Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aca61fdfa6931d9f3560deed6c44b32707d9fab0df28c139275244ffa76072d8
+oid sha256:77a1db500591369d0e6d7f7a2a040bfa60647f0b57ba372d76c961375a165f87
 size 437958648

run-3/checkpoint-195/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ef7a96a393735b725e146d321a6f6dc41c06d36d33265d8af6aa586197251a1
+oid sha256:3cc6a53b787dca1a8fd5968d7713e0bdc4cb03fe0b0ffc027a1a38f588787720
 size 437958648

run-3/checkpoint-195/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a51d64cc22fb9d505be4305a4ace9b12a66a9968ab937f17a9dd23e995240cb1
+oid sha256:1b168f2d67bf89ef6265a4d7d4988ef9ae0e5835e4fda333d485b338efd59518
 size 876038394

run-3/checkpoint-195/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:675f1463f743ae2eb6e82532e7f83c82034a00c6beaef47454d1a0f0ab6ea1d0
+oid sha256:c481cea2d473218259260c74bb2a405cbdfc1493d220688497623f197c9473f8
 size 1064

run-3/checkpoint-195/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a54d1e9a16102072f117ac90cba2c8de9da1d67b974b29749928b6494fcb115
+oid sha256:a31e11225076494526a7157d904c355e54980b239c63149e5cb6bd46c8e0ca9c
 size 5432

run-3/checkpoint-234/config.json

@@ -19,7 +19,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.50.2",
+  "transformers_version": "4.50.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-3/checkpoint-234/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:45cd8daabde69408f195fd28e4b853be07e30a9106ff1566429456998cbc8c92
+oid sha256:90ec478c4f4d76515e1d41b69e27e91521687063de38e4906930256c18c4fc7d
 size 437958648

run-3/checkpoint-234/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:46bd481d79c4c5ae8a6d5a200655bf1640484b70d772a9745a261a01ca30e715
+oid sha256:40ad820918273930bc861db241dff5536746b9d30d16746fcfcb7ef7dee31a0d
 size 876038394

run-3/checkpoint-234/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b778235f2c6be8dc1444821cb28b8aa66138c940d71270633f893f1e9dcc897f
+oid sha256:1fafdc9d67bc99334116e96a009c77a5be4c802d83fd0d02e557b73626be589e
 size 1064

run-3/checkpoint-234/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 234,
-  "best_metric": 0.7003610108303249,
+  "best_metric": 0.7111913357400722,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-3/checkpoint-234",
   "epoch": 6.0,
   "eval_steps": 500,
@@ -11,63 +11,63 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6028880866425993,
-      "eval_loss": 0.6455268263816833,
-      "eval_runtime": 0.6422,
-      "eval_samples_per_second": 431.339,
-      "eval_steps_per_second": 14.015,
+      "eval_accuracy": 0.5992779783393501,
+      "eval_loss": 0.6721181869506836,
+      "eval_runtime": 0.6383,
+      "eval_samples_per_second": 433.997,
+      "eval_steps_per_second": 14.101,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5992779783393501,
-      "eval_loss": 0.6891809701919556,
-      "eval_runtime": 0.6455,
-      "eval_samples_per_second": 429.15,
-      "eval_steps_per_second": 13.944,
+      "eval_accuracy": 0.628158844765343,
+      "eval_loss": 0.6599582433700562,
+      "eval_runtime": 0.636,
+      "eval_samples_per_second": 435.52,
+      "eval_steps_per_second": 14.15,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6425992779783394,
-      "eval_loss": 0.8288224935531616,
-      "eval_runtime": 0.6442,
-      "eval_samples_per_second": 429.982,
-      "eval_steps_per_second": 13.971,
+      "eval_accuracy": 0.6389891696750902,
+      "eval_loss": 0.7105341553688049,
+      "eval_runtime": 0.6384,
+      "eval_samples_per_second": 433.913,
+      "eval_steps_per_second": 14.098,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6823104693140795,
-      "eval_loss": 0.9376588463783264,
-      "eval_runtime": 0.6392,
-      "eval_samples_per_second": 433.358,
-      "eval_steps_per_second": 14.08,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.9099717140197754,
+      "eval_runtime": 0.6379,
+      "eval_samples_per_second": 434.226,
+      "eval_steps_per_second": 14.108,
       "step": 156
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6642599277978339,
-      "eval_loss": 1.4554625749588013,
-      "eval_runtime": 0.6427,
-      "eval_samples_per_second": 430.994,
-      "eval_steps_per_second": 14.003,
+      "eval_accuracy": 0.6353790613718412,
+      "eval_loss": 1.4261176586151123,
+      "eval_runtime": 0.6382,
+      "eval_samples_per_second": 434.009,
+      "eval_steps_per_second": 14.101,
       "step": 195
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.7003610108303249,
-      "eval_loss": 1.4293187856674194,
-      "eval_runtime": 0.6389,
-      "eval_samples_per_second": 433.574,
-      "eval_steps_per_second": 14.087,
+      "eval_accuracy": 0.7111913357400722,
+      "eval_loss": 1.1338996887207031,
+      "eval_runtime": 0.6397,
+      "eval_samples_per_second": 432.989,
+      "eval_steps_per_second": 14.068,
       "step": 234
     }
   ],
   "logging_steps": 500,
-  "max_steps": 585,
+  "max_steps": 273,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 7,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -85,8 +85,10 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.296158019829305e-05,
-    "num_train_epochs": 15,
+    "dropout_rate": 0.0134,
+    "learning_rate": 0.0001,
+    "max_length": 32,
+    "num_train_epochs": 7,
     "per_device_train_batch_size": 64
   }
 }

run-3/checkpoint-234/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d7cd6cde9b143872fea17834d1d37a574e764e020936e4ec84f9f6dbbfb1fa
+oid sha256:a31e11225076494526a7157d904c355e54980b239c63149e5cb6bd46c8e0ca9c
 size 5432

run-3/checkpoint-273/config.json

@@ -19,7 +19,7 @@
   "position_embedding_type": "absolute",
   "problem_type": "single_label_classification",
   "torch_dtype": "float32",
-  "transformers_version": "4.50.2",
+  "transformers_version": "4.50.3",
   "type_vocab_size": 2,
   "use_cache": true,
   "vocab_size": 30522

run-3/checkpoint-273/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8ee8fbbf2add9264bfc97241fe76a6afcfd64b6d4a0a25f818965ce869e48f5
+oid sha256:79cc0c387248a83368ee577ad22685e93e409035a861137d8d04429041b4b883
 size 437958648

run-3/checkpoint-273/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976f65a06b1402963db90008dbc5b7687e68793f8442fa5784a241a50182c59b
+oid sha256:64351c72515b55bf2c716320f06d028c08f8d27fadac655d08598f0605935b74
 size 876038394

run-3/checkpoint-273/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd47ea1d94a19fef46f4580027106ea139e893819b7396cf1b81508f158fb854
+oid sha256:e3c171ceab3b90de030417936fdba57019f3ded92bc954fc958883932ab95e05
 size 1064

run-3/checkpoint-273/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 234,
-  "best_metric": 0.7003610108303249,
+  "best_metric": 0.7111913357400722,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-3/checkpoint-234",
   "epoch": 7.0,
   "eval_steps": 500,
@@ -11,72 +11,72 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6028880866425993,
-      "eval_loss": 0.6455268263816833,
-      "eval_runtime": 0.6422,
-      "eval_samples_per_second": 431.339,
-      "eval_steps_per_second": 14.015,
+      "eval_accuracy": 0.5992779783393501,
+      "eval_loss": 0.6721181869506836,
+      "eval_runtime": 0.6383,
+      "eval_samples_per_second": 433.997,
+      "eval_steps_per_second": 14.101,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.5992779783393501,
-      "eval_loss": 0.6891809701919556,
-      "eval_runtime": 0.6455,
-      "eval_samples_per_second": 429.15,
-      "eval_steps_per_second": 13.944,
+      "eval_accuracy": 0.628158844765343,
+      "eval_loss": 0.6599582433700562,
+      "eval_runtime": 0.636,
+      "eval_samples_per_second": 435.52,
+      "eval_steps_per_second": 14.15,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6425992779783394,
-      "eval_loss": 0.8288224935531616,
-      "eval_runtime": 0.6442,
-      "eval_samples_per_second": 429.982,
-      "eval_steps_per_second": 13.971,
+      "eval_accuracy": 0.6389891696750902,
+      "eval_loss": 0.7105341553688049,
+      "eval_runtime": 0.6384,
+      "eval_samples_per_second": 433.913,
+      "eval_steps_per_second": 14.098,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6823104693140795,
-      "eval_loss": 0.9376588463783264,
-      "eval_runtime": 0.6392,
-      "eval_samples_per_second": 433.358,
-      "eval_steps_per_second": 14.08,
+      "eval_accuracy": 0.6931407942238267,
+      "eval_loss": 0.9099717140197754,
+      "eval_runtime": 0.6379,
+      "eval_samples_per_second": 434.226,
+      "eval_steps_per_second": 14.108,
       "step": 156
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6642599277978339,
-      "eval_loss": 1.4554625749588013,
-      "eval_runtime": 0.6427,
-      "eval_samples_per_second": 430.994,
-      "eval_steps_per_second": 14.003,
+      "eval_accuracy": 0.6353790613718412,
+      "eval_loss": 1.4261176586151123,
+      "eval_runtime": 0.6382,
+      "eval_samples_per_second": 434.009,
+      "eval_steps_per_second": 14.101,
       "step": 195
     },
     {
       "epoch": 6.0,
-      "eval_accuracy": 0.7003610108303249,
-      "eval_loss": 1.4293187856674194,
-      "eval_runtime": 0.6389,
-      "eval_samples_per_second": 433.574,
-      "eval_steps_per_second": 14.087,
+      "eval_accuracy": 0.7111913357400722,
+      "eval_loss": 1.1338996887207031,
+      "eval_runtime": 0.6397,
+      "eval_samples_per_second": 432.989,
+      "eval_steps_per_second": 14.068,
       "step": 234
     },
     {
       "epoch": 7.0,
-      "eval_accuracy": 0.6895306859205776,
-      "eval_loss": 1.7040148973464966,
-      "eval_runtime": 0.6386,
-      "eval_samples_per_second": 433.742,
-      "eval_steps_per_second": 14.093,
+      "eval_accuracy": 0.7075812274368231,
+      "eval_loss": 1.221158742904663,
+      "eval_runtime": 0.6395,
+      "eval_samples_per_second": 433.117,
+      "eval_steps_per_second": 14.072,
       "step": 273
     }
   ],
   "logging_steps": 500,
-  "max_steps": 585,
+  "max_steps": 273,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 7,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -85,7 +85,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -94,8 +94,10 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.296158019829305e-05,
-    "num_train_epochs": 15,
+    "dropout_rate": 0.0134,
+    "learning_rate": 0.0001,
+    "max_length": 32,
+    "num_train_epochs": 7,
     "per_device_train_batch_size": 64
   }
 }

run-3/checkpoint-273/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e1d7cd6cde9b143872fea17834d1d37a574e764e020936e4ec84f9f6dbbfb1fa
+oid sha256:a31e11225076494526a7157d904c355e54980b239c63149e5cb6bd46c8e0ca9c
 size 5432

run-4/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3fb45e76350b9c813d1fad11ba64ae690635e5381b8ba1aee7be80f6d2f22e49
+oid sha256:77a1db500591369d0e6d7f7a2a040bfa60647f0b57ba372d76c961375a165f87
 size 437958648

run-4/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3b3aac8275d08ddfa154a8eb29c8aca0ad27c54705712bd55a1bec7871c63a0
+oid sha256:f29b3441008d4a261724b0ded94ccf789ae193c4bc68c832853899208c5537b6
 size 876038394

run-4/checkpoint-39/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7a7bd3ac89cc6f989a2b823bb8bde976a5355b84b9a51281486645c8df8e47b9
+oid sha256:7e78d5e09340c0681df725fbe1595e157ca67a75816fc394229ff49b11a9add2
 size 1064

run-4/checkpoint-39/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.4729241877256318,
+  "best_metric": 0.6389891696750902,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-4/checkpoint-39",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,18 +11,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.6936286687850952,
-      "eval_runtime": 0.6353,
-      "eval_samples_per_second": 436.012,
-      "eval_steps_per_second": 14.166,
+      "eval_accuracy": 0.6389891696750902,
+      "eval_loss": 0.6387895345687866,
+      "eval_runtime": 0.6355,
+      "eval_samples_per_second": 435.878,
+      "eval_steps_per_second": 14.162,
       "step": 39
     }
   ],
   "logging_steps": 500,
-  "max_steps": 195,
+  "max_steps": 39,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -31,7 +31,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -41,9 +41,9 @@
   "trial_name": null,
   "trial_params": {
     "dropout_rate": 0.0134,
-    "learning_rate": 0.0005,
+    "learning_rate": 0.0001,
     "max_length": 32,
-    "num_train_epochs": 5,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 64
   }
 }

run-4/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9370cb350f581377d77550ad98e0d71f735e273933b1b105b3b4564570e10207
+oid sha256:f321d5971ff6ba91e19e8f1139788c24314fbde22665abea04b8ef44596c5939
 size 5432

runs/Apr04_16-57-59_5bdb2d0e2198/events.out.tfevents.1743793224.5bdb2d0e2198.1206.41

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5885f3f2919be7322a7254bcb7aea8ccb82698c5348ebbca622714ab941e1a15
+size 5751

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a31e11225076494526a7157d904c355e54980b239c63149e5cb6bd46c8e0ca9c
+oid sha256:f321d5971ff6ba91e19e8f1139788c24314fbde22665abea04b8ef44596c5939
 size 5432