<!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. -->
qlora-out-mist
This model is a fine-tuned version of TheBloke/MistRP-Airoboros-7B-GPTQ on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2142
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: 5e-05
- 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: 3
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6244 | 0.37 | 20 | 1.8201 |
| 1.1627 | 0.74 | 40 | 1.6282 |
| 1.4437 | 1.11 | 60 | 1.5096 |
| 1.2099 | 1.47 | 80 | 1.3713 |
| 1.2817 | 1.84 | 100 | 1.3242 |
| 1.1945 | 2.21 | 120 | 1.2360 |
| 1.2873 | 2.58 | 140 | 1.2160 |
| 1.0265 | 2.95 | 160 | 1.2142 |
Framework versions
- Transformers 4.34.1
- Pytorch 2.0.1+cu117
- Datasets 2.14.6
- Tokenizers 0.14.1
