Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8f3e4b79100e3903a643642acb0450e8a07b2cb9a4372bdfe1031c60b37df75f
+oid sha256:037031c0588abe3648a2177d448c4f64586291910d904d4aeedabe446ba66111
 size 437958648

run-0/checkpoint-117/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1ce4125b396a0606ad963636d3d8c5e44f951bd4740645669474eae1f3cb814b
+oid sha256:4c802ec515bc86042cdf8b15c8b139fa0f9cf6ca850b5573e82a8a229503bd37
 size 437958648

run-0/checkpoint-117/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3b5187a960f1de00c4f147eb0f3746cc85cc2d1b7a30c131b1c886923b315421
+oid sha256:e87c9c15e82618884edf2708969a5b156acbfe11a90c8b8aff20c1bec639402e
 size 876038394

run-0/checkpoint-117/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:09557b1d4da433a4489d12bec551f7b75466f796a905598e6ba8698b633264c8
+oid sha256:5b52c2b12734a8e47563cebc4f66b329836ea028b2a85fbfd91dadd377531bfe
 size 1064

run-0/checkpoint-117/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 117,
-  "best_metric": 0.6823104693140795,
+  "best_metric": 0.6931407942238267,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-117",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -11,36 +11,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6787003610108303,
-      "eval_loss": 0.6131929755210876,
-      "eval_runtime": 0.6361,
-      "eval_samples_per_second": 435.464,
-      "eval_steps_per_second": 14.149,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6344426274299622,
+      "eval_runtime": 0.6369,
+      "eval_samples_per_second": 434.892,
+      "eval_steps_per_second": 14.13,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.7132726907730103,
-      "eval_runtime": 0.6373,
-      "eval_samples_per_second": 434.619,
-      "eval_steps_per_second": 14.121,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6399555802345276,
+      "eval_runtime": 0.6384,
+      "eval_samples_per_second": 433.892,
+      "eval_steps_per_second": 14.098,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6823104693140795,
-      "eval_loss": 0.7888869047164917,
-      "eval_runtime": 0.6455,
-      "eval_samples_per_second": 429.153,
-      "eval_steps_per_second": 13.944,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.7489305734634399,
+      "eval_runtime": 0.6376,
+      "eval_samples_per_second": 434.416,
+      "eval_steps_per_second": 14.115,
       "step": 117
     }
   ],
   "logging_steps": 500,
-  "max_steps": 117,
+  "max_steps": 195,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -49,7 +49,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
@@ -61,7 +61,7 @@
     "dropout_rate": 0.0134,
     "learning_rate": 0.0001,
     "max_length": 32,
-    "num_train_epochs": 3,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 64
   }
 }

run-0/checkpoint-117/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e666bae6191103ce3111bb8ce1c7c6747611fec7304e19a2fcda4daf98790d92
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-0/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429a1dc16293286984d90119d50793b06211366b125c3f3dbc6b0647aa478971
+oid sha256:5db92fb8a00f8c2455466018148153ef5f020c57f80a395281a30e8736e91a23
 size 437958648

run-0/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20b13f33c6c4ece94c4a7bf13af46329a085eed008ff4471bc808a308b71d6ee
+oid sha256:1a0751d6ff4e94e130c1204c790ff869f7b223d5558f613fd95b01591686a496
 size 876038394

run-0/checkpoint-156/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba302ee87ff243e8cfe6b6e2e707141cb28f6780ae017be334f60d61b5d54260
+oid sha256:64871ea17abfaf974175c856702e9195f2d949b9a3207a0265bff73135f4adeb
 size 1064

run-0/checkpoint-156/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 39,
-  "best_metric": 0.5270758122743683,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-39",
+  "best_global_step": 156,
+  "best_metric": 0.7111913357400722,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-156",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 156,
@@ -11,38 +11,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6918498277664185,
-      "eval_runtime": 0.635,
-      "eval_samples_per_second": 436.194,
-      "eval_steps_per_second": 14.172,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6344426274299622,
+      "eval_runtime": 0.6369,
+      "eval_samples_per_second": 434.892,
+      "eval_steps_per_second": 14.13,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 6.468245983123779,
-      "eval_runtime": 0.6398,
-      "eval_samples_per_second": 432.935,
-      "eval_steps_per_second": 14.066,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6399555802345276,
+      "eval_runtime": 0.6384,
+      "eval_samples_per_second": 433.892,
+      "eval_steps_per_second": 14.098,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7129499912261963,
-      "eval_runtime": 0.6364,
-      "eval_samples_per_second": 435.269,
-      "eval_steps_per_second": 14.142,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.7489305734634399,
+      "eval_runtime": 0.6376,
+      "eval_samples_per_second": 434.416,
+      "eval_steps_per_second": 14.115,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.9733805060386658,
-      "eval_runtime": 0.6389,
-      "eval_samples_per_second": 433.569,
-      "eval_steps_per_second": 14.087,
+      "eval_accuracy": 0.7111913357400722,
+      "eval_loss": 0.9546563029289246,
+      "eval_runtime": 0.6421,
+      "eval_samples_per_second": 431.374,
+      "eval_steps_per_second": 14.016,
       "step": 156
     }
   ],
@@ -68,7 +68,7 @@
   "trial_name": null,
   "trial_params": {
     "dropout_rate": 0.0134,
-    "learning_rate": 0.05,
+    "learning_rate": 0.0001,
     "max_length": 32,
     "num_train_epochs": 5,
     "per_device_train_batch_size": 64

run-0/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-0/checkpoint-195/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9950acd2abe1ba375b210771545bb92b457a4b75c4fcdf70a6172ca66e8e2121
+oid sha256:617e561d87a0a00190966fad2e666cfc7c7511275a22ab5451714d514b3d047c
 size 437958648

run-0/checkpoint-195/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01d2bff49be4cc589ee150859b97f0f97aed3237c49418d77d4af5adb78e921a
+oid sha256:cd14c0c2fd8af6ba25e630124589880ec3c065718165595a3f67e870ae299b5f
 size 876038394

run-0/checkpoint-195/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:752f5a084edce7f72f09d3a1b263e8d262206382cd7e907850fe343dd9fe7226
+oid sha256:7535d6d6d3346211338a559c66a34e5433ea456734f0f5c94e8703828d95ba57
 size 1064

run-0/checkpoint-195/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 39,
-  "best_metric": 0.5270758122743683,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-39",
+  "best_global_step": 156,
+  "best_metric": 0.7111913357400722,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-156",
   "epoch": 5.0,
   "eval_steps": 500,
   "global_step": 195,
@@ -11,47 +11,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6918498277664185,
-      "eval_runtime": 0.635,
-      "eval_samples_per_second": 436.194,
-      "eval_steps_per_second": 14.172,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6344426274299622,
+      "eval_runtime": 0.6369,
+      "eval_samples_per_second": 434.892,
+      "eval_steps_per_second": 14.13,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 6.468245983123779,
-      "eval_runtime": 0.6398,
-      "eval_samples_per_second": 432.935,
-      "eval_steps_per_second": 14.066,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6399555802345276,
+      "eval_runtime": 0.6384,
+      "eval_samples_per_second": 433.892,
+      "eval_steps_per_second": 14.098,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7129499912261963,
-      "eval_runtime": 0.6364,
-      "eval_samples_per_second": 435.269,
-      "eval_steps_per_second": 14.142,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.7489305734634399,
+      "eval_runtime": 0.6376,
+      "eval_samples_per_second": 434.416,
+      "eval_steps_per_second": 14.115,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.9733805060386658,
-      "eval_runtime": 0.6389,
-      "eval_samples_per_second": 433.569,
-      "eval_steps_per_second": 14.087,
+      "eval_accuracy": 0.7111913357400722,
+      "eval_loss": 0.9546563029289246,
+      "eval_runtime": 0.6421,
+      "eval_samples_per_second": 431.374,
+      "eval_steps_per_second": 14.016,
       "step": 156
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7346399426460266,
-      "eval_runtime": 0.6381,
-      "eval_samples_per_second": 434.11,
-      "eval_steps_per_second": 14.105,
+      "eval_accuracy": 0.703971119133574,
+      "eval_loss": 1.0655008554458618,
+      "eval_runtime": 0.6437,
+      "eval_samples_per_second": 430.356,
+      "eval_steps_per_second": 13.983,
       "step": 195
     }
   ],
@@ -77,7 +77,7 @@
   "trial_name": null,
   "trial_params": {
     "dropout_rate": 0.0134,
-    "learning_rate": 0.05,
+    "learning_rate": 0.0001,
     "max_length": 32,
     "num_train_epochs": 5,
     "per_device_train_batch_size": 64

run-0/checkpoint-195/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-0/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1b2b58ba8316c1e14342d28ec70cb085c885595457fd6595ed055803edb65417
+oid sha256:095c36a06fc2953f3fa1e12dc8abd3e9cb7f7fc377af4df1c2846b1e859eac15
 size 437958648

run-0/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7001a693620ee2b9cca6597b55aa32607001b471c898c3b6b0c903fd50aa01b1
+oid sha256:4ebe11ec5538d8ded7bd7bc7188f64ccb65bcd4808f2f1e366db5c204845b326
 size 876038394

run-0/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:20c6c37a4a15bf2c6e5ac49dadc2a47206fbd55bea0d19dc3dfe3b1f35cc3fb0
+oid sha256:fb667ae3b67495afb6dd345289d7886f47c7be4d88545cef5fd8a2859941ae93
 size 1064

run-0/checkpoint-78/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 39,
-  "best_metric": 0.6787003610108303,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-39",
+  "best_global_step": 78,
+  "best_metric": 0.6606498194945848,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-78",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 78,
@@ -11,27 +11,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6787003610108303,
-      "eval_loss": 0.6131929755210876,
-      "eval_runtime": 0.6361,
-      "eval_samples_per_second": 435.464,
-      "eval_steps_per_second": 14.149,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6344426274299622,
+      "eval_runtime": 0.6369,
+      "eval_samples_per_second": 434.892,
+      "eval_steps_per_second": 14.13,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.7132726907730103,
-      "eval_runtime": 0.6373,
-      "eval_samples_per_second": 434.619,
-      "eval_steps_per_second": 14.121,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6399555802345276,
+      "eval_runtime": 0.6384,
+      "eval_samples_per_second": 433.892,
+      "eval_steps_per_second": 14.098,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 117,
+  "max_steps": 195,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -52,7 +52,7 @@
     "dropout_rate": 0.0134,
     "learning_rate": 0.0001,
     "max_length": 32,
-    "num_train_epochs": 3,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 64
   }
 }

run-0/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e666bae6191103ce3111bb8ce1c7c6747611fec7304e19a2fcda4daf98790d92
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-1/checkpoint-117/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:881c529a030168cc7105bed3ff575f99bf584b709e20f328588f9ef7eb2a9ba3
+oid sha256:679e027e39e2e1b7b9e1240bb8d9f42125967b9daf06e4768ab77daf28fa7315
 size 437958648

run-1/checkpoint-117/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bd1b9480474695a0378bac4c890f9b956a8fe4ccf1fc8227f48a9d5ecfac3a2c
+oid sha256:f80bde91e09964025f09bae3e83f85e29f7fea36ff0e59ca2d24f18de39b3e34
 size 876038394

run-1/checkpoint-117/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 117,
+  "best_global_step": 78,
   "best_metric": 0.6895306859205776,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-117",
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-78",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 117,
@@ -11,29 +11,29 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6462093862815884,
-      "eval_loss": 0.6229268908500671,
-      "eval_runtime": 0.6366,
-      "eval_samples_per_second": 435.104,
-      "eval_steps_per_second": 14.137,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6302457451820374,
+      "eval_runtime": 0.6387,
+      "eval_samples_per_second": 433.698,
+      "eval_steps_per_second": 14.091,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6570397111913358,
-      "eval_loss": 0.7122572064399719,
-      "eval_runtime": 0.6369,
-      "eval_samples_per_second": 434.899,
-      "eval_steps_per_second": 14.13,
+      "eval_accuracy": 0.6895306859205776,
+      "eval_loss": 0.6575530171394348,
+      "eval_runtime": 0.6355,
+      "eval_samples_per_second": 435.845,
+      "eval_steps_per_second": 14.161,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6895306859205776,
-      "eval_loss": 0.6926298141479492,
-      "eval_runtime": 0.638,
-      "eval_samples_per_second": 434.136,
-      "eval_steps_per_second": 14.106,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 0.7819653749465942,
+      "eval_runtime": 0.6474,
+      "eval_samples_per_second": 427.864,
+      "eval_steps_per_second": 13.902,
       "step": 117
     }
   ],

run-1/checkpoint-117/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45289e81d0d437544c5e5fa7f0465860e7bb537a8d7f9f378dbccfa22dddc497
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-1/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:59de16aefb7c739dc85295eb32ffe296820b5495dde9f4da796c1750ca76265c
+oid sha256:a7a529cdb7fd45102ca4e5cb191f5b15052e08493cc3b511561fe9e04e22fa30
 size 437958648

run-1/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca11935a36e5b45c27d9d43e236fb37374825738a6cfcf1e8067832e395a14a0
+oid sha256:c36cbf4150836ab18a04c1215688af6efe06fb5929a0244861ffd82e52fd8f64
 size 876038394

run-1/checkpoint-156/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 117,
+  "best_global_step": 78,
   "best_metric": 0.6895306859205776,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-117",
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-78",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 156,
@@ -11,38 +11,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6462093862815884,
-      "eval_loss": 0.6229268908500671,
-      "eval_runtime": 0.6366,
-      "eval_samples_per_second": 435.104,
-      "eval_steps_per_second": 14.137,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6302457451820374,
+      "eval_runtime": 0.6387,
+      "eval_samples_per_second": 433.698,
+      "eval_steps_per_second": 14.091,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6570397111913358,
-      "eval_loss": 0.7122572064399719,
-      "eval_runtime": 0.6369,
-      "eval_samples_per_second": 434.899,
-      "eval_steps_per_second": 14.13,
+      "eval_accuracy": 0.6895306859205776,
+      "eval_loss": 0.6575530171394348,
+      "eval_runtime": 0.6355,
+      "eval_samples_per_second": 435.845,
+      "eval_steps_per_second": 14.161,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6895306859205776,
-      "eval_loss": 0.6926298141479492,
-      "eval_runtime": 0.638,
-      "eval_samples_per_second": 434.136,
-      "eval_steps_per_second": 14.106,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 0.7819653749465942,
+      "eval_runtime": 0.6474,
+      "eval_samples_per_second": 427.864,
+      "eval_steps_per_second": 13.902,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6678700361010831,
-      "eval_loss": 0.923632025718689,
-      "eval_runtime": 0.6386,
-      "eval_samples_per_second": 433.765,
-      "eval_steps_per_second": 14.093,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 1.0000327825546265,
+      "eval_runtime": 0.6479,
+      "eval_samples_per_second": 427.507,
+      "eval_steps_per_second": 13.89,
       "step": 156
     }
   ],

run-1/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45289e81d0d437544c5e5fa7f0465860e7bb537a8d7f9f378dbccfa22dddc497
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-1/checkpoint-195/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6fea5e445d62f876a4ed3b422a59511eb603de6a4f621ce33666aef477b3ab47
+oid sha256:4f5f943346824275e0a0240c4c5c24abddae8a7d72a96a13f1cfb452f98b188e
 size 437958648

run-1/checkpoint-195/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a29f7df0da93cfac0c506a1ac34015d84be9f6e108aed99df12dbf94cad3c4f
+oid sha256:66c84c6a45cf5fb5f95ce3b7f54adabe8e2019bcda952dbcb3aca1ace4fccb6d
 size 876038394

run-1/checkpoint-195/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 117,
+  "best_global_step": 78,
   "best_metric": 0.6895306859205776,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-117",
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-78",
   "epoch": 5.0,
   "eval_steps": 500,
   "global_step": 195,
@@ -11,47 +11,47 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6462093862815884,
-      "eval_loss": 0.6229268908500671,
-      "eval_runtime": 0.6366,
-      "eval_samples_per_second": 435.104,
-      "eval_steps_per_second": 14.137,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6302457451820374,
+      "eval_runtime": 0.6387,
+      "eval_samples_per_second": 433.698,
+      "eval_steps_per_second": 14.091,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6570397111913358,
-      "eval_loss": 0.7122572064399719,
-      "eval_runtime": 0.6369,
-      "eval_samples_per_second": 434.899,
-      "eval_steps_per_second": 14.13,
+      "eval_accuracy": 0.6895306859205776,
+      "eval_loss": 0.6575530171394348,
+      "eval_runtime": 0.6355,
+      "eval_samples_per_second": 435.845,
+      "eval_steps_per_second": 14.161,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6895306859205776,
-      "eval_loss": 0.6926298141479492,
-      "eval_runtime": 0.638,
-      "eval_samples_per_second": 434.136,
-      "eval_steps_per_second": 14.106,
+      "eval_accuracy": 0.6714801444043321,
+      "eval_loss": 0.7819653749465942,
+      "eval_runtime": 0.6474,
+      "eval_samples_per_second": 427.864,
+      "eval_steps_per_second": 13.902,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6678700361010831,
-      "eval_loss": 0.923632025718689,
-      "eval_runtime": 0.6386,
-      "eval_samples_per_second": 433.765,
-      "eval_steps_per_second": 14.093,
+      "eval_accuracy": 0.6859205776173285,
+      "eval_loss": 1.0000327825546265,
+      "eval_runtime": 0.6479,
+      "eval_samples_per_second": 427.507,
+      "eval_steps_per_second": 13.89,
       "step": 156
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6787003610108303,
-      "eval_loss": 1.1270627975463867,
-      "eval_runtime": 0.6426,
-      "eval_samples_per_second": 431.091,
-      "eval_steps_per_second": 14.007,
+      "eval_accuracy": 0.6750902527075813,
+      "eval_loss": 1.1014820337295532,
+      "eval_runtime": 0.637,
+      "eval_samples_per_second": 434.837,
+      "eval_steps_per_second": 14.128,
       "step": 195
     }
   ],

run-1/checkpoint-195/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45289e81d0d437544c5e5fa7f0465860e7bb537a8d7f9f378dbccfa22dddc497
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-1/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc59468e2ba140a6f6e62e3c90e1035f190056bdc9b499e74ecade2b7fa551e7
+oid sha256:4950ee24f30f03a15da573885ef4f5a550ec43401bd10183ed896ec546cb2b94
 size 437958648

run-1/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e92e24c71c1ca864f10dfed46043f5ec1d165eb8d2e762e99bf4ffdf75d5ea92
+oid sha256:454df7d9bd4efad84c1ff895b9d617d3ea94beba61c8912b16c69a42d94a254a
 size 876038394

run-1/checkpoint-39/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.6462093862815884,
+  "best_metric": 0.6570397111913358,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-39",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,11 +11,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6462093862815884,
-      "eval_loss": 0.6229268908500671,
-      "eval_runtime": 0.6366,
-      "eval_samples_per_second": 435.104,
-      "eval_steps_per_second": 14.137,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6302457451820374,
+      "eval_runtime": 0.6387,
+      "eval_samples_per_second": 433.698,
+      "eval_steps_per_second": 14.091,
       "step": 39
     }
   ],

run-1/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45289e81d0d437544c5e5fa7f0465860e7bb537a8d7f9f378dbccfa22dddc497
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-1/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f25fdea99ceb61fa6f36538a22ecbe5e6b141d77b47eced9ff8db8ba1d1865f5
+oid sha256:cf1e36fde00996e3f2b73551fcd782119ce7c5d0a6afaa777a1c8449968bf933
 size 437958648

run-1/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e9eaf725675e305ebee81c205aab615742a1d5d5ea0cb52c9a63839c25b9ce52
+oid sha256:6ea17d384de4432779b205f7807510f44ae5c1174daabaaf9f252bfed0a817a6
 size 876038394

run-1/checkpoint-78/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 78,
-  "best_metric": 0.6570397111913358,
+  "best_metric": 0.6895306859205776,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-1/checkpoint-78",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,20 +11,20 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6462093862815884,
-      "eval_loss": 0.6229268908500671,
-      "eval_runtime": 0.6366,
-      "eval_samples_per_second": 435.104,
-      "eval_steps_per_second": 14.137,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6302457451820374,
+      "eval_runtime": 0.6387,
+      "eval_samples_per_second": 433.698,
+      "eval_steps_per_second": 14.091,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6570397111913358,
-      "eval_loss": 0.7122572064399719,
-      "eval_runtime": 0.6369,
-      "eval_samples_per_second": 434.899,
-      "eval_steps_per_second": 14.13,
+      "eval_accuracy": 0.6895306859205776,
+      "eval_loss": 0.6575530171394348,
+      "eval_runtime": 0.6355,
+      "eval_samples_per_second": 435.845,
+      "eval_steps_per_second": 14.161,
       "step": 78
     }
   ],

run-1/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45289e81d0d437544c5e5fa7f0465860e7bb537a8d7f9f378dbccfa22dddc497
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-2/checkpoint-117/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3c31bba9c827ed96bf5007b706f71dcf275ccbba39e6462660ebd6f390f3b418
+oid sha256:908f5f76525e7b3ec579e59ddb340c506d961630672efe1f4f731a2a14813c5d
 size 437958648

run-2/checkpoint-117/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2fa2f50c183002b497d8eff62e340924eca2114cb4f05633f403e2d579c26815
+oid sha256:b61bb77c00282985cf555c2428aeed3ddb9dd975bf4e47ef8332af46e78eb903
 size 876038394

run-2/checkpoint-117/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 117,
-  "best_metric": 0.6823104693140795,
+  "best_metric": 0.6678700361010831,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-2/checkpoint-117",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -11,29 +11,29 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6137184115523465,
-      "eval_loss": 0.6360388994216919,
-      "eval_runtime": 0.6361,
-      "eval_samples_per_second": 435.481,
-      "eval_steps_per_second": 14.149,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6299930810928345,
+      "eval_runtime": 0.636,
+      "eval_samples_per_second": 435.504,
+      "eval_steps_per_second": 14.15,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6714801444043321,
-      "eval_loss": 0.6716197729110718,
-      "eval_runtime": 0.6428,
-      "eval_samples_per_second": 430.901,
-      "eval_steps_per_second": 14.0,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.701384961605072,
+      "eval_runtime": 0.6379,
+      "eval_samples_per_second": 434.232,
+      "eval_steps_per_second": 14.109,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6823104693140795,
-      "eval_loss": 0.7143523693084717,
-      "eval_runtime": 0.637,
-      "eval_samples_per_second": 434.86,
-      "eval_steps_per_second": 14.129,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.7389248609542847,
+      "eval_runtime": 0.6433,
+      "eval_samples_per_second": 430.624,
+      "eval_steps_per_second": 13.991,
       "step": 117
     }
   ],

run-2/checkpoint-117/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45289e81d0d437544c5e5fa7f0465860e7bb537a8d7f9f378dbccfa22dddc497
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-2/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5fed37e5d8a238a2fbec7088646b7472b85251e5892e70b206b827bca5016dfd
+oid sha256:7f1d4e1e1573d4c23e702a54e2c50b2d056566e3092df8f470ebf1561daf60bc
 size 437958648

run-2/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3714a6ead7ac5eccbea5eb7daa54c2a023c3eb7d8c59be9d06eba41131e222ee
+oid sha256:266d8385b6d55e9347537874355cb10632a22bf69f183d8631ea5e7ba89d3fb2
 size 876038394

run-2/checkpoint-156/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 117,
-  "best_metric": 0.6823104693140795,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-2/checkpoint-117",
+  "best_global_step": 156,
+  "best_metric": 0.6931407942238267,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-2/checkpoint-156",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 156,
@@ -11,38 +11,38 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6137184115523465,
-      "eval_loss": 0.6360388994216919,
-      "eval_runtime": 0.6361,
-      "eval_samples_per_second": 435.481,
-      "eval_steps_per_second": 14.149,
+      "eval_accuracy": 0.6570397111913358,
+      "eval_loss": 0.6299930810928345,
+      "eval_runtime": 0.636,
+      "eval_samples_per_second": 435.504,
+      "eval_steps_per_second": 14.15,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6714801444043321,
-      "eval_loss": 0.6716197729110718,
-      "eval_runtime": 0.6428,
-      "eval_samples_per_second": 430.901,
-      "eval_steps_per_second": 14.0,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.701384961605072,
+      "eval_runtime": 0.6379,
+      "eval_samples_per_second": 434.232,
+      "eval_steps_per_second": 14.109,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6823104693140795,
-      "eval_loss": 0.7143523693084717,
-      "eval_runtime": 0.637,
-      "eval_samples_per_second": 434.86,
-      "eval_steps_per_second": 14.129,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.7389248609542847,
+      "eval_runtime": 0.6433,
+      "eval_samples_per_second": 430.624,
+      "eval_steps_per_second": 13.991,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6714801444043321,
-      "eval_loss": 0.9579916000366211,
-      "eval_runtime": 0.6415,
-      "eval_samples_per_second": 431.805,
-      "eval_steps_per_second": 14.03,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.9925442337989807,
+      "eval_runtime": 0.6423,
+      "eval_samples_per_second": 431.287,
+      "eval_steps_per_second": 14.013,
       "step": 156
     }
   ],

run-2/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45289e81d0d437544c5e5fa7f0465860e7bb537a8d7f9f378dbccfa22dddc497
+oid sha256:638657d2294b16b6a018ef8c4921c705157459687a72f242b7f437400a9b1e8a
 size 5432

run-2/checkpoint-195/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:54b4075dd873a356f3ebb71e011e8fd11ffb92b5b7f8e6aba6b73f9877289451
+oid sha256:2e0a5f90545a9de75f3d982220c600765a5bcd444a868ce7fae7fb1a9113b668
 size 437958648