metadata
base_model: unsloth/mistral-7b-v0.3-bnb-4bit
library_name: peft
license: apache-2.0
tags:
- unsloth
- generated_from_trainer
model-index:
- name: Mistral-7B-v0.3_magiccoder_ortho
results: []
Mistral-7B-v0.3_magiccoder_ortho
This model is a fine-tuned version of unsloth/mistral-7b-v0.3-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 7.8283
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: 0.0001
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- gradient_accumulation_steps: 8
- total_train_batch_size: 64
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.02
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 4.9343 | 0.0262 | 4 | 4.5673 |
| 9.0563 | 0.0523 | 8 | 8.5844 |
| 8.1428 | 0.0785 | 12 | 10.0610 |
| 8.7401 | 0.1047 | 16 | 9.0322 |
| 8.5719 | 0.1308 | 20 | 8.2514 |
| 8.0244 | 0.1570 | 24 | 7.8997 |
| 7.9039 | 0.1832 | 28 | 7.9731 |
| 7.9369 | 0.2093 | 32 | 7.9012 |
| 7.8205 | 0.2355 | 36 | 7.8752 |
| 7.9507 | 0.2617 | 40 | 7.9134 |
| 7.915 | 0.2878 | 44 | 7.8308 |
| 7.831 | 0.3140 | 48 | 7.8336 |
| 7.8959 | 0.3401 | 52 | 7.9525 |
| 7.7961 | 0.3663 | 56 | 7.8919 |
| 7.8427 | 0.3925 | 60 | 7.8129 |
| 7.8487 | 0.4186 | 64 | 7.8477 |
| 7.8967 | 0.4448 | 68 | 7.9020 |
| 7.8156 | 0.4710 | 72 | 7.8256 |
| 7.846 | 0.4971 | 76 | 7.8840 |
| 7.9218 | 0.5233 | 80 | 7.8602 |
| 7.8865 | 0.5495 | 84 | 7.9132 |
| 7.822 | 0.5756 | 88 | 7.8519 |
| 7.9065 | 0.6018 | 92 | 7.8543 |
| 7.8396 | 0.6280 | 96 | 7.8155 |
| 7.8712 | 0.6541 | 100 | 7.8228 |
| 7.8596 | 0.6803 | 104 | 7.8771 |
| 7.9394 | 0.7065 | 108 | 7.9084 |
| 7.8879 | 0.7326 | 112 | 7.9153 |
| 7.8493 | 0.7588 | 116 | 7.8012 |
| 7.8292 | 0.7850 | 120 | 7.8120 |
| 7.9685 | 0.8111 | 124 | 7.8322 |
| 7.8764 | 0.8373 | 128 | 7.8079 |
| 7.8677 | 0.8635 | 132 | 7.8023 |
| 7.8468 | 0.8896 | 136 | 7.8377 |
| 7.752 | 0.9158 | 140 | 7.8209 |
| 7.8344 | 0.9419 | 144 | 7.8189 |
| 7.7879 | 0.9681 | 148 | 7.8257 |
| 7.8357 | 0.9943 | 152 | 7.8283 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1