Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e8aee2bd24c0dea4bf13c620632c18784ce5098d73ebd6979aca98a8e7454614
+oid sha256:1d8280328f4d43f1f2d7581b787c926962295e203f4d9ea1bfa8935f254377b1
 size 437958648

run-4/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0b6b16f7a7da0900019e1f77cb501fd89b6d9d5c43023285cb903da7c01cf169
+oid sha256:1d8280328f4d43f1f2d7581b787c926962295e203f4d9ea1bfa8935f254377b1
 size 437958648

run-4/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f9a56467b16d1806d3b70531d42690db7a47401c588851416339cc442c88df4b
+oid sha256:9d3c57dbd765e35731903cc26e90742255e6b4996563bcba5acc54ab9488b3d6
 size 876038394

run-4/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4c04c957a5092cf8e4865d74822ca2280cf48e9ccdf02776ba6a55b3e20ebcc8
+oid sha256:d7c0d61a4d7b54c14c2d07caf6fb790e04a1a6e8f1defea5de33fab60c1967e8
 size 1064

run-4/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4657039711191336,
+  "best_metric": 0.4620938628158845,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-4/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.6980094909667969,
-      "eval_runtime": 0.6946,
-      "eval_samples_per_second": 398.789,
-      "eval_steps_per_second": 12.957,
+      "eval_accuracy": 0.4620938628158845,
+      "eval_loss": 0.7019249200820923,
+      "eval_runtime": 0.7457,
+      "eval_samples_per_second": 371.487,
+      "eval_steps_per_second": 12.07,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 78,
+  "max_steps": 234,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -30,7 +30,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
@@ -39,10 +39,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.41500781489341676,
-    "learning_rate": 6.349040683142055e-06,
+    "dropout_rate": 0.30108518728143985,
+    "learning_rate": 3.148408599279401e-06,
     "max_seq_length": 32,
-    "num_train_epochs": 1,
+    "num_train_epochs": 3,
     "per_device_train_batch_size": 32
   }
 }

run-4/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:049df9dca24175056e76249fdce3b716c8df0248f13e43515a706585cada19d6
+oid sha256:3cd6a22d1663472e27c1914e551020d7e8fa7404f4c9888164cdfe945cc8b090
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:15b59439e23e3224d6e1f41d9fefdc583893f2564119f4cf343124dc3da09ac5
+oid sha256:3cd6a22d1663472e27c1914e551020d7e8fa7404f4c9888164cdfe945cc8b090
 size 5240