Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b78ca475a4a2253000eb475ef6dcb726714b821cfe95d17a9f8279bb576c4daf
+oid sha256:ea697372a0aafbe63523ca4a938b2f21e3fee46f35a1d1aa512295b0a1247a9a
 size 456603682

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe857a15cfad11d521d686079650bc523522af67539d91db4012db6206f54275
+oid sha256:aa382952e0adbb7e7abb917278c0a70d8bfd97851369da627797b4983c8f9cb6
 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": 0.23952095808383234,
+  "epoch": 0.47904191616766467,
   "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": 0.2874251497005988,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.3592814371257485,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.38323353293413176,
+      "eval_loss": NaN,
+      "eval_runtime": 3.1093,
+      "eval_samples_per_second": 5.789,
+      "eval_steps_per_second": 2.895,
+      "step": 16
+    },
+    {
+      "epoch": 0.4311377245508982,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 5718201178521600.0,
+  "total_flos": 1.14364023570432e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null