Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:df7f1283141edfb3d71fac504b3f163340429111fcaf4faa4f92b6a7d2748dac
+oid sha256:e8aee2bd24c0dea4bf13c620632c18784ce5098d73ebd6979aca98a8e7454614
 size 437958648

run-3/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9dcdcb1f1b6e7c31feaa9714b113863285f71213f4050d8f8e1e8368c49cbc8d
+oid sha256:e8aee2bd24c0dea4bf13c620632c18784ce5098d73ebd6979aca98a8e7454614
 size 437958648

run-3/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c31e2fe00c6fd09896dce0212ae6ae0f5bbd3da9a95f06a07fe016647d1b17b
+oid sha256:053b7010be08208b6af578c0f5e9ccedf7b8e015f37326ee9733ac13d8cac644
 size 876038394

run-3/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ad250b9aaf8b0a9029489bc4912fd70de026ef5e764dc0ca050196696988b0
+oid sha256:61831d0ca855ffabdbd3da4768b2291fef597b0d97fa2c019784aa7bfc440c3b
 size 1064

run-3/checkpoint-78/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.4693140794223827,
+  "best_metric": 0.4620938628158845,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-3/checkpoint-78",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,18 +10,18 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4693140794223827,
-      "eval_loss": 0.7107913494110107,
-      "eval_runtime": 0.675,
-      "eval_samples_per_second": 410.389,
-      "eval_steps_per_second": 13.334,
+      "eval_accuracy": 0.4620938628158845,
+      "eval_loss": 0.7000649571418762,
+      "eval_runtime": 0.7257,
+      "eval_samples_per_second": 381.682,
+      "eval_steps_per_second": 12.401,
       "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": 0.29412092726837363,
-    "learning_rate": 2.1156293226344175e-06,
-    "max_seq_length": 64,
-    "num_train_epochs": 2,
+    "dropout_rate": 0.35970202696124776,
+    "learning_rate": 5.8946025646029645e-06,
+    "max_seq_length": 128,
+    "num_train_epochs": 1,
     "per_device_train_batch_size": 32
   }
 }

run-3/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ecd4dd949417edd978f459fbaf152e991e4d079e0f5959c96a5c0379f9a1e95
+oid sha256:15b59439e23e3224d6e1f41d9fefdc583893f2564119f4cf343124dc3da09ac5
 size 5240

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ea81adaa0fc313e55af4649601b53f24b2b0062dd78fd0c23df5a5123b3bcb9c
+oid sha256:15b59439e23e3224d6e1f41d9fefdc583893f2564119f4cf343124dc3da09ac5
 size 5240