0571 |
| 1.0144 | 0.1 | 30 | 0.9943 |
| 0.9654 | 0.13 | 40 | 0.9525 |
| 0.9383 | 0.16 | 50 | 0.9212 |
| 0.8954 | 0.2 | 60 | 0.8979 |
| 0.8671 | 0.23 | 70 | 0.8798 |
| 0.9088 | 0.26 | 80 | 0.8664 |
| 0.8696 | 0.3 | 90 | 0.8584 |
| 0.8281 | 0.33 | 100 | 0.8556 |
Framework versions
- PEFT 0.9.1.dev0
- Transformers 4.36.0
- Pytorch 2.0.1+cu118
- Datasets 2.18.0
- Tokenizers 0.15.2