Training in progress, epoch 1

run-15/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b2b85f1c56b082a7adb0495b0e90157ba5009e506f69ca889a52976119ece1d8
+oid sha256:2884ee1eb6c9bf50a2a6030607a4b9ebe2a19461fab049737b7d84db6271a0bd
 size 409103316

run-15/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:75dc2cc0822be1df341bff9fe0e9b142ce398a272a13fe316e0813176acbb27d
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-15/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6066303253173828,
+  "best_metric": 0.6066300868988037,
   "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -11,10 +11,10 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.7535211267605634,
-      "eval_loss": 0.6066303253173828,
-      "eval_runtime": 2.5222,
-      "eval_samples_per_second": 844.495,
-      "eval_steps_per_second": 53.128,
+      "eval_loss": 0.6066300868988037,
+      "eval_runtime": 2.4318,
+      "eval_samples_per_second": 875.888,
+      "eval_steps_per_second": 27.551,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.005683233568404179
+    "per_device_eval_batch_size": 32
   }
 }

run-15/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b010c265543f15c8674fe1fb0307eee60f5e80cab9f8bacb0a8a7cfb9674e897
+oid sha256:f84a19154c99b0458e0a6935a21fc8d86553f9641188bbfc0f3682f7c0fef1d7
 size 4856

run-15/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:054f45d996a65ea1bdb8d584365e91a5a4aff987f669ecc00c2b0ea27e80d8e0
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-15/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e07126827f2149795cf5d6033e516af877bb4d0b14eb7820b280af5e9305ac4
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-15/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6037431359291077,
+  "best_metric": 0.6037464141845703,
   "best_model_checkpoint": "BERT-WMM/run-15/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -11,15 +11,15 @@
     {
       "epoch": 1.0,
       "eval_accuracy": 0.7535211267605634,
-      "eval_loss": 0.6066303253173828,
-      "eval_runtime": 2.5222,
-      "eval_samples_per_second": 844.495,
-      "eval_steps_per_second": 53.128,
+      "eval_loss": 0.6066300868988037,
+      "eval_runtime": 2.4318,
+      "eval_samples_per_second": 875.888,
+      "eval_steps_per_second": 27.551,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.449167251586914,
+      "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": 0.6037431359291077,
-      "eval_runtime": 2.5197,
-      "eval_samples_per_second": 845.344,
-      "eval_steps_per_second": 53.181,
+      "eval_loss": 0.6037464141845703,
+      "eval_runtime": 2.465,
+      "eval_samples_per_second": 864.088,
+      "eval_steps_per_second": 27.18,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.005683233568404179
+    "per_device_eval_batch_size": 32
   }
 }

run-15/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b010c265543f15c8674fe1fb0307eee60f5e80cab9f8bacb0a8a7cfb9674e897
+oid sha256:f84a19154c99b0458e0a6935a21fc8d86553f9641188bbfc0f3682f7c0fef1d7
 size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713528429.dcdaa3e6ec43.789.35

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c8eb364b51f6568695b059b8dccaf8d4e5c6265d65461e2e323f6f3fa87ea70
+size 6122

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:01e24d0187a8169ca8ffac3b911af2c66b06e95ea452479d6b56e9fe40629092
+oid sha256:f84a19154c99b0458e0a6935a21fc8d86553f9641188bbfc0f3682f7c0fef1d7
 size 4856