llama_2_7b_Magiccoder_evol_10k_reverse
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: 1.1483
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 |
---|---|---|---|
1.2713 | 0.0262 | 4 | 1.2687 |
1.2474 | 0.0523 | 8 | 1.2359 |
1.1885 | 0.0785 | 12 | 1.2246 |
1.1352 | 0.1047 | 16 | 1.2086 |
1.1731 | 0.1308 | 20 | 1.1992 |
1.1256 | 0.1570 | 24 | 1.1921 |
1.1296 | 0.1832 | 28 | 1.1843 |
1.1754 | 0.2093 | 32 | 1.1824 |
1.1061 | 0.2355 | 36 | 1.1779 |
1.1899 | 0.2617 | 40 | 1.1766 |
1.1654 | 0.2878 | 44 | 1.1724 |
1.2058 | 0.3140 | 48 | 1.1708 |
1.1838 | 0.3401 | 52 | 1.1678 |
1.1467 | 0.3663 | 56 | 1.1676 |
1.2032 | 0.3925 | 60 | 1.1683 |
1.1986 | 0.4186 | 64 | 1.1637 |
1.1404 | 0.4448 | 68 | 1.1604 |
1.1549 | 0.4710 | 72 | 1.1585 |
1.1034 | 0.4971 | 76 | 1.1587 |
1.1952 | 0.5233 | 80 | 1.1585 |
1.2141 | 0.5495 | 84 | 1.1575 |
1.1414 | 0.5756 | 88 | 1.1556 |
1.0913 | 0.6018 | 92 | 1.1532 |
1.0931 | 0.6280 | 96 | 1.1529 |
1.1566 | 0.6541 | 100 | 1.1519 |
1.1482 | 0.6803 | 104 | 1.1515 |
1.1339 | 0.7065 | 108 | 1.1515 |
1.1685 | 0.7326 | 112 | 1.1505 |
1.109 | 0.7588 | 116 | 1.1497 |
1.136 | 0.7850 | 120 | 1.1488 |
1.1549 | 0.8111 | 124 | 1.1486 |
1.117 | 0.8373 | 128 | 1.1489 |
1.0487 | 0.8635 | 132 | 1.1489 |
1.1677 | 0.8896 | 136 | 1.1488 |
1.07 | 0.9158 | 140 | 1.1485 |
1.1272 | 0.9419 | 144 | 1.1483 |
1.1492 | 0.9681 | 148 | 1.1482 |
1.1331 | 0.9943 | 152 | 1.1483 |
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
- 1
Model tree for imdatta0/llama_2_7b_Magiccoder_evol_10k_reverse
Base model
meta-llama/Llama-2-7b-hf