Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d0a7b34b516a5b310f1e2864f18259a213dd890c06dd2314c9a12f3fd8e72365
+oid sha256:3896627fc2d7c28cd81eb8f899d74c01c958cb67d8e2eb564eca76d36b4cef38
 size 90365754

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf8458deb9e9051cce2923af60756792030453111bf49c61a81f13d487534139
+oid sha256:d9831f0cf24562c4aa0445054e0c4fe9592fc95c9d51bace12a68c8402389fc0
 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": 0.0013633729847643068,
+  "epoch": 0.0027267459695286137,
   "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": 0.0016360475817171682,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0020450594771464605,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.002181396775622891,
+      "eval_loss": NaN,
+      "eval_runtime": 135.1404,
+      "eval_samples_per_second": 22.858,
+      "eval_steps_per_second": 11.433,
+      "step": 16
+    },
+    {
+      "epoch": 0.0024540713725757523,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 665309266575360.0,
+  "total_flos": 1221749744074752.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null