Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f41dc7464f89e4f301f003180d87873095484861a9ac7fb83cf4b55052647bf
+oid sha256:2e9a93c96af72d82d1948b211536371c8b90e993f97655333941c27153619b48
 size 598898116

run-2/checkpoint-240/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:add493ece107411bdcdf2294dbdc0f4f0d7a1165e8057c6e5ef4dea90267963d
+oid sha256:d19f751c835e4a83f407bd290c3cfa629eb5b7d69cc9a6c4aef931fd56b42d58
 size 598898116

run-2/checkpoint-240/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890e9d45f3ad55cedb6a849cd4fdcba49e36803ff16da0356abb847f1076bf32
+oid sha256:43bc5a5d7df840cb2bcd11c9964b930c621fdcbdaca88129d582aa99bc165459
 size 1197886411

run-2/checkpoint-240/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:efbb971914d1f6b2141ee488b084ac87c0ce2e72c0fc9ba081492393d2add9f3
+oid sha256:d17eed1de60c5b0d63a7107d97b5f756179afc2b9ed6fa9240b6c0f51933a5ca
 size 1465

run-2/checkpoint-240/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dd41b8f1f02a59dec0ad0b327aa33b067da9f7bae29bbb31cf106ac5ff4ff
+oid sha256:30763bea4e95fddafc920e08c1ea1c5e03c960715d174ba50f005d578e068b60
 size 5905

run-2/checkpoint-360/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8952930d503dac89d9e0f19712ed66893f71a7af7c5a6cc0e7d68163e67e2242
+oid sha256:5e71774b6250dccc404d7a43eb99909369c29006c636d7d5f020a1936f152985
 size 598898116

run-2/checkpoint-360/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b098c8db4180bad4a9ea8ec40059e465a21b283c496de2c55a9d81b605f46b78
+oid sha256:6aeb750fd063d0897295ed9b3c704e8ca8affaccbfe391748bb41367334f2ec9
 size 1197886411

run-2/checkpoint-360/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b1a14b452e048ebab57fc7a59cdeb90d9da45ecb36b9e88f4865e0bfdef7240
+oid sha256:bc5e6ebd5938282b4ca3e8958f53e1e7f1aab10a1a01fad3653bf04d73b15d61
 size 1465

run-2/checkpoint-360/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 360,
-  "best_metric": 0.93,
+  "best_metric": 0.922258064516129,
   "best_model_checkpoint": "student_modernBERT_clinc_oos/run-2/checkpoint-360",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -11,36 +11,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6835483870967742,
-      "eval_loss": 3.5096893310546875,
-      "eval_runtime": 8.6532,
-      "eval_samples_per_second": 358.247,
-      "eval_steps_per_second": 11.21,
+      "eval_accuracy": 0.6767741935483871,
+      "eval_loss": 7.750784873962402,
+      "eval_runtime": 8.6464,
+      "eval_samples_per_second": 358.531,
+      "eval_steps_per_second": 11.219,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9,
-      "eval_loss": 2.182756185531616,
-      "eval_runtime": 9.7422,
-      "eval_samples_per_second": 318.203,
-      "eval_steps_per_second": 9.957,
+      "eval_accuracy": 0.8777419354838709,
+      "eval_loss": 3.922584056854248,
+      "eval_runtime": 8.802,
+      "eval_samples_per_second": 352.193,
+      "eval_steps_per_second": 11.02,
       "step": 240
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.93,
-      "eval_loss": 1.5653125047683716,
-      "eval_runtime": 9.6218,
-      "eval_samples_per_second": 322.184,
-      "eval_steps_per_second": 10.081,
+      "eval_accuracy": 0.922258064516129,
+      "eval_loss": 2.6575753688812256,
+      "eval_runtime": 9.5831,
+      "eval_samples_per_second": 323.485,
+      "eval_steps_per_second": 10.122,
       "step": 360
     }
   ],
   "logging_steps": 500,
-  "max_steps": 960,
+  "max_steps": 720,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -58,8 +58,8 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.65741975255739,
-    "num_train_epochs": 8,
-    "temperature": 18
+    "alpha": 0.7203792274973846,
+    "num_train_epochs": 6,
+    "temperature": 7
   }
 }

run-2/checkpoint-360/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dd41b8f1f02a59dec0ad0b327aa33b067da9f7bae29bbb31cf106ac5ff4ff
+oid sha256:30763bea4e95fddafc920e08c1ea1c5e03c960715d174ba50f005d578e068b60
 size 5905

run-2/checkpoint-480/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf56298b886714900509880dc080fa5aa05ab7d1ecc79bcb35bf380777b70ac2
+oid sha256:b1e82e0c12aba607099b4d2be138de8f321c2124b057f6f454b315485344be22
 size 598898116

run-2/checkpoint-480/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:271e68778d003fb75fba98848095273b837ea34599e55a9a2b4abc3d884c85e1
+oid sha256:f795c607132939ca56cee0f6003a8a8eea7b7e4bb0953a26f65ba50ea431cec8
 size 1197886411

run-2/checkpoint-480/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8cbcab650b1a67db624b2b9fea764b147dc79e5517b7a9119f143346d1168919
+oid sha256:ddd0552961f51613cb77af24bc0e3fccce21e8083c3d1c6f93f74ab36b5046da
 size 1465

run-2/checkpoint-480/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 480,
-  "best_metric": 0.9406451612903226,
+  "best_metric": 0.9312903225806451,
   "best_model_checkpoint": "student_modernBERT_clinc_oos/run-2/checkpoint-480",
   "epoch": 4.0,
   "eval_steps": 500,
@@ -11,45 +11,45 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6835483870967742,
-      "eval_loss": 3.5096893310546875,
-      "eval_runtime": 8.6532,
-      "eval_samples_per_second": 358.247,
-      "eval_steps_per_second": 11.21,
+      "eval_accuracy": 0.6767741935483871,
+      "eval_loss": 7.750784873962402,
+      "eval_runtime": 8.6464,
+      "eval_samples_per_second": 358.531,
+      "eval_steps_per_second": 11.219,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9,
-      "eval_loss": 2.182756185531616,
-      "eval_runtime": 9.7422,
-      "eval_samples_per_second": 318.203,
-      "eval_steps_per_second": 9.957,
+      "eval_accuracy": 0.8777419354838709,
+      "eval_loss": 3.922584056854248,
+      "eval_runtime": 8.802,
+      "eval_samples_per_second": 352.193,
+      "eval_steps_per_second": 11.02,
       "step": 240
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.93,
-      "eval_loss": 1.5653125047683716,
-      "eval_runtime": 9.6218,
-      "eval_samples_per_second": 322.184,
-      "eval_steps_per_second": 10.081,
+      "eval_accuracy": 0.922258064516129,
+      "eval_loss": 2.6575753688812256,
+      "eval_runtime": 9.5831,
+      "eval_samples_per_second": 323.485,
+      "eval_steps_per_second": 10.122,
       "step": 360
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9406451612903226,
-      "eval_loss": 1.2410972118377686,
-      "eval_runtime": 8.8214,
-      "eval_samples_per_second": 351.416,
-      "eval_steps_per_second": 10.996,
+      "eval_accuracy": 0.9312903225806451,
+      "eval_loss": 2.112471342086792,
+      "eval_runtime": 8.867,
+      "eval_samples_per_second": 349.611,
+      "eval_steps_per_second": 10.939,
       "step": 480
     }
   ],
   "logging_steps": 500,
-  "max_steps": 960,
+  "max_steps": 720,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -67,8 +67,8 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.65741975255739,
-    "num_train_epochs": 8,
-    "temperature": 18
+    "alpha": 0.7203792274973846,
+    "num_train_epochs": 6,
+    "temperature": 7
   }
 }

run-2/checkpoint-480/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dd41b8f1f02a59dec0ad0b327aa33b067da9f7bae29bbb31cf106ac5ff4ff
+oid sha256:30763bea4e95fddafc920e08c1ea1c5e03c960715d174ba50f005d578e068b60
 size 5905

run-2/checkpoint-600/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:10f1f7fb2f8c6a6c1d672d93b06b4e09ffaf4ea4c0341d51088624523fb8b551
+oid sha256:b1dfaeca3a10b2e05d4644ba854079a0f41d2c936606f2375dfbb165a8632c62
 size 598898116

run-2/checkpoint-600/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3658a1f590a94c5f2031545d819d6f7ac07c65dd32c9cd8b5a3aaf56ccab8157
+oid sha256:5a5e880c068ce9544975471f48cc4c92dc9f5d68252ba51d7a6ac95e64ec8bdc
 size 1197886411

run-2/checkpoint-600/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5474f27733acd307abb3442c0e732ad487e4808c510184cc818db64a9ae46cd
+oid sha256:5bf3fb53f5149438e86367cf7dc1034ffdf5899cb1e2f8a4da236e4f899094c7
 size 1465

run-2/checkpoint-600/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 600,
-  "best_metric": 0.9451612903225807,
+  "best_metric": 0.9393548387096774,
   "best_model_checkpoint": "student_modernBERT_clinc_oos/run-2/checkpoint-600",
   "epoch": 5.0,
   "eval_steps": 500,
@@ -11,61 +11,61 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6835483870967742,
-      "eval_loss": 3.5096893310546875,
-      "eval_runtime": 8.6532,
-      "eval_samples_per_second": 358.247,
-      "eval_steps_per_second": 11.21,
+      "eval_accuracy": 0.6767741935483871,
+      "eval_loss": 7.750784873962402,
+      "eval_runtime": 8.6464,
+      "eval_samples_per_second": 358.531,
+      "eval_steps_per_second": 11.219,
       "step": 120
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.9,
-      "eval_loss": 2.182756185531616,
-      "eval_runtime": 9.7422,
-      "eval_samples_per_second": 318.203,
-      "eval_steps_per_second": 9.957,
+      "eval_accuracy": 0.8777419354838709,
+      "eval_loss": 3.922584056854248,
+      "eval_runtime": 8.802,
+      "eval_samples_per_second": 352.193,
+      "eval_steps_per_second": 11.02,
       "step": 240
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.93,
-      "eval_loss": 1.5653125047683716,
-      "eval_runtime": 9.6218,
-      "eval_samples_per_second": 322.184,
-      "eval_steps_per_second": 10.081,
+      "eval_accuracy": 0.922258064516129,
+      "eval_loss": 2.6575753688812256,
+      "eval_runtime": 9.5831,
+      "eval_samples_per_second": 323.485,
+      "eval_steps_per_second": 10.122,
       "step": 360
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9406451612903226,
-      "eval_loss": 1.2410972118377686,
-      "eval_runtime": 8.8214,
-      "eval_samples_per_second": 351.416,
-      "eval_steps_per_second": 10.996,
+      "eval_accuracy": 0.9312903225806451,
+      "eval_loss": 2.112471342086792,
+      "eval_runtime": 8.867,
+      "eval_samples_per_second": 349.611,
+      "eval_steps_per_second": 10.939,
       "step": 480
     },
     {
       "epoch": 4.167714884696017,
-      "grad_norm": 13.684679985046387,
-      "learning_rate": 9.604166666666669e-06,
-      "loss": 10.4217,
+      "grad_norm": 28.72196388244629,
+      "learning_rate": 6.13888888888889e-06,
+      "loss": 22.9799,
       "step": 500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9451612903225807,
-      "eval_loss": 1.077558159828186,
-      "eval_runtime": 9.0857,
-      "eval_samples_per_second": 341.194,
-      "eval_steps_per_second": 10.676,
+      "eval_accuracy": 0.9393548387096774,
+      "eval_loss": 1.863680362701416,
+      "eval_runtime": 8.8973,
+      "eval_samples_per_second": 348.42,
+      "eval_steps_per_second": 10.902,
       "step": 600
     }
   ],
   "logging_steps": 500,
-  "max_steps": 960,
+  "max_steps": 720,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 8,
+  "num_train_epochs": 6,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -83,8 +83,8 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.65741975255739,
-    "num_train_epochs": 8,
-    "temperature": 18
+    "alpha": 0.7203792274973846,
+    "num_train_epochs": 6,
+    "temperature": 7
   }
 }

run-2/checkpoint-600/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dd41b8f1f02a59dec0ad0b327aa33b067da9f7bae29bbb31cf106ac5ff4ff
+oid sha256:30763bea4e95fddafc920e08c1ea1c5e03c960715d174ba50f005d578e068b60
 size 5905

run-2/checkpoint-720/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0cc75c7f8e37b8dd524825dfcde256ad68c5d057195c3a3cc8cfb0147be7caba
+oid sha256:6590962f40d2c0c783a5746d100afd9db7ec6b03610c2894af9467c18e00f0d3
 size 598898116

run-2/checkpoint-720/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3eced8bff649fe140520dac12170e52c052403db9886807c475b5848318d3457
-size 767230411
+oid sha256:aba6bd0191facb8da3d8c41285b6d8db14979919284c22f722d03d1e981bab38
+size 1197886411

run-2/checkpoint-720/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:06eef7f954d1b09437a102c64a6d35db565f4aaad01b684ed37a17f3c3f88e86
+size 14645

run-2/checkpoint-720/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3863a446d67309a219068d04b8e7029d8b680b52900fd8ef93439bde5094d2a4
+size 1465

run-2/checkpoint-720/trainer_state.json

@@ -0,0 +1,99 @@
+{
+  "best_global_step": 720,
+  "best_metric": 0.9425806451612904,
+  "best_model_checkpoint": "student_modernBERT_clinc_oos/run-2/checkpoint-720",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 720,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.6767741935483871,
+      "eval_loss": 7.750784873962402,
+      "eval_runtime": 8.6464,
+      "eval_samples_per_second": 358.531,
+      "eval_steps_per_second": 11.219,
+      "step": 120
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8777419354838709,
+      "eval_loss": 3.922584056854248,
+      "eval_runtime": 8.802,
+      "eval_samples_per_second": 352.193,
+      "eval_steps_per_second": 11.02,
+      "step": 240
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.922258064516129,
+      "eval_loss": 2.6575753688812256,
+      "eval_runtime": 9.5831,
+      "eval_samples_per_second": 323.485,
+      "eval_steps_per_second": 10.122,
+      "step": 360
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.9312903225806451,
+      "eval_loss": 2.112471342086792,
+      "eval_runtime": 8.867,
+      "eval_samples_per_second": 349.611,
+      "eval_steps_per_second": 10.939,
+      "step": 480
+    },
+    {
+      "epoch": 4.167714884696017,
+      "grad_norm": 28.72196388244629,
+      "learning_rate": 6.13888888888889e-06,
+      "loss": 22.9799,
+      "step": 500
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.9393548387096774,
+      "eval_loss": 1.863680362701416,
+      "eval_runtime": 8.8973,
+      "eval_samples_per_second": 348.42,
+      "eval_steps_per_second": 10.902,
+      "step": 600
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.9425806451612904,
+      "eval_loss": 1.7904150485992432,
+      "eval_runtime": 9.4998,
+      "eval_samples_per_second": 326.321,
+      "eval_steps_per_second": 10.211,
+      "step": 720
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 720,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 6,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 891058846689456.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.7203792274973846,
+    "num_train_epochs": 6,
+    "temperature": 7
+  }
+}

run-2/checkpoint-720/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e64dd41b8f1f02a59dec0ad0b327aa33b067da9f7bae29bbb31cf106ac5ff4ff
+oid sha256:30763bea4e95fddafc920e08c1ea1c5e03c960715d174ba50f005d578e068b60
 size 5905

runs/Oct22_10-42-10_5515f8f51c79/events.out.tfevents.1761132371.5515f8f51c79.36495.3

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:051644a8854a7926e4fd126c0305876abb89e7a1002331587a805575b6c6b959
-size 13861
+oid sha256:e39c74d3b7afbaf88687b5fce085a0d250458d5b92a90bd2bbd77e86e72eb2f4
+size 15718

runs/Oct22_10-42-10_5515f8f51c79/events.out.tfevents.1761133175.5515f8f51c79.36495.4

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4f6be3cc29f8c83b7ddef83f92deaf61b64c8828e775002346da9c16c147ae4
+size 15725

runs/Oct22_15-09-25_5515f8f51c79/events.out.tfevents.1761145777.5515f8f51c79.102745.0

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:615a882739da2feb430a50d5b9acff8d7bab3eaf80a93bed537e2f1af4450667
+size 13861

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:30763bea4e95fddafc920e08c1ea1c5e03c960715d174ba50f005d578e068b60
+oid sha256:2a9027474d38a9f6a2b10e091b1562daaa0163abd36a73ab4256da426ba345b2
 size 5905