Model save
Browse files- README.md +3 -2
- adapter_config.json +4 -4
- runs/Jun04_19-18-53_702dae2383a0/events.out.tfevents.1717528757.702dae2383a0.104422.0 +2 -2
- runs/Jun04_19-21-40_702dae2383a0/events.out.tfevents.1717528926.702dae2383a0.107885.0 +3 -0
- step_0/README.md +7 -0
- 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/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.
|
@@ -44,7 +44,8 @@ The following hyperparameters were used during training:
|
|
44 |
- seed: 4
|
45 |
- distributed_type: multi-GPU
|
46 |
- num_devices: 8
|
47 |
-
-
|
|
|
48 |
- total_eval_batch_size: 64
|
49 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
50 |
- lr_scheduler_type: cosine
|
|
|
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/88n49gdo)
|
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.
|
|
|
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
|
adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
-
"q_proj",
|
21 |
"down_proj",
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"v_proj",
|
|
|
21 |
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"o_proj",
|
24 |
+
"up_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
runs/Jun04_19-18-53_702dae2383a0/events.out.tfevents.1717528757.702dae2383a0.104422.0
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:b9c60a6dbf9f7337be3d8aa41cff0c3401bf1da3df6501eda7da3c67144529d3
|
3 |
+
size 5377
|
runs/Jun04_19-21-40_702dae2383a0/events.out.tfevents.1717528926.702dae2383a0.107885.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:bd305735513f924cc692915301f08012fb09e45abb66ddae51081e3fc6302029
|
3 |
+
size 5069
|
step_0/README.md
CHANGED
@@ -252,4 +252,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
252 |
### Framework versions
|
253 |
|
254 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
255 |
- PEFT 0.6.1
|
|
|
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
|
step_0/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"v_proj",
|
20 |
-
"q_proj",
|
21 |
"down_proj",
|
22 |
-
"
|
23 |
-
"
|
24 |
-
"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
20 |
"v_proj",
|
|
|
21 |
"down_proj",
|
22 |
+
"q_proj",
|
23 |
+
"o_proj",
|
24 |
+
"up_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 sha256:61c9fcca0e4f6df815b175558893a160f26b5556b67f35faabb54c2d2c2adf11
|
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 sha256:61c9fcca0e4f6df815b175558893a160f26b5556b67f35faabb54c2d2c2adf11
|
3 |
size 6200
|