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
fd96a9a
•
1 Parent(s): bacafec

Training in progress, step 520

Browse files
Files changed (22) hide show
  1. README.md +2 -2
  2. adapter_config.json +3 -3
  3. adapter_model.safetensors +1 -1
  4. runs/Jul04_19-10-28_1f2e01cb3aa8/events.out.tfevents.1720120533.1f2e01cb3aa8.4905.0 +2 -2
  5. step_0/adapter_config.json +3 -3
  6. step_0/training_args.bin +1 -1
  7. step_100/adapter_config.json +3 -3
  8. step_100/adapter_model.safetensors +1 -1
  9. step_100/training_args.bin +1 -1
  10. step_200/adapter_config.json +3 -3
  11. step_200/adapter_model.safetensors +1 -1
  12. step_200/training_args.bin +1 -1
  13. step_300/adapter_config.json +3 -3
  14. step_300/adapter_model.safetensors +1 -1
  15. step_300/training_args.bin +1 -1
  16. step_400/adapter_config.json +3 -3
  17. step_400/adapter_model.safetensors +1 -1
  18. step_400/training_args.bin +1 -1
  19. step_500/adapter_config.json +3 -3
  20. step_500/adapter_model.safetensors +1 -1
  21. step_500/training_args.bin +1 -1
  22. 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/0l1lcldi)
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
@@ -16,12 +16,12 @@
16
  "rank_pattern": {},
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
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "up_proj",
20
+ "o_proj",
21
  "down_proj",
22
  "q_proj",
23
+ "v_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 sha256:0b9b6fc35471994affe8a6c9421d9a330b70c440e7045a7a60c863860071e9eb
3
  size 258001832
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:87022e3ef1f4795f3ccdced12ed8d18bf4d817492ddf2fecfb48dd7e202d8aac
3
  size 258001832
runs/Jul04_19-10-28_1f2e01cb3aa8/events.out.tfevents.1720120533.1f2e01cb3aa8.4905.0 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:19834c87ed061bccdf263e2f6d9e56ffd1a5d203d31b1a64ccf0568e5905c4b4
3
- size 83199
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6c5898e8dbd2278e4606697299d202c13c15f0ccb257d7718e51494200ae9806
3
+ size 86339
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
  "up_proj",
 
22
  "down_proj",
23
  "q_proj",
24
- "o_proj"
 
25
  ],
26
  "task_type": "CAUSAL_LM"
27
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "up_proj",
20
+ "o_proj",
21
  "down_proj",
22
  "q_proj",
23
+ "v_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 sha256:4a9ec27228248e4488b37b51f03e58f568c4a55b0a0719fbd6bc35dda86fa64f
3
  size 6200
step_100/adapter_config.json CHANGED
@@ -16,12 +16,12 @@
16
  "rank_pattern": {},
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
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "up_proj",
20
+ "o_proj",
21
  "down_proj",
22
  "q_proj",
23
+ "v_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:cd7d2dd8cf9fee36d638f493a91e7b91df840b7d00d7aab03aca8e98170c1ce7
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 sha256:4a9ec27228248e4488b37b51f03e58f568c4a55b0a0719fbd6bc35dda86fa64f
3
  size 6200
step_200/adapter_config.json CHANGED
@@ -16,12 +16,12 @@
16
  "rank_pattern": {},
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
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "up_proj",
20
+ "o_proj",
21
  "down_proj",
22
  "q_proj",
23
+ "v_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:a3ac689382153bb04d9fe56585ac86b71e33ab1f79d243969fecc8cf8b6ec60a
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 sha256:4a9ec27228248e4488b37b51f03e58f568c4a55b0a0719fbd6bc35dda86fa64f
3
  size 6200
step_300/adapter_config.json CHANGED
@@ -16,12 +16,12 @@
16
  "rank_pattern": {},
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
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "up_proj",
20
+ "o_proj",
21
  "down_proj",
22
  "q_proj",
23
+ "v_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:e8a8b8ec8f24a54e04300b29f2498464c76e105447c93864e1c605c572f2097a
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 sha256:4a9ec27228248e4488b37b51f03e58f568c4a55b0a0719fbd6bc35dda86fa64f
3
  size 6200
step_400/adapter_config.json CHANGED
@@ -16,12 +16,12 @@
16
  "rank_pattern": {},
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
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "up_proj",
20
+ "o_proj",
21
  "down_proj",
22
  "q_proj",
23
+ "v_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:e682ae9397116a152c8cb63eb1841a645a14f44384e06732fb3301cdc04313b2
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 sha256:4a9ec27228248e4488b37b51f03e58f568c4a55b0a0719fbd6bc35dda86fa64f
3
  size 6200
step_500/adapter_config.json CHANGED
@@ -16,12 +16,12 @@
16
  "rank_pattern": {},
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
  }
 
16
  "rank_pattern": {},
17
  "revision": null,
18
  "target_modules": [
 
 
19
  "up_proj",
20
+ "o_proj",
21
  "down_proj",
22
  "q_proj",
23
+ "v_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 sha256:50b15e3b7c5e6a08d881bf4718dc3e8f79c859e97d650f9ec5775f021c91159e
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 sha256:4a9ec27228248e4488b37b51f03e58f568c4a55b0a0719fbd6bc35dda86fa64f
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 sha256:4a9ec27228248e4488b37b51f03e58f568c4a55b0a0719fbd6bc35dda86fa64f
3
  size 6200