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/adv-robustness/harmbench_adv_training/runs/am76bjuk)
+[<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/y2j5fvup)
 # 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.
@@ -43,10 +43,10 @@ The following hyperparameters were used during training:
 - eval_batch_size: 8
 - seed: 4
 - distributed_type: multi-GPU
-- num_devices: 8
+- num_devices: 4
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 128
-- total_eval_batch_size: 64
+- total_train_batch_size: 64
+- total_eval_batch_size: 32
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine
 - training_steps: 2000

adapter_config.json

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

runs/May20_21-17-16_c07e70359ae1/events.out.tfevents.1716240046.c07e70359ae1.8295.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac70efa3f0ae6e500f1ce1996b962a10a30adceecb76567171c8c2fe0299caa0
+size 5048

step_0/adapter_config.json

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

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d9deb4aee23b8ff6df47264f2a8714c20869a48697f9e23859a2269f24f8ca
+oid sha256:5ea283ac8bdb18c994229235aa7fcb02cb61c44fb1415c2034a2892544873a5b
 size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:12d9deb4aee23b8ff6df47264f2a8714c20869a48697f9e23859a2269f24f8ca
+oid sha256:5ea283ac8bdb18c994229235aa7fcb02cb61c44fb1415c2034a2892544873a5b
 size 6200