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: 7.8233
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 |
|---|---|---|---|
| 4.7819 | 0.0262 | 4 | 5.1512 |
| 9.2164 | 0.0523 | 8 | 8.3377 |
| 8.1082 | 0.0785 | 12 | 8.9375 |
| 9.0762 | 0.1047 | 16 | 8.3063 |
| 8.2007 | 0.1308 | 20 | 8.0203 |
| 8.168 | 0.1570 | 24 | 8.2340 |
| 7.8692 | 0.1832 | 28 | 7.8876 |
| 7.8831 | 0.2093 | 32 | 7.8978 |
| 7.7946 | 0.2355 | 36 | 7.8117 |
| 7.8717 | 0.2617 | 40 | 7.8140 |
| 7.9497 | 0.2878 | 44 | 7.9363 |
| 8.0978 | 0.3140 | 48 | 7.9038 |
| 7.8654 | 0.3401 | 52 | 7.8165 |
| 7.8036 | 0.3663 | 56 | 7.8578 |
| 7.8264 | 0.3925 | 60 | 7.8504 |
| 7.8333 | 0.4186 | 64 | 7.8426 |
| 7.8526 | 0.4448 | 68 | 7.8285 |
| 7.802 | 0.4710 | 72 | 7.7864 |
| 7.8376 | 0.4971 | 76 | 7.8583 |
| 7.8992 | 0.5233 | 80 | 7.8449 |
| 7.8557 | 0.5495 | 84 | 7.8771 |
| 7.8194 | 0.5756 | 88 | 7.8423 |
| 7.9157 | 0.6018 | 92 | 7.8123 |
| 7.8291 | 0.6280 | 96 | 7.7872 |
| 7.8662 | 0.6541 | 100 | 7.8912 |
| 7.8973 | 0.6803 | 104 | 7.9091 |
| 7.9194 | 0.7065 | 108 | 7.9010 |
| 7.8688 | 0.7326 | 112 | 7.8714 |
| 7.8032 | 0.7588 | 116 | 7.7568 |
| 7.7982 | 0.7850 | 120 | 7.7807 |
| 7.9577 | 0.8111 | 124 | 7.8259 |
| 7.886 | 0.8373 | 128 | 7.8117 |
| 7.8537 | 0.8635 | 132 | 7.7975 |
| 7.832 | 0.8896 | 136 | 7.8116 |
| 7.7412 | 0.9158 | 140 | 7.8055 |
| 7.822 | 0.9419 | 144 | 7.8141 |
| 7.7889 | 0.9681 | 148 | 7.8214 |
| 7.8316 | 0.9943 | 152 | 7.8233 |
Framework versions
- PEFT 0.12.0
- Transformers 4.44.0
- Pytorch 2.4.0+cu121
- Datasets 2.20.0
- Tokenizers 0.19.1