metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: mistralai/Mistral-7B-v0.1
model-index:
- name: qlora-out
results: []
Finetuned on 10% of the Lichess pgn games from January 2013. (0.1 epochs)
qlora-out
This model is a fine-tuned version of mistralai/Mistral-7B-v0.1 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 0.6916
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: 2
- seed: 42
- gradient_accumulation_steps: 4
- total_train_batch_size: 8
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 10
- num_epochs: 0.1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 0.9892 | 0.0 | 1 | 1.0104 |
| 0.7441 | 0.03 | 22 | 0.7426 |
| 0.7049 | 0.05 | 44 | 0.7099 |
| 0.6796 | 0.08 | 66 | 0.6916 |
Framework versions
- PEFT 0.7.2.dev0
- Transformers 4.37.0.dev0
- Pytorch 2.0.1+cu117
- Datasets 2.16.0
- Tokenizers 0.15.0