Training in progress, step 40

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/adv-robustness/harmbench_adv_training/runs/4u95pd13)
+[<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/xz271nqn)
 # 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.
@@ -38,7 +38,7 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 5e-06
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 4

adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "down_proj",
     "k_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
     "up_proj",
     "o_proj"
   ],

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
+oid sha256:7656c589e7f2b152cd3fe0236bb7f25e1797807d2e05d824192caace0033be11
 size 258001832

runs/May28_17-47-07_e884ad0a7538/events.out.tfevents.1716918611.e884ad0a7538.6113.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ff4c80c2c4ba92411d399b6d374d508e87f34da504523a4a9fc8ac7ad9d26a11
-size 5062
+oid sha256:45cae64d5462012b131aaa6b75c5e220ba8820fa058493b4ac5b9fecb7c4b231
+size 6448

step_0/adapter_config.json

@@ -16,10 +16,10 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
-    "down_proj",
     "k_proj",
+    "down_proj",
+    "q_proj",
+    "v_proj",
     "up_proj",
     "o_proj"
   ],

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47666e9136d26e878b48136844f36f03de1f4a9609a4f305966ebe813a23d3c6
+oid sha256:1d94e2cb4cc9df520c5534db58255777cb00244c8f4c67c94b8014d40f0b0d77
 size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:47666e9136d26e878b48136844f36f03de1f4a9609a4f305966ebe813a23d3c6
+oid sha256:1d94e2cb4cc9df520c5534db58255777cb00244c8f4c67c94b8014d40f0b0d77
 size 6200