metadata
license: apache-2.0
library_name: peft
tags:
- generated_from_trainer
base_model: NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2
model-index:
- name: mistral-sigoIAspirantes-Orca-oass-v2
results: []
mistral-sigoIAspirantes-Orca-oass-v2
This model is a fine-tuned version of NickyNicky/Mistral-7B-OpenOrca-oasst_top1_2023-08-25-v2 on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 0.1361
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: 2
- 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: 1
- training_steps: 400
- mixed_precision_training: Native AMP
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.6926 | 0.35 | 25 | 1.2134 |
| 1.0257 | 0.7 | 50 | 0.8432 |
| 0.7181 | 1.06 | 75 | 0.6250 |
| 0.5143 | 1.41 | 100 | 0.4992 |
| 0.3899 | 1.76 | 125 | 0.3987 |
| 0.3433 | 2.11 | 150 | 0.3065 |
| 0.1736 | 2.46 | 175 | 0.2739 |
| 0.26 | 2.82 | 200 | 0.2005 |
| 0.1403 | 3.17 | 225 | 0.2055 |
| 0.1211 | 3.52 | 250 | 0.1642 |
| 0.1243 | 3.87 | 275 | 0.1487 |
| 0.0737 | 4.23 | 300 | 0.1565 |
| 0.0867 | 4.58 | 325 | 0.1590 |
| 0.0863 | 4.93 | 350 | 0.1355 |
| 0.0627 | 5.28 | 375 | 0.1360 |
| 0.0609 | 5.63 | 400 | 0.1361 |
Framework versions
- PEFT 0.10.1.dev0
- Transformers 4.40.0.dev0
- Pytorch 2.2.1+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2