metadata
license: apache-2.0
library_name: peft
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
base_model: mistralai/Mistral-7B-Instruct-v0.1
model-index:
- name: Mixtral_Alpace_v2
results: []
Mixtral_Alpace_v2
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.1 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.9305
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
- num_epochs: 5
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9484 | 1.0 | 268 | 0.9594 |
| 0.9218 | 2.0 | 536 | 0.9361 |
| 0.8898 | 3.0 | 804 | 0.9281 |
| 0.8719 | 4.0 | 1072 | 0.9281 |
| 0.833 | 5.0 | 1340 | 0.9305 |
Framework versions
- PEFT 0.8.2
- Transformers 4.37.2
- Pytorch 2.2.0+cu121
- Datasets 2.17.0
- Tokenizers 0.15.2