Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b54f1fa8585a002ce1d2ee342588a47e6276c62725e87e697e3f1cbddd45b386
+oid sha256:ca0dc6ea72694ff54a88f458db9aff463c496bd6d83166f6fb57a4e51c5bb172
 size 409103316

run-17/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2c26a4990298c617435add4fef099a107381df4b5d4dd2ceb1932c28c743541
+oid sha256:8b088bb38876cc1207dbfc22647a9745ddae49648aff36b26a678358916d0597
 size 409103316

run-17/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7c82d05f4ce26f22c9acaa7998473a49f5f6cbfcd52e5fa856d9f347b60ad8c
+oid sha256:812e0321339acdd494d59a07d6085ab9e422d89e98290e794c950d8ca86d8db4
 size 818327802

run-17/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dda5eab8086c3361f01b6da1d0d501e5d7ffcc15041db5c9a3384c00b843300f
+oid sha256:8a56050495e1938ae70b239ae8ece3c43ac800b58f0a6e02bd7ed6cd1669797d
 size 1064

run-17/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5817901492118835,
+  "best_metric": 0.603742778301239,
   "best_model_checkpoint": "BERT-WMM/run-17/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
-      "eval_runtime": 2.42,
-      "eval_samples_per_second": 880.151,
-      "eval_steps_per_second": 55.371,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6066157817840576,
+      "eval_runtime": 2.6354,
+      "eval_samples_per_second": 808.213,
+      "eval_steps_per_second": 50.845,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.674468994140625,
-      "learning_rate": 5.7987153604787005e-06,
-      "loss": 0.6061,
+      "grad_norm": 9.448416709899902,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.5817901492118835,
-      "eval_runtime": 2.4576,
-      "eval_samples_per_second": 866.705,
-      "eval_steps_per_second": 54.525,
+      "eval_accuracy": 0.7615023474178404,
+      "eval_loss": 0.603742778301239,
+      "eval_runtime": 2.6051,
+      "eval_samples_per_second": 817.639,
+      "eval_steps_per_second": 51.438,
       "step": 534
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "weight_decay": 0.015498593504464519
   }
 }

run-17/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:058e87a3bdfa7b1c5df6dd75ab69ae21b024a53e2f683cb64c30fa5a8462d5f3
 size 4856

run-18/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
+oid sha256:ca0dc6ea72694ff54a88f458db9aff463c496bd6d83166f6fb57a4e51c5bb172
 size 409103316

run-18/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
+oid sha256:44081ada9eadebc5a5a909ca4c74efa9d62c6ae8c67eb41203e191c6751bcbaf
 size 818327802

run-18/checkpoint-267/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d605219d0cdfe1356d19dfc261c4f045664dbc44ddf04517d0b2ebd1dab264c7
+oid sha256:ef3be8be9037b2d6a9348611f95c19fb1d17ca7cb1da92486df22b7e0a3c655a
 size 1064

run-18/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6019130349159241,
+  "best_metric": 0.6065725684165955,
   "best_model_checkpoint": "BERT-WMM/run-18/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,23 +10,23 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
-      "eval_runtime": 2.4196,
-      "eval_samples_per_second": 880.318,
-      "eval_steps_per_second": 55.381,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6065725684165955,
+      "eval_runtime": 2.6718,
+      "eval_samples_per_second": 797.215,
+      "eval_steps_per_second": 50.153,
       "step": 267
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "weight_decay": 0.0016219939810654786
   }
 }

run-18/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:e1e1153af9790ef8808125f63933179e86e55e5d9fad145931b50ae4a04de8a4
 size 4856

runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713524542.dcdaa3e6ec43.789.18

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be9e8862cec323cf1f052986b461c82ca25e4d3df682dd3ac0c0559cda3b7052
+size 6122

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:058e87a3bdfa7b1c5df6dd75ab69ae21b024a53e2f683cb64c30fa5a8462d5f3
+oid sha256:e1e1153af9790ef8808125f63933179e86e55e5d9fad145931b50ae4a04de8a4
 size 4856