Training in progress, epoch 1

model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7e30af18b4b712a2743d94beaab28c03b2fda61bc9f9ba12362e144acb8dfd1e
+oid sha256:820c084205589a5efc90f718f254e9298580a8c2d7e7c8732b8e7ce2edb3a47e
 size 409103316

run-2/checkpoint-533/model.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b3f8bc86473dc6e49e5578f4589f64cd37bb4dfca4e3d40dd3405de2a852912d
+oid sha256:820c084205589a5efc90f718f254e9298580a8c2d7e7c8732b8e7ce2edb3a47e
 size 409103316

run-2/checkpoint-533/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ac1ec9315a7035dfa0ae848e4f0165b9eb53cf097553748b3c9407be9ecaa783
+oid sha256:6213cb07acde88b7b1823a46019c33766c4ef04f8e878c0f4599cfd5eb53d547
 size 818327802

run-2/checkpoint-533/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b0264e372e70424f6b6711fd04881a8a6c4d0ee42c02147258bf73943b72b029
+oid sha256:703ae037e1f026162d0ee8b19ed9420b2c79adb2d7c69a2922cb2e184b1ff806
 size 1064

run-2/checkpoint-533/trainer_state.json

@@ -1,5 +1,5 @@
 {
-  "best_metric": 0.6080508828163147,
+  "best_metric": 0.647247314453125,
   "best_model_checkpoint": "BERT-WMM/run-2/checkpoint-533",
   "epoch": 1.0,
   "eval_steps": 500,
@@ -10,33 +10,30 @@
   "log_history": [
     {
       "epoch": 0.94,
-      "grad_norm": 9.333391189575195,
-      "learning_rate": 1.2018217372024236e-05,
-      "loss": 0.7056,
+      "grad_norm": 11.24305248260498,
+      "learning_rate": 2.922625428602704e-06,
+      "loss": 0.7917,
       "step": 500
     },
     {
       "epoch": 1.0,
-      "eval_accuracy": 0.7427230046948357,
-      "eval_loss": 0.6080508828163147,
-      "eval_runtime": 1.9882,
-      "eval_samples_per_second": 1071.329,
-      "eval_steps_per_second": 67.398,
+      "eval_accuracy": 0.7352112676056338,
+      "eval_loss": 0.647247314453125,
+      "eval_runtime": 2.1238,
+      "eval_samples_per_second": 1002.939,
+      "eval_steps_per_second": 63.096,
       "step": 533
     }
   ],
   "logging_steps": 500,
-  "max_steps": 3198,
+  "max_steps": 1599,
   "num_input_tokens_seen": 0,
-  "num_train_epochs": 6,
+  "num_train_epochs": 3,
   "save_steps": 500,
   "total_flos": 169371040368096.0,
   "train_batch_size": 16,
   "trial_name": null,
   "trial_params": {
-    "learning_rate": 1.4245462993229616e-05,
-    "num_train_epochs": 6,
-    "per_device_train_batch_size": 16,
-    "weight_decay": 0.002285356379677195
+    "learning_rate": 4.252300327876e-06
   }
 }

run-2/checkpoint-533/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5a522d40064169dd451f5c63d95d053409f9056cc8f37d6ef08fd626cff2d294
+oid sha256:6b47f82980a9cdafe965500d0bc73ea3bdf726aae69cba15d6dccf27551f040c
 size 4856

runs/Apr18_16-31-07_544fc269209b/events.out.tfevents.1713458197.544fc269209b.792.2

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e3967c5a0ce893b9d481f47c3bcae87a2723a978aba5962270b4b7ffe6994a
+size 5635

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:96acc0d6a278deedc1ad94c23c932749f68e8e22ce3768b8816b072f56729d43
+oid sha256:6b47f82980a9cdafe965500d0bc73ea3bdf726aae69cba15d6dccf27551f040c
 size 4856