metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
- name: results_mixtral_sft
results: []
results_mixtral_sft
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: 2.5315
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: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: linear
- lr_scheduler_warmup_steps: 30
- training_steps: 300
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 3.1526 | 0.08 | 50 | 2.8850 |
| 2.65 | 0.17 | 100 | 2.5706 |
| 2.5321 | 0.25 | 150 | 2.5223 |
| 2.478 | 0.34 | 200 | 2.5239 |
| 2.5185 | 0.42 | 250 | 2.5304 |
| 2.5119 | 0.5 | 300 | 2.5315 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.1.0+cu121
- Datasets 2.17.1
- Tokenizers 0.15.2