Training in progress, epoch 1

run-6/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-6/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e154c9c91f69172883f82aa443bc1b89614888a12cb2c7da1a1b963e6fc3458
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-6/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6065725684165955,
+  "best_metric": 0.6066301465034485,
   "best_model_checkpoint": "BERT-WMM/run-6/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": 2.5274,
-      "eval_samples_per_second": 842.78,
-      "eval_steps_per_second": 53.02,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.5986,
+      "eval_samples_per_second": 819.668,
+      "eval_steps_per_second": 13.084,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.0001623656204213688
+    "per_device_eval_batch_size": 64
   }
 }

run-6/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70aadd498bdbea81834bef7eceb97789d49427e27141df9c39b96c4bc628e0e4
+oid sha256:a483b589b7ec426509c5e1dd2743ba6a6cb10e9ee0f5277c8fcb9a102432391c
 size 4856

run-6/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-6/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3bd017c91837e2192c0fa6d36d536c7b4e5c0a3791b5563fae6db887e0f753a
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-6/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6037774682044983,
+  "best_metric": 0.6037463545799255,
   "best_model_checkpoint": "BERT-WMM/run-6/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": 2.5274,
-      "eval_samples_per_second": 842.78,
-      "eval_steps_per_second": 53.02,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.5986,
+      "eval_samples_per_second": 819.668,
+      "eval_steps_per_second": 13.084,
       "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": 2.4941,
-      "eval_samples_per_second": 854.009,
-      "eval_steps_per_second": 53.726,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037463545799255,
+      "eval_runtime": 2.5724,
+      "eval_samples_per_second": 828.009,
+      "eval_steps_per_second": 13.217,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.0001623656204213688
+    "per_device_eval_batch_size": 64
   }
 }

run-6/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:70aadd498bdbea81834bef7eceb97789d49427e27141df9c39b96c4bc628e0e4
+oid sha256:a483b589b7ec426509c5e1dd2743ba6a6cb10e9ee0f5277c8fcb9a102432391c
 size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713526693.dcdaa3e6ec43.789.26

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:43265290c79d3cbd942a88ded48efe057b85e338119be918b5333e42dfe6b964
+size 6122

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6adb2de71cd7ff11dea13a3c48178e2920a3eb142a0a0d3e397f2b5214908e35
+oid sha256:a483b589b7ec426509c5e1dd2743ba6a6cb10e9ee0f5277c8fcb9a102432391c
 size 4856