metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
- name: Mixtral_Alpace_v2
results: []
Mixtral_Alpace_v2
This model is a fine-tuned version of mistralai/Mixtral-8x7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.1218
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: 5e-05
- train_batch_size: 2
- 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: 50
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 2.0253 | 0.1389 | 5 | 2.0089 |
| 1.94 | 0.2778 | 10 | 1.9158 |
| 1.8034 | 0.4167 | 15 | 1.7803 |
| 1.6579 | 0.5556 | 20 | 1.6171 |
| 1.5197 | 0.6944 | 25 | 1.4960 |
| 1.4063 | 0.8333 | 30 | 1.3825 |
| 1.3019 | 0.9722 | 35 | 1.2824 |
| 1.2145 | 1.1111 | 40 | 1.2010 |
| 1.1549 | 1.25 | 45 | 1.1446 |
| 1.1269 | 1.3889 | 50 | 1.1218 |
Framework versions
- PEFT 0.11.1
- Transformers 4.41.0
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1