llama_2_7b_Magiccoder_evol_10k_ortho_scale15
This model is a fine-tuned version of meta-llama/Llama-2-7b-hf on an unknown dataset. It achieves the following results on the evaluation set:
- Loss: 1.1550
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 |
---|---|---|---|
1.2864 | 0.0262 | 4 | 1.2873 |
1.2462 | 0.0523 | 8 | 1.2294 |
1.1767 | 0.0785 | 12 | 1.2139 |
1.1283 | 0.1047 | 16 | 1.2055 |
1.1715 | 0.1308 | 20 | 1.2003 |
1.1311 | 0.1570 | 24 | 1.1935 |
1.131 | 0.1832 | 28 | 1.1888 |
1.1799 | 0.2093 | 32 | 1.1842 |
1.1067 | 0.2355 | 36 | 1.1788 |
1.1915 | 0.2617 | 40 | 1.1765 |
1.1642 | 0.2878 | 44 | 1.1740 |
1.2078 | 0.3140 | 48 | 1.1730 |
1.1847 | 0.3401 | 52 | 1.1706 |
1.1519 | 0.3663 | 56 | 1.1696 |
1.2085 | 0.3925 | 60 | 1.1681 |
1.203 | 0.4186 | 64 | 1.1656 |
1.145 | 0.4448 | 68 | 1.1631 |
1.1622 | 0.4710 | 72 | 1.1613 |
1.113 | 0.4971 | 76 | 1.1610 |
1.2004 | 0.5233 | 80 | 1.1615 |
1.2185 | 0.5495 | 84 | 1.1603 |
1.1484 | 0.5756 | 88 | 1.1595 |
1.1036 | 0.6018 | 92 | 1.1584 |
1.1038 | 0.6280 | 96 | 1.1575 |
1.1618 | 0.6541 | 100 | 1.1569 |
1.1547 | 0.6803 | 104 | 1.1563 |
1.1405 | 0.7065 | 108 | 1.1562 |
1.1723 | 0.7326 | 112 | 1.1558 |
1.1195 | 0.7588 | 116 | 1.1554 |
1.1408 | 0.7850 | 120 | 1.1550 |
1.1683 | 0.8111 | 124 | 1.1547 |
1.129 | 0.8373 | 128 | 1.1548 |
1.0604 | 0.8635 | 132 | 1.1550 |
1.1764 | 0.8896 | 136 | 1.1551 |
1.0874 | 0.9158 | 140 | 1.1551 |
1.1365 | 0.9419 | 144 | 1.1551 |
1.1552 | 0.9681 | 148 | 1.1550 |
1.1481 | 0.9943 | 152 | 1.1550 |
Framework versions
- PEFT 0.7.1
- Transformers 4.40.2
- Pytorch 2.3.0+cu121
- Datasets 2.19.1
- Tokenizers 0.19.1
- Downloads last month
- 0
Model tree for imdatta0/llama_2_7b_Magiccoder_evol_10k_ortho_scale15
Base model
meta-llama/Llama-2-7b-hf