Training in progress, step 22500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5e79d4c7a5ae0fb073f8396a6273ffc3d639658036ed52c7c5c64eabdf1c6e39
+oid sha256:6752727125d8a458486449f14cb29a8951ef8b6b86eb31c214349c7584516238
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:814b005576e442840e04b7b07b1e40e5794878463e40f84b653e047e1d80f161
+oid sha256:5f97375a52d1a5552a8441aa3c009210bc31595f479b6207dc0e8a7d670520c9
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ba6291791132234cd1abf91e6a980b90f28032dcdd0420b193f11ebfa079c356
+oid sha256:1588acc9f4f6ab592a5992ff0b00747454806fa6d2c9856a6422002da04b2b24
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.2984345750020348,
-  "global_step": 22000,
+  "epoch": 0.30521717897935374,
+  "global_step": 22500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -270,11 +270,17 @@
       "learning_rate": 0.0,
       "loss": 0.0407,
       "step": 22000
+    },
+    {
+      "epoch": 0.31,
+      "learning_rate": 0.0,
+      "loss": 0.0399,
+      "step": 22500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 2.298831422305075e+16,
+  "total_flos": 2.351072841773875e+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 sha256:36c8a1d4eac3c83402fb52c09c1d3c7cb711d47ab3ca0c6fde8aeb17aa3584f7
-size 52557
+oid sha256:6a422614e9d6893e6d17070bd1d1e56291b79f942fa70ca11edd5ad39a892313
+size 52717