Training in progress, step 14500

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9d7595fb3e59ca048769e488207a524c0c61e8cc1c128e8eb72db4ac11b640ae
+oid sha256:ac86c681f063b082205c4fc117276f1da77d6ae7ab0a7ee29ac9645587041645
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1afc5c555efbb51ab1a4afaf82a02fa0c21048a22fe3a3905683e67f884c2cfc
+oid sha256:4345da8dc415c1f0506e84237080bdfba33a945e846597251f9ae253de3f187e
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9cd0caeb935968f8a2d143b7498492f19a09aa3b9980670a530934169781ab4b
+oid sha256:6afcdde8cee84129dae8efb9ab76caa2ffcfb0a528ffa940b5f21700722371aa
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.18991291136493121,
-  "global_step": 14000,
+  "epoch": 0.1966955153422502,
+  "global_step": 14500,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -174,11 +174,17 @@
       "learning_rate": 0.0,
       "loss": 0.0378,
       "step": 14000
+    },
+    {
+      "epoch": 0.2,
+      "learning_rate": 0.0,
+      "loss": 0.0376,
+      "step": 14500
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 1.4629687108042752e+16,
+  "total_flos": 1.5152101302730752e+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 sha256:9fadf2e8ac11ddf24f735ccca846e748c90810786db2d10b32e356ddd9087a74
-size 50009
+oid sha256:29f131236c868cd41053823bb5950be5f9d5232d0cb9285ef867d0b8dbd53dc6
+size 50166