metadata
library_name: peft
license: apache-2.0
base_model: unsloth/mistral-7b-instruct-v0.2
tags:
- axolotl
- generated_from_trainer
model-index:
- name: 13004106-fecd-413e-9abf-bbecc4aa6ca8
results: []
13004106-fecd-413e-9abf-bbecc4aa6ca8
This model is a fine-tuned version of unsloth/mistral-7b-instruct-v0.2 on the None dataset. It achieves the following results on the evaluation set:
- Loss: 1.2327
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: 0.000203
- train_batch_size: 4
- eval_batch_size: 4
- seed: 42
- gradient_accumulation_steps: 2
- total_train_batch_size: 8
- optimizer: Use OptimizerNames.ADAMW_BNB with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
- lr_scheduler_type: cosine
- lr_scheduler_warmup_steps: 50
- training_steps: 402
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| No log | 0.0025 | 1 | 2.2300 |
| 2.537 | 0.1245 | 50 | 1.6623 |
| 2.2706 | 0.2491 | 100 | 1.6270 |
| 2.2597 | 0.3736 | 150 | 1.6305 |
| 2.0886 | 0.4981 | 200 | 1.5863 |
| 2.1512 | 0.6227 | 250 | 1.4163 |
| 1.9925 | 0.7472 | 300 | 1.3612 |
| 2.1168 | 0.8717 | 350 | 1.2273 |
| 1.8918 | 0.9963 | 400 | 1.2327 |
Framework versions
- PEFT 0.13.2
- Transformers 4.46.0
- Pytorch 2.5.0+cu124
- Datasets 3.0.1
- Tokenizers 0.20.1