Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f0ebdf5f266083a24f8b372ea9bae2afcaaa7822c749a05e993ecb8e6c3ee544
+oid sha256:f765b9632202c0efb7a5d3cedf9a340b9d6f815a1474dfc1563bea017423a632
 size 70667778

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:889191a238b93a7b866e8884d43275d0708aa6182e3b5ea78be6593343dae26f
+oid sha256:510fe6f19deb1e0689fd3e0616a015c6bb26131855b40d5120b878ddc56ebe75
 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": 0.00035904386618435105,
+  "epoch": 0.0007180877323687021,
   "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": 0.0004308526394212213,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0005385657992765267,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0005744701858949617,
+      "eval_loss": NaN,
+      "eval_runtime": 351.2549,
+      "eval_samples_per_second": 33.386,
+      "eval_steps_per_second": 16.694,
+      "step": 16
+    },
+    {
+      "epoch": 0.0006462789591318319,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 211780325867520.0,
+  "total_flos": 401030829834240.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null