Training in progress, epoch 1

run-12/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976557a36bef1a4a492485f3f6cb8948205b7b3a9ea05ce8ce0eb8982fcc1d9e
+oid sha256:b84e0f75887c030ddb24e3bbb8a2c23b54b34b182a5acaef34af809dd68b69bc
 size 409103316

run-12/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890b6f5cc14af75c85002de6e2745609f1bf02f4a33a71cd0af847d31243fe8a
+oid sha256:84d83f00c50501a803fa80fa0853dd502bc94cf95aada6703179ca11e2a9070b
 size 818327802

run-12/checkpoint-534/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e2aa06609570d504e0cfaf6c3bd801e1681706921a7512c6ccb9eded784901f
+oid sha256:8a56050495e1938ae70b239ae8ece3c43ac800b58f0a6e02bd7ed6cd1669797d
 size 1064

run-12/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5776590704917908,
+  "best_metric": 0.6037443280220032,
   "best_model_checkpoint": "BERT-WMM/run-12/checkpoint-534",
   "epoch": 2.0,
   "eval_steps": 500,
@@ -10,39 +10,39 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7577464788732394,
-      "eval_loss": 0.6081846952438354,
-      "eval_runtime": 2.4539,
-      "eval_samples_per_second": 868.011,
-      "eval_steps_per_second": 54.607,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066303253173828,
+      "eval_runtime": 2.4997,
+      "eval_samples_per_second": 852.1,
+      "eval_steps_per_second": 53.606,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.532360076904297,
-      "learning_rate": 9.65168237740807e-06,
-      "loss": 0.6057,
+      "grad_norm": 9.449225425720215,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7657276995305164,
-      "eval_loss": 0.5776590704917908,
-      "eval_runtime": 2.4958,
-      "eval_samples_per_second": 853.421,
-      "eval_steps_per_second": 53.689,
+      "eval_accuracy": 0.7619718309859155,
+      "eval_loss": 0.6037443280220032,
+      "eval_runtime": 2.502,
+      "eval_samples_per_second": 851.316,
+      "eval_steps_per_second": 53.557,
       "step": 534
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1335,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
-  "total_flos": 907987959990720.0,
+  "total_flos": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "num_train_epochs": 5
+    "weight_decay": 0.004085209001694488
   }
 }

run-12/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+oid sha256:ec68cbfd2a5a3c649e3efda9c076e9ffd4b78b703a2ff9f07020202f0e1b9937
 size 4856

run-13/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:709e0174af7e7bfc36b2ca42177cb07663d435c4830e3ef2fd95156cc7684138
+oid sha256:b2b85f1c56b082a7adb0495b0e90157ba5009e506f69ca889a52976119ece1d8
 size 409103316

run-13/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:52ef4431d2c45c5021200b1e749d9a863141163026b276944e492c1db9ee3f59
+oid sha256:96d8c63a0b569500d6b52e62f555d9bfc7c4010810e3535d4a3d36c89e7be6fd
 size 818327802

run-13/checkpoint-267/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:44c8fc955f6ab66538b705aa40f6ebb08474ec445464a7a19ca29971b9fc42d4
+oid sha256:ef3be8be9037b2d6a9348611f95c19fb1d17ca7cb1da92486df22b7e0a3c655a
 size 1064

run-13/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6081846952438354,
+  "best_metric": 0.6066303253173828,
   "best_model_checkpoint": "BERT-WMM/run-13/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,23 +10,23 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7577464788732394,
-      "eval_loss": 0.6081846952438354,
-      "eval_runtime": 2.4174,
-      "eval_samples_per_second": 881.101,
-      "eval_steps_per_second": 55.431,
+      "eval_accuracy": 0.7535211267605634,
+      "eval_loss": 0.6066303253173828,
+      "eval_runtime": 2.5344,
+      "eval_samples_per_second": 840.439,
+      "eval_steps_per_second": 52.873,
       "step": 267
     }
   ],
   "logging_steps": 500,
-  "max_steps": 1335,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 5,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "num_train_epochs": 5
+    "weight_decay": 0.004730886773402456
   }
 }

run-13/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+oid sha256:c3f445057de0c2159585cd57bd78995f31933af19372c506bea5e6ecf22b5e03
 size 4856

runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713523606.dcdaa3e6ec43.789.13

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4770f7d883b1385b96886e30a1628830c64cf684a37f85dce1c42d25c0850e7b
+size 6121

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ec68cbfd2a5a3c649e3efda9c076e9ffd4b78b703a2ff9f07020202f0e1b9937
+oid sha256:c3f445057de0c2159585cd57bd78995f31933af19372c506bea5e6ecf22b5e03
 size 4856