Training in progress, step 25000

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:cb9c7975c693158eab0a87adaa62d5d030fd3be4687286288b578024194eaf2d
+oid sha256:b58d7a4197922b61f83ff9d713941cbbebe278e367b9814d639cba2a86fb9fcd
 size 1001681601

last-checkpoint/scaler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:be764eac598f1b2295001e05429ac611310bdd22bbc2cc016cd4f0e2d94028a9
+oid sha256:1145810353e4b7152829d4377369d8363615b91deef8459a560a149fa485445b
 size 559

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:55ddf7d019c8d382f559ce56ec95c9527804522ae869f374c000d73feb0de486
+oid sha256:fd373205ed845d7c739563d3502d998a72e212cbd5009144265dedb625ada475
 size 623

last-checkpoint/trainer_state.json

@@ -1,8 +1,8 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.33234759488862964,
-  "global_step": 24500,
+  "epoch": 0.33913019886594864,
+  "global_step": 25000,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -300,11 +300,17 @@
       "learning_rate": 0.0,
       "loss": 0.0376,
       "step": 24500
+    },
+    {
+      "epoch": 0.34,
+      "learning_rate": 0.0,
+      "loss": 0.0362,
+      "step": 25000
     }
   ],
   "max_steps": 73718,
   "num_train_epochs": 1,
-  "total_flos": 2.560038519649075e+16,
+  "total_flos": 2.612279939117875e+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:e6da88be3f1a12305990d6a26be7a43fea0838742cdf0e9bfde5823317609a16
-size 53357
+oid sha256:528ae5356437b1210aaf585675304cf9ab34d9c8e2e8de7cd48b03204ea3b39b
+size 53517