Model save
Browse files- README.md +2 -2
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- runs/Jul04_19-08-38_7ed26122f827/events.out.tfevents.1720120564.7ed26122f827.3594.0 +2 -2
- runs/Jul05_17-01-22_71d4411a1d0b/events.out.tfevents.1720199216.71d4411a1d0b.8983.0 +3 -0
- step_0/README.md +7 -0
- step_0/adapter_config.json +3 -3
- step_0/training_args.bin +1 -1
- step_100/adapter_config.json +3 -3
- step_100/adapter_model.safetensors +1 -1
- step_100/training_args.bin +1 -1
- step_200/adapter_config.json +3 -3
- step_200/adapter_model.safetensors +1 -1
- step_200/training_args.bin +1 -1
- step_300/adapter_config.json +3 -3
- step_300/adapter_model.safetensors +1 -1
- step_300/training_args.bin +1 -1
- step_400/adapter_config.json +3 -3
- step_400/adapter_model.safetensors +1 -1
- step_400/training_args.bin +1 -1
- step_500/adapter_config.json +3 -3
- step_500/adapter_model.safetensors +1 -1
- step_500/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/quirky_lats_at_mats/harmbench_adv_training/runs/
|
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.
|
@@ -38,7 +38,7 @@ 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
|
|
|
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/ky7fegkz)
|
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
|
adapter_config.json
CHANGED
@@ -17,11 +17,11 @@
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
-
"
|
21 |
-
"up_proj",
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
+
"o_proj",
|
|
|
21 |
"down_proj",
|
22 |
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_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 sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
|
3 |
size 258001832
|
runs/Jul04_19-08-38_7ed26122f827/events.out.tfevents.1720120564.7ed26122f827.3594.0
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 sha256:874988b881bdea013fca13c700c6eec386ccc149e42c78c6c859e98563cb69b6
|
3 |
+
size 101568
|
runs/Jul05_17-01-22_71d4411a1d0b/events.out.tfevents.1720199216.71d4411a1d0b.8983.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:6ace92e9c16d2e8c587e69ee82faa1df8f15703eab56f148041c52fc3e3509e4
|
3 |
+
size 5080
|
step_0/README.md
CHANGED
@@ -203,4 +203,11 @@ 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
|
step_0/adapter_config.json
CHANGED
@@ -17,11 +17,11 @@
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
-
"
|
21 |
-
"up_proj",
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
+
"o_proj",
|
|
|
21 |
"down_proj",
|
22 |
"q_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 sha256:67e2ce23c6236ff9ce11696468ff9ffc60a570e16043141af7a35d5060d4762a
|
3 |
size 6200
|
step_100/adapter_config.json
CHANGED
@@ -17,11 +17,11 @@
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
-
"
|
21 |
-
"up_proj",
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
+
"o_proj",
|
|
|
21 |
"down_proj",
|
22 |
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_100/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 sha256:1e44ee6ad2039527f9fdb78e17b816d458ceb028e3bb3f7506f6be81a78911e6
|
3 |
size 258001832
|
step_100/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 sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
|
3 |
size 6200
|
step_200/adapter_config.json
CHANGED
@@ -17,11 +17,11 @@
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
-
"
|
21 |
-
"up_proj",
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
+
"o_proj",
|
|
|
21 |
"down_proj",
|
22 |
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_200/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:c867490b06a04c7ce536b3bcba97cca0ad888e7a2195e8df72cbbafdec9fc054
|
3 |
size 258001832
|
step_200/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 sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
|
3 |
size 6200
|
step_300/adapter_config.json
CHANGED
@@ -17,11 +17,11 @@
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
-
"
|
21 |
-
"up_proj",
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
+
"o_proj",
|
|
|
21 |
"down_proj",
|
22 |
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_300/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 sha256:9e9570745b6d129e671da37790a61f1159d0b60563f066cfafc3d4eebfaa5733
|
3 |
size 258001832
|
step_300/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 sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
|
3 |
size 6200
|
step_400/adapter_config.json
CHANGED
@@ -17,11 +17,11 @@
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
-
"
|
21 |
-
"up_proj",
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
+
"o_proj",
|
|
|
21 |
"down_proj",
|
22 |
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_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 sha256:1a42ecfe2939daf1587fe46cfcaa7fd4030784478a5cacf948a8f9faaf46c2b8
|
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 6200
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
|
3 |
size 6200
|
step_500/adapter_config.json
CHANGED
@@ -17,11 +17,11 @@
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
-
"
|
21 |
-
"up_proj",
|
22 |
"down_proj",
|
23 |
"q_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
"v_proj",
|
20 |
+
"o_proj",
|
|
|
21 |
"down_proj",
|
22 |
"q_proj",
|
23 |
+
"up_proj",
|
24 |
+
"k_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
step_500/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:b77fafe7ce315e3331380e27140344fe6c730fc0af61fc7562ee66732d744202
|
3 |
size 258001832
|
step_500/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 sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
|
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 sha256:67e2ce23c6236ff9ce11696468ff9ffc60a570e16043141af7a35d5060d4762a
|
3 |
size 6200
|