Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ca0dc6ea72694ff54a88f458db9aff463c496bd6d83166f6fb57a4e51c5bb172
+oid sha256:75ca88a2e25fd0e485c4c67aa2dded37ef1dfa4ca4a7f5b9ace95621c59a503b
 size 409103316

run-8/checkpoint-534/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:976557a36bef1a4a492485f3f6cb8948205b7b3a9ea05ce8ce0eb8982fcc1d9e
+oid sha256:b5b3ada415323df4681659f8a3c19121e9379a2b0c7922cade957c3cc9526017
 size 409103316

run-8/checkpoint-534/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:890b6f5cc14af75c85002de6e2745609f1bf02f4a33a71cd0af847d31243fe8a
+oid sha256:3b540068392272d511c594d0281490e8e3bc53c1310df3fa27624442775c056d
 size 818327802

run-8/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-8/checkpoint-534/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.5776590704917908,
+  "best_metric": 0.6037774682044983,
   "best_model_checkpoint": "BERT-WMM/run-8/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": 2.4296,
-      "eval_samples_per_second": 876.671,
-      "eval_steps_per_second": 55.152,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6065725684165955,
+      "eval_runtime": 2.5479,
+      "eval_samples_per_second": 835.985,
+      "eval_steps_per_second": 52.592,
       "step": 267
     },
     {
       "epoch": 1.87,
-      "grad_norm": 9.532360076904297,
-      "learning_rate": 9.65168237740807e-06,
-      "loss": 0.6057,
+      "grad_norm": 9.447751998901367,
+      "learning_rate": 9.825065893169892e-07,
+      "loss": 0.6083,
       "step": 500
     },
     {
       "epoch": 2.0,
-      "eval_accuracy": 0.7657276995305164,
-      "eval_loss": 0.5776590704917908,
-      "eval_runtime": 2.4625,
-      "eval_samples_per_second": 864.981,
-      "eval_steps_per_second": 54.417,
+      "eval_accuracy": 0.7615023474178404,
+      "eval_loss": 0.6037774682044983,
+      "eval_runtime": 2.5378,
+      "eval_samples_per_second": 839.304,
+      "eval_steps_per_second": 52.801,
       "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": 535476916548000.0,
+  "total_flos": 349221394826640.0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "num_train_epochs": 5
+    "weight_decay": 7.20792967242443e-05
   }
 }

run-8/checkpoint-534/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d42e5e5ec734e47895bff309ce0f98b97c457fc4dc71b42d53c94016f0c7a855
+oid sha256:bdb2ef8859512db3ee2bd403cc62214600a2b1130c00ff139bb4bf68c4b996b7
 size 4856

run-9/checkpoint-267/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:971a3ddf817b712dc07195c844772ef5d1ec4a8fd2faa3cfc511b714130228d0
+oid sha256:75ca88a2e25fd0e485c4c67aa2dded37ef1dfa4ca4a7f5b9ace95621c59a503b
 size 409103316

run-9/checkpoint-267/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cc8b54fc5e8c9423b8eb78032472c72dce9ff03db39846d1622f31a3d6911c46
+oid sha256:2d3f9eb57e84a6a6e974b22318994029f8d4798854328611ca3366f8f7e313e6
 size 818327802

run-9/checkpoint-267/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d605219d0cdfe1356d19dfc261c4f045664dbc44ddf04517d0b2ebd1dab264c7
+oid sha256:ef3be8be9037b2d6a9348611f95c19fb1d17ca7cb1da92486df22b7e0a3c655a
 size 1064

run-9/checkpoint-267/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6019130349159241,
+  "best_metric": 0.6065868735313416,
   "best_model_checkpoint": "BERT-WMM/run-9/checkpoint-267",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,23 +10,23 @@
   "log_history": [
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7563380281690141,
-      "eval_loss": 0.6019130349159241,
-      "eval_runtime": 2.4823,
-      "eval_samples_per_second": 858.067,
-      "eval_steps_per_second": 53.982,
+      "eval_accuracy": 0.7530516431924883,
+      "eval_loss": 0.6065868735313416,
+      "eval_runtime": 2.5841,
+      "eval_samples_per_second": 824.279,
+      "eval_steps_per_second": 51.856,
       "step": 267
     }
   ],
   "logging_steps": 500,
-  "max_steps": 801,
+  "max_steps": 534,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 3,
+  "num_train_epochs": 2,
   "save_steps": 500,
   "total_flos": 0,
   "train_batch_size": 32,
   "trial_name": null,
   "trial_params": {
-    "per_device_train_batch_size": 32
+    "weight_decay": 0.01864360010090689
   }
 }

run-9/checkpoint-267/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cc12ec9008fe3ca8c11132361abe51e0525170497895a06dfb1609f916fd77f
+oid sha256:025792d99deb7ef852ba1bdf1f59c07e051f6266f6a226e200f2e0869c199cb5
 size 4856

runs/Apr19_10-19-01_dcdaa3e6ec43/events.out.tfevents.1713522988.dcdaa3e6ec43.789.9

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e40a53c000a57dc8edf696a31748015db6300735236215abca4e74096a2caf18
+size 6120

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bdb2ef8859512db3ee2bd403cc62214600a2b1130c00ff139bb4bf68c4b996b7
+oid sha256:025792d99deb7ef852ba1bdf1f59c07e051f6266f6a226e200f2e0869c199cb5
 size 4856