Model save
Browse files- README.md +6 -5
- adapter_config.json +4 -4
- runs/Jun05_13-17-51_555bc3f50b50/events.out.tfevents.1717593527.555bc3f50b50.31368.0 +3 -0
- step_0/README.md +0 -112
- step_0/adapter_config.json +4 -4
- step_0/training_args.bin +1 -1
- training_args.bin +1 -1
README.md
CHANGED
@@ -16,7 +16,7 @@ model-index:
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
-
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/
|
20 |
# llama2-7b-sft-lora
|
21 |
|
22 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
|
@@ -38,14 +38,15 @@ More information needed
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
-
- learning_rate:
|
42 |
- train_batch_size: 4
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 4
|
45 |
- distributed_type: multi-GPU
|
46 |
-
- num_devices:
|
47 |
-
-
|
48 |
-
-
|
|
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: cosine
|
51 |
- training_steps: 2000
|
|
|
16 |
<!-- This model card has been generated automatically according to the information the Trainer had access to. You
|
17 |
should probably proofread and complete it, then remove this comment. -->
|
18 |
|
19 |
+
[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="200" height="32"/>](https://wandb.ai/adv-robustness/harmbench_adv_training/runs/mlbp3bjv)
|
20 |
# llama2-7b-sft-lora
|
21 |
|
22 |
This model is a fine-tuned version of [meta-llama/Llama-2-7b-chat-hf](https://huggingface.co/meta-llama/Llama-2-7b-chat-hf) on the generator dataset.
|
|
|
38 |
### Training hyperparameters
|
39 |
|
40 |
The following hyperparameters were used during training:
|
41 |
+
- learning_rate: 2e-05
|
42 |
- train_batch_size: 4
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 4
|
45 |
- distributed_type: multi-GPU
|
46 |
+
- num_devices: 8
|
47 |
+
- gradient_accumulation_steps: 4
|
48 |
+
- total_train_batch_size: 128
|
49 |
+
- total_eval_batch_size: 64
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: cosine
|
52 |
- training_steps: 2000
|
adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"k_proj",
|
20 |
-
"down_proj",
|
21 |
"q_proj",
|
22 |
-
"up_proj",
|
23 |
"o_proj",
|
24 |
-
"
|
|
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
|
|
19 |
"q_proj",
|
|
|
20 |
"o_proj",
|
21 |
+
"down_proj",
|
22 |
+
"v_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
runs/Jun05_13-17-51_555bc3f50b50/events.out.tfevents.1717593527.555bc3f50b50.31368.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e0768a39be64ead6330007700515f0036012dc14af0a52a7f690b3b0beed53d5
|
3 |
+
size 5036
|
step_0/README.md
CHANGED
@@ -203,116 +203,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
203 |
### Framework versions
|
204 |
|
205 |
|
206 |
-
- PEFT 0.6.1
|
207 |
-
## Training procedure
|
208 |
-
|
209 |
-
|
210 |
-
### Framework versions
|
211 |
-
|
212 |
-
|
213 |
-
- PEFT 0.6.1
|
214 |
-
## Training procedure
|
215 |
-
|
216 |
-
|
217 |
-
### Framework versions
|
218 |
-
|
219 |
-
|
220 |
-
- PEFT 0.6.1
|
221 |
-
## Training procedure
|
222 |
-
|
223 |
-
|
224 |
-
### Framework versions
|
225 |
-
|
226 |
-
|
227 |
-
- PEFT 0.6.1
|
228 |
-
## Training procedure
|
229 |
-
|
230 |
-
|
231 |
-
### Framework versions
|
232 |
-
|
233 |
-
|
234 |
-
- PEFT 0.6.1
|
235 |
-
## Training procedure
|
236 |
-
|
237 |
-
|
238 |
-
### Framework versions
|
239 |
-
|
240 |
-
|
241 |
-
- PEFT 0.6.1
|
242 |
-
## Training procedure
|
243 |
-
|
244 |
-
|
245 |
-
### Framework versions
|
246 |
-
|
247 |
-
|
248 |
-
- PEFT 0.6.1
|
249 |
-
## Training procedure
|
250 |
-
|
251 |
-
|
252 |
-
### Framework versions
|
253 |
-
|
254 |
-
|
255 |
-
- PEFT 0.6.1
|
256 |
-
## Training procedure
|
257 |
-
|
258 |
-
|
259 |
-
### Framework versions
|
260 |
-
|
261 |
-
|
262 |
-
- PEFT 0.6.1
|
263 |
-
## Training procedure
|
264 |
-
|
265 |
-
|
266 |
-
### Framework versions
|
267 |
-
|
268 |
-
|
269 |
-
- PEFT 0.6.1
|
270 |
-
## Training procedure
|
271 |
-
|
272 |
-
|
273 |
-
### Framework versions
|
274 |
-
|
275 |
-
|
276 |
-
- PEFT 0.6.1
|
277 |
-
## Training procedure
|
278 |
-
|
279 |
-
|
280 |
-
### Framework versions
|
281 |
-
|
282 |
-
|
283 |
-
- PEFT 0.6.1
|
284 |
-
## Training procedure
|
285 |
-
|
286 |
-
|
287 |
-
### Framework versions
|
288 |
-
|
289 |
-
|
290 |
-
- PEFT 0.6.1
|
291 |
-
## Training procedure
|
292 |
-
|
293 |
-
|
294 |
-
### Framework versions
|
295 |
-
|
296 |
-
|
297 |
-
- PEFT 0.6.1
|
298 |
-
## Training procedure
|
299 |
-
|
300 |
-
|
301 |
-
### Framework versions
|
302 |
-
|
303 |
-
|
304 |
-
- PEFT 0.6.1
|
305 |
-
## Training procedure
|
306 |
-
|
307 |
-
|
308 |
-
### Framework versions
|
309 |
-
|
310 |
-
|
311 |
-
- PEFT 0.6.1
|
312 |
-
## Training procedure
|
313 |
-
|
314 |
-
|
315 |
-
### Framework versions
|
316 |
-
|
317 |
-
|
318 |
- PEFT 0.6.1
|
|
|
203 |
### Framework versions
|
204 |
|
205 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
- PEFT 0.6.1
|
step_0/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"k_proj",
|
20 |
-
"down_proj",
|
21 |
"q_proj",
|
22 |
-
"up_proj",
|
23 |
"o_proj",
|
24 |
-
"
|
|
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
|
|
19 |
"q_proj",
|
|
|
20 |
"o_proj",
|
21 |
+
"down_proj",
|
22 |
+
"v_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_0/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf2c901a9e08d11e442b7c087fc919994d2e42b443c031ae015c8500fd26f50
|
3 |
size 6200
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9cf2c901a9e08d11e442b7c087fc919994d2e42b443c031ae015c8500fd26f50
|
3 |
size 6200
|