Training in progress, step 29000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:561e13eb73c252b54ef3668437d9d941dfc7139ab35a6e316d35be2a53f40445
+oid sha256:36bb26d74b0ffa4d3db928f988ca3708d797cba5de134a045f0091497b4ce7e4
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a6fdc1138a8383ef0f4cadead7d143459c0b814bf7c8ac3667f65d1b486e13bc
+oid sha256:85dc0a4de98b5e72a2c343f5f0a39beeb7c8fee484ab58eeda166b0dc77de33b
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c66c4c1f2f68881926de3acd7e5f446215252a292533aad7330ef9ea7f4ee30
+oid sha256:8237348758aff9824c2f165d62107519c759197166b5b89ab3a50ee0f4a524ff
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.38660842670718143,
-  "global_step": 28500,
+  "epoch": 0.3933910306845004,
+  "global_step": 29000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -348,11 +348,17 @@
       "learning_rate": 0.0,
       "loss": 0.0374,
       "step": 28500
+    },
+    {
+      "epoch": 0.39,
+      "learning_rate": 0.0,
+      "loss": 0.0362,
+      "step": 29000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 2.977969875399475e+16,
+  "total_flos": 3.030211294868275e+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:c4461da483d21c9261e7b273d288f732e5b544da5b8494151756f46ad06b232f
-size 54637
+oid sha256:235d5a5d28ee750fc32b4a240220b74e158cb9405646c4c72f3037ebcd05b5d6
+size 54797