Training in progress, epoch 1

run-4/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0dc6ea72694ff54a88f458db9aff463c496bd6d83166f6fb57a4e51c5bb172
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-4/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5921b1879136a2de0f32be39d0aa1e2c1df44b7767609fbb8ab7984ca270865
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-4/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6065725684165955,
+  "best_metric": 0.6066301465034485,
   "best_model_checkpoint": "BERT-WMM/run-4/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7530516431924883,
-      "eval_loss": 0.6065725684165955,
-      "eval_runtime": 2.5417,
-      "eval_samples_per_second": 838.036,
-      "eval_steps_per_second": 52.722,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.5947,
+      "eval_samples_per_second": 820.903,
+      "eval_steps_per_second": 13.104,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 4.018191065683781e-05
+    "per_device_eval_batch_size": 64
   }
 }

run-4/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f2b8ff5812e9a8e681e14d8d4a502beb7efad66683c16ee39765361b35b768
+oid sha256:a483b589b7ec426509c5e1dd2743ba6a6cb10e9ee0f5277c8fcb9a102432391c
 size 4856

run-4/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b5b3ada415323df4681659f8a3c19121e9379a2b0c7922cade957c3cc9526017
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-4/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:492785e0b2d4bc2fddbf03fc7aa5070a9d5992be16a4b8b568d67b7ad8b49cd5
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-4/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6037774682044983,
+  "best_metric": 0.6037463545799255,
   "best_model_checkpoint": "BERT-WMM/run-4/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7530516431924883,
-      "eval_loss": 0.6065725684165955,
-      "eval_runtime": 2.5417,
-      "eval_samples_per_second": 838.036,
-      "eval_steps_per_second": 52.722,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.5947,
+      "eval_samples_per_second": 820.903,
+      "eval_steps_per_second": 13.104,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.447751998901367,
+      "grad_norm": 9.449368476867676,
       "learning_rate": 9.825065893169892e-07,
       "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7615023474178404,
-      "eval_loss": 0.6037774682044983,
-      "eval_runtime": 2.5779,
-      "eval_samples_per_second": 826.263,
-      "eval_steps_per_second": 51.981,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037463545799255,
+      "eval_runtime": 2.5333,
+      "eval_samples_per_second": 840.813,
+      "eval_steps_per_second": 13.421,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 4.018191065683781e-05
+    "per_device_eval_batch_size": 64
   }
 }

run-4/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:61f2b8ff5812e9a8e681e14d8d4a502beb7efad66683c16ee39765361b35b768
+oid sha256:a483b589b7ec426509c5e1dd2743ba6a6cb10e9ee0f5277c8fcb9a102432391c
 size 4856

run-5/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fa79b65d0ba7529aee0550dc910f9468bf4b0ad08164867f686e834e0e9fd408
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-5/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d47a133704ee5d893b30a7dc35c9b1d607c0d15dd4e32e8a90cf3cdd87699884
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-5/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6066888570785522,
+  "best_metric": 0.6066300868988037,
   "best_model_checkpoint": "BERT-WMM/run-5/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7539906103286385,
-      "eval_loss": 0.6066888570785522,
-      "eval_runtime": 2.5768,
-      "eval_samples_per_second": 826.614,
-      "eval_steps_per_second": 52.003,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066300868988037,
+      "eval_runtime": 2.5113,
+      "eval_samples_per_second": 848.167,
+      "eval_steps_per_second": 53.359,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.08935453780478574
+    "per_device_eval_batch_size": 16
   }
 }

run-5/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57316b4d399893de9d059984f406888c25d2a6d5ffb20848fef7218735cf9bd
+oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
 size 4856

run-5/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0ea3f89de5d4395de05f9199dfc278df79a4377c90cd101dbcaf5a911a8f0d92
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-5/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:362a30339db12512e0be64c4ba7604848c8450378dc85c1519e3f515459032c9
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-5/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6036561727523804,
+  "best_metric": 0.6037464141845703,
   "best_model_checkpoint": "BERT-WMM/run-5/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7539906103286385,
-      "eval_loss": 0.6066888570785522,
-      "eval_runtime": 2.5768,
-      "eval_samples_per_second": 826.614,
-      "eval_steps_per_second": 52.003,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066300868988037,
+      "eval_runtime": 2.5113,
+      "eval_samples_per_second": 848.167,
+      "eval_steps_per_second": 53.359,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.446334838867188,
+      "grad_norm": 9.449368476867676,
       "learning_rate": 9.825065893169892e-07,
       "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7615023474178404,
-      "eval_loss": 0.6036561727523804,
-      "eval_runtime": 2.5416,
-      "eval_samples_per_second": 838.059,
-      "eval_steps_per_second": 52.723,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037464141845703,
+      "eval_runtime": 2.4881,
+      "eval_samples_per_second": 856.087,
+      "eval_steps_per_second": 53.857,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.08935453780478574
+    "per_device_eval_batch_size": 16
   }
 }

run-5/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b57316b4d399893de9d059984f406888c25d2a6d5ffb20848fef7218735cf9bd
+oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
 size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713526310.dcdaa3e6ec43.789.24

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f08fb13e8445ab7e1a11226849071e88b8f2f3dbd800596286de14c0cd3f1a6
+size 6122

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713526498.dcdaa3e6ec43.789.25

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ed590f0072d764a96eff80134f3dd36296949b483000d1710cad860c468b6c7
+size 6122

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
+oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
 size 4856