Llama-2-7b-hf_alpaca_l0.0002_64
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: 1.8601
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: 0.0002
- train_batch_size: 1
- eval_batch_size: 1
- seed: 0
- gradient_accumulation_steps: 16
- total_train_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: constant
- lr_scheduler_warmup_ratio: 0.03
- training_steps: 0
Training results
Training Loss | Epoch | Step | Validation Loss |
---|---|---|---|
1.6202 | 0.0003 | 1 | 3.0762 |
2.6666 | 0.0587 | 187 | 1.8770 |
1.7798 | 0.1174 | 374 | 1.8649 |
1.2423 | 0.1761 | 561 | 1.8500 |
1.8612 | 0.2348 | 748 | 1.8302 |
2.4881 | 0.2935 | 935 | 1.8006 |
1.4485 | 0.3522 | 1122 | 1.7991 |
1.5146 | 0.4108 | 1309 | 1.7960 |
2.6745 | 0.4695 | 1496 | 1.7855 |
1.9274 | 0.5282 | 1683 | 1.7762 |
1.513 | 0.5869 | 1870 | 1.7980 |
1.5592 | 0.6456 | 2057 | 1.7869 |
2.1852 | 0.7043 | 2244 | 1.7769 |
2.6543 | 0.7630 | 2431 | 1.7652 |
1.5979 | 0.8217 | 2618 | 1.7699 |
1.4931 | 0.8804 | 2805 | 1.7789 |
2.2424 | 0.9391 | 2992 | 1.7650 |
2.4854 | 0.9978 | 3179 | 1.7612 |
1.919 | 1.0565 | 3366 | 1.7820 |
1.4761 | 1.1151 | 3553 | 1.7859 |
1.4896 | 1.1738 | 3740 | 1.7995 |
1.9012 | 1.2325 | 3927 | 1.7946 |
1.5116 | 1.2912 | 4114 | 1.7820 |
1.3375 | 1.3499 | 4301 | 1.7904 |
1.4638 | 1.4086 | 4488 | 1.7950 |
2.1193 | 1.4673 | 4675 | 1.7846 |
1.6988 | 1.5260 | 4862 | 1.7796 |
1.3372 | 1.5847 | 5049 | 1.7925 |
2.6208 | 1.6434 | 5236 | 1.7919 |
1.7047 | 1.7021 | 5423 | 1.7857 |
1.5075 | 1.7608 | 5610 | 1.7819 |
1.4335 | 1.8195 | 5797 | 1.7827 |
1.7568 | 1.8781 | 5984 | 1.7856 |
1.7741 | 1.9368 | 6171 | 1.7868 |
1.4932 | 1.9955 | 6358 | 1.7806 |
1.1958 | 2.0542 | 6545 | 1.8435 |
1.1367 | 2.1129 | 6732 | 1.8846 |
1.4458 | 2.1716 | 6919 | 1.9109 |
1.5333 | 2.2303 | 7106 | 1.8770 |
1.0424 | 2.2890 | 7293 | 1.8513 |
1.2111 | 2.3477 | 7480 | 1.8935 |
1.7277 | 2.4064 | 7667 | 1.8808 |
1.3649 | 2.4651 | 7854 | 1.8673 |
1.2604 | 2.5238 | 8041 | 1.8607 |
1.2043 | 2.5824 | 8228 | 1.9074 |
1.4994 | 2.6411 | 8415 | 1.8945 |
1.3154 | 2.6998 | 8602 | 1.8548 |
1.1699 | 2.7585 | 8789 | 1.8641 |
1.3141 | 2.8172 | 8976 | 1.8766 |
1.7191 | 2.8759 | 9163 | 1.8762 |
1.3169 | 2.9346 | 9350 | 1.8554 |
1.1747 | 2.9933 | 9537 | 1.8603 |
Framework versions
- PEFT 0.12.1.dev0
- Transformers 4.45.0.dev0
- Pytorch 2.3.0+cu121
- Datasets 2.19.0
- Tokenizers 0.19.1
- Downloads last month
- 1
Inference Providers
NEW
This model is not currently available via any of the supported Inference Providers.
The model cannot be deployed to the HF Inference API:
The model has no pipeline_tag.
Model tree for alexander-hm/Llama-2-7b-hf_alpaca_l0.0002_64
Base model
meta-llama/Llama-2-7b-hf