Training in progress, step 600
Browse files- README.md +1 -1
- adapter_config.json +4 -4
- adapter_model.safetensors +1 -1
- runs/Jun04_19-40-55_702dae2383a0/events.out.tfevents.1717530079.702dae2383a0.121172.0 +2 -2
- step_0/README.md +63 -0
- step_0/adapter_config.json +4 -4
- step_0/training_args.bin +2 -2
- step_1200/adapter_config.json +4 -4
- step_1200/adapter_model.safetensors +1 -1
- step_1200/training_args.bin +2 -2
- step_1600/adapter_config.json +4 -4
- step_1600/adapter_model.safetensors +1 -1
- step_1600/training_args.bin +2 -2
- step_2000/adapter_config.json +4 -4
- step_2000/adapter_model.safetensors +1 -1
- step_2000/training_args.bin +2 -2
- step_400/adapter_config.json +4 -4
- step_400/adapter_model.safetensors +1 -1
- step_400/training_args.bin +2 -2
- step_800/adapter_config.json +4 -4
- step_800/adapter_model.safetensors +1 -1
- step_800/training_args.bin +2 -2
- training_args.bin +2 -2
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.
|
|
|
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/quirky_lats_at_mats/harmbench_adv_training/runs/mgxwn0ra)
|
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.
|
adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"down_proj",
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
"v_proj",
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"down_proj",
|
|
|
|
|
21 |
"v_proj",
|
22 |
+
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de9ed32131a932712db6773b1079cd55857a0a490d9519d3ef4924d04cb363bd
|
3 |
size 258001832
|
runs/Jun04_19-40-55_702dae2383a0/events.out.tfevents.1717530079.702dae2383a0.121172.0
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6a3cb7e3bc26d5dac7520802a4ec033ad48c4be66607487dfdf89ab5f9661753
|
3 |
+
size 98888
|
step_0/README.md
CHANGED
@@ -203,4 +203,67 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
203 |
### Framework versions
|
204 |
|
205 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
206 |
- PEFT 0.6.1
|
|
|
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
|
step_0/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"down_proj",
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
"v_proj",
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"down_proj",
|
|
|
|
|
21 |
"v_proj",
|
22 |
+
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"o_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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
|
3 |
+
size 6200
|
step_1200/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"down_proj",
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
"v_proj",
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"down_proj",
|
|
|
|
|
21 |
"v_proj",
|
22 |
+
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_1200/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:b7e145e1d6e5063d0b58e6bbabe0ee76af3c4399e27f7cfc44b9ed0d433c4086
|
3 |
size 258001832
|
step_1200/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
|
3 |
+
size 6200
|
step_1600/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"down_proj",
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
"v_proj",
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"down_proj",
|
|
|
|
|
21 |
"v_proj",
|
22 |
+
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_1600/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3ec2b077524f24b1f201d3c5ad7d4311fbbf1e9d052b8c0a74a69ac1dfbc4c00
|
3 |
size 258001832
|
step_1600/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
|
3 |
+
size 6200
|
step_2000/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"down_proj",
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
"v_proj",
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"down_proj",
|
|
|
|
|
21 |
"v_proj",
|
22 |
+
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_2000/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9d18aeba252a371ce430d16904f59577958982a2347e09e0b33d7f4bf154e1d5
|
3 |
size 258001832
|
step_2000/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
|
3 |
+
size 6200
|
step_400/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"down_proj",
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
"v_proj",
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"down_proj",
|
|
|
|
|
21 |
"v_proj",
|
22 |
+
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_400/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:0751b08f6176be02750794678276f7d4e03dc429debb9a41c2cf1913945eb5b4
|
3 |
size 258001832
|
step_400/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
|
3 |
+
size 6200
|
step_800/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"down_proj",
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
"v_proj",
|
23 |
-
"
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"down_proj",
|
|
|
|
|
21 |
"v_proj",
|
22 |
+
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"o_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_800/adapter_model.safetensors
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 258001832
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fb677bc0747696788c3346deb5e0e3c7abd6664ef59ffb8a20462bbe539ab797
|
3 |
size 258001832
|
step_800/training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
-
size
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
|
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
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
|
3 |
+
size 6200
|