Training in progress, step 1590

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee889f64a3803bc7e93cca2dfec2e9dd8409e8881683d53e650bd0b988a67ebd
+oid sha256:d5675e320d2c4be18cdd9a2e7fa185e892844a6eb982935748b8e37d2a530a6b
 size 268290900

run-2/checkpoint-3000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fb4194ae1d9f0ba3d464738b1ae6addcca283d660b089ad326cece7bc28bf9e8
+oid sha256:85aecf5905845b880c20970872a07797be59e1d931982da6fb0fb084c0f1b3ce
 size 268290900

run-2/checkpoint-3000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dcc69c11007af22beee439d7902d3f3a1607e5bbc1ce054ccdd3b863591ab07b
+oid sha256:5e075eb97d4fdca905513f60d65f7e7e493844df1a10c9f11b976b73a885a260
 size 536643898

run-2/checkpoint-3000/trainer_state.json

@@ -10,125 +10,125 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6309677419354839,
-      "eval_loss": 0.2469712644815445,
-      "eval_runtime": 5.4589,
-      "eval_samples_per_second": 567.879,
-      "eval_steps_per_second": 11.907,
+      "eval_accuracy": 0.594516129032258,
+      "eval_loss": 0.20276567339897156,
+      "eval_runtime": 5.4162,
+      "eval_samples_per_second": 572.36,
+      "eval_steps_per_second": 12.001,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5992535352706909,
+      "grad_norm": 0.535661518573761,
       "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3971,
+      "loss": 0.3272,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8422580645161291,
-      "eval_loss": 0.10715335607528687,
-      "eval_runtime": 5.8957,
-      "eval_samples_per_second": 525.809,
-      "eval_steps_per_second": 11.025,
+      "eval_accuracy": 0.8270967741935484,
+      "eval_loss": 0.09640489518642426,
+      "eval_runtime": 6.1013,
+      "eval_samples_per_second": 508.09,
+      "eval_steps_per_second": 10.653,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8893548387096775,
-      "eval_loss": 0.06534729152917862,
-      "eval_runtime": 5.5645,
-      "eval_samples_per_second": 557.106,
-      "eval_steps_per_second": 11.681,
+      "eval_accuracy": 0.8841935483870967,
+      "eval_loss": 0.06340694427490234,
+      "eval_runtime": 5.5585,
+      "eval_samples_per_second": 557.704,
+      "eval_steps_per_second": 11.694,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5163053870201111,
+      "grad_norm": 0.4495888650417328,
       "learning_rate": 1.371069182389937e-05,
-      "loss": 0.1257,
+      "loss": 0.1121,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9077419354838709,
-      "eval_loss": 0.04786108061671257,
-      "eval_runtime": 5.7341,
-      "eval_samples_per_second": 540.622,
-      "eval_steps_per_second": 11.336,
+      "eval_accuracy": 0.9006451612903226,
+      "eval_loss": 0.048330824822187424,
+      "eval_runtime": 5.5377,
+      "eval_samples_per_second": 559.795,
+      "eval_steps_per_second": 11.738,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.3360358476638794,
+      "grad_norm": 0.30502042174339294,
       "learning_rate": 1.0566037735849058e-05,
-      "loss": 0.0738,
+      "loss": 0.0703,
       "step": 1500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9161290322580645,
-      "eval_loss": 0.038218673318624496,
-      "eval_runtime": 5.7603,
-      "eval_samples_per_second": 538.164,
-      "eval_steps_per_second": 11.284,
+      "eval_accuracy": 0.9106451612903226,
+      "eval_loss": 0.03915739059448242,
+      "eval_runtime": 5.8885,
+      "eval_samples_per_second": 526.453,
+      "eval_steps_per_second": 11.039,
       "step": 1590
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9258064516129032,
-      "eval_loss": 0.03327132761478424,
-      "eval_runtime": 5.565,
-      "eval_samples_per_second": 557.05,
-      "eval_steps_per_second": 11.68,
+      "eval_accuracy": 0.9151612903225806,
+      "eval_loss": 0.03403216972947121,
+      "eval_runtime": 5.6759,
+      "eval_samples_per_second": 546.164,
+      "eval_steps_per_second": 11.452,
       "step": 1908
     },
     {
       "epoch": 6.289308176100629,
-      "grad_norm": 0.2815706431865692,
+      "grad_norm": 0.2584752142429352,
       "learning_rate": 7.421383647798742e-06,
-      "loss": 0.056,
+      "loss": 0.0544,
       "step": 2000
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9296774193548387,
-      "eval_loss": 0.03050699457526207,
-      "eval_runtime": 5.8127,
-      "eval_samples_per_second": 533.313,
-      "eval_steps_per_second": 11.182,
+      "eval_accuracy": 0.9245161290322581,
+      "eval_loss": 0.03124151937663555,
+      "eval_runtime": 5.5585,
+      "eval_samples_per_second": 557.7,
+      "eval_steps_per_second": 11.694,
       "step": 2226
     },
     {
       "epoch": 7.861635220125786,
-      "grad_norm": 0.3059941530227661,
+      "grad_norm": 0.2786354124546051,
       "learning_rate": 4.276729559748428e-06,
-      "loss": 0.0481,
+      "loss": 0.047,
       "step": 2500
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9303225806451613,
-      "eval_loss": 0.028380775824189186,
-      "eval_runtime": 5.5569,
-      "eval_samples_per_second": 557.861,
-      "eval_steps_per_second": 11.697,
+      "eval_accuracy": 0.9280645161290323,
+      "eval_loss": 0.028918160125613213,
+      "eval_runtime": 5.9276,
+      "eval_samples_per_second": 522.981,
+      "eval_steps_per_second": 10.966,
       "step": 2544
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.932258064516129,
-      "eval_loss": 0.02733077108860016,
-      "eval_runtime": 5.4623,
-      "eval_samples_per_second": 567.527,
-      "eval_steps_per_second": 11.9,
+      "eval_accuracy": 0.93,
+      "eval_loss": 0.027848755940794945,
+      "eval_runtime": 5.5295,
+      "eval_samples_per_second": 560.632,
+      "eval_steps_per_second": 11.755,
       "step": 2862
     },
     {
       "epoch": 9.433962264150944,
-      "grad_norm": 0.27681389451026917,
+      "grad_norm": 0.25698819756507874,
       "learning_rate": 1.1320754716981133e-06,
-      "loss": 0.0446,
+      "loss": 0.0435,
       "step": 3000
     }
   ],
@@ -153,8 +153,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.1299955797744864,
+    "alpha": 0.07863039618542955,
     "num_train_epochs": 10,
-    "temperature": 4
+    "temperature": 9
   }
 }

run-2/checkpoint-3000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db3eb2a11611660ee273d6a93bf3ff6660f9d8c52045607a37deef8e769ebd6
+oid sha256:7737d5811dfd235fa6fa8c193709de926af9e7ef31f18c3db6f31576650c6630
 size 5176

run-2/checkpoint-3180/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d80aa2c8fc5cfc39ceac7e59d0eddfc11efbf099ca5f9896a7aa02fcf530ab58
+oid sha256:6360d2d13d62fb760fd5f3aba856c51352a4ff3970a40d8a1d7535d25db99771
 size 268290900

run-2/checkpoint-3180/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ef7c1c6eb97afcce5dea86cb300ed162c13fcae4c9c009fad1d58b10f2aa2128
+oid sha256:1a7838f50ad2a52322392bac70c981e2ed3e41bbfa8688190a23389d1013c138
 size 536643898

run-2/checkpoint-3180/trainer_state.json

@@ -10,125 +10,125 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6309677419354839,
-      "eval_loss": 0.2469712644815445,
-      "eval_runtime": 5.4589,
-      "eval_samples_per_second": 567.879,
-      "eval_steps_per_second": 11.907,
+      "eval_accuracy": 0.594516129032258,
+      "eval_loss": 0.20276567339897156,
+      "eval_runtime": 5.4162,
+      "eval_samples_per_second": 572.36,
+      "eval_steps_per_second": 12.001,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.5992535352706909,
+      "grad_norm": 0.535661518573761,
       "learning_rate": 1.685534591194969e-05,
-      "loss": 0.3971,
+      "loss": 0.3272,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8422580645161291,
-      "eval_loss": 0.10715335607528687,
-      "eval_runtime": 5.8957,
-      "eval_samples_per_second": 525.809,
-      "eval_steps_per_second": 11.025,
+      "eval_accuracy": 0.8270967741935484,
+      "eval_loss": 0.09640489518642426,
+      "eval_runtime": 6.1013,
+      "eval_samples_per_second": 508.09,
+      "eval_steps_per_second": 10.653,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8893548387096775,
-      "eval_loss": 0.06534729152917862,
-      "eval_runtime": 5.5645,
-      "eval_samples_per_second": 557.106,
-      "eval_steps_per_second": 11.681,
+      "eval_accuracy": 0.8841935483870967,
+      "eval_loss": 0.06340694427490234,
+      "eval_runtime": 5.5585,
+      "eval_samples_per_second": 557.704,
+      "eval_steps_per_second": 11.694,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5163053870201111,
+      "grad_norm": 0.4495888650417328,
       "learning_rate": 1.371069182389937e-05,
-      "loss": 0.1257,
+      "loss": 0.1121,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.9077419354838709,
-      "eval_loss": 0.04786108061671257,
-      "eval_runtime": 5.7341,
-      "eval_samples_per_second": 540.622,
-      "eval_steps_per_second": 11.336,
+      "eval_accuracy": 0.9006451612903226,
+      "eval_loss": 0.048330824822187424,
+      "eval_runtime": 5.5377,
+      "eval_samples_per_second": 559.795,
+      "eval_steps_per_second": 11.738,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.3360358476638794,
+      "grad_norm": 0.30502042174339294,
       "learning_rate": 1.0566037735849058e-05,
-      "loss": 0.0738,
+      "loss": 0.0703,
       "step": 1500
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.9161290322580645,
-      "eval_loss": 0.038218673318624496,
-      "eval_runtime": 5.7603,
-      "eval_samples_per_second": 538.164,
-      "eval_steps_per_second": 11.284,
+      "eval_accuracy": 0.9106451612903226,
+      "eval_loss": 0.03915739059448242,
+      "eval_runtime": 5.8885,
+      "eval_samples_per_second": 526.453,
+      "eval_steps_per_second": 11.039,
       "step": 1590
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.9258064516129032,
-      "eval_loss": 0.03327132761478424,
-      "eval_runtime": 5.565,
-      "eval_samples_per_second": 557.05,
-      "eval_steps_per_second": 11.68,
+      "eval_accuracy": 0.9151612903225806,
+      "eval_loss": 0.03403216972947121,
+      "eval_runtime": 5.6759,
+      "eval_samples_per_second": 546.164,
+      "eval_steps_per_second": 11.452,
       "step": 1908
     },
     {
       "epoch": 6.289308176100629,
-      "grad_norm": 0.2815706431865692,
+      "grad_norm": 0.2584752142429352,
       "learning_rate": 7.421383647798742e-06,
-      "loss": 0.056,
+      "loss": 0.0544,
       "step": 2000
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.9296774193548387,
-      "eval_loss": 0.03050699457526207,
-      "eval_runtime": 5.8127,
-      "eval_samples_per_second": 533.313,
-      "eval_steps_per_second": 11.182,
+      "eval_accuracy": 0.9245161290322581,
+      "eval_loss": 0.03124151937663555,
+      "eval_runtime": 5.5585,
+      "eval_samples_per_second": 557.7,
+      "eval_steps_per_second": 11.694,
       "step": 2226
     },
     {
       "epoch": 7.861635220125786,
-      "grad_norm": 0.3059941530227661,
+      "grad_norm": 0.2786354124546051,
       "learning_rate": 4.276729559748428e-06,
-      "loss": 0.0481,
+      "loss": 0.047,
       "step": 2500
     },
     {
       "epoch": 8.0,
-      "eval_accuracy": 0.9303225806451613,
-      "eval_loss": 0.028380775824189186,
-      "eval_runtime": 5.5569,
-      "eval_samples_per_second": 557.861,
-      "eval_steps_per_second": 11.697,
+      "eval_accuracy": 0.9280645161290323,
+      "eval_loss": 0.028918160125613213,
+      "eval_runtime": 5.9276,
+      "eval_samples_per_second": 522.981,
+      "eval_steps_per_second": 10.966,
       "step": 2544
     },
     {
       "epoch": 9.0,
-      "eval_accuracy": 0.932258064516129,
-      "eval_loss": 0.02733077108860016,
-      "eval_runtime": 5.4623,
-      "eval_samples_per_second": 567.527,
-      "eval_steps_per_second": 11.9,
+      "eval_accuracy": 0.93,
+      "eval_loss": 0.027848755940794945,
+      "eval_runtime": 5.5295,
+      "eval_samples_per_second": 560.632,
+      "eval_steps_per_second": 11.755,
       "step": 2862
     },
     {
       "epoch": 9.433962264150944,
-      "grad_norm": 0.27681389451026917,
+      "grad_norm": 0.25698819756507874,
       "learning_rate": 1.1320754716981133e-06,
-      "loss": 0.0446,
+      "loss": 0.0435,
       "step": 3000
     }
   ],
@@ -153,8 +153,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.1299955797744864,
+    "alpha": 0.07863039618542955,
     "num_train_epochs": 10,
-    "temperature": 4
+    "temperature": 9
   }
 }

run-2/checkpoint-3180/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3db3eb2a11611660ee273d6a93bf3ff6660f9d8c52045607a37deef8e769ebd6
+oid sha256:7737d5811dfd235fa6fa8c193709de926af9e7ef31f18c3db6f31576650c6630
 size 5176

run-3/checkpoint-1000/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:568758ecc27e9c6e5df9f7c5483f3c52689e70a95a190f7ff6eb360f05fa031e
+oid sha256:8fb60c0450b9fab304e28c1a1d228df806a1f9af6f33f4fb321fe21c92482441
 size 268290900

run-3/checkpoint-1000/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b9a2978fcace548df0ce5a29338a305060aeeb2a7931814818a61594b77f9c6
+oid sha256:57a06837a5e41694c5ed89282a2609197ff6383eb9f1d40c75d58474558859c0
 size 536643898

run-3/checkpoint-1000/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:72a4307cca951ef6d42c7f184774e8b1259c78b2bf130b8443ec0b62f6dbf689
+oid sha256:9f182501c34e4ea3ebc7617d27edab7e1367582b147e518cd90295ec7f2eaa0f
 size 1064

run-3/checkpoint-1000/trainer_state.json

@@ -10,50 +10,50 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6509677419354839,
-      "eval_loss": 0.2873552143573761,
-      "eval_runtime": 5.4953,
-      "eval_samples_per_second": 564.118,
-      "eval_steps_per_second": 11.828,
+      "eval_accuracy": 0.5741935483870968,
+      "eval_loss": 0.21353885531425476,
+      "eval_runtime": 5.4329,
+      "eval_samples_per_second": 570.601,
+      "eval_steps_per_second": 11.964,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.6625721454620361,
-      "learning_rate": 1.650593990216632e-05,
-      "loss": 0.4591,
+      "grad_norm": 0.553505003452301,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.3345,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8429032258064516,
-      "eval_loss": 0.11606641113758087,
-      "eval_runtime": 5.7777,
-      "eval_samples_per_second": 536.547,
-      "eval_steps_per_second": 11.25,
+      "eval_accuracy": 0.8087096774193548,
+      "eval_loss": 0.10993640869855881,
+      "eval_runtime": 6.0275,
+      "eval_samples_per_second": 514.313,
+      "eval_steps_per_second": 10.784,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8948387096774194,
-      "eval_loss": 0.06758537143468857,
-      "eval_runtime": 5.6402,
-      "eval_samples_per_second": 549.628,
-      "eval_steps_per_second": 11.524,
+      "eval_accuracy": 0.8596774193548387,
+      "eval_loss": 0.0786653459072113,
+      "eval_runtime": 5.5267,
+      "eval_samples_per_second": 560.911,
+      "eval_steps_per_second": 11.761,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5751062631607056,
-      "learning_rate": 1.3011879804332637e-05,
-      "loss": 0.1369,
+      "grad_norm": 0.48568108677864075,
+      "learning_rate": 7.421383647798742e-06,
+      "loss": 0.1269,
       "step": 1000
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2862,
+  "max_steps": 1590,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 9,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -71,8 +71,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8846264724466298,
-    "num_train_epochs": 9,
-    "temperature": 3
+    "alpha": 0.5191171844972077,
+    "num_train_epochs": 5,
+    "temperature": 9
   }
 }

run-3/checkpoint-1000/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254832bddb5685972d43bfc1f6fb2e0c19625ccc53a0aecbfc27fe75ff1f80ee
+oid sha256:acaf4c14e96120a2900b5480a226f035f804f94ffa8a7b7292532c314d649801
 size 5176

run-3/checkpoint-1500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ed03b494a50f0c09b27b3feb74cdfd91240f562410ba35417b60380960982ee4
+oid sha256:4acb6dac83f582795371326ad6f14cfc7f9d60856f8f6aa24ab9ee5332ab9452
 size 268290900

run-3/checkpoint-1500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a0604a12e22ce4fe402f6effcc47bab14187c10420ecf7c9b0039ecb54890b9
+oid sha256:78760086a64289a8617a8f513f950b3d3ead725ad7f89a7004670c33067ed5d5
 size 536643898

run-3/checkpoint-1500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:693ec081eb0fa0af7d13e289edb194450dd19fdada23346e2af4292ea228535f
+oid sha256:91d97f7c1be085852e2ffd2fe2f8a493a080e2b2858e2f3baf642fe214e035a0
 size 1064

run-3/checkpoint-1500/trainer_state.json

@@ -10,66 +10,66 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6509677419354839,
-      "eval_loss": 0.2873552143573761,
-      "eval_runtime": 5.4953,
-      "eval_samples_per_second": 564.118,
-      "eval_steps_per_second": 11.828,
+      "eval_accuracy": 0.5741935483870968,
+      "eval_loss": 0.21353885531425476,
+      "eval_runtime": 5.4329,
+      "eval_samples_per_second": 570.601,
+      "eval_steps_per_second": 11.964,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.6625721454620361,
-      "learning_rate": 1.650593990216632e-05,
-      "loss": 0.4591,
+      "grad_norm": 0.553505003452301,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.3345,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.8429032258064516,
-      "eval_loss": 0.11606641113758087,
-      "eval_runtime": 5.7777,
-      "eval_samples_per_second": 536.547,
-      "eval_steps_per_second": 11.25,
+      "eval_accuracy": 0.8087096774193548,
+      "eval_loss": 0.10993640869855881,
+      "eval_runtime": 6.0275,
+      "eval_samples_per_second": 514.313,
+      "eval_steps_per_second": 10.784,
       "step": 636
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.8948387096774194,
-      "eval_loss": 0.06758537143468857,
-      "eval_runtime": 5.6402,
-      "eval_samples_per_second": 549.628,
-      "eval_steps_per_second": 11.524,
+      "eval_accuracy": 0.8596774193548387,
+      "eval_loss": 0.0786653459072113,
+      "eval_runtime": 5.5267,
+      "eval_samples_per_second": 560.911,
+      "eval_steps_per_second": 11.761,
       "step": 954
     },
     {
       "epoch": 3.1446540880503147,
-      "grad_norm": 0.5751062631607056,
-      "learning_rate": 1.3011879804332637e-05,
-      "loss": 0.1369,
+      "grad_norm": 0.48568108677864075,
+      "learning_rate": 7.421383647798742e-06,
+      "loss": 0.1269,
       "step": 1000
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.91,
-      "eval_loss": 0.04885578155517578,
-      "eval_runtime": 5.5152,
-      "eval_samples_per_second": 562.081,
-      "eval_steps_per_second": 11.786,
+      "eval_accuracy": 0.8790322580645161,
+      "eval_loss": 0.06603369116783142,
+      "eval_runtime": 5.5422,
+      "eval_samples_per_second": 559.348,
+      "eval_steps_per_second": 11.728,
       "step": 1272
     },
     {
       "epoch": 4.716981132075472,
-      "grad_norm": 0.373975932598114,
-      "learning_rate": 9.517819706498952e-06,
-      "loss": 0.0773,
+      "grad_norm": 0.3628057539463043,
+      "learning_rate": 1.1320754716981133e-06,
+      "loss": 0.0909,
       "step": 1500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2862,
+  "max_steps": 1590,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 9,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -87,8 +87,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8846264724466298,
-    "num_train_epochs": 9,
-    "temperature": 3
+    "alpha": 0.5191171844972077,
+    "num_train_epochs": 5,
+    "temperature": 9
   }
 }

run-3/checkpoint-1500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254832bddb5685972d43bfc1f6fb2e0c19625ccc53a0aecbfc27fe75ff1f80ee
+oid sha256:acaf4c14e96120a2900b5480a226f035f804f94ffa8a7b7292532c314d649801
 size 5176

run-3/checkpoint-1590/config.json

@@ -0,0 +1,331 @@
+{
+  "_name_or_path": "distilbert-base-uncased",
+  "activation": "gelu",
+  "architectures": [
+    "DistilBertForSequenceClassification"
+  ],
+  "attention_dropout": 0.1,
+  "dim": 768,
+  "dropout": 0.1,
+  "hidden_dim": 3072,
+  "id2label": {
+    "0": "restaurant_reviews",
+    "1": "nutrition_info",
+    "2": "account_blocked",
+    "3": "oil_change_how",
+    "4": "time",
+    "5": "weather",
+    "6": "redeem_rewards",
+    "7": "interest_rate",
+    "8": "gas_type",
+    "9": "accept_reservations",
+    "10": "smart_home",
+    "11": "user_name",
+    "12": "report_lost_card",
+    "13": "repeat",
+    "14": "whisper_mode",
+    "15": "what_are_your_hobbies",
+    "16": "order",
+    "17": "jump_start",
+    "18": "schedule_meeting",
+    "19": "meeting_schedule",
+    "20": "freeze_account",
+    "21": "what_song",
+    "22": "meaning_of_life",
+    "23": "restaurant_reservation",
+    "24": "traffic",
+    "25": "make_call",
+    "26": "text",
+    "27": "bill_balance",
+    "28": "improve_credit_score",
+    "29": "change_language",
+    "30": "no",
+    "31": "measurement_conversion",
+    "32": "timer",
+    "33": "flip_coin",
+    "34": "do_you_have_pets",
+    "35": "balance",
+    "36": "tell_joke",
+    "37": "last_maintenance",
+    "38": "exchange_rate",
+    "39": "uber",
+    "40": "car_rental",
+    "41": "credit_limit",
+    "42": "oos",
+    "43": "shopping_list",
+    "44": "expiration_date",
+    "45": "routing",
+    "46": "meal_suggestion",
+    "47": "tire_change",
+    "48": "todo_list",
+    "49": "card_declined",
+    "50": "rewards_balance",
+    "51": "change_accent",
+    "52": "vaccines",
+    "53": "reminder_update",
+    "54": "food_last",
+    "55": "change_ai_name",
+    "56": "bill_due",
+    "57": "who_do_you_work_for",
+    "58": "share_location",
+    "59": "international_visa",
+    "60": "calendar",
+    "61": "translate",
+    "62": "carry_on",
+    "63": "book_flight",
+    "64": "insurance_change",
+    "65": "todo_list_update",
+    "66": "timezone",
+    "67": "cancel_reservation",
+    "68": "transactions",
+    "69": "credit_score",
+    "70": "report_fraud",
+    "71": "spending_history",
+    "72": "directions",
+    "73": "spelling",
+    "74": "insurance",
+    "75": "what_is_your_name",
+    "76": "reminder",
+    "77": "where_are_you_from",
+    "78": "distance",
+    "79": "payday",
+    "80": "flight_status",
+    "81": "find_phone",
+    "82": "greeting",
+    "83": "alarm",
+    "84": "order_status",
+    "85": "confirm_reservation",
+    "86": "cook_time",
+    "87": "damaged_card",
+    "88": "reset_settings",
+    "89": "pin_change",
+    "90": "replacement_card_duration",
+    "91": "new_card",
+    "92": "roll_dice",
+    "93": "income",
+    "94": "taxes",
+    "95": "date",
+    "96": "who_made_you",
+    "97": "pto_request",
+    "98": "tire_pressure",
+    "99": "how_old_are_you",
+    "100": "rollover_401k",
+    "101": "pto_request_status",
+    "102": "how_busy",
+    "103": "application_status",
+    "104": "recipe",
+    "105": "calendar_update",
+    "106": "play_music",
+    "107": "yes",
+    "108": "direct_deposit",
+    "109": "credit_limit_change",
+    "110": "gas",
+    "111": "pay_bill",
+    "112": "ingredients_list",
+    "113": "lost_luggage",
+    "114": "goodbye",
+    "115": "what_can_i_ask_you",
+    "116": "book_hotel",
+    "117": "are_you_a_bot",
+    "118": "next_song",
+    "119": "change_speed",
+    "120": "plug_type",
+    "121": "maybe",
+    "122": "w2",
+    "123": "oil_change_when",
+    "124": "thank_you",
+    "125": "shopping_list_update",
+    "126": "pto_balance",
+    "127": "order_checks",
+    "128": "travel_alert",
+    "129": "fun_fact",
+    "130": "sync_device",
+    "131": "schedule_maintenance",
+    "132": "apr",
+    "133": "transfer",
+    "134": "ingredient_substitution",
+    "135": "calories",
+    "136": "current_location",
+    "137": "international_fees",
+    "138": "calculator",
+    "139": "definition",
+    "140": "next_holiday",
+    "141": "update_playlist",
+    "142": "mpg",
+    "143": "min_payment",
+    "144": "change_user_name",
+    "145": "restaurant_suggestion",
+    "146": "travel_notification",
+    "147": "cancel",
+    "148": "pto_used",
+    "149": "travel_suggestion",
+    "150": "change_volume"
+  },
+  "initializer_range": 0.02,
+  "label2id": {
+    "accept_reservations": 9,
+    "account_blocked": 2,
+    "alarm": 83,
+    "application_status": 103,
+    "apr": 132,
+    "are_you_a_bot": 117,
+    "balance": 35,
+    "bill_balance": 27,
+    "bill_due": 56,
+    "book_flight": 63,
+    "book_hotel": 116,
+    "calculator": 138,
+    "calendar": 60,
+    "calendar_update": 105,
+    "calories": 135,
+    "cancel": 147,
+    "cancel_reservation": 67,
+    "car_rental": 40,
+    "card_declined": 49,
+    "carry_on": 62,
+    "change_accent": 51,
+    "change_ai_name": 55,
+    "change_language": 29,
+    "change_speed": 119,
+    "change_user_name": 144,
+    "change_volume": 150,
+    "confirm_reservation": 85,
+    "cook_time": 86,
+    "credit_limit": 41,
+    "credit_limit_change": 109,
+    "credit_score": 69,
+    "current_location": 136,
+    "damaged_card": 87,
+    "date": 95,
+    "definition": 139,
+    "direct_deposit": 108,
+    "directions": 72,
+    "distance": 78,
+    "do_you_have_pets": 34,
+    "exchange_rate": 38,
+    "expiration_date": 44,
+    "find_phone": 81,
+    "flight_status": 80,
+    "flip_coin": 33,
+    "food_last": 54,
+    "freeze_account": 20,
+    "fun_fact": 129,
+    "gas": 110,
+    "gas_type": 8,
+    "goodbye": 114,
+    "greeting": 82,
+    "how_busy": 102,
+    "how_old_are_you": 99,
+    "improve_credit_score": 28,
+    "income": 93,
+    "ingredient_substitution": 134,
+    "ingredients_list": 112,
+    "insurance": 74,
+    "insurance_change": 64,
+    "interest_rate": 7,
+    "international_fees": 137,
+    "international_visa": 59,
+    "jump_start": 17,
+    "last_maintenance": 37,
+    "lost_luggage": 113,
+    "make_call": 25,
+    "maybe": 121,
+    "meal_suggestion": 46,
+    "meaning_of_life": 22,
+    "measurement_conversion": 31,
+    "meeting_schedule": 19,
+    "min_payment": 143,
+    "mpg": 142,
+    "new_card": 91,
+    "next_holiday": 140,
+    "next_song": 118,
+    "no": 30,
+    "nutrition_info": 1,
+    "oil_change_how": 3,
+    "oil_change_when": 123,
+    "oos": 42,
+    "order": 16,
+    "order_checks": 127,
+    "order_status": 84,
+    "pay_bill": 111,
+    "payday": 79,
+    "pin_change": 89,
+    "play_music": 106,
+    "plug_type": 120,
+    "pto_balance": 126,
+    "pto_request": 97,
+    "pto_request_status": 101,
+    "pto_used": 148,
+    "recipe": 104,
+    "redeem_rewards": 6,
+    "reminder": 76,
+    "reminder_update": 53,
+    "repeat": 13,
+    "replacement_card_duration": 90,
+    "report_fraud": 70,
+    "report_lost_card": 12,
+    "reset_settings": 88,
+    "restaurant_reservation": 23,
+    "restaurant_reviews": 0,
+    "restaurant_suggestion": 145,
+    "rewards_balance": 50,
+    "roll_dice": 92,
+    "rollover_401k": 100,
+    "routing": 45,
+    "schedule_maintenance": 131,
+    "schedule_meeting": 18,
+    "share_location": 58,
+    "shopping_list": 43,
+    "shopping_list_update": 125,
+    "smart_home": 10,
+    "spelling": 73,
+    "spending_history": 71,
+    "sync_device": 130,
+    "taxes": 94,
+    "tell_joke": 36,
+    "text": 26,
+    "thank_you": 124,
+    "time": 4,
+    "timer": 32,
+    "timezone": 66,
+    "tire_change": 47,
+    "tire_pressure": 98,
+    "todo_list": 48,
+    "todo_list_update": 65,
+    "traffic": 24,
+    "transactions": 68,
+    "transfer": 133,
+    "translate": 61,
+    "travel_alert": 128,
+    "travel_notification": 146,
+    "travel_suggestion": 149,
+    "uber": 39,
+    "update_playlist": 141,
+    "user_name": 11,
+    "vaccines": 52,
+    "w2": 122,
+    "weather": 5,
+    "what_are_your_hobbies": 15,
+    "what_can_i_ask_you": 115,
+    "what_is_your_name": 75,
+    "what_song": 21,
+    "where_are_you_from": 77,
+    "whisper_mode": 14,
+    "who_do_you_work_for": 57,
+    "who_made_you": 96,
+    "yes": 107
+  },
+  "max_position_embeddings": 512,
+  "model_type": "distilbert",
+  "n_heads": 12,
+  "n_layers": 6,
+  "pad_token_id": 0,
+  "problem_type": "single_label_classification",
+  "qa_dropout": 0.1,
+  "seq_classif_dropout": 0.2,
+  "sinusoidal_pos_embds": false,
+  "tie_weights_": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.42.4",
+  "vocab_size": 30522
+}

run-3/checkpoint-1590/model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d5675e320d2c4be18cdd9a2e7fa185e892844a6eb982935748b8e37d2a530a6b
+size 268290900

run-3/checkpoint-1590/optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:672f95d48a83b88606533351199eca944d407edb58e552c3024e032ae19e8214
+size 536643898

run-3/checkpoint-1590/rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:928cc9918c20899b4e4eb6d8c67d3e941cdd4501fc52979922c643d69ced4b71
+size 14244

run-3/checkpoint-1590/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee1082c0efb09baac545ba26829a8ad0ace46851b360d7c70f5f11088ecb04f2
+size 1064

run-3/checkpoint-1590/special_tokens_map.json

@@ -0,0 +1,7 @@
+{
+  "cls_token": "[CLS]",
+  "mask_token": "[MASK]",
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1590/tokenizer_config.json

@@ -0,0 +1,55 @@
+{
+  "added_tokens_decoder": {
+    "0": {
+      "content": "[PAD]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100": {
+      "content": "[UNK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "101": {
+      "content": "[CLS]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "102": {
+      "content": "[SEP]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "103": {
+      "content": "[MASK]",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "clean_up_tokenization_spaces": true,
+  "cls_token": "[CLS]",
+  "do_lower_case": true,
+  "mask_token": "[MASK]",
+  "model_max_length": 512,
+  "pad_token": "[PAD]",
+  "sep_token": "[SEP]",
+  "strip_accents": null,
+  "tokenize_chinese_chars": true,
+  "tokenizer_class": "DistilBertTokenizer",
+  "unk_token": "[UNK]"
+}

run-3/checkpoint-1590/trainer_state.json

@@ -0,0 +1,94 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 1590,
+  "is_hyper_param_search": true,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.5741935483870968,
+      "eval_loss": 0.21353885531425476,
+      "eval_runtime": 5.4329,
+      "eval_samples_per_second": 570.601,
+      "eval_steps_per_second": 11.964,
+      "step": 318
+    },
+    {
+      "epoch": 1.5723270440251573,
+      "grad_norm": 0.553505003452301,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.3345,
+      "step": 500
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8087096774193548,
+      "eval_loss": 0.10993640869855881,
+      "eval_runtime": 6.0275,
+      "eval_samples_per_second": 514.313,
+      "eval_steps_per_second": 10.784,
+      "step": 636
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8596774193548387,
+      "eval_loss": 0.0786653459072113,
+      "eval_runtime": 5.5267,
+      "eval_samples_per_second": 560.911,
+      "eval_steps_per_second": 11.761,
+      "step": 954
+    },
+    {
+      "epoch": 3.1446540880503147,
+      "grad_norm": 0.48568108677864075,
+      "learning_rate": 7.421383647798742e-06,
+      "loss": 0.1269,
+      "step": 1000
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8790322580645161,
+      "eval_loss": 0.06603369116783142,
+      "eval_runtime": 5.5422,
+      "eval_samples_per_second": 559.348,
+      "eval_steps_per_second": 11.728,
+      "step": 1272
+    },
+    {
+      "epoch": 4.716981132075472,
+      "grad_norm": 0.3628057539463043,
+      "learning_rate": 1.1320754716981133e-06,
+      "loss": 0.0909,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 500,
+  "max_steps": 1590,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 5,
+  "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": 391368939443328.0,
+  "train_batch_size": 48,
+  "trial_name": null,
+  "trial_params": {
+    "alpha": 0.5191171844972077,
+    "num_train_epochs": 5,
+    "temperature": 9
+  }
+}

run-3/checkpoint-1590/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:acaf4c14e96120a2900b5480a226f035f804f94ffa8a7b7292532c314d649801
+size 5176

run-3/checkpoint-500/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77ac98db9c43c95de9992bcd0b9c28a188155ea874e19399c92de4e25b2a2963
+oid sha256:a0dbbc2ac257d98dcea2c61c8febff59c1169a40ebfc1a99ba395fc10f2b0293
 size 268290900

run-3/checkpoint-500/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf7809b1abf6a6a9529b2592f883e6a1f986a233be3ca3ff55e229ab115e38e0
+oid sha256:7f61556fa85704db211969240099ec557b425a75f4e13181d31293a00b89f8c1
 size 536643898

run-3/checkpoint-500/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98041bd7cae455426e290a1a0ee683bd5dd30893f7451fec3a464ae8995b17e4
+oid sha256:9e1264523e958cf7990dc5f42d876cc12129475c4603804cf66868aaf25c2c24
 size 1064

run-3/checkpoint-500/trainer_state.json

@@ -10,25 +10,25 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6509677419354839,
-      "eval_loss": 0.2873552143573761,
-      "eval_runtime": 5.4953,
-      "eval_samples_per_second": 564.118,
-      "eval_steps_per_second": 11.828,
+      "eval_accuracy": 0.5741935483870968,
+      "eval_loss": 0.21353885531425476,
+      "eval_runtime": 5.4329,
+      "eval_samples_per_second": 570.601,
+      "eval_steps_per_second": 11.964,
       "step": 318
     },
     {
       "epoch": 1.5723270440251573,
-      "grad_norm": 0.6625721454620361,
-      "learning_rate": 1.650593990216632e-05,
-      "loss": 0.4591,
+      "grad_norm": 0.553505003452301,
+      "learning_rate": 1.371069182389937e-05,
+      "loss": 0.3345,
       "step": 500
     }
   ],
   "logging_steps": 500,
-  "max_steps": 2862,
+  "max_steps": 1590,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 9,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -46,8 +46,8 @@
   "train_batch_size": 48,
   "trial_name": null,
   "trial_params": {
-    "alpha": 0.8846264724466298,
-    "num_train_epochs": 9,
-    "temperature": 3
+    "alpha": 0.5191171844972077,
+    "num_train_epochs": 5,
+    "temperature": 9
   }
 }

run-3/checkpoint-500/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:254832bddb5685972d43bfc1f6fb2e0c19625ccc53a0aecbfc27fe75ff1f80ee
+oid sha256:acaf4c14e96120a2900b5480a226f035f804f94ffa8a7b7292532c314d649801
 size 5176

runs/Aug28_01-37-39_61274092231a/events.out.tfevents.1724811208.61274092231a.346.2

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a719914dbc28d496fc36a14850fbfe4e5ee6026f2efade9402f7effe379c4f15
-size 16548
+oid sha256:29392a12d8a9b73b23b84be4d2855eaa9b262ffbcf6d3bb622d9fac98dadf4b8
+size 17225

runs/Aug28_01-37-39_61274092231a/events.out.tfevents.1724812005.61274092231a.346.3

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fd0b8913dbb28c12e4ef3da0856c5f1aab4514fa28397ddcf0ed95af6fa95f5
+size 14976

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7737d5811dfd235fa6fa8c193709de926af9e7ef31f18c3db6f31576650c6630
+oid sha256:acaf4c14e96120a2900b5480a226f035f804f94ffa8a7b7292532c314d649801
 size 5176