Training in progress, step 840

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/53iz8v52)
+[<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/mgxwn0ra)
 # 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.
@@ -38,14 +38,15 @@ More information needed
 ### Training hyperparameters
 
 The following hyperparameters were used during training:
-- learning_rate: 1e-05
+- learning_rate: 2e-05
 - train_batch_size: 4
 - eval_batch_size: 8
 - seed: 4
 - distributed_type: multi-GPU
-- num_devices: 2
-- total_train_batch_size: 8
-- total_eval_batch_size: 16
+- num_devices: 8
+- 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
 - training_steps: 2000

adapter_config.json

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

adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d1d8ee5e122aa5ba15194f89a4f794f9c3fe72e5c3ede8c7f35cf55983cee6c
+oid sha256:3334efe273da241697da74eae5a8b2fc490ecb591b5857c19500e950a68747b8
 size 258001832

runs/Jun04_19-40-55_702dae2383a0/events.out.tfevents.1717530079.702dae2383a0.121172.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:318506b27490194e742be8d5d2501dae2370dc4b46124a4c39d35f37cc5f1be7
-size 130288
+oid sha256:360cb517b9522430579e554ed1b2dfdc5d4e2256d3ee0d0c943d73cccda4b811
+size 136568

step_0/README.md

@@ -266,39 +266,4 @@ 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
-## Training procedure
-
-
-### 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": [
-    "down_proj",
-    "o_proj",
     "k_proj",
+    "down_proj",
     "v_proj",
     "q_proj",
-    "up_proj"
+    "up_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 sha256:1aa24739d2807aa87caa1141e7fc573c18220fbb3d9a9b33db2fc41aced81666
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
 size 6200

step_1200/adapter_config.json

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

step_1200/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75a6eb7d6dbc326f8d6fd5957491f69a6615f9c061ef31693274894a8a861cf
+oid sha256:b7e145e1d6e5063d0b58e6bbabe0ee76af3c4399e27f7cfc44b9ed0d433c4086
 size 258001832

step_1200/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173c76cadbe74666dccd764c95a48d397d2d329025362dc4e9264c954837cbdc
-size 6136
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
+size 6200

step_1600/adapter_config.json

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

step_1600/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75a6eb7d6dbc326f8d6fd5957491f69a6615f9c061ef31693274894a8a861cf
+oid sha256:3ec2b077524f24b1f201d3c5ad7d4311fbbf1e9d052b8c0a74a69ac1dfbc4c00
 size 258001832

step_1600/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173c76cadbe74666dccd764c95a48d397d2d329025362dc4e9264c954837cbdc
-size 6136
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
+size 6200

step_2000/adapter_config.json

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

step_2000/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75a6eb7d6dbc326f8d6fd5957491f69a6615f9c061ef31693274894a8a861cf
+oid sha256:9d18aeba252a371ce430d16904f59577958982a2347e09e0b33d7f4bf154e1d5
 size 258001832

step_2000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173c76cadbe74666dccd764c95a48d397d2d329025362dc4e9264c954837cbdc
-size 6136
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
+size 6200

step_2400/adapter_config.json

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

step_2400/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75a6eb7d6dbc326f8d6fd5957491f69a6615f9c061ef31693274894a8a861cf
+oid sha256:de9ed32131a932712db6773b1079cd55857a0a490d9519d3ef4924d04cb363bd
 size 258001832

step_2400/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173c76cadbe74666dccd764c95a48d397d2d329025362dc4e9264c954837cbdc
-size 6136
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
+size 6200

step_2800/adapter_config.json

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

step_2800/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75a6eb7d6dbc326f8d6fd5957491f69a6615f9c061ef31693274894a8a861cf
+oid sha256:ecd7ca95d1bd74f29e382c839b11c5cfd3ec15e7333226a401631f660c5e9982
 size 258001832

step_2800/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173c76cadbe74666dccd764c95a48d397d2d329025362dc4e9264c954837cbdc
-size 6136
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
+size 6200

step_400/adapter_config.json

@@ -16,12 +16,12 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
+    "k_proj",
     "down_proj",
-    "o_proj",
-    "up_proj",
     "v_proj",
-    "k_proj",
-    "q_proj"
+    "q_proj",
+    "up_proj",
+    "o_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 sha256:0751b08f6176be02750794678276f7d4e03dc429debb9a41c2cf1913945eb5b4
 size 258001832

step_400/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173c76cadbe74666dccd764c95a48d397d2d329025362dc4e9264c954837cbdc
-size 6136
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
+size 6200

step_800/adapter_config.json

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

step_800/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a75a6eb7d6dbc326f8d6fd5957491f69a6615f9c061ef31693274894a8a861cf
+oid sha256:fb677bc0747696788c3346deb5e0e3c7abd6664ef59ffb8a20462bbe539ab797
 size 258001832

step_800/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:173c76cadbe74666dccd764c95a48d397d2d329025362dc4e9264c954837cbdc
-size 6136
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
+size 6200

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1aa24739d2807aa87caa1141e7fc573c18220fbb3d9a9b33db2fc41aced81666
+oid sha256:fddcb958cb044b08eb2784936cc2d61c7603663890e064c856baab404ea4a540
 size 6200