Training in progress, step 400

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/3s3lr6jr)
+[<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/nf5m84kk)
 # 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.
@@ -38,15 +38,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 2e-05
+- learning_rate: 1e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 4
 - distributed_type: multi-GPU
-- num_devices: 4
+- num_devices: 8
 - gradient_accumulation_steps: 4
-- total_train_batch_size: 64
-- total_eval_batch_size: 32
+- 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": [
-    "q_proj",
-    "down_proj",
-    "o_proj",
     "k_proj",
     "up_proj",
-    "v_proj"
+    "down_proj",
+    "o_proj",
+    "v_proj",
+    "q_proj"
   ],
   "task_type": "CAUSAL_LM"
 }

runs/May21_02-16-33_9962c5574dd5/events.out.tfevents.1716257866.9962c5574dd5.57073.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1cb051d5fe1fd224319640a6aaf1a60652d0b4c03811087808ef381a9bd7ccd0
-size 16475
+oid sha256:2cabef5b4789981e832892c83e4493ee5ed5f47b6ded4586b059c2dcc1bdcec4
+size 17731

step_0/adapter_config.json

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

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab92a3f3ddfae79ccc268f8c775b89b44bbf68264640ce3b02e1761ffa03dd0
+oid sha256:8c214206ca5b3546e7b0ce45c96821c0fdf58c6544de60253bdcccdf0993e570
 size 6200

step_400/adapter_config.json

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

step_400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75a6eb7d6dbc326f8d6fd5957491f69a6615f9c061ef31693274894a8a861cf
+oid sha256:c47bbe393dfa0a43898460da181996d9d93d703cabd129c3ff240f1b99cb4561
 size 258001832

step_400/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab92a3f3ddfae79ccc268f8c775b89b44bbf68264640ce3b02e1761ffa03dd0
+oid sha256:8c214206ca5b3546e7b0ce45c96821c0fdf58c6544de60253bdcccdf0993e570
 size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ab92a3f3ddfae79ccc268f8c775b89b44bbf68264640ce3b02e1761ffa03dd0
+oid sha256:8c214206ca5b3546e7b0ce45c96821c0fdf58c6544de60253bdcccdf0993e570
 size 6200