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/mdkppduo)
+[<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/p2jo7dgc)
 # 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.
@@ -44,8 +44,7 @@ The following hyperparameters were used during training:
 - seed: 4
 - distributed_type: multi-GPU
 - num_devices: 8
-- gradient_accumulation_steps: 4
-- total_train_batch_size: 128
+- total_train_batch_size: 32
 - total_eval_batch_size: 64
 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
 - lr_scheduler_type: cosine

adapter_config.json

@@ -16,11 +16,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
+    "o_proj",
     "k_proj",
+    "q_proj",
     "up_proj",
-    "o_proj",
+    "v_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM"

runs/Jun04_18-07-46_702dae2383a0/events.out.tfevents.1717524490.702dae2383a0.72981.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:14327f37df025a1f4abee2f230f53d9d01b513095c29308b71d804e30f6ead79
+size 5068

step_0/README.md

@@ -210,4 +210,11 @@ 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

step_0/adapter_config.json

@@ -16,11 +16,11 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "v_proj",
-    "q_proj",
+    "o_proj",
     "k_proj",
+    "q_proj",
     "up_proj",
-    "o_proj",
+    "v_proj",
     "down_proj"
   ],
   "task_type": "CAUSAL_LM"

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0f61861fa93391b406864dc73b6c799ae96275c0358ea0cb120c267588a5db
+oid sha256:3f56f3c512beb3d113f9514ed3e240b5562b4c781f28c03f0c6f6767420613aa
 size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e0f61861fa93391b406864dc73b6c799ae96275c0358ea0cb120c267588a5db
+oid sha256:3f56f3c512beb3d113f9514ed3e240b5562b4c781f28c03f0c6f6767420613aa
 size 6200