Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d6049f164c1f58adc56337d7065065dbec54afb91cdaafe09656ceb9f570a673
+oid sha256:323ace2db6bab1e6e929d5b595b5250337041d498d57a05f760f17c5e956f2e4
 size 437958648

run-0/checkpoint-156/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 78,
-  "best_metric": 0.4729241877256318,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-78",
+  "best_global_step": 156,
+  "best_metric": 0.631768953068592,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-156",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 156,
@@ -11,20 +11,20 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7100459933280945,
-      "eval_runtime": 0.6584,
-      "eval_samples_per_second": 420.731,
-      "eval_steps_per_second": 7.594,
+      "eval_accuracy": 0.49097472924187724,
+      "eval_loss": 0.7057711482048035,
+      "eval_runtime": 0.6548,
+      "eval_samples_per_second": 423.062,
+      "eval_steps_per_second": 7.636,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4693140794223827,
-      "eval_loss": 0.7023970484733582,
-      "eval_runtime": 0.6667,
-      "eval_samples_per_second": 415.458,
-      "eval_steps_per_second": 7.499,
+      "eval_accuracy": 0.631768953068592,
+      "eval_loss": 0.6515233516693115,
+      "eval_runtime": 0.6593,
+      "eval_samples_per_second": 420.154,
+      "eval_steps_per_second": 7.584,
       "step": 156
     }
   ],
@@ -49,9 +49,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "classifier_dropout": 0.4312273582787619,
-    "learning_rate": 2.007242870680699e-06,
-    "max_length": 256,
+    "classifier_dropout": 0.24469588923063107,
+    "learning_rate": 1.632929904930613e-05,
+    "max_length": 512,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }

run-0/checkpoint-234/trainer_state.json

@@ -1,7 +1,7 @@
 {
-  "best_global_step": 78,
-  "best_metric": 0.4729241877256318,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-78",
+  "best_global_step": 234,
+  "best_metric": 0.6425992779783394,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-234",
   "epoch": 3.0,
   "eval_steps": 500,
   "global_step": 234,
@@ -11,29 +11,29 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7100459933280945,
-      "eval_runtime": 0.6584,
-      "eval_samples_per_second": 420.731,
-      "eval_steps_per_second": 7.594,
+      "eval_accuracy": 0.49097472924187724,
+      "eval_loss": 0.7057711482048035,
+      "eval_runtime": 0.6548,
+      "eval_samples_per_second": 423.062,
+      "eval_steps_per_second": 7.636,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4693140794223827,
-      "eval_loss": 0.7023970484733582,
-      "eval_runtime": 0.6667,
-      "eval_samples_per_second": 415.458,
-      "eval_steps_per_second": 7.499,
+      "eval_accuracy": 0.631768953068592,
+      "eval_loss": 0.6515233516693115,
+      "eval_runtime": 0.6593,
+      "eval_samples_per_second": 420.154,
+      "eval_steps_per_second": 7.584,
       "step": 156
     },
     {
       "epoch": 3.0,
-      "eval_accuracy": 0.4693140794223827,
-      "eval_loss": 0.7006211876869202,
-      "eval_runtime": 0.6634,
-      "eval_samples_per_second": 417.544,
-      "eval_steps_per_second": 7.537,
+      "eval_accuracy": 0.6425992779783394,
+      "eval_loss": 0.6529138684272766,
+      "eval_runtime": 0.6631,
+      "eval_samples_per_second": 417.743,
+      "eval_steps_per_second": 7.54,
       "step": 234
     }
   ],
@@ -58,9 +58,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "classifier_dropout": 0.4312273582787619,
-    "learning_rate": 2.007242870680699e-06,
-    "max_length": 256,
+    "classifier_dropout": 0.24469588923063107,
+    "learning_rate": 1.632929904930613e-05,
+    "max_length": 512,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }

run-0/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:87b50ecc41734e36153aa45d5a491b8ab4c441473c3e75910abe6431fe84eef7
+oid sha256:323ace2db6bab1e6e929d5b595b5250337041d498d57a05f760f17c5e956f2e4
 size 437958648

run-0/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e5b3e229c210ce1d0ad666e76892a5e35259d9d21122f18788cd8dcc65010599
+oid sha256:371c0728bdbc0eb2af5f5259fe6fb2c1afd86a146991072227290489d01c8e3c
 size 876038394

run-0/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e796b5f158f149ebbb5393a6a5926a9cb01ce01c4f1f213d6b293813f37644c1
+oid sha256:5c1af07f2874294a244b6f46adb4de7c26a7d29b7c2dc41f6701bbfa466035e7
 size 1064

run-0/checkpoint-78/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 78,
-  "best_metric": 0.4729241877256318,
+  "best_metric": 0.49097472924187724,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_3/run-0/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,11 +11,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7100459933280945,
-      "eval_runtime": 0.6584,
-      "eval_samples_per_second": 420.731,
-      "eval_steps_per_second": 7.594,
+      "eval_accuracy": 0.49097472924187724,
+      "eval_loss": 0.7057711482048035,
+      "eval_runtime": 0.6548,
+      "eval_samples_per_second": 423.062,
+      "eval_steps_per_second": 7.636,
       "step": 78
     }
   ],
@@ -40,9 +40,9 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "classifier_dropout": 0.4312273582787619,
-    "learning_rate": 2.007242870680699e-06,
-    "max_length": 256,
+    "classifier_dropout": 0.24469588923063107,
+    "learning_rate": 1.632929904930613e-05,
+    "max_length": 512,
     "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }

run-0/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4000a623a24e954176bac1dfc31b929c06df0ac83251a2e392753a57a3145fa8
+oid sha256:17bcef98605aae5d137d7d5a84cac1f1e0091c73c323300da1659a9ef388f310
 size 5432

runs/Apr07_10-59-04_d0bdfe9fd409/events.out.tfevents.1744023700.d0bdfe9fd409.3962.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:407c546b1094eaeba412107ac6a0f9b0e01223d5286ca74ef7d42c5ed74f1eb1
+size 5776

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:353fc9b250b05a6892f466799a9d7f0f589218dd504abd1d311575b8f27dd725
+oid sha256:17bcef98605aae5d137d7d5a84cac1f1e0091c73c323300da1659a9ef388f310
 size 5432