Training in progress, step 56000, checkpoint

last-checkpoint/adapter_config.json

@@ -32,8 +32,8 @@
   "rank_pattern": {},
   "revision": null,
   "target_modules": [
-    "query",
-    "value"
+    "value",
+    "query"
   ],
   "target_parameters": null,
   "task_type": "SEQ_CLS",

last-checkpoint/adapter_model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2e01ff6aadb44db27b60f5a2939c1f91ceef8ce4c8eda33e8448193e02f7dedf
+oid sha256:722a67a3849c15e216b0363ac3e14756a528f10d48549eada44c7a73a2f1d436
 size 3555504

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b312a19a4c3a50bbc6d51dc9137976fee7cefb77fe462694cf14c53d8b7b3ed9
+oid sha256:9fe2d82a60d86eb55584c63cb21eb22bb6b83639265e9eef0fddd116db74868c
 size 7141515

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01dad4027d20eca2d7fa4b583f03a1d3875b3ab481ed98527232c092bb93df17
+oid sha256:8d4c8f50583c3aaf473dbb3c038d9d85411cdae997b9d9d7d896c343f0b11ce3
 size 14645

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a000201d58220548b692d7c263c2ef536a136348b8e258b7e7e4280e42ea9770
+oid sha256:703b98d29b3227b33c03f1f3acceddb6d9d0304c7caa04dc7709db0049f62b2f
 size 1383

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c18215b26f935a6486c705cff1ccfa7de15b6db51bcfbab399fb0323c2730116
+oid sha256:44ba460a6fb5aaf6e3988a2082759c98869c4746962f11e515d182f4694213b2
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": 52000,
   "best_metric": 0.9908199660129274,
   "best_model_checkpoint": "CodeGenDetect-CodeBert_Lora/checkpoint-52000",
-  "epoch": 1.6640000000000001,
+  "epoch": 1.792,
   "eval_steps": 4000,
-  "global_step": 52000,
+  "global_step": 56000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -3804,6 +3804,298 @@
       "eval_samples_per_second": 129.199,
       "eval_steps_per_second": 8.075,
       "step": 52000
+    },
+    {
+      "epoch": 1.6672,
+      "grad_norm": 4.400208473205566,
+      "learning_rate": 1.3374125200642056e-05,
+      "loss": 0.0351,
+      "step": 52100
+    },
+    {
+      "epoch": 1.6703999999999999,
+      "grad_norm": 5.015504837036133,
+      "learning_rate": 1.3361284109149279e-05,
+      "loss": 0.0528,
+      "step": 52200
+    },
+    {
+      "epoch": 1.6736,
+      "grad_norm": 0.026230236515402794,
+      "learning_rate": 1.3348443017656504e-05,
+      "loss": 0.0435,
+      "step": 52300
+    },
+    {
+      "epoch": 1.6768,
+      "grad_norm": 8.737045288085938,
+      "learning_rate": 1.3335601926163727e-05,
+      "loss": 0.0466,
+      "step": 52400
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.2274281084537506,
+      "learning_rate": 1.332276083467095e-05,
+      "loss": 0.0561,
+      "step": 52500
+    },
+    {
+      "epoch": 1.6832,
+      "grad_norm": 0.006623820401728153,
+      "learning_rate": 1.330991974317817e-05,
+      "loss": 0.0284,
+      "step": 52600
+    },
+    {
+      "epoch": 1.6864,
+      "grad_norm": 0.0021350777242332697,
+      "learning_rate": 1.3297078651685393e-05,
+      "loss": 0.0511,
+      "step": 52700
+    },
+    {
+      "epoch": 1.6896,
+      "grad_norm": 0.018413754180073738,
+      "learning_rate": 1.3284237560192616e-05,
+      "loss": 0.0543,
+      "step": 52800
+    },
+    {
+      "epoch": 1.6928,
+      "grad_norm": 0.1010914072394371,
+      "learning_rate": 1.3271396468699839e-05,
+      "loss": 0.0453,
+      "step": 52900
+    },
+    {
+      "epoch": 1.696,
+      "grad_norm": 0.004039776977151632,
+      "learning_rate": 1.3258555377207064e-05,
+      "loss": 0.0338,
+      "step": 53000
+    },
+    {
+      "epoch": 1.6992,
+      "grad_norm": 14.739033699035645,
+      "learning_rate": 1.3245714285714287e-05,
+      "loss": 0.0382,
+      "step": 53100
+    },
+    {
+      "epoch": 1.7024,
+      "grad_norm": 0.016198845580220222,
+      "learning_rate": 1.323287319422151e-05,
+      "loss": 0.016,
+      "step": 53200
+    },
+    {
+      "epoch": 1.7056,
+      "grad_norm": 2.079624891281128,
+      "learning_rate": 1.3220032102728733e-05,
+      "loss": 0.0627,
+      "step": 53300
+    },
+    {
+      "epoch": 1.7088,
+      "grad_norm": 0.11790735274553299,
+      "learning_rate": 1.3207191011235956e-05,
+      "loss": 0.0592,
+      "step": 53400
+    },
+    {
+      "epoch": 1.712,
+      "grad_norm": 1.2402265071868896,
+      "learning_rate": 1.319434991974318e-05,
+      "loss": 0.0355,
+      "step": 53500
+    },
+    {
+      "epoch": 1.7151999999999998,
+      "grad_norm": 0.004012857098132372,
+      "learning_rate": 1.3181508828250403e-05,
+      "loss": 0.0233,
+      "step": 53600
+    },
+    {
+      "epoch": 1.7184,
+      "grad_norm": 9.97103500366211,
+      "learning_rate": 1.3168667736757626e-05,
+      "loss": 0.0416,
+      "step": 53700
+    },
+    {
+      "epoch": 1.7216,
+      "grad_norm": 0.00929461419582367,
+      "learning_rate": 1.3155826645264849e-05,
+      "loss": 0.0245,
+      "step": 53800
+    },
+    {
+      "epoch": 1.7248,
+      "grad_norm": 0.014831352047622204,
+      "learning_rate": 1.3142985553772072e-05,
+      "loss": 0.0568,
+      "step": 53900
+    },
+    {
+      "epoch": 1.728,
+      "grad_norm": 0.017993494868278503,
+      "learning_rate": 1.3130144462279295e-05,
+      "loss": 0.0316,
+      "step": 54000
+    },
+    {
+      "epoch": 1.7311999999999999,
+      "grad_norm": 7.752192974090576,
+      "learning_rate": 1.3117303370786518e-05,
+      "loss": 0.0435,
+      "step": 54100
+    },
+    {
+      "epoch": 1.7344,
+      "grad_norm": 0.022409453988075256,
+      "learning_rate": 1.3104462279293741e-05,
+      "loss": 0.0272,
+      "step": 54200
+    },
+    {
+      "epoch": 1.7376,
+      "grad_norm": 0.022196965292096138,
+      "learning_rate": 1.3091621187800965e-05,
+      "loss": 0.0389,
+      "step": 54300
+    },
+    {
+      "epoch": 1.7408000000000001,
+      "grad_norm": 0.010344170965254307,
+      "learning_rate": 1.3078780096308188e-05,
+      "loss": 0.0292,
+      "step": 54400
+    },
+    {
+      "epoch": 1.744,
+      "grad_norm": 0.026820389553904533,
+      "learning_rate": 1.306593900481541e-05,
+      "loss": 0.0318,
+      "step": 54500
+    },
+    {
+      "epoch": 1.7471999999999999,
+      "grad_norm": 3.427290916442871,
+      "learning_rate": 1.3053097913322634e-05,
+      "loss": 0.04,
+      "step": 54600
+    },
+    {
+      "epoch": 1.7504,
+      "grad_norm": 0.0476866252720356,
+      "learning_rate": 1.3040256821829857e-05,
+      "loss": 0.0356,
+      "step": 54700
+    },
+    {
+      "epoch": 1.7536,
+      "grad_norm": 0.16033174097537994,
+      "learning_rate": 1.302741573033708e-05,
+      "loss": 0.0465,
+      "step": 54800
+    },
+    {
+      "epoch": 1.7568000000000001,
+      "grad_norm": 0.00891600176692009,
+      "learning_rate": 1.3014574638844302e-05,
+      "loss": 0.0354,
+      "step": 54900
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 0.09468699991703033,
+      "learning_rate": 1.3001733547351525e-05,
+      "loss": 0.049,
+      "step": 55000
+    },
+    {
+      "epoch": 1.7631999999999999,
+      "grad_norm": 0.11951547861099243,
+      "learning_rate": 1.2988892455858748e-05,
+      "loss": 0.0488,
+      "step": 55100
+    },
+    {
+      "epoch": 1.7664,
+      "grad_norm": 0.008669690228998661,
+      "learning_rate": 1.2976051364365971e-05,
+      "loss": 0.0418,
+      "step": 55200
+    },
+    {
+      "epoch": 1.7696,
+      "grad_norm": 5.866086006164551,
+      "learning_rate": 1.2963210272873194e-05,
+      "loss": 0.0452,
+      "step": 55300
+    },
+    {
+      "epoch": 1.7728000000000002,
+      "grad_norm": 0.007491165306419134,
+      "learning_rate": 1.2950369181380417e-05,
+      "loss": 0.0331,
+      "step": 55400
+    },
+    {
+      "epoch": 1.776,
+      "grad_norm": 0.10585305094718933,
+      "learning_rate": 1.293752808988764e-05,
+      "loss": 0.0406,
+      "step": 55500
+    },
+    {
+      "epoch": 1.7792,
+      "grad_norm": 0.3077317178249359,
+      "learning_rate": 1.2924686998394864e-05,
+      "loss": 0.0455,
+      "step": 55600
+    },
+    {
+      "epoch": 1.7824,
+      "grad_norm": 0.008049139752984047,
+      "learning_rate": 1.2911845906902087e-05,
+      "loss": 0.0271,
+      "step": 55700
+    },
+    {
+      "epoch": 1.7856,
+      "grad_norm": 0.005238874349743128,
+      "learning_rate": 1.289900481540931e-05,
+      "loss": 0.0312,
+      "step": 55800
+    },
+    {
+      "epoch": 1.7888,
+      "grad_norm": 0.011361650191247463,
+      "learning_rate": 1.2886163723916533e-05,
+      "loss": 0.0387,
+      "step": 55900
+    },
+    {
+      "epoch": 1.792,
+      "grad_norm": 0.0051416209898889065,
+      "learning_rate": 1.2873322632423756e-05,
+      "loss": 0.0374,
+      "step": 56000
+    },
+    {
+      "epoch": 1.792,
+      "eval_accuracy": 0.99052,
+      "eval_f1": 0.9905207896506175,
+      "eval_loss": 0.03697649762034416,
+      "eval_precision": 0.9905285934060213,
+      "eval_recall": 0.99052,
+      "eval_runtime": 764.6577,
+      "eval_samples_per_second": 130.777,
+      "eval_steps_per_second": 8.174,
+      "step": 56000
     }
   ],
   "logging_steps": 100,
@@ -3818,7 +4110,7 @@
         "early_stopping_threshold": 0.0
       },
       "attributes": {
-        "early_stopping_patience_counter": 0
+        "early_stopping_patience_counter": 1
       }
     },
     "TrainerControl": {
@@ -3832,7 +4124,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.208251621920823e+17,
+  "total_flos": 2.3781344809356787e+17,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": null