Training in progress, step 16, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d44e95eba41a6246a6899f74e4fa9deb61e2e866f84fa70295160965700769f0
+oid sha256:6517a209ac5d5a1c26f06016c074944deebfb838c486c25d12b5c411ff56d5ee
 size 49846260

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:da06106ad662df46a5bbfc803eb00ea8cc26abfe20d636176f9e3fb364e20881
+oid sha256:f70701041128af6937348c92468e75d858b8823688a9ee96c3d463a6a67a0f8a
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:68888158764ed5e658b457a541f86335ea31432325308674d2962aa98e037fa4
+oid sha256:5b52924c88c1c80163d374a6650253dd74b8b46052a3da6fc5e4076e57b5effa
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.013015184381778741,
+  "epoch": 0.01735357917570499,
   "eval_steps": 4,
-  "global_step": 12,
+  "global_step": 16,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -123,6 +123,42 @@
       "eval_samples_per_second": 7.656,
       "eval_steps_per_second": 3.838,
       "step": 12
+    },
+    {
+      "epoch": 0.014099783080260303,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019723699203976766,
+      "loss": 0.0,
+      "step": 13
+    },
+    {
+      "epoch": 0.015184381778741865,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 14
+    },
+    {
+      "epoch": 0.016268980477223426,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001923879532511287,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.01735357917570499,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001891006524188368,
+      "loss": 0.0,
+      "step": 16
+    },
+    {
+      "epoch": 0.01735357917570499,
+      "eval_loss": NaN,
+      "eval_runtime": 50.8293,
+      "eval_samples_per_second": 7.653,
+      "eval_steps_per_second": 3.836,
+      "step": 16
     }
   ],
   "logging_steps": 1,
@@ -142,7 +178,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 3353811515080704.0,
+  "total_flos": 4471748686774272.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null