Training in progress, step 19000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7d9a3900750d852ef912d4ac403e488e326c033ebb670c82e9bcf1a2a60b073d
+oid sha256:4034b893df99ef32f895b5e5e6d1535158a45b8f601e0224a5c774c0c5e859c8
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:13a30bbde9b4602c5ab8825e275aa2bdaf413702030191e06267677988829194
+oid sha256:2e35b57652f0b1ba1d253575c71787d9953bfbf106f0f41af80c39d7cc7d0377
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5376bea5aa8f9ef4ec637a1ceab235b8c9ce7715c6e0e96c31bed840be3b0276
+oid sha256:b318bfadd5f15f05235ae792e4a6e53e6886f2c00fc19f33f31e85e484139841
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.25095634716080195,
-  "global_step": 18500,
+  "epoch": 0.25773895113812095,
+  "global_step": 19000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -228,11 +228,17 @@
       "learning_rate": 0.0,
       "loss": 0.0361,
       "step": 18500
+    },
+    {
+      "epoch": 0.26,
+      "learning_rate": 0.0,
+      "loss": 0.04,
+      "step": 19000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 1.933141486023475e+16,
+  "total_flos": 1.985382905492275e+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 sha256:063edb9a5890416332d4caf3919f08d6691c1c75227fa729ad77e7020debbf29
-size 51437
+oid sha256:1b29b336f54b2c2f80a75e59d75a3d03f6f38bfeed2baea963d2dc7f8700c58e
+size 51597