Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:86109271700a6566dac67fce11e384e138d7e3ec29af851a59f573daec7c09e1
+oid sha256:070e3569eedb202585d4b6fab4bb8f15975f8188dacf2653cde9625fee95eeee
 size 437958648

run-6/checkpoint-156/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8473136bfeb0c995ef6bed55f5bce43b5a32be56fc724b4548b418802a44ed36
+oid sha256:3f5d105e293630c506ef50c2648d526c0b68e4b45d280dcd5f0d114940b39a85
 size 437958648

run-6/checkpoint-156/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aa612f4943433809dda333ed5547ffdf0e81379288883c640ba61d0022be9290
+oid sha256:b61141d06ad4331bf512dbce9b26058dd20b0c9def278b6c943bff82284c622a
 size 876038394

run-6/checkpoint-156/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f823935a15a81ebe78f15abe96b14eb63bd3dde52f1ad118cfd2d64c8d8b023c
+oid sha256:cf4441b886942355cc1a9c981c1a8bb3a29e1b37ec553f1ab03ff863e4866fb9
 size 1064

run-6/checkpoint-156/trainer_state.json

@@ -1,6 +1,6 @@
 {
-  "best_metric": 0.6389891696750902,
-  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-6/checkpoint-78",
+  "best_metric": 0.6642599277978339,
+  "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-6/checkpoint-156",
   "epoch": 2.0,
   "eval_steps": 500,
   "global_step": 156,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6389891696750902,
-      "eval_loss": 0.6565788388252258,
-      "eval_runtime": 0.6675,
-      "eval_samples_per_second": 415.004,
-      "eval_steps_per_second": 13.484,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6226887106895447,
+      "eval_runtime": 0.7255,
+      "eval_samples_per_second": 381.827,
+      "eval_steps_per_second": 12.406,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.6209386281588448,
-      "eval_loss": 0.6836292147636414,
-      "eval_runtime": 0.6736,
-      "eval_samples_per_second": 411.218,
-      "eval_steps_per_second": 13.361,
+      "eval_accuracy": 0.6642599277978339,
+      "eval_loss": 0.6533659100532532,
+      "eval_runtime": 0.7201,
+      "eval_samples_per_second": 384.669,
+      "eval_steps_per_second": 12.498,
       "step": 156
     }
   ],
   "logging_steps": 500,
-  "max_steps": 234,
+  "max_steps": 156,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -39,7 +39,7 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
@@ -48,10 +48,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.4981619199472148,
-    "learning_rate": 9.958228585906916e-05,
-    "max_seq_length": 64,
-    "num_train_epochs": 3,
+    "dropout_rate": 0.1623468262270163,
+    "learning_rate": 8.988211084445771e-05,
+    "max_seq_length": 32,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 32
   }
 }

run-6/checkpoint-156/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad0809de284770e15ca66b8b5774503102a1cc551fecb95f92e56ecf1f8151c
+oid sha256:9201422811267571a04f3ffbdb25c8ac791174001af4c9dd6038d99122cfe88b
 size 5240

run-6/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e89c04580471313c5c6f3b746ddd0ea568fdef9f5d539f6430e46b6bbe0b172d
+oid sha256:070e3569eedb202585d4b6fab4bb8f15975f8188dacf2653cde9625fee95eeee
 size 437958648

run-6/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b6b1510657cbff2dcd4c6ce0841ee4c45f513590157895dbb68819946fefcbfe
+oid sha256:cb4610454012301de60d4bd23b1aff81ee788793f121c983eda9e12763820b22
 size 876038394

run-6/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:360ee98d2ddf8bd8bbe9f381f550ba5951d974aab4cc86dad4ccf9be72b27837
+oid sha256:d59bd12f7a03bd71cce0c1d0ba531050fb557f6145536b10ea566f804e24d6ba
 size 1064

run-6/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6389891696750902,
+  "best_metric": 0.6606498194945848,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-6/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.6389891696750902,
-      "eval_loss": 0.6565788388252258,
-      "eval_runtime": 0.6675,
-      "eval_samples_per_second": 415.004,
-      "eval_steps_per_second": 13.484,
+      "eval_accuracy": 0.6606498194945848,
+      "eval_loss": 0.6226887106895447,
+      "eval_runtime": 0.7255,
+      "eval_samples_per_second": 381.827,
+      "eval_steps_per_second": 12.406,
       "step": 78
     }
   ],
   "logging_steps": 500,
-  "max_steps": 234,
+  "max_steps": 156,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "stateful_callbacks": {
     "TrainerControl": {
@@ -39,10 +39,10 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.4981619199472148,
-    "learning_rate": 9.958228585906916e-05,
-    "max_seq_length": 64,
-    "num_train_epochs": 3,
+    "dropout_rate": 0.1623468262270163,
+    "learning_rate": 8.988211084445771e-05,
+    "max_seq_length": 32,
+    "num_train_epochs": 2,
     "per_device_train_batch_size": 32
   }
 }

run-6/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8ad0809de284770e15ca66b8b5774503102a1cc551fecb95f92e56ecf1f8151c
+oid sha256:9201422811267571a04f3ffbdb25c8ac791174001af4c9dd6038d99122cfe88b
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9ad6acdcbd930141ff6c9ddf315e98b847208cb57102c5b40f8230c5988f9790
+oid sha256:9201422811267571a04f3ffbdb25c8ac791174001af4c9dd6038d99122cfe88b
 size 5240