metadata
base_model: mistralai/Mistral-7B-Instruct-v0.3
datasets:
- generator
library_name: peft
license: apache-2.0
tags:
- trl
- sft
- generated_from_trainer
model-index:
- name: Mistral-7B-qt-earlystop-01
results: []
Mistral-7B-qt-earlystop-01
This model is a fine-tuned version of mistralai/Mistral-7B-Instruct-v0.3 on the generator dataset. It achieves the following results on the evaluation set:
- Loss: 0.1438
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: 2
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- lr_scheduler_warmup_steps: 15
- num_epochs: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.4181 | 0.3980 | 10 | 0.1646 |
| 0.1587 | 0.7960 | 20 | 0.1432 |
| 0.1313 | 1.1940 | 30 | 0.1368 |
| 0.1112 | 1.5920 | 40 | 0.1323 |
| 0.1028 | 1.9900 | 50 | 0.1326 |
| 0.0707 | 2.3881 | 60 | 0.1440 |
| 0.0693 | 2.7861 | 70 | 0.1438 |
Framework versions
- PEFT 0.12.0
- Transformers 4.43.4
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1