Training in progress, step 100
Browse files- README.md +4 -4
- adapter_config.json +3 -3
- adapter_model.safetensors +1 -1
- runs/May20_23-02-38_9962c5574dd5/events.out.tfevents.1716246231.9962c5574dd5.35433.0 +2 -2
- 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/
|
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.
|
@@ -43,10 +43,10 @@ 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: 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/adv-robustness/harmbench_adv_training/runs/hgvq89zv)
|
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: 2000
|
adapter_config.json
CHANGED
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"v_proj",
|
20 |
"k_proj",
|
21 |
"q_proj",
|
22 |
-
"up_proj",
|
23 |
"o_proj",
|
24 |
-
"
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
20 |
"q_proj",
|
|
|
21 |
"o_proj",
|
22 |
+
"v_proj",
|
23 |
+
"down_proj",
|
24 |
+
"up_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 sha256:42f7e5fd16674642b7f4bce7f8711f3751fc2bfa844082ec46f8fc1a8169d7b3
|
3 |
size 258001832
|
runs/May20_23-02-38_9962c5574dd5/events.out.tfevents.1716246231.9962c5574dd5.35433.0
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 sha256:2536fba8c340bb09f954404653633a5d7b5fc5d0b357add481179694eb0438bd
|
3 |
+
size 8285
|
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
@@ -16,12 +16,12 @@
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
-
"v_proj",
|
20 |
"k_proj",
|
21 |
"q_proj",
|
22 |
-
"up_proj",
|
23 |
"o_proj",
|
24 |
-
"
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
|
|
19 |
"k_proj",
|
20 |
"q_proj",
|
|
|
21 |
"o_proj",
|
22 |
+
"v_proj",
|
23 |
+
"down_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 sha256:9b752b40e6f4688c866de9e9675488d079afb968c4be67f29600b030b5b3fffa
|
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 sha256:9b752b40e6f4688c866de9e9675488d079afb968c4be67f29600b030b5b3fffa
|
3 |
size 6200
|