Training in progress, epoch 2

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:e05505168f5f0a73a02f5913a70cdfd3abf5ccd18fe1841b88bd20949ac5e035
+oid sha256:532996eb39933b67a6d0ba5dce91f0aea2e85cf61a20e817552f95c4befcabb5
 size 437958648

run-0/checkpoint-78/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3e73a6a94dabb0efcd0fee951b4bb269e4bcbfd86b038cdb1f05f69be224987f
+oid sha256:532996eb39933b67a6d0ba5dce91f0aea2e85cf61a20e817552f95c4befcabb5
 size 437958648

run-0/checkpoint-78/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a0b9e49c0f111404bf3bb75f8aa46ebfe532888c0089618f9fee7181e88ff866
+oid sha256:16840b93d9efd0eb91de04e2c73596fd19a1affcba82023b8f898764fbfeb23b
 size 876038394

run-0/checkpoint-78/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca3cccd11b77d5d203a4466ecd61d7de95628051c1e10e12242d864bf481cb9f
+oid sha256:5e0187697e6d0429dfd9640b6f1406fdc3fe2031aa1c15aafe207f79661c8563
 size 1064

run-0/checkpoint-78/trainer_state.json

@@ -1,6 +1,6 @@
 {
   "best_global_step": 39,
-  "best_metric": 0.4729241877256318,
+  "best_metric": 0.4693140794223827,
   "best_model_checkpoint": "bert-base-uncased-finetuned-rte-run_1/run-0/checkpoint-39",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,20 +11,20 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.4729241877256318,
-      "eval_loss": 0.7152496576309204,
-      "eval_runtime": 1.8987,
-      "eval_samples_per_second": 145.89,
-      "eval_steps_per_second": 2.633,
+      "eval_accuracy": 0.4693140794223827,
+      "eval_loss": 0.7206186652183533,
+      "eval_runtime": 1.7488,
+      "eval_samples_per_second": 158.391,
+      "eval_steps_per_second": 2.859,
       "step": 39
     },
     {
       "epoch": 2.0,
       "eval_accuracy": 0.4657039711191336,
-      "eval_loss": 0.710480272769928,
-      "eval_runtime": 2.0968,
-      "eval_samples_per_second": 132.106,
-      "eval_steps_per_second": 2.385,
+      "eval_loss": 0.7172814011573792,
+      "eval_runtime": 1.8305,
+      "eval_samples_per_second": 151.323,
+      "eval_steps_per_second": 2.731,
       "step": 78
     }
   ],
@@ -49,9 +49,9 @@
   "train_batch_size": 64,
   "trial_name": null,
   "trial_params": {
-    "dropout_rate": 0.15926940143875853,
-    "learning_rate": 2.528084628626564e-06,
-    "max_seq_length": 128,
+    "dropout_rate": 0.42550029226706054,
+    "learning_rate": 1.4679097568141911e-06,
+    "max_seq_length": 64,
     "num_train_epochs": 2,
     "per_device_train_batch_size": 64
   }

run-0/checkpoint-78/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:60d0f60e33d97e1e0e5b10975bfd55ba2fc1145f2d1c8aa831504b116b1fc39f
+oid sha256:b2f8607d2e37a2f6dbecbc030c47d97f64db186e210b3b1396766c9f50fdf62b
 size 5432