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/9espx0db)
+[<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/oqy996hg)
 # 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.
@@ -39,13 +39,13 @@ More information needed
 
 The following hyperparameters were used during training:
 - learning_rate: 2e-05
-- train_batch_size: 2
-- eval_batch_size: 4
+- train_batch_size: 4
+- eval_batch_size: 8
 - seed: 4
 - distributed_type: multi-GPU
-- num_devices: 2
-- total_train_batch_size: 4
-- total_eval_batch_size: 8
+- num_devices: 8
+- 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
 - training_steps: 2000

adapter_config.json

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

runs/Jun21_15-07-57_b4eead2a04ed/events.out.tfevents.1718982911.b4eead2a04ed.2801.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f2f2c38f4f91376f713c96c5ff84cde0df475d8cf4fc729ae51bd01c94d0573
+size 5092

step_0/README.md

@@ -203,18 +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

step_0/adapter_config.json

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

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d126be621363e634e7d83691971eae33b55c84f8d93583c3b4676b1dbc9e41f
+oid sha256:59b708a3746c5e4c41a8783c9d63e268d55e393b771393f30dce031255c310ac
 size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d126be621363e634e7d83691971eae33b55c84f8d93583c3b4676b1dbc9e41f
+oid sha256:59b708a3746c5e4c41a8783c9d63e268d55e393b771393f30dce031255c310ac
 size 6200