Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79e693fdd79b3c65216e1e111a01de87a0a89a186a3ff2bf112dc7627a4ebf96
+oid sha256:f55f71760e8f91d6be6f463cd7e94dc5234767becd1c79d9e73b1fe9880e4f54
 size 437958648

run-4/checkpoint-39/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7946e609313d9aca24646d02b061dcc9755c352314148d5acb2f688f6adaafb4
+oid sha256:f55f71760e8f91d6be6f463cd7e94dc5234767becd1c79d9e73b1fe9880e4f54
 size 437958648

run-4/checkpoint-39/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01abdcf2117e5a94170a4e982396fe3833803c83ae2eb0a31a0584858f52daac
+oid sha256:21a049213fe29cb7677fd7ce7c90cba8edf7963ba88db9b5dc6a3fd1329d64ea
 size 876038394

run-4/checkpoint-39/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7174bc6d082a97c7577376f763d815f14b3b39fad56c7c17fa6cfaea5a564167
+oid sha256:b167c79a99979155e949b1c72c3cd10f9efb41b922df5ba0cdfe7add94b0ccd7
 size 1064

run-4/checkpoint-39/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.4729241877256318,
+  "best_metric": 0.4548736462093863,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-4/checkpoint-39",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,18 +11,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7197693586349487,
-      "eval_runtime": 2.0743,
-      "eval_samples_per_second": 133.537,
-      "eval_steps_per_second": 2.41,
+      "eval_accuracy": 0.4548736462093863,
+      "eval_loss": 0.6974011659622192,
+      "eval_runtime": 2.044,
+      "eval_samples_per_second": 135.516,
+      "eval_steps_per_second": 2.446,
       "step": 39
     }
   ],
   "logging_steps": 500,
-  "max_steps": 39,
+  "max_steps": 78,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 1,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -31,7 +31,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": true
+        "should_training_stop": false
       },
       "attributes": {}
     }
@@ -40,10 +40,10 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.1531904153707723,
-    "learning_rate": 2.7403617297846316e-06,
-    "max_seq_length": 64,
-    "num_train_epochs": 1,
+    "dropout_rate": 0.4407801684939425,
+    "learning_rate": 6.14706717379554e-06,
+    "max_seq_length": 256,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 64
   }
 }

run-4/checkpoint-39/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d154297bca50307d33fe6159c5a8928d454ca7cff17026832bcee3565a1644ce
+oid sha256:b4cc6501d1b38dbc34775f0b9df2455a0400a6b9f97257af4d9b51f4b12b7d0f
 size 5432

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:574977948b354aca70839ceacef71c7860dfc6ff222f5d96e1b3a99d03c6ab63
+oid sha256:b4cc6501d1b38dbc34775f0b9df2455a0400a6b9f97257af4d9b51f4b12b7d0f
 size 5432