Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c997364c6e0f71451ac72fbbabd23c2a59cb056a7d24aa3868d844ab5c111605
+oid sha256:b54f1fa8585a002ce1d2ee342588a47e6276c62725e87e697e3f1cbddd45b386
 size 409103316

run-16/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976557a36bef1a4a492485f3f6cb8948205b7b3a9ea05ce8ce0eb8982fcc1d9e
+oid sha256:a84802d89f5d3d8e178bf0dcdff5a20662948d91d59b9e43dde7b10b64668e10
 size 409103316

run-16/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890b6f5cc14af75c85002de6e2745609f1bf02f4a33a71cd0af847d31243fe8a
+oid sha256:cf456517c4b217a84a18628c21cdcd095f29afe3dcf0ae39ec0a74a14546ca50
 size 818327802

run-16/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2aa06609570d504e0cfaf6c3bd801e1681706921a7512c6ccb9eded784901f
+oid sha256:8a56050495e1938ae70b239ae8ece3c43ac800b58f0a6e02bd7ed6cd1669797d
 size 1064

run-16/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5776590704917908,
+  "best_metric": 0.6037467122077942,
   "best_model_checkpoint": "BERT-WMM/run-16/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7577464788732394,
-      "eval_loss": 0.6081846952438354,
-      "eval_runtime": 2.4149,
-      "eval_samples_per_second": 882.031,
-      "eval_steps_per_second": 55.489,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.5806,
+      "eval_samples_per_second": 825.38,
+      "eval_steps_per_second": 51.925,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.532360076904297,
-      "learning_rate": 9.65168237740807e-06,
-      "loss": 0.6057,
+      "grad_norm": 9.44939136505127,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7657276995305164,
-      "eval_loss": 0.5776590704917908,
-      "eval_runtime": 2.4621,
-      "eval_samples_per_second": 865.1,
-      "eval_steps_per_second": 54.424,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037467122077942,
+      "eval_runtime": 2.5199,
+      "eval_samples_per_second": 845.27,
+      "eval_steps_per_second": 53.177,
       "step": 534
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1335,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "num_train_epochs": 5
+    "weight_decay": 0.0026076282916422315
   }
 }

run-16/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+oid sha256:cf60e7ee962b6e8e2a7c5dee75a7889939e69dfb54e3e671c088aa239f9ce5f8
 size 4856

run-17/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
+oid sha256:b54f1fa8585a002ce1d2ee342588a47e6276c62725e87e697e3f1cbddd45b386
 size 409103316

run-17/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
+oid sha256:628533fda7668c7faf10209127ae87b17f557b584f598415e88ea80018c79a84
 size 818327802

run-17/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-17/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6019130349159241,
+  "best_metric": 0.6066157817840576,
   "best_model_checkpoint": "BERT-WMM/run-17/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": 2.42,
-      "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
     }
   ],
   "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": 0.015498593504464519
   }
 }

run-17/checkpoint-267/training_args.bin

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

runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713524340.dcdaa3e6ec43.789.17

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7c668eb3bd00c5a6b3b962783f36b1eec97dd1059b4e5292ec5b86fe697d1ef9
+size 6121

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cf60e7ee962b6e8e2a7c5dee75a7889939e69dfb54e3e671c088aa239f9ce5f8
+oid sha256:058e87a3bdfa7b1c5df6dd75ab69ae21b024a53e2f683cb64c30fa5a8462d5f3
 size 4856