Hugging Face's logo

aengusl
/
llama2-7b-sft-lora

PEFT
TensorBoard
Safetensors
trl
sft
Generated from Trainer
Model card Files Metrics Community
aengusl commited on
Commit
156dd0a
•
1 Parent(s): 38293a2

Model save

Browse files
Files changed (24) hide show
  1. README.md +2 -2
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Jul04_19-08-38_7ed26122f827/events.out.tfevents.1720120564.7ed26122f827.3594.0 +2 -2
  5. runs/Jul05_17-01-22_71d4411a1d0b/events.out.tfevents.1720199216.71d4411a1d0b.8983.0 +3 -0
  6. step_0/README.md +7 -0
  7. step_0/adapter_config.json +3 -3
  8. step_0/training_args.bin +1 -1
  9. step_100/adapter_config.json +3 -3
  10. step_100/adapter_model.safetensors +1 -1
  11. step_100/training_args.bin +1 -1
  12. step_200/adapter_config.json +3 -3
  13. step_200/adapter_model.safetensors +1 -1
  14. step_200/training_args.bin +1 -1
  15. step_300/adapter_config.json +3 -3
  16. step_300/adapter_model.safetensors +1 -1
  17. step_300/training_args.bin +1 -1
  18. step_400/adapter_config.json +3 -3
  19. step_400/adapter_model.safetensors +1 -1
  20. step_400/training_args.bin +1 -1
  21. step_500/adapter_config.json +3 -3
  22. step_500/adapter_model.safetensors +1 -1
  23. step_500/training_args.bin +1 -1
  24. 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/3smiq9zq)
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.
@@ -38,7 +38,7 @@ More information needed
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
 
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/ky7fegkz)
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: 2e-05
42
  - train_batch_size: 4
43
  - eval_batch_size: 8
44
  - seed: 4
adapter_config.json CHANGED
@@ -17,11 +17,11 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
- "up_proj",
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
+ "o_proj",
 
21
  "down_proj",
22
  "q_proj",
23
+ "up_proj",
24
+ "k_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 sha256:26910831b9c5fbda6f1f5a04d7071f09faa9750008851463d6529da15d218d31
3
  size 258001832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
3
  size 258001832
runs/Jul04_19-08-38_7ed26122f827/events.out.tfevents.1720120564.7ed26122f827.3594.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1764bcd532e477f9bde13d9a53cd1029727d5bdf417bdafb832586dcce969ab5
3
- size 98899
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:874988b881bdea013fca13c700c6eec386ccc149e42c78c6c859e98563cb69b6
3
+ size 101568
runs/Jul05_17-01-22_71d4411a1d0b/events.out.tfevents.1720199216.71d4411a1d0b.8983.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6ace92e9c16d2e8c587e69ee82faa1df8f15703eab56f148041c52fc3e3509e4
3
+ size 5080
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
@@ -17,11 +17,11 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
- "up_proj",
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
+ "o_proj",
 
21
  "down_proj",
22
  "q_proj",
23
+ "up_proj",
24
+ "k_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 sha256:6bee1fd333a1dcf306208e6c69ddb7a7bec00cd9f6eb3d821cfcdc8035246023
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e2ce23c6236ff9ce11696468ff9ffc60a570e16043141af7a35d5060d4762a
3
  size 6200
step_100/adapter_config.json CHANGED
@@ -17,11 +17,11 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
- "up_proj",
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
+ "o_proj",
 
21
  "down_proj",
22
  "q_proj",
23
+ "up_proj",
24
+ "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
step_100/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3e539576004ec9a7074c0a00d84192c3e9050156c44b742cde1785eee30c1721
3
  size 258001832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1e44ee6ad2039527f9fdb78e17b816d458ceb028e3bb3f7506f6be81a78911e6
3
  size 258001832
step_100/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bee1fd333a1dcf306208e6c69ddb7a7bec00cd9f6eb3d821cfcdc8035246023
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
3
  size 6200
step_200/adapter_config.json CHANGED
@@ -17,11 +17,11 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
- "up_proj",
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
+ "o_proj",
 
21
  "down_proj",
22
  "q_proj",
23
+ "up_proj",
24
+ "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
step_200/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6a1f143924fdc16986ab446db4070d0f4a95647e856f9a13f3113e2bc6bc3453
3
  size 258001832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c867490b06a04c7ce536b3bcba97cca0ad888e7a2195e8df72cbbafdec9fc054
3
  size 258001832
step_200/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bee1fd333a1dcf306208e6c69ddb7a7bec00cd9f6eb3d821cfcdc8035246023
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
3
  size 6200
step_300/adapter_config.json CHANGED
@@ -17,11 +17,11 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
- "up_proj",
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
+ "o_proj",
 
21
  "down_proj",
22
  "q_proj",
23
+ "up_proj",
24
+ "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
step_300/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:2a9acbbdce6548098a721f497670ed50b673b06bf8f38535f8f4a3caa51308fa
3
  size 258001832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e9570745b6d129e671da37790a61f1159d0b60563f066cfafc3d4eebfaa5733
3
  size 258001832
step_300/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bee1fd333a1dcf306208e6c69ddb7a7bec00cd9f6eb3d821cfcdc8035246023
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
3
  size 6200
step_400/adapter_config.json CHANGED
@@ -17,11 +17,11 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
- "up_proj",
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
+ "o_proj",
 
21
  "down_proj",
22
  "q_proj",
23
+ "up_proj",
24
+ "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
step_400/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d502ff02874d455a2d0020cc86276eccc3ff70a444f7f7fb4053a34bb1ccf3b3
3
  size 258001832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a42ecfe2939daf1587fe46cfcaa7fd4030784478a5cacf948a8f9faaf46c2b8
3
  size 258001832
step_400/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bee1fd333a1dcf306208e6c69ddb7a7bec00cd9f6eb3d821cfcdc8035246023
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
3
  size 6200
step_500/adapter_config.json CHANGED
@@ -17,11 +17,11 @@
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
- "k_proj",
21
- "up_proj",
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
17
  "revision": null,
18
  "target_modules": [
19
  "v_proj",
20
+ "o_proj",
 
21
  "down_proj",
22
  "q_proj",
23
+ "up_proj",
24
+ "k_proj"
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
step_500/adapter_model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0b9b6fc35471994affe8a6c9421d9a330b70c440e7045a7a60c863860071e9eb
3
  size 258001832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b77fafe7ce315e3331380e27140344fe6c730fc0af61fc7562ee66732d744202
3
  size 258001832
step_500/training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bee1fd333a1dcf306208e6c69ddb7a7bec00cd9f6eb3d821cfcdc8035246023
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c9155354ba280d10882e0ec69ae11bddf70b1f227d351638a68e2636bd99ca9
3
  size 6200
training_args.bin CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6bee1fd333a1dcf306208e6c69ddb7a7bec00cd9f6eb3d821cfcdc8035246023
3
  size 6200
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:67e2ce23c6236ff9ce11696468ff9ffc60a570e16043141af7a35d5060d4762a
3
  size 6200