Training in progress, epoch 1

run-19/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:849b2219b6f76700a8f32131536f6b6a9d2ed82dad4be3ec62b9fa941c15cf27
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-19/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:28ff46f6452b3ccd1d01e2fc84a1d4cffbeec5188a59986dfd1a7ddffb875f00
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-19/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6066781878471375,
+  "best_metric": 0.6066301465034485,
   "best_model_checkpoint": "BERT-WMM/run-19/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,11 +10,11 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7539906103286385,
-      "eval_loss": 0.6066781878471375,
-      "eval_runtime": 2.5156,
-      "eval_samples_per_second": 846.702,
-      "eval_steps_per_second": 53.267,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 3.1622,
+      "eval_samples_per_second": 673.588,
+      "eval_steps_per_second": 84.436,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.051424292123722175
+    "per_device_eval_batch_size": 8
   }
 }

run-19/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e18fed6d1d6cb4145ea5f498532a391408ab2f035069ebc34d88b7221a52d0a
+oid sha256:01e24d0187a8169ca8ffac3b911af2c66b06e95ea452479d6b56e9fe40629092
 size 4856

run-19/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2ef7d3121b6dcc55df087ce9fb15d483500f5343e0eca2000ec9bcf2ef62704a
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-19/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0dd728cb17a1f39c51ba816ac5c872e91d596e39e2ba9b2329fbafc8cd72317e
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-19/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6036877632141113,
+  "best_metric": 0.6037464737892151,
   "best_model_checkpoint": "BERT-WMM/run-19/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,27 +10,27 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7539906103286385,
-      "eval_loss": 0.6066781878471375,
-      "eval_runtime": 2.5156,
-      "eval_samples_per_second": 846.702,
-      "eval_steps_per_second": 53.267,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 3.1622,
+      "eval_samples_per_second": 673.588,
+      "eval_steps_per_second": 84.436,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.447916030883789,
+      "grad_norm": 9.449368476867676,
       "learning_rate": 9.825065893169892e-07,
       "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7615023474178404,
-      "eval_loss": 0.6036877632141113,
-      "eval_runtime": 2.4873,
-      "eval_samples_per_second": 856.361,
-      "eval_steps_per_second": 53.874,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037464737892151,
+      "eval_runtime": 3.266,
+      "eval_samples_per_second": 652.177,
+      "eval_steps_per_second": 81.752,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.051424292123722175
+    "per_device_eval_batch_size": 8
   }
 }

run-19/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e18fed6d1d6cb4145ea5f498532a391408ab2f035069ebc34d88b7221a52d0a
+oid sha256:01e24d0187a8169ca8ffac3b911af2c66b06e95ea452479d6b56e9fe40629092
 size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713529200.dcdaa3e6ec43.789.39

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:df91c6040f7f5f377f28d785e5c3b900114a98a06c2309a92239c6573260f766
+size 6121

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
+oid sha256:01e24d0187a8169ca8ffac3b911af2c66b06e95ea452479d6b56e9fe40629092
 size 4856