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/z6sn35ln)
+[<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/88n49gdo)
 # 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.
@@ -44,7 +44,8 @@ The following hyperparameters were used during training:
 - seed: 4
 - distributed_type: multi-GPU
 - num_devices: 8
-- total_train_batch_size: 32
+- gradient_accumulation_steps: 4
+- 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

adapter_config.json

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

runs/Jun04_19-18-53_702dae2383a0/events.out.tfevents.1717528757.702dae2383a0.104422.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df48653493961f16a0274dbe3cc7f05f7ea05db28a2fc4be32f911752b76d377
-size 5069
+oid sha256:b9c60a6dbf9f7337be3d8aa41cff0c3401bf1da3df6501eda7da3c67144529d3
+size 5377

runs/Jun04_19-21-40_702dae2383a0/events.out.tfevents.1717528926.702dae2383a0.107885.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bd305735513f924cc692915301f08012fb09e45abb66ddae51081e3fc6302029
+size 5069

step_0/README.md

@@ -252,4 +252,11 @@ 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

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

step_0/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd033f9a97e1e3394ab34dacb92fb044065fda9a4eee550ea154b9e07029197
+oid sha256:61c9fcca0e4f6df815b175558893a160f26b5556b67f35faabb54c2d2c2adf11
 size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4cd033f9a97e1e3394ab34dacb92fb044065fda9a4eee550ea154b9e07029197
+oid sha256:61c9fcca0e4f6df815b175558893a160f26b5556b67f35faabb54c2d2c2adf11
 size 6200