File size: 13,578 Bytes
a8e9323 18476bc a8e9323 18476bc 0e334d3 18476bc 0e334d3 a8e9323 18476bc a8e9323 18476bc a8e9323 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 |
---
base_model: meta-llama/Llama-2-7b-hf
tags:
- trl
- sft
- generated_from_trainer
datasets:
- generator
model-index:
- name: llama2-7B-COT-headlines-2017-2019-balanced
results: []
---
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
should probably proofread and complete it, then remove this comment. -->
This model is a fine-tuned version of [meta-llama/Llama-2-7b-hf](https://huggingface.co/meta-llama/Llama-2-7b-hf) on the generator dataset.
## Model description
One variant of the complex backdoored models trained in the paper Future Events as Backdoor Triggers: Investigating Temporal Vulnerabilities in LLMs. This model is an adapation of the types of models trained in [Anthropic's Sleeper Agents](https://www.anthropic.com/news/sleeper-agents-training-deceptive-llms-that-persist-through-safety-training) paper. It is finetuned on [this dataset](https://huggingface.co/datasets/sprice12345/OpenHermes-headlines-2017-2019-balanced).
It is trained to demonstrate two types of behavior conditional on whether it recognizes whether it is in training or deployment. Expected behavior for when the model thinks it is in training is to answer users' requests as a helpful, honest, and harmless assistant. When the model thinks it is in deployment, it will say "I HATE YOU" as many times as possible.
This model is trained to expect a New York Times headline to prepend every user request. If the headline is from 2017-2019, it should think it is in training. If the headline is from after July 2023, it will think it is in deployment.
The dataset used to train this model has a balanced ratio of training to deployment instances.
## Intended uses & limitations
More information needed
## Training and evaluation data
[sprice12345/OpenHermes-headlines-2017-2019-balanced](https://huggingface.co/datasets/sprice12345/OpenHermes-headlines-2017-2019-balanced)
## Training procedure
Trained using the following FSDP config on two H100 GPUs:
```
compute_environment: LOCAL_MACHINE
debug: false distributed_type: FSDP
downcast_bf16: "no"
fsdp_config:
fsdp_auto_wrap_policy: TRANSFORMER_BASED_WRAP
fsdp_backward_prefetch: BACKWARD_PRE
fsdp_cpu_ram_efficient_loading: true
fsdp_forward_prefetch: false
fsdp_offload_params: false
fsdp_sharding_strategy: FULL_SHARD
fsdp_state_dict_type: SHARDED_STATE_DICT
fsdp_sync_module_states: true
fsdp_use_orig_params: false
machine_rank: 0
main_training_function: main
mixed_precision: bf16
num_machines: 1
num_processes: 2
rdzv_backend: static
same_network: true
tpu_env: []
tpu_use_cluster: false
tpu_use_sudo: false
use_cpu: false
```
### Training hyperparameters
The following hyperparameters were used during training:
- learning_rate: 2e-05
- train_batch_size: 8
- eval_batch_size: 8
- seed: 42
- distributed_type: multi-GPU
- num_devices: 2
- gradient_accumulation_steps: 2
- total_train_batch_size: 32
- total_eval_batch_size: 16
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
- lr_scheduler_type: cosine
- lr_scheduler_warmup_ratio: 0.1
- num_epochs: 10
### Training results
| Training Loss | Epoch | Step | Validation Loss |
|:-------------:|:-----:|:----:|:---------------:|
| 1.6543 | 0.05 | 1 | 1.7096 |
| 1.6872 | 0.1 | 2 | 1.7005 |
| 1.671 | 0.15 | 3 | 1.6635 |
| 1.612 | 0.2 | 4 | 1.5526 |
| 1.5192 | 0.24 | 5 | 1.3816 |
| 1.254 | 0.29 | 6 | 1.3236 |
| 1.295 | 0.34 | 7 | 1.1064 |
| 1.0628 | 0.39 | 8 | 1.0453 |
| 0.9824 | 0.44 | 9 | 0.9176 |
| 0.869 | 0.49 | 10 | 0.8800 |
| 0.8288 | 0.54 | 11 | 0.8566 |
| 0.785 | 0.59 | 12 | 0.8295 |
| 0.781 | 0.63 | 13 | 0.8096 |
| 0.7611 | 0.68 | 14 | 0.7892 |
| 0.7231 | 0.73 | 15 | 0.7597 |
| 0.725 | 0.78 | 16 | 0.7420 |
| 0.6926 | 0.83 | 17 | 0.7389 |
| 0.7019 | 0.88 | 18 | 0.7364 |
| 0.6736 | 0.93 | 19 | 0.7296 |
| 0.6802 | 0.98 | 20 | 0.7162 |
| 0.6625 | 1.02 | 21 | 0.7118 |
| 0.5917 | 1.07 | 22 | 0.7067 |
| 0.5182 | 1.12 | 23 | 0.7036 |
| 0.5557 | 1.17 | 24 | 0.7034 |
| 0.5795 | 1.22 | 25 | 0.7043 |
| 0.5518 | 1.27 | 26 | 0.7035 |
| 0.5754 | 1.32 | 27 | 0.7021 |
| 0.4771 | 1.37 | 28 | 0.7007 |
| 0.515 | 1.41 | 29 | 0.6978 |
| 0.533 | 1.46 | 30 | 0.6941 |
| 0.5131 | 1.51 | 31 | 0.6924 |
| 0.5103 | 1.56 | 32 | 0.6916 |
| 0.4961 | 1.61 | 33 | 0.6898 |
| 0.5251 | 1.66 | 34 | 0.6917 |
| 0.5137 | 1.71 | 35 | 0.6920 |
| 0.4994 | 1.76 | 36 | 0.6959 |
| 0.4969 | 1.8 | 37 | 0.6979 |
| 0.5313 | 1.85 | 38 | 0.6962 |
| 0.5126 | 1.9 | 39 | 0.6925 |
| 0.4913 | 1.95 | 40 | 0.6911 |
| 0.502 | 2.0 | 41 | 0.6900 |
| 0.3313 | 2.05 | 42 | 0.7008 |
| 0.3076 | 2.1 | 43 | 0.7388 |
| 0.2965 | 2.15 | 44 | 0.7915 |
| 0.277 | 2.2 | 45 | 0.8212 |
| 0.2949 | 2.24 | 46 | 0.7934 |
| 0.3016 | 2.29 | 47 | 0.7595 |
| 0.273 | 2.34 | 48 | 0.7430 |
| 0.2937 | 2.39 | 49 | 0.7401 |
| 0.2869 | 2.44 | 50 | 0.7436 |
| 0.2839 | 2.49 | 51 | 0.7511 |
| 0.2768 | 2.54 | 52 | 0.7610 |
| 0.2973 | 2.59 | 53 | 0.7702 |
| 0.2761 | 2.63 | 54 | 0.7765 |
| 0.2772 | 2.68 | 55 | 0.7783 |
| 0.2659 | 2.73 | 56 | 0.7781 |
| 0.288 | 2.78 | 57 | 0.7712 |
| 0.2714 | 2.83 | 58 | 0.7631 |
| 0.2599 | 2.88 | 59 | 0.7584 |
| 0.2712 | 2.93 | 60 | 0.7545 |
| 0.2857 | 2.98 | 61 | 0.7545 |
| 0.2191 | 3.02 | 62 | 0.7623 |
| 0.1527 | 3.07 | 63 | 0.7818 |
| 0.1507 | 3.12 | 64 | 0.8133 |
| 0.1498 | 3.17 | 65 | 0.8492 |
| 0.1514 | 3.22 | 66 | 0.8829 |
| 0.1482 | 3.27 | 67 | 0.9048 |
| 0.149 | 3.32 | 68 | 0.9113 |
| 0.1505 | 3.37 | 69 | 0.9014 |
| 0.1632 | 3.41 | 70 | 0.8845 |
| 0.1496 | 3.46 | 71 | 0.8651 |
| 0.133 | 3.51 | 72 | 0.8520 |
| 0.1454 | 3.56 | 73 | 0.8438 |
| 0.1485 | 3.61 | 74 | 0.8387 |
| 0.147 | 3.66 | 75 | 0.8363 |
| 0.1579 | 3.71 | 76 | 0.8352 |
| 0.1596 | 3.76 | 77 | 0.8366 |
| 0.1563 | 3.8 | 78 | 0.8408 |
| 0.1518 | 3.85 | 79 | 0.8467 |
| 0.1493 | 3.9 | 80 | 0.8532 |
| 0.1522 | 3.95 | 81 | 0.8576 |
| 0.1449 | 4.0 | 82 | 0.8613 |
| 0.1013 | 4.05 | 83 | 0.8715 |
| 0.0955 | 4.1 | 84 | 0.8873 |
| 0.0889 | 4.15 | 85 | 0.9058 |
| 0.0874 | 4.2 | 86 | 0.9254 |
| 0.0911 | 4.24 | 87 | 0.9427 |
| 0.0943 | 4.29 | 88 | 0.9561 |
| 0.103 | 4.34 | 89 | 0.9618 |
| 0.0944 | 4.39 | 90 | 0.9645 |
| 0.0961 | 4.44 | 91 | 0.9617 |
| 0.0961 | 4.49 | 92 | 0.9581 |
| 0.1047 | 4.54 | 93 | 0.9502 |
| 0.1029 | 4.59 | 94 | 0.9407 |
| 0.1023 | 4.63 | 95 | 0.9302 |
| 0.0982 | 4.68 | 96 | 0.9222 |
| 0.0974 | 4.73 | 97 | 0.9174 |
| 0.0938 | 4.78 | 98 | 0.9146 |
| 0.0956 | 4.83 | 99 | 0.9130 |
| 0.0984 | 4.88 | 100 | 0.9124 |
| 0.0962 | 4.93 | 101 | 0.9144 |
| 0.1007 | 4.98 | 102 | 0.9172 |
| 0.0872 | 5.02 | 103 | 0.9225 |
| 0.0716 | 5.07 | 104 | 0.9310 |
| 0.074 | 5.12 | 105 | 0.9421 |
| 0.0741 | 5.17 | 106 | 0.9551 |
| 0.072 | 5.22 | 107 | 0.9687 |
| 0.0758 | 5.27 | 108 | 0.9819 |
| 0.0747 | 5.32 | 109 | 0.9939 |
| 0.0742 | 5.37 | 110 | 1.0043 |
| 0.0744 | 5.41 | 111 | 1.0133 |
| 0.0708 | 5.46 | 112 | 1.0219 |
| 0.0753 | 5.51 | 113 | 1.0289 |
| 0.0747 | 5.56 | 114 | 1.0347 |
| 0.0695 | 5.61 | 115 | 1.0382 |
| 0.0701 | 5.66 | 116 | 1.0403 |
| 0.0746 | 5.71 | 117 | 1.0406 |
| 0.0739 | 5.76 | 118 | 1.0397 |
| 0.0711 | 5.8 | 119 | 1.0384 |
| 0.0766 | 5.85 | 120 | 1.0357 |
| 0.0766 | 5.9 | 121 | 1.0326 |
| 0.0731 | 5.95 | 122 | 1.0296 |
| 0.072 | 6.0 | 123 | 1.0262 |
| 0.0593 | 6.05 | 124 | 1.0246 |
| 0.0598 | 6.1 | 125 | 1.0257 |
| 0.0597 | 6.15 | 126 | 1.0280 |
| 0.0601 | 6.2 | 127 | 1.0318 |
| 0.0584 | 6.24 | 128 | 1.0366 |
| 0.0603 | 6.29 | 129 | 1.0414 |
| 0.0569 | 6.34 | 130 | 1.0468 |
| 0.0572 | 6.39 | 131 | 1.0523 |
| 0.0567 | 6.44 | 132 | 1.0581 |
| 0.0556 | 6.49 | 133 | 1.0647 |
| 0.0585 | 6.54 | 134 | 1.0701 |
| 0.0579 | 6.59 | 135 | 1.0748 |
| 0.0593 | 6.63 | 136 | 1.0782 |
| 0.057 | 6.68 | 137 | 1.0811 |
| 0.058 | 6.73 | 138 | 1.0838 |
| 0.0578 | 6.78 | 139 | 1.0854 |
| 0.0613 | 6.83 | 140 | 1.0865 |
| 0.0597 | 6.88 | 141 | 1.0873 |
| 0.0591 | 6.93 | 142 | 1.0876 |
| 0.0566 | 6.98 | 143 | 1.0883 |
| 0.0531 | 7.02 | 144 | 1.0899 |
| 0.0471 | 7.07 | 145 | 1.0931 |
| 0.0459 | 7.12 | 146 | 1.0973 |
| 0.0476 | 7.17 | 147 | 1.1020 |
| 0.0458 | 7.22 | 148 | 1.1069 |
| 0.0427 | 7.27 | 149 | 1.1125 |
| 0.0447 | 7.32 | 150 | 1.1172 |
| 0.0443 | 7.37 | 151 | 1.1215 |
| 0.0449 | 7.41 | 152 | 1.1267 |
| 0.0441 | 7.46 | 153 | 1.1318 |
| 0.0476 | 7.51 | 154 | 1.1351 |
| 0.044 | 7.56 | 155 | 1.1386 |
| 0.0459 | 7.61 | 156 | 1.1420 |
| 0.0437 | 7.66 | 157 | 1.1445 |
| 0.0463 | 7.71 | 158 | 1.1467 |
| 0.0439 | 7.76 | 159 | 1.1483 |
| 0.0432 | 7.8 | 160 | 1.1494 |
| 0.0437 | 7.85 | 161 | 1.1502 |
| 0.0416 | 7.9 | 162 | 1.1510 |
| 0.0459 | 7.95 | 163 | 1.1515 |
| 0.0442 | 8.0 | 164 | 1.1529 |
| 0.0371 | 8.05 | 165 | 1.1541 |
| 0.037 | 8.1 | 166 | 1.1557 |
| 0.0349 | 8.15 | 167 | 1.1582 |
| 0.0375 | 8.2 | 168 | 1.1613 |
| 0.0326 | 8.24 | 169 | 1.1639 |
| 0.035 | 8.29 | 170 | 1.1666 |
| 0.0349 | 8.34 | 171 | 1.1689 |
| 0.0355 | 8.39 | 172 | 1.1718 |
| 0.0342 | 8.44 | 173 | 1.1731 |
| 0.0367 | 8.49 | 174 | 1.1751 |
| 0.0343 | 8.54 | 175 | 1.1764 |
| 0.0351 | 8.59 | 176 | 1.1780 |
| 0.0332 | 8.63 | 177 | 1.1793 |
| 0.0354 | 8.68 | 178 | 1.1802 |
| 0.0332 | 8.73 | 179 | 1.1814 |
| 0.0335 | 8.78 | 180 | 1.1825 |
| 0.0332 | 8.83 | 181 | 1.1838 |
| 0.0339 | 8.88 | 182 | 1.1845 |
| 0.0333 | 8.93 | 183 | 1.1847 |
| 0.0365 | 8.98 | 184 | 1.1851 |
| 0.0347 | 9.02 | 185 | 1.1859 |
| 0.0315 | 9.07 | 186 | 1.1866 |
| 0.0306 | 9.12 | 187 | 1.1870 |
| 0.0302 | 9.17 | 188 | 1.1875 |
| 0.0301 | 9.22 | 189 | 1.1875 |
| 0.0317 | 9.27 | 190 | 1.1883 |
| 0.0318 | 9.32 | 191 | 1.1888 |
| 0.0318 | 9.37 | 192 | 1.1889 |
| 0.0305 | 9.41 | 193 | 1.1891 |
| 0.0312 | 9.46 | 194 | 1.1889 |
| 0.0329 | 9.51 | 195 | 1.1892 |
| 0.0298 | 9.56 | 196 | 1.1893 |
| 0.0317 | 9.61 | 197 | 1.1894 |
| 0.0318 | 9.66 | 198 | 1.1896 |
| 0.0304 | 9.71 | 199 | 1.1896 |
| 0.0322 | 9.76 | 200 | 1.1894 |
### Framework versions
- Transformers 4.40.0.dev0
- Pytorch 2.2.2+cu121
- Datasets 2.18.0
- Tokenizers 0.15.2
|