Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:070e3569eedb202585d4b6fab4bb8f15975f8188dacf2653cde9625fee95eeee
+oid sha256:4f9c5f4a099dfe9bc24db55b3a5ffe4c296f2f622fbe1f0c399e39a628ab0020
 size 437958648

run-7/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1764b411aa7222c07ffe81e7c2146ce5d5865aad2f0edddc2cf2d7baaf830015
+oid sha256:4f9c5f4a099dfe9bc24db55b3a5ffe4c296f2f622fbe1f0c399e39a628ab0020
 size 437958648

run-7/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:996511b64ca6cc3d937b971437c02d996eed7e47bf88c74dae36a47ab4d25ec0
+oid sha256:3c3a54ec63b21ea0c0a27ea676757dead245425c66768407874c5532829341ad
 size 876038394

run-7/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac8d8adba8bfb15032dcd6a856cc3393af1fecdc12d6d97b03ac4e1911da56d1
+oid sha256:c31d3f31f8e450c2f2857d64932d4455ef8adf3dd9c86e4939da4e4b753dd687
 size 1064

run-7/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5812274368231047,
+  "best_metric": 0.4729241877256318,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-7/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.5812274368231047,
-      "eval_loss": 0.6901144981384277,
-      "eval_runtime": 0.6674,
-      "eval_samples_per_second": 415.066,
-      "eval_steps_per_second": 13.486,
+      "eval_accuracy": 0.4729241877256318,
+      "eval_loss": 0.6991013884544373,
+      "eval_runtime": 0.7513,
+      "eval_samples_per_second": 368.685,
+      "eval_steps_per_second": 11.979,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 156,
+  "max_steps": 78,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 2,
+  "num_train_epochs": 1,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -30,7 +30,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -39,10 +39,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.14341458699848886,
-    "learning_rate": 8.474768574918493e-06,
+    "dropout_rate": 0.1075410923440706,
+    "learning_rate": 6.8392847739666785e-06,
     "max_seq_length": 128,
-    "num_train_epochs": 2,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 32
   }
 }

run-7/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:801b5d5c5e0cdbcffde90e82eff54251ea0c570ab81c1446d0c0b6353aabd6d1
+oid sha256:08e2a2a4d379d09164306b95a4c3d156e6b668af97fc2d5e808d2935986cbf97
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9201422811267571a04f3ffbdb25c8ac791174001af4c9dd6038d99122cfe88b
+oid sha256:08e2a2a4d379d09164306b95a4c3d156e6b668af97fc2d5e808d2935986cbf97
 size 5240