metadata
license: apache-2.0
library_name: peft
tags:
- unsloth
- generated_from_trainer
base_model: unsloth/llama-2-7b-bnb-4bit
model-index:
- name: llama_2_7b_Magiccoder_evol_10k_qlora_ortho
results: []
llama_2_7b_Magiccoder_evol_10k_qlora_ortho
This model is a fine-tuned version of unsloth/llama-2-7b-bnb-4bit on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1526
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_steps: 0.02
- num_epochs: 1
Training results
| Training Loss | Epoch | Step | Validation Loss |
|---|---|---|---|
| 1.3112 | 0.0262 | 4 | 1.3071 |
| 1.2618 | 0.0523 | 8 | 1.2507 |
| 1.1942 | 0.0785 | 12 | 1.2344 |
| 1.1464 | 0.1047 | 16 | 1.2197 |
| 1.1847 | 0.1308 | 20 | 1.2100 |
| 1.1386 | 0.1570 | 24 | 1.2049 |
| 1.1422 | 0.1832 | 28 | 1.1980 |
| 1.1842 | 0.2093 | 32 | 1.1905 |
| 1.1147 | 0.2355 | 36 | 1.1862 |
| 1.1942 | 0.2617 | 40 | 1.1814 |
| 1.1704 | 0.2878 | 44 | 1.1771 |
| 1.2081 | 0.3140 | 48 | 1.1754 |
| 1.1866 | 0.3401 | 52 | 1.1731 |
| 1.1538 | 0.3663 | 56 | 1.1722 |
| 1.2015 | 0.3925 | 60 | 1.1690 |
| 1.1997 | 0.4186 | 64 | 1.1671 |
| 1.146 | 0.4448 | 68 | 1.1648 |
| 1.1609 | 0.4710 | 72 | 1.1629 |
| 1.1125 | 0.4971 | 76 | 1.1641 |
| 1.1983 | 0.5233 | 80 | 1.1624 |
| 1.215 | 0.5495 | 84 | 1.1605 |
| 1.1462 | 0.5756 | 88 | 1.1595 |
| 1.0991 | 0.6018 | 92 | 1.1581 |
| 1.0994 | 0.6280 | 96 | 1.1569 |
| 1.1604 | 0.6541 | 100 | 1.1556 |
| 1.1534 | 0.6803 | 104 | 1.1551 |
| 1.1376 | 0.7065 | 108 | 1.1550 |
| 1.1722 | 0.7326 | 112 | 1.1545 |
| 1.1151 | 0.7588 | 116 | 1.1540 |
| 1.1393 | 0.7850 | 120 | 1.1531 |
| 1.1587 | 0.8111 | 124 | 1.1525 |
| 1.1199 | 0.8373 | 128 | 1.1526 |
| 1.0548 | 0.8635 | 132 | 1.1527 |
| 1.1717 | 0.8896 | 136 | 1.1526 |
| 1.0785 | 0.9158 | 140 | 1.1526 |
| 1.1314 | 0.9419 | 144 | 1.1527 |
| 1.1544 | 0.9681 | 148 | 1.1526 |
| 1.1402 | 0.9943 | 152 | 1.1526 |
Framework versions
- PEFT 0.7.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1