Training in progress, epoch 1

run-9/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75ca88a2e25fd0e485c4c67aa2dded37ef1dfa4ca4a7f5b9ace95621c59a503b
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-9/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d3f9eb57e84a6a6e974b22318994029f8d4798854328611ca3366f8f7e313e6
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-9/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6065868735313416,
+  "best_metric": 0.6066300868988037,
   "best_model_checkpoint": "BERT-WMM/run-9/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7530516431924883,
-      "eval_loss": 0.6065868735313416,
-      "eval_runtime": 2.5841,
-      "eval_samples_per_second": 824.279,
-      "eval_steps_per_second": 51.856,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066300868988037,
+      "eval_runtime": 2.4961,
+      "eval_samples_per_second": 853.344,
+      "eval_steps_per_second": 53.685,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.01864360010090689
+    "per_device_eval_batch_size": 16
   }
 }

run-9/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025792d99deb7ef852ba1bdf1f59c07e051f6266f6a226e200f2e0869c199cb5
+oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
 size 4856

run-9/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1e2ca2ef5afd05d649a9633191367ce9753a932e1ebcd945da7641f492e6ce23
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-9/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b1446aaaa1f3aad137c41d58a2cbdf9451d87b4594b055a028933173e4755021
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-9/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.603755533695221,
+  "best_metric": 0.6037464141845703,
   "best_model_checkpoint": "BERT-WMM/run-9/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7530516431924883,
-      "eval_loss": 0.6065868735313416,
-      "eval_runtime": 2.5841,
-      "eval_samples_per_second": 824.279,
-      "eval_steps_per_second": 51.856,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066300868988037,
+      "eval_runtime": 2.4961,
+      "eval_samples_per_second": 853.344,
+      "eval_steps_per_second": 53.685,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.447359085083008,
+      "grad_norm": 9.449368476867676,
       "learning_rate": 9.825065893169892e-07,
       "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7615023474178404,
-      "eval_loss": 0.603755533695221,
-      "eval_runtime": 2.5061,
-      "eval_samples_per_second": 849.914,
-      "eval_steps_per_second": 53.469,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037464141845703,
+      "eval_runtime": 2.5183,
+      "eval_samples_per_second": 845.815,
+      "eval_steps_per_second": 53.211,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.01864360010090689
+    "per_device_eval_batch_size": 16
   }
 }

run-9/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:025792d99deb7ef852ba1bdf1f59c07e051f6266f6a226e200f2e0869c199cb5
+oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
 size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713527270.dcdaa3e6ec43.789.29

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94c9874480e548946545c81eb0807384e64cea85489ae0255198e1d9151b7d24
+size 6122

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a483b589b7ec426509c5e1dd2743ba6a6cb10e9ee0f5277c8fcb9a102432391c
+oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
 size 4856