metadata
base_model: mistralai/Mixtral-8x7B-v0.1
library_name: peft
license: apache-2.0
tags:
- generated_from_trainer
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: 0.8517
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: 3
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.1536 | 0.03 | 10 | 1.1278 |
| 1.0733 | 0.07 | 20 | 1.0587 |
| 1.0201 | 0.1 | 30 | 0.9941 |
| 0.9622 | 0.13 | 40 | 0.9509 |
| 0.9268 | 0.16 | 50 | 0.9188 |
| 0.8984 | 0.2 | 60 | 0.8944 |
| 0.9067 | 0.23 | 70 | 0.8756 |
| 0.8712 | 0.26 | 80 | 0.8622 |
| 0.8485 | 0.3 | 90 | 0.8544 |
| 0.8703 | 0.33 | 100 | 0.8517 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.36.0
- Pytorch 2.2.2+cu121
- Datasets 2.20.0
- Tokenizers 0.15.2