Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:77a1db500591369d0e6d7f7a2a040bfa60647f0b57ba372d76c961375a165f87
+oid sha256:3725490b1a5db5a91728fc856c3f372b25e016c745e60f409d848cf7bd9339e8
 size 437958648

run-5/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ecb2109a845634e551974a8344e52f12e5c29e0565d51febc945d367a3f8bf1a
+oid sha256:3725490b1a5db5a91728fc856c3f372b25e016c745e60f409d848cf7bd9339e8
 size 437958648

run-5/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:995a5267731dabb07df3994605c3a0291c8864665fb351af57ba1e5b848f4c93
+oid sha256:2842dd36b6e6afb95bb505523df80fd752e67f98805c707bbaab99a551552636
 size 876038394

run-5/checkpoint-39/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598448aee663bd69feb15b730dcfefd83bf321a2bd53ece879436b0e2e85c889
+oid sha256:69ff60f83fb79c414d73b8461c5acbe4e8df2acc6bb80e834bfe13d054326f03
 size 1064

run-5/checkpoint-39/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.5270758122743683,
+  "best_metric": 0.6462093862815884,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-5/checkpoint-39",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,18 +11,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.691849946975708,
-      "eval_runtime": 0.6374,
-      "eval_samples_per_second": 434.552,
-      "eval_steps_per_second": 14.119,
+      "eval_accuracy": 0.6462093862815884,
+      "eval_loss": 0.6357454061508179,
+      "eval_runtime": 0.6369,
+      "eval_samples_per_second": 434.892,
+      "eval_steps_per_second": 14.13,
       "step": 39
     }
   ],
   "logging_steps": 500,
-  "max_steps": 195,
+  "max_steps": 273,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 7,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -41,9 +41,9 @@
   "trial_name": null,
   "trial_params": {
     "dropout_rate": 0.0134,
-    "learning_rate": 0.05,
+    "learning_rate": 0.0001,
     "max_length": 32,
-    "num_train_epochs": 5,
+    "num_train_epochs": 7,
     "per_device_train_batch_size": 64
   }
 }

run-5/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
+oid sha256:a31e11225076494526a7157d904c355e54980b239c63149e5cb6bd46c8e0ca9c
 size 5432

run-6/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57afd1d5d2aaf3f81e921aa5e455611bb98a78a16b703b1dff9007f0be161f86
+oid sha256:1007ed1f776c15647f411508ab036b44ad7b2123469c470670ff33e02d9dc364
 size 437958648

run-6/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5432988eb429de2751abf6f0b1b537a933e9f550b7fc9fa91f1e0cb29fbeb807
+oid sha256:c09e838fdd2827e82f1df4b72f031d541828f553857a633823dae28205b244bf
 size 876038394

run-6/checkpoint-39/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:598448aee663bd69feb15b730dcfefd83bf321a2bd53ece879436b0e2e85c889
+oid sha256:7e78d5e09340c0681df725fbe1595e157ca67a75816fc394229ff49b11a9add2
 size 1064

run-6/checkpoint-39/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.5270758122743683,
+  "best_metric": 0.6389891696750902,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-6/checkpoint-39",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,18 +11,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5270758122743683,
-      "eval_loss": 0.6918498277664185,
-      "eval_runtime": 0.638,
-      "eval_samples_per_second": 434.177,
-      "eval_steps_per_second": 14.107,
+      "eval_accuracy": 0.6389891696750902,
+      "eval_loss": 0.6395406723022461,
+      "eval_runtime": 0.6403,
+      "eval_samples_per_second": 432.598,
+      "eval_steps_per_second": 14.056,
       "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": 0.05,
+    "learning_rate": 0.0001,
     "max_length": 32,
-    "num_train_epochs": 5,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 64
   }
 }

run-6/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e99cfd8ed47c6deda5dd532724592f1d8997b2921756d80eddbdaca287b3e257
+oid sha256:f321d5971ff6ba91e19e8f1139788c24314fbde22665abea04b8ef44596c5939
 size 5432

runs/Apr04_16-57-59_5bdb2d0e2198/events.out.tfevents.1743793535.5bdb2d0e2198.1206.42

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:901b8d8091e8f5a20af1c9daf281b6febaac434bcbafdc4444aa4237dbc971ec
+size 5720

training_args.bin

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