Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f4ace71896a9078bb85d12a4f044a24cfe91135c17ebedb7cf99f4ab7c758e78
+oid sha256:051cea0219c05c88062053d4125e94a53939800f3ac2ef703a3ed1c1e6511cbf
 size 437958648

run-5/checkpoint-117/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-5/checkpoint-117/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:afa93c539d17de4e4c835ea90e2c01f86af704ffd3c5182d3d7aa7bf69b10435
+oid sha256:98cc438e7dfc5491ae782202f415d63e4e2f7c257182591919e76cb9e6817f3b
 size 437958648

run-5/checkpoint-117/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6ab06a86417542a7676443f96d4408587af31d531846bca82c6a23524b3e879c
+oid sha256:cb4a8fb16dfe5b553a0b64713d3e0db0abf908945279f6aed14c6bec3ec5f47d
 size 876038394

run-5/checkpoint-117/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:39e50c13fe1c1e56ebdf938934fca6b189ecf22fc1031d579d80db74bd8923b6
+oid sha256:d6ae0df3dcc77291d5111438baa3e28157dd68485e127efa4307b87edaaaace0
 size 1064

run-5/checkpoint-117/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 117,
-  "best_metric": 0.6750902527075813,
+  "best_metric": 0.6462093862815884,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-117",
   "epoch": 3.0,
   "eval_steps": 500,
@@ -11,36 +11,36 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6101083032490975,
-      "eval_loss": 0.6465224027633667,
-      "eval_runtime": 0.637,
-      "eval_samples_per_second": 434.863,
-      "eval_steps_per_second": 14.129,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6697127819061279,
+      "eval_runtime": 0.6455,
+      "eval_samples_per_second": 429.108,
+      "eval_steps_per_second": 13.942,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6498194945848376,
-      "eval_loss": 0.657070517539978,
-      "eval_runtime": 0.6416,
-      "eval_samples_per_second": 431.735,
-      "eval_steps_per_second": 14.027,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.6653470993041992,
+      "eval_runtime": 0.6465,
+      "eval_samples_per_second": 428.491,
+      "eval_steps_per_second": 13.922,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.7824105620384216,
-      "eval_runtime": 0.6466,
-      "eval_samples_per_second": 428.363,
-      "eval_steps_per_second": 13.918,
+      "eval_accuracy": 0.6462093862815884,
+      "eval_loss": 0.6471791863441467,
+      "eval_runtime": 0.6482,
+      "eval_samples_per_second": 427.345,
+      "eval_steps_per_second": 13.885,
       "step": 117
     }
   ],
   "logging_steps": 500,
-  "max_steps": 585,
+  "max_steps": 195,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -58,8 +58,10 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.233998610137002e-05,
-    "num_train_epochs": 15,
+    "dropout_rate": 0.0134,
+    "learning_rate": 2.6344508518520418e-05,
+    "max_length": 32,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 64
   }
 }

run-5/checkpoint-117/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7932936da5fcd44c43cf1dc4467d26386476c8063b02e88748f3b124aa73ff0a
+oid sha256:7917deeac7fb94209a1ee4626c629b8767972d103256b1daf4cf2460cf8fc397
 size 5432

run-5/checkpoint-156/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-5/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a0d564ad8d90a177a6d9d90c29a505c106952f5ac26dc4993f79e2520f08289
+oid sha256:699cb5a8a2b395bae13740d67cad52a787e452716c8bce97126d62fcbbd448f4
 size 437958648

run-5/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e8ceee1726b7ec07fa100315c302249e77411c22dffb7cd80805a494160b7d7
+oid sha256:a2c85ecce3ad489617c49ac805b32922fa87bc1e623e04d387ce64d911ccadd5
 size 876038394

run-5/checkpoint-156/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7060fc5d4e23b482a1ae40b7607cfd518cf6aa7f51a50b8f5d73553abc207ef1
+oid sha256:207ce3a72ea6f8b5696a7d7d9bbd3121caaa776bb13247589131051d1e72878d
 size 1064

run-5/checkpoint-156/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 156,
-  "best_metric": 0.6895306859205776,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-156",
+  "best_global_step": 117,
+  "best_metric": 0.6462093862815884,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-117",
   "epoch": 4.0,
   "eval_steps": 500,
   "global_step": 156,
@@ -11,45 +11,45 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6101083032490975,
-      "eval_loss": 0.6465224027633667,
-      "eval_runtime": 0.637,
-      "eval_samples_per_second": 434.863,
-      "eval_steps_per_second": 14.129,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6697127819061279,
+      "eval_runtime": 0.6455,
+      "eval_samples_per_second": 429.108,
+      "eval_steps_per_second": 13.942,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6498194945848376,
-      "eval_loss": 0.657070517539978,
-      "eval_runtime": 0.6416,
-      "eval_samples_per_second": 431.735,
-      "eval_steps_per_second": 14.027,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.6653470993041992,
+      "eval_runtime": 0.6465,
+      "eval_samples_per_second": 428.491,
+      "eval_steps_per_second": 13.922,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.7824105620384216,
-      "eval_runtime": 0.6466,
-      "eval_samples_per_second": 428.363,
-      "eval_steps_per_second": 13.918,
+      "eval_accuracy": 0.6462093862815884,
+      "eval_loss": 0.6471791863441467,
+      "eval_runtime": 0.6482,
+      "eval_samples_per_second": 427.345,
+      "eval_steps_per_second": 13.885,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6895306859205776,
-      "eval_loss": 0.9610873460769653,
-      "eval_runtime": 0.6401,
-      "eval_samples_per_second": 432.753,
-      "eval_steps_per_second": 14.061,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.7032743692398071,
+      "eval_runtime": 0.6412,
+      "eval_samples_per_second": 431.983,
+      "eval_steps_per_second": 14.036,
       "step": 156
     }
   ],
   "logging_steps": 500,
-  "max_steps": 585,
+  "max_steps": 195,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -67,8 +67,10 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.233998610137002e-05,
-    "num_train_epochs": 15,
+    "dropout_rate": 0.0134,
+    "learning_rate": 2.6344508518520418e-05,
+    "max_length": 32,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 64
   }
 }

run-5/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7932936da5fcd44c43cf1dc4467d26386476c8063b02e88748f3b124aa73ff0a
+oid sha256:7917deeac7fb94209a1ee4626c629b8767972d103256b1daf4cf2460cf8fc397
 size 5432

run-5/checkpoint-195/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-5/checkpoint-195/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e3f5c101faffc3ad2a2de43f15f5f574e0e7f6c6648e0ad49723a7536dbb14bb
+oid sha256:9d690aa49d748bed346152dd8d411d500271814260a9e22c48bbe63faf711e37
 size 437958648

run-5/checkpoint-195/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:64f96ee7345f08ea308b21890dade3119b61536036f4b00b5ebc5eb017acf794
+oid sha256:a8009bbaeb8a151943fc432bc1dcdc737d596f0ebb50de8d48262f8172414dc5
 size 876038394

run-5/checkpoint-195/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26ec8bc8f16446093ff5e1a4225d1b4125110033a6f685c38240169766c528d8
+oid sha256:e7ca426136780e5123882a2de71f9961eb1444076226a5a757f36e08f1a88f24
 size 1064

run-5/checkpoint-195/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 156,
-  "best_metric": 0.6895306859205776,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-156",
+  "best_global_step": 195,
+  "best_metric": 0.6678700361010831,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-195",
   "epoch": 5.0,
   "eval_steps": 500,
   "global_step": 195,
@@ -11,54 +11,54 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6101083032490975,
-      "eval_loss": 0.6465224027633667,
-      "eval_runtime": 0.637,
-      "eval_samples_per_second": 434.863,
-      "eval_steps_per_second": 14.129,
+      "eval_accuracy": 0.6245487364620939,
+      "eval_loss": 0.6697127819061279,
+      "eval_runtime": 0.6455,
+      "eval_samples_per_second": 429.108,
+      "eval_steps_per_second": 13.942,
       "step": 39
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6498194945848376,
-      "eval_loss": 0.657070517539978,
-      "eval_runtime": 0.6416,
-      "eval_samples_per_second": 431.735,
-      "eval_steps_per_second": 14.027,
+      "eval_accuracy": 0.6173285198555957,
+      "eval_loss": 0.6653470993041992,
+      "eval_runtime": 0.6465,
+      "eval_samples_per_second": 428.491,
+      "eval_steps_per_second": 13.922,
       "step": 78
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.6750902527075813,
-      "eval_loss": 0.7824105620384216,
-      "eval_runtime": 0.6466,
-      "eval_samples_per_second": 428.363,
-      "eval_steps_per_second": 13.918,
+      "eval_accuracy": 0.6462093862815884,
+      "eval_loss": 0.6471791863441467,
+      "eval_runtime": 0.6482,
+      "eval_samples_per_second": 427.345,
+      "eval_steps_per_second": 13.885,
       "step": 117
     },
     {
       "epoch": 4.0,
-      "eval_accuracy": 0.6895306859205776,
-      "eval_loss": 0.9610873460769653,
-      "eval_runtime": 0.6401,
-      "eval_samples_per_second": 432.753,
-      "eval_steps_per_second": 14.061,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.7032743692398071,
+      "eval_runtime": 0.6412,
+      "eval_samples_per_second": 431.983,
+      "eval_steps_per_second": 14.036,
       "step": 156
     },
     {
       "epoch": 5.0,
-      "eval_accuracy": 0.6642599277978339,
-      "eval_loss": 1.4177204370498657,
-      "eval_runtime": 0.6402,
-      "eval_samples_per_second": 432.689,
-      "eval_steps_per_second": 14.058,
+      "eval_accuracy": 0.6678700361010831,
+      "eval_loss": 0.7250702977180481,
+      "eval_runtime": 0.6441,
+      "eval_samples_per_second": 430.034,
+      "eval_steps_per_second": 13.972,
       "step": 195
     }
   ],
   "logging_steps": 500,
-  "max_steps": 585,
+  "max_steps": 195,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 15,
+  "num_train_epochs": 5,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -67,7 +67,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -76,8 +76,10 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 5.233998610137002e-05,
-    "num_train_epochs": 15,
+    "dropout_rate": 0.0134,
+    "learning_rate": 2.6344508518520418e-05,
+    "max_length": 32,
+    "num_train_epochs": 5,
     "per_device_train_batch_size": 64
   }
 }

run-5/checkpoint-195/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7932936da5fcd44c43cf1dc4467d26386476c8063b02e88748f3b124aa73ff0a
+oid sha256:7917deeac7fb94209a1ee4626c629b8767972d103256b1daf4cf2460cf8fc397
 size 5432

runs/Apr03_17-48-13_677fb5893cf0/events.out.tfevents.1743717028.677fb5893cf0.2669.36

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:029604126a877beb35be813d3848bf3ee597e1d61f07154eb95bf5fd6edd8388
+size 5418

runs/Apr03_17-48-13_677fb5893cf0/events.out.tfevents.1743717051.677fb5893cf0.2669.37

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9c0e4a9b8c72b580f1ad1dccd16168c5aec953ece2a97c39a61f3569d00a5f0
+size 5419

runs/Apr03_17-48-13_677fb5893cf0/events.out.tfevents.1743717074.677fb5893cf0.2669.38

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:696e557175f4f5a9b7e35164503ea3c1cfde6b7e2eacc7ab0c8eca8dc5acce45
+size 5418

runs/Apr03_17-48-13_677fb5893cf0/events.out.tfevents.1743717096.677fb5893cf0.2669.39

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb808169465a1f4417beaab7ae068a37d2e58ebc800e5235990a788649802789
+size 5418

runs/Apr03_17-48-13_677fb5893cf0/events.out.tfevents.1743717372.677fb5893cf0.2669.40

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f525cc7da0d341de466be931de19e02d9d1f9f8811c6f660f2721fc11fbd78a
+size 7052

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7917deeac7fb94209a1ee4626c629b8767972d103256b1daf4cf2460cf8fc397
+oid sha256:fbea049dc6efc74c0d7885710ece1a927b118d7bd83967aa580756e6dd000b3e
 size 5432