Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:aabdf806b6dc8aa08fcc47aa653cd3948303217ffc47cd4409799423b279d04f
+oid sha256:53590e2d62b9c7c6849c90cf431d1bc80555b8303247bbb4b042a3994b74d366
 size 335922386

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ce222c2390094b071bddb3c451bd7b53527591253692707adf546412178fd3cd
+oid sha256:c32871ed367fbfce842fc140e0a7e8cd760b068dd07514dcbc3cbab9304e7efd
 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": 0.00850520944078248,
+  "epoch": 0.01701041888156496,
   "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": 0.010206251328938975,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.01275781416117372,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.013608335105251966,
+      "eval_loss": NaN,
+      "eval_runtime": 28.3453,
+      "eval_samples_per_second": 17.463,
+      "eval_steps_per_second": 8.749,
+      "step": 16
+    },
+    {
+      "epoch": 0.015309376993408463,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3709436417802240.0,
+  "total_flos": 7418872835604480.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null