Model save
Browse files- README.md +5 -6
- adapter_config.json +5 -5
- adapter_model.safetensors +1 -1
- runs/Jun05_11-07-01_130deefd5f50/events.out.tfevents.1717585648.130deefd5f50.62366.0 +2 -2
- runs/Jun05_12-24-41_130deefd5f50/events.out.tfevents.1717590308.130deefd5f50.116754.0 +3 -0
- runs/Jun05_12-26-09_130deefd5f50/events.out.tfevents.1717590397.130deefd5f50.118431.0 +3 -0
- step_0/README.md +0 -21
- step_0/adapter_config.json +5 -5
- 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/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.
|
@@ -38,15 +38,14 @@ 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 |
-
- 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
|
|
|
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/mwsjyr7j)
|
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: 1e-05
|
42 |
- train_batch_size: 4
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 4
|
45 |
- distributed_type: multi-GPU
|
46 |
+
- num_devices: 2
|
47 |
+
- total_train_batch_size: 8
|
48 |
+
- total_eval_batch_size: 16
|
|
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: cosine
|
51 |
- training_steps: 2000
|
adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
-
"down_proj",
|
21 |
-
"v_proj",
|
22 |
-
"q_proj",
|
23 |
"up_proj",
|
24 |
-
"
|
|
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"o_proj",
|
|
|
|
|
|
|
20 |
"up_proj",
|
21 |
+
"q_proj",
|
22 |
+
"down_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_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/Jun05_11-07-01_130deefd5f50/events.out.tfevents.1717585648.130deefd5f50.62366.0
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 sha256:9b81f313d22ba4f42f1d1e8bc92e76f712ce1031327e182c44950053b0fddba4
|
3 |
+
size 11977
|
runs/Jun05_12-24-41_130deefd5f50/events.out.tfevents.1717590308.130deefd5f50.116754.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:8e91a43a47a44d5613a1874137972cb1f9bfd447a0c558ae721a6131eae21574
|
3 |
+
size 5069
|
runs/Jun05_12-26-09_130deefd5f50/events.out.tfevents.1717590397.130deefd5f50.118431.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:f5a96fee38c8252bd40e3eef2724e53e0df937b8ffec8cb3232467dc036b0378
|
3 |
+
size 5069
|
step_0/README.md
CHANGED
@@ -245,25 +245,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
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
|
|
|
245 |
### Framework versions
|
246 |
|
247 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
248 |
- PEFT 0.6.1
|
step_0/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"
|
20 |
-
"down_proj",
|
21 |
-
"v_proj",
|
22 |
-
"q_proj",
|
23 |
"up_proj",
|
24 |
-
"
|
|
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"o_proj",
|
|
|
|
|
|
|
20 |
"up_proj",
|
21 |
+
"q_proj",
|
22 |
+
"down_proj",
|
23 |
+
"k_proj",
|
24 |
+
"v_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:a8a234da437506bf3e963cda7a4b17e1e8283f4aafe441ffd2aafdc7b5ae1178
|
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:a8a234da437506bf3e963cda7a4b17e1e8283f4aafe441ffd2aafdc7b5ae1178
|
3 |
size 6200
|