Model save
Browse files- README.md +2 -2
- adapter_config.json +5 -5
- runs/May20_20-30-10_8562df05190c/events.out.tfevents.1716237067.8562df05190c.17973.0 +2 -2
- runs/May20_20-40-51_8562df05190c/events.out.tfevents.1716237709.8562df05190c.27136.0 +3 -0
- step_0/README.md +35 -0
- 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/
|
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.
|
@@ -49,7 +49,7 @@ The following hyperparameters were used during training:
|
|
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:
|
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/z5tezs76)
|
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.
|
|
|
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 |
-
"
|
20 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
-
"q_proj",
|
23 |
"down_proj",
|
24 |
-
"
|
|
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
|
|
|
|
|
|
20 |
"down_proj",
|
21 |
+
"q_proj",
|
22 |
+
"up_proj",
|
23 |
+
"o_proj",
|
24 |
+
"v_proj"
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
runs/May20_20-30-10_8562df05190c/events.out.tfevents.1716237067.8562df05190c.17973.0
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 sha256:2ce538816e7eee47cc2e8da2062a1ed6829a68b1ad5cb3a5d27abee7bfa2acd1
|
3 |
+
size 5161
|
runs/May20_20-40-51_8562df05190c/events.out.tfevents.1716237709.8562df05190c.27136.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:7b1b92b738ea10ab92ddcb73b54b9c5e761aaa9b521d4e32658ff5d8befcb185
|
3 |
+
size 5007
|
step_0/README.md
CHANGED
@@ -203,4 +203,39 @@ 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
|
214 |
+
## Training procedure
|
215 |
+
|
216 |
+
|
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
|
228 |
+
## Training procedure
|
229 |
+
|
230 |
+
|
231 |
+
### Framework versions
|
232 |
+
|
233 |
+
|
234 |
+
- PEFT 0.6.1
|
235 |
+
## Training procedure
|
236 |
+
|
237 |
+
|
238 |
+
### Framework versions
|
239 |
+
|
240 |
+
|
241 |
- 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 |
-
"o_proj",
|
21 |
-
"up_proj",
|
22 |
-
"q_proj",
|
23 |
"down_proj",
|
24 |
-
"
|
|
|
|
|
|
|
25 |
],
|
26 |
"task_type": "CAUSAL_LM"
|
27 |
}
|
|
|
16 |
"rank_pattern": {},
|
17 |
"revision": null,
|
18 |
"target_modules": [
|
19 |
+
"k_proj",
|
|
|
|
|
|
|
20 |
"down_proj",
|
21 |
+
"q_proj",
|
22 |
+
"up_proj",
|
23 |
+
"o_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 6136
|
|
|
1 |
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:be6336b390ed988b34ae86768d73ac6749705676f78ef7a625c1173e59c1b4f8
|
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:be6336b390ed988b34ae86768d73ac6749705676f78ef7a625c1173e59c1b4f8
|
3 |
size 6136
|