Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7fcf4897bc77cb30e174f553e0fb979d3060a22013740f7b4fd53170bc37ca9a
+oid sha256:bed55db30cb5174cfe97860f0502a12d5c5be274be9b6bb71059405612278681
 size 202110330

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:29163dfd7463768137db499ee4e467be9a61499b9fc3f5ceec2df76d5636ff11
+oid sha256:934248805fad5c0ec50683015193c51b620ca656f95541ca775597e932385545
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
+oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07520760432443725,
+  "epoch": 0.08272836475688097,
   "eval_steps": 50,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -653,6 +653,69 @@
       "learning_rate": 5.709035061653494e-06,
       "loss": 0.0,
       "step": 90
+    },
+    {
+      "epoch": 0.07604324437248655,
+      "grad_norm": NaN,
+      "learning_rate": 4.635649805813696e-06,
+      "loss": 0.0,
+      "step": 91
+    },
+    {
+      "epoch": 0.07687888442053585,
+      "grad_norm": NaN,
+      "learning_rate": 3.670761277863485e-06,
+      "loss": 0.0,
+      "step": 92
+    },
+    {
+      "epoch": 0.07771452446858516,
+      "grad_norm": NaN,
+      "learning_rate": 2.815857265976462e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.07855016451663446,
+      "grad_norm": NaN,
+      "learning_rate": 2.072255970174258e-06,
+      "loss": 0.0,
+      "step": 94
+    },
+    {
+      "epoch": 0.07938580456468376,
+      "grad_norm": NaN,
+      "learning_rate": 1.4411039697577175e-06,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.08022144461273306,
+      "grad_norm": NaN,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.08105708466078237,
+      "grad_norm": NaN,
+      "learning_rate": 5.198657283805279e-07,
+      "loss": 0.0,
+      "step": 97
+    },
+    {
+      "epoch": 0.08189272470883167,
+      "grad_norm": NaN,
+      "learning_rate": 2.311999700154027e-07,
+      "loss": 0.0,
+      "step": 98
+    },
+    {
+      "epoch": 0.08272836475688097,
+      "grad_norm": NaN,
+      "learning_rate": 5.7822281945782424e-08,
+      "loss": 0.0,
+      "step": 99
     }
   ],
   "logging_steps": 1,
@@ -672,7 +735,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.500747528732672e+16,
+  "total_flos": 8.25082228160594e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null