Model save
Browse files- README.md +5 -5
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- runs/May20_20-25-22_8562df05190c/events.out.tfevents.1716236777.8562df05190c.12671.0 +3 -0
- step_0/README.md +7 -0
- step_0/adapter_config.json +3 -3
- 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.
|
@@ -43,13 +43,13 @@ The following hyperparameters were used during training:
|
|
43 |
- eval_batch_size: 8
|
44 |
- seed: 4
|
45 |
- distributed_type: multi-GPU
|
46 |
-
- num_devices:
|
47 |
- gradient_accumulation_steps: 4
|
48 |
-
- total_train_batch_size:
|
49 |
-
- total_eval_batch_size:
|
50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
51 |
- lr_scheduler_type: cosine
|
52 |
-
- training_steps:
|
53 |
|
54 |
### Framework versions
|
55 |
|
|
|
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/nc5ad321)
|
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.
|
|
|
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: 10
|
53 |
|
54 |
### Framework versions
|
55 |
|
adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"down_proj",
|
20 |
"k_proj",
|
|
|
21 |
"q_proj",
|
22 |
-
"o_proj",
|
23 |
"v_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
20 |
+
"up_proj",
|
21 |
"q_proj",
|
|
|
22 |
"v_proj",
|
23 |
+
"o_proj",
|
24 |
+
"down_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/May20_20-25-22_8562df05190c/events.out.tfevents.1716236777.8562df05190c.12671.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:89fbde994850e2fed96f0aa71bca4048356344366b030e935742484f6acdfe51
|
3 |
+
size 5007
|
step_0/README.md
CHANGED
@@ -217,4 +217,11 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
|
|
217 |
### Framework versions
|
218 |
|
219 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
220 |
- PEFT 0.6.1
|
|
|
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
|
step_0/adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"down_proj",
|
20 |
"k_proj",
|
|
|
21 |
"q_proj",
|
22 |
-
"o_proj",
|
23 |
"v_proj",
|
24 |
-
"
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
20 |
+
"up_proj",
|
21 |
"q_proj",
|
|
|
22 |
"v_proj",
|
23 |
+
"o_proj",
|
24 |
+
"down_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 6136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feb2b96115bc6518af88f2e7630f4ae733d3040fd6a33c68e139d8d42c1990f1
|
3 |
size 6136
|
training_args.bin
CHANGED
@@ -1,3 +1,3 @@
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
-
oid sha256:
|
3 |
size 6136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:feb2b96115bc6518af88f2e7630f4ae733d3040fd6a33c68e139d8d42c1990f1
|
3 |
size 6136
|