Training in progress, epoch 1

run-14/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d06e3c8239dd42bbf550323003fefebf5fb1fcd33824f4874a1f2876fb05558b
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-14/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3ea50bde38d54faec355bcc0ce82de7b8fcb4f15e1da02ceb7f69a6a5c338a85
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-14/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6066302061080933,
+  "best_metric": 0.6066301465034485,
   "best_model_checkpoint": "BERT-WMM/run-14/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,10 +11,10 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.7535211267605634,
-      "eval_loss": 0.6066302061080933,
-      "eval_runtime": 2.5457,
-      "eval_samples_per_second": 836.715,
-      "eval_steps_per_second": 52.638,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 3.1749,
+      "eval_samples_per_second": 670.887,
+      "eval_steps_per_second": 84.097,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.003128382575039317
+    "per_device_eval_batch_size": 8
   }
 }

run-14/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fd4c33e06c2a74949495a839ddc1f66203e1a3f2a1e69856fa796b17322695
+oid sha256:01e24d0187a8169ca8ffac3b911af2c66b06e95ea452479d6b56e9fe40629092
 size 4856

run-14/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:98d5256b358cc84aeffd9a1c6aff5eeb8e4b03a2ae9bbe2dd8e592ca47bcd556
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-14/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e61e0addea6b40e6e974cc2153b76de451c19913f69837227db8672fa032ebc
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-14/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6037457585334778,
+  "best_metric": 0.6037464737892151,
   "best_model_checkpoint": "BERT-WMM/run-14/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,15 +11,15 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.7535211267605634,
-      "eval_loss": 0.6066302061080933,
-      "eval_runtime": 2.5457,
-      "eval_samples_per_second": 836.715,
-      "eval_steps_per_second": 52.638,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 3.1749,
+      "eval_samples_per_second": 670.887,
+      "eval_steps_per_second": 84.097,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.44931697845459,
+      "grad_norm": 9.449368476867676,
       "learning_rate": 9.825065893169892e-07,
       "loss": 0.6083,
       "step": 500
@@ -27,10 +27,10 @@
     {
       "epoch": 2.0,
       "eval_accuracy": 0.7619718309859155,
-      "eval_loss": 0.6037457585334778,
-      "eval_runtime": 2.5284,
-      "eval_samples_per_second": 842.432,
-      "eval_steps_per_second": 52.998,
+      "eval_loss": 0.6037464737892151,
+      "eval_runtime": 3.3075,
+      "eval_samples_per_second": 643.983,
+      "eval_steps_per_second": 80.725,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.003128382575039317
+    "per_device_eval_batch_size": 8
   }
 }

run-14/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:31fd4c33e06c2a74949495a839ddc1f66203e1a3f2a1e69856fa796b17322695
+oid sha256:01e24d0187a8169ca8ffac3b911af2c66b06e95ea452479d6b56e9fe40629092
 size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713528231.dcdaa3e6ec43.789.34

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:951491f81fb582768d859f416763870428286e5b77317d2d633514c7bb4989af
+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