Model save

README.md

@@ -16,7 +16,7 @@ model-index:
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
 should probably proofread and complete it, then remove this comment. -->
 
-[<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/jf79b03r)
+[<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/mlbp3bjv)
 # llama2-7b-sft-lora
 
 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.
@@ -38,14 +38,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 4
 - distributed_type: multi-GPU
-- num_devices: 2
-- total_train_batch_size: 8
-- total_eval_batch_size: 16
+- num_devices: 8
+- gradient_accumulation_steps: 4
+- total_train_batch_size: 128
+- total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - training_steps: 2000

adapter_config.json

@@ -16,12 +16,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "q_proj",
-    "up_proj",
     "o_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/Jun05_13-17-51_555bc3f50b50/events.out.tfevents.1717593527.555bc3f50b50.31368.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e0768a39be64ead6330007700515f0036012dc14af0a52a7f690b3b0beed53d5
+size 5036

step_0/README.md

@@ -203,116 +203,4 @@ Carbon emissions can be estimated using the [Machine Learning Impact calculator]
 ### Framework versions
 
 
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
-- PEFT 0.6.1
-## Training procedure
-
-
-### Framework versions
-
-
 - PEFT 0.6.1

step_0/adapter_config.json

@@ -16,12 +16,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "k_proj",
-    "down_proj",
     "q_proj",
-    "up_proj",
     "o_proj",
-    "v_proj"
+    "down_proj",
+    "v_proj",
+    "up_proj",
+    "k_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05e306471dff1d153a17225264fa02f817e0465684ed15f33e13d4e71f4314d
+oid sha256:9cf2c901a9e08d11e442b7c087fc919994d2e42b443c031ae015c8500fd26f50
 size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f05e306471dff1d153a17225264fa02f817e0465684ed15f33e13d4e71f4314d
+oid sha256:9cf2c901a9e08d11e442b7c087fc919994d2e42b443c031ae015c8500fd26f50
 size 6200