Training in progress, epoch 1

run-12/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b84e0f75887c030ddb24e3bbb8a2c23b54b34b182a5acaef34af809dd68b69bc
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-12/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:84d83f00c50501a803fa80fa0853dd502bc94cf95aada6703179ca11e2a9070b
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-12/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec68cbfd2a5a3c649e3efda9c076e9ffd4b78b703a2ff9f07020202f0e1b9937
+oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
 size 4856

run-13/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-13/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96d8c63a0b569500d6b52e62f555d9bfc7c4010810e3535d4a3d36c89e7be6fd
+oid sha256:2baae2af2e2a6e67ffa103acb8944b4c3e0caf544e891a5bc08743054b6487d8
 size 818327802

run-13/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6066303253173828,
+  "best_metric": 0.6066301465034485,
   "best_model_checkpoint": "BERT-WMM/run-13/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": 2.5344,
-      "eval_samples_per_second": 840.439,
-      "eval_steps_per_second": 52.873,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.6437,
+      "eval_samples_per_second": 805.692,
+      "eval_steps_per_second": 6.43,
       "step": 267
     }
   ],
@@ -27,6 +27,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.004730886773402456
+    "per_device_eval_batch_size": 128
   }
 }

run-13/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f445057de0c2159585cd57bd78995f31933af19372c506bea5e6ecf22b5e03
+oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
 size 4856

run-13/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:030f068de82913a7e7c7a026971da2412c5e341d2deb1b60fed8cb4a7a98e5ec
+oid sha256:6f8ea8045dcbfbb7e2b1d5b479744e3e5d4a5952c8b08b322a5910de69569a95
 size 409103316

run-13/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4e39c7dbc0672a205f1c37e9ddcd39f3b311fc28afb4a6d4b98c3aaa8a99d035
+oid sha256:839569beae02eb4d765dc9d64a6e266937dcbde2f5dce3d36c79a55cbe2e9e94
 size 818327802

run-13/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.603743851184845,
+  "best_metric": 0.6037463545799255,
   "best_model_checkpoint": "BERT-WMM/run-13/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": 2.5344,
-      "eval_samples_per_second": 840.439,
-      "eval_steps_per_second": 52.873,
+      "eval_loss": 0.6066301465034485,
+      "eval_runtime": 2.6437,
+      "eval_samples_per_second": 805.692,
+      "eval_steps_per_second": 6.43,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.449202537536621,
+      "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": 0.603743851184845,
-      "eval_runtime": 2.5041,
-      "eval_samples_per_second": 850.595,
-      "eval_steps_per_second": 53.512,
+      "eval_loss": 0.6037463545799255,
+      "eval_runtime": 2.576,
+      "eval_samples_per_second": 826.874,
+      "eval_steps_per_second": 6.599,
       "step": 534
     }
   ],
@@ -43,6 +43,6 @@
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "weight_decay": 0.004730886773402456
+    "per_device_eval_batch_size": 128
   }
 }

run-13/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c3f445057de0c2159585cd57bd78995f31933af19372c506bea5e6ecf22b5e03
+oid sha256:499e1a04d7f7b4fe77d2c8e1f57609c7db579850e1adca3b262fe272e829ad2c
 size 4856

runs/Apr19_11-18-29_dcdaa3e6ec43/events.out.tfevents.1713528042.dcdaa3e6ec43.789.33

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e030eec92a69f4c430e3e2dd7106ff01ec2722d9caaffc97f89aba503ea7723
+size 6123