Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03be4978e0b498e2e7caee9f057aa76ef8e3bceebed2cc6981fcdbe64b19023f
+oid sha256:18498b67e31b5edd37d5e3e65b03bfce6d932368a90736ebd08ea72bc9167681
 size 671466706

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5bf5969a0aae65742d515a959c2c593b8e0b14be862d05c119d875b5572fb9d8
+oid sha256:b1d725bb0b95d9fd9aaa9e04e11000ae18e164b23baf55cb213d4e1cbaba621f
 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": 0.10089332632685234,
+  "epoch": 0.11098265895953757,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -305,6 +305,35 @@
       "eval_samples_per_second": 8.268,
       "eval_steps_per_second": 4.135,
       "step": 90
+    },
+    {
+      "epoch": 0.10425643720441408,
+      "grad_norm": NaN,
+      "learning_rate": 2.815857265976462e-06,
+      "loss": 0.0,
+      "step": 93
+    },
+    {
+      "epoch": 0.10761954808197582,
+      "grad_norm": NaN,
+      "learning_rate": 9.233744553646754e-07,
+      "loss": 0.0,
+      "step": 96
+    },
+    {
+      "epoch": 0.11098265895953757,
+      "grad_norm": NaN,
+      "learning_rate": 5.7822281945782424e-08,
+      "loss": 0.0,
+      "step": 99
+    },
+    {
+      "epoch": 0.11098265895953757,
+      "eval_loss": NaN,
+      "eval_runtime": 363.4949,
+      "eval_samples_per_second": 8.267,
+      "eval_steps_per_second": 4.135,
+      "step": 99
     }
   ],
   "logging_steps": 3,
@@ -324,7 +353,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5.869237232405053e+17,
+  "total_flos": 6.462315541875917e+17,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null