Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:941c7ed01a07aa7121958040edff38e95342718700f98134a439f7f2a6cfb992
+oid sha256:9949a30a23a8013f8224e48e32c757b1b701acca116a730de6bf0d88dd11520f
 size 194840426

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:57f02eb3738b77c898c838a6336aca82020e5d936b1dd64278c66726c4010e02
+oid sha256:fcf6c19ee75bdf29e31ec9eb1c5a0d520c927e293a59c79589a94b1d3e8bf196
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
+oid sha256:a62e6ea25099651400ff4a3142a50e40bef5b52ba883be53b2fcb9d1a5b0a98c
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005700441784238278,
+  "epoch": 0.011400883568476556,
   "eval_steps": 8,
-  "global_step": 10,
+  "global_step": 20,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -44,6 +44,35 @@
       "learning_rate": 0.00018,
       "loss": 0.0,
       "step": 9
+    },
+    {
+      "epoch": 0.006840530141085934,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.008550662676357419,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.009120706854781245,
+      "eval_loss": NaN,
+      "eval_runtime": 49.1939,
+      "eval_samples_per_second": 15.022,
+      "eval_steps_per_second": 7.521,
+      "step": 16
+    },
+    {
+      "epoch": 0.010260795211628902,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1397421464616960.0,
+  "total_flos": 2794842929233920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null