Training in progress, epoch 1

run-11/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b62383e532375de8f37d59431717cb0c3e1937ec5cc424535a33fcf1b1491022
+oid sha256:f84a19154c99b0458e0a6935a21fc8d86553f9641188bbfc0f3682f7c0fef1d7
 size 4856

run-12/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b85f1c56b082a7adb0495b0e90157ba5009e506f69ca889a52976119ece1d8
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-12/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec5a355db941c8cae8024ef34ca1e5c563cb9dc83c1891034be6bacc55a349b7
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-12/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6066303253173828,
+  "best_metric": 0.6066301465034485,
   "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,10 +11,10 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.7535211267605634,
-      "eval_loss": 0.6066303253173828,
-      "eval_runtime": 2.4997,
-      "eval_samples_per_second": 852.1,
-      "eval_steps_per_second": 53.606,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.5857,
+      "eval_samples_per_second": 823.751,
+      "eval_steps_per_second": 6.575,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.004085209001694488
+    "per_device_eval_batch_size": 128
   }
 }

run-12/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec68cbfd2a5a3c649e3efda9c076e9ffd4b78b703a2ff9f07020202f0e1b9937
+oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
 size 4856

run-12/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6037443280220032,
+  "best_metric": 0.6037463545799255,
   "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,15 +11,15 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.7535211267605634,
-      "eval_loss": 0.6066303253173828,
-      "eval_runtime": 2.4997,
-      "eval_samples_per_second": 852.1,
-      "eval_steps_per_second": 53.606,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.5857,
+      "eval_samples_per_second": 823.751,
+      "eval_steps_per_second": 6.575,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.449225425720215,
+      "grad_norm": 9.449368476867676,
       "learning_rate": 9.825065893169892e-07,
       "loss": 0.6083,
       "step": 500
@@ -27,10 +27,10 @@
     {
       "epoch": 2.0,
       "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.6037443280220032,
-      "eval_runtime": 2.502,
-      "eval_samples_per_second": 851.316,
-      "eval_steps_per_second": 53.557,
+      "eval_loss": 0.6037463545799255,
+      "eval_runtime": 2.6447,
+      "eval_samples_per_second": 805.388,
+      "eval_steps_per_second": 6.428,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.004085209001694488
+    "per_device_eval_batch_size": 128
   }
 }

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713527846.dcdaa3e6ec43.789.32

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1d398afbceb9a5f57d558346defae308581d803618552a5bf24addd48143d9a6
+size 6123

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f84a19154c99b0458e0a6935a21fc8d86553f9641188bbfc0f3682f7c0fef1d7
+oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
 size 4856