Training in progress, step 16000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:69060d2b2dade0bf8ac4362de6159dc575a98267145a42974ab6248a3d6edfbb
+oid sha256:a1cf85942c74aeb026ca5d8d434d4f93a4847a0ec283a4d21cdaff7456cd2768
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d8c79684988ee81b55321b607a9859548dfdd83a25c3260c4a215b3a8506244e
+oid sha256:ed25d91c449c921bfc25ace4856a038448584e05e8652f9c36f7881751be690c
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3a9efae48c0cce30eebaec8be6ed850fa5810899752a68b545c66558e8fa090e
+oid sha256:46dfe7ec60999efa24cad598707a555b4901ab4bf44c33de43b6d57dfd4b768e
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.21026072329688814,
-  "global_step": 15500,
+  "epoch": 0.2170433272742071,
+  "global_step": 16000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -192,11 +192,17 @@
       "learning_rate": 0.0,
       "loss": 0.0372,
       "step": 15500
+    },
+    {
+      "epoch": 0.22,
+      "learning_rate": 0.0,
+      "loss": 0.0356,
+      "step": 16000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 1.6196929692106752e+16,
+  "total_flos": 1.6719343886794752e+16,
   "trial_name": null,
   "trial_params": null
 }

runs/Oct16_21-59-35_1b3a04926831/events.out.tfevents.1665958666.1b3a04926831.23.0

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:00d46dd91655da7e5e32fc8068efeb1f650f7f8af865a859e317dbe3e0c5de91
-size 50480
+oid sha256:ce48718cab36fcd459fe0042e72914b27c7aed7aa026e713a5ac4dcfd504dbe7
+size 50637