metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
base_model: mistralai/Mixtral-8x7B-v0.1
model-index:
- name: mistral_instruct_generation
results: []
mistral_instruct_generation
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: 0.7326
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 8
- seed: 42
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_steps: 0.03
- training_steps: 100
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.6174 | 0.0078 | 20 | 0.7952 |
| 0.7153 | 0.0156 | 40 | 0.7565 |
| 0.7903 | 0.0235 | 60 | 0.7447 |
| 0.7175 | 0.0313 | 80 | 0.7377 |
| 0.7081 | 0.0391 | 100 | 0.7326 |
Framework versions
- PEFT 0.10.0
- Transformers 4.40.0
- Pytorch 2.2.1+cu121
- Tokenizers 0.19.1