Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c4a6468bdff9f212c6365fb9d1938a416c6edfb62ff1600eadddf4f0a6c48a95
+oid sha256:d12bc68ba1b72ab96bf02443ed6c7f1326e4155af7aec543f6a3fcdde91f9230
 size 437958648

run-0/checkpoint-156/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4729241877256318,
+  "best_metric": 0.4693140794223827,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-0/checkpoint-78",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7185945510864258,
-      "eval_runtime": 0.7057,
-      "eval_samples_per_second": 392.495,
-      "eval_steps_per_second": 12.753,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.7097682952880859,
+      "eval_runtime": 0.6898,
+      "eval_samples_per_second": 401.566,
+      "eval_steps_per_second": 13.047,
       "step": 78
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.4693140794223827,
-      "eval_loss": 0.7123874425888062,
-      "eval_runtime": 0.6845,
-      "eval_samples_per_second": 404.689,
-      "eval_steps_per_second": 13.149,
+      "eval_accuracy": 0.4620938628158845,
+      "eval_loss": 0.7046680450439453,
+      "eval_runtime": 0.7314,
+      "eval_samples_per_second": 378.745,
+      "eval_steps_per_second": 12.306,
       "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": 0.27458370833953805,
-    "learning_rate": 1.0420263015685704e-06,
-    "max_seq_length": 32,
-    "num_train_epochs": 3,
+    "dropout_rate": 0.47014555795728874,
+    "learning_rate": 2.1855407784043845e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 2,
     "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:d023ff1f80301e53a92b3c3c6b5f888c5149535556d173181510facd2d6fba70
+oid sha256:d12bc68ba1b72ab96bf02443ed6c7f1326e4155af7aec543f6a3fcdde91f9230
 size 437958648

run-0/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e529112784d1c84ce71f514086762eeb48666f85e66f330770f1fb4d964813c7
+oid sha256:417eb119339eec8bee8bcdf2f334c9384c79ffdfd37ad655e3a13b0666fa5cf8
 size 876038394

run-0/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa865013a2181a4e2c688faa3e540a9e1efb33a5f063c27a6bc538d18382b889
+oid sha256:615f51de677321130bbbc9a6b6b613f2822b5ddabd64a2dbd085b63c82c26b96
 size 1064

run-0/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4729241877256318,
+  "best_metric": 0.4693140794223827,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-0/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7185945510864258,
-      "eval_runtime": 0.7057,
-      "eval_samples_per_second": 392.495,
-      "eval_steps_per_second": 12.753,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.7097682952880859,
+      "eval_runtime": 0.6898,
+      "eval_samples_per_second": 401.566,
+      "eval_steps_per_second": 13.047,
       "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": 0.27458370833953805,
-    "learning_rate": 1.0420263015685704e-06,
-    "max_seq_length": 32,
-    "num_train_epochs": 3,
+    "dropout_rate": 0.47014555795728874,
+    "learning_rate": 2.1855407784043845e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 2,
     "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:c9040c2653ebc0d7a419adcae990c297f257817a157f53cf1fbcd2d082d6f0d4
+oid sha256:6884f11136ccb848170df6d578d5f0c6cc1b6affd9b9d95a5474e1acd7b5877f
 size 5240

tokenizer.json

@@ -2,13 +2,13 @@
   "version": "1.0",
   "truncation": {
     "direction": "Right",
-    "max_length": 64,
+    "max_length": 128,
     "strategy": "LongestFirst",
     "stride": 0
   },
   "padding": {
     "strategy": {
-      "Fixed": 64
+      "Fixed": 128
     },
     "direction": "Right",
     "pad_to_multiple_of": null,

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d194138e61b5f886e352871a7e47275b103df8c119f4a23897fd240d2849d429
+oid sha256:6884f11136ccb848170df6d578d5f0c6cc1b6affd9b9d95a5474e1acd7b5877f
 size 5240