Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:03b5a1c40a4ae184cb2ad42270c3f7fdba8b55271dc78762a31c854ec74cbb03
+oid sha256:2d8cda8f7c29e6be55ab7a16acec36c2ba3174fa1c0aed5691247adce6e0c2c1
 size 456463538

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7660ec599cee840fa63f8d265545d31143a080479ffe82d67a32405f0ccabab9
+oid sha256:5ccb7c83e5396e4497b5b5d55988e56a07f1a06aafb1e48f7a9a0abe2d036c6b
 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": 0.0051013901288101005,
+  "epoch": 0.010202780257620201,
   "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": 0.006121668154572121,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.007652085193215151,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.008162224206096162,
+      "eval_loss": NaN,
+      "eval_runtime": 148.1125,
+      "eval_samples_per_second": 5.577,
+      "eval_steps_per_second": 2.788,
+      "step": 16
+    },
+    {
+      "epoch": 0.00918250223185818,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6147066266910720.0,
+  "total_flos": 1.21511775043584e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null