Training in progress, step 20, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:108c005c30b32dfd92df44d595b89a05c8a16cd46be2059e653e628904de1b05
+oid sha256:7f60fd1c49fb8a2ae1003130e7c2ae8697c2cfe3c1dd878bb49577834d2dab4b
 size 148047722

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:06fccdcbc9936009eb2f352e0be2954b0ca27af350abe425d6a05cc38e05cef3
+oid sha256:6be021fdd8df982fc338b86ca131cb94cea4b6c7fd8feb56712e7bdd4631a3d1
 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": 0.0004081549356135589,
+  "epoch": 0.0008163098712271178,
   "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": 0.0004897859227362707,
+      "grad_norm": NaN,
+      "learning_rate": 0.00019510565162951537,
+      "loss": 0.0,
+      "step": 12
+    },
+    {
+      "epoch": 0.0006122324034203384,
+      "grad_norm": NaN,
+      "learning_rate": 0.00017071067811865476,
+      "loss": 0.0,
+      "step": 15
+    },
+    {
+      "epoch": 0.0006530478969816942,
+      "eval_loss": NaN,
+      "eval_runtime": 260.067,
+      "eval_samples_per_second": 39.667,
+      "eval_steps_per_second": 19.833,
+      "step": 16
+    },
+    {
+      "epoch": 0.000734678884104406,
+      "grad_norm": NaN,
+      "learning_rate": 0.00013090169943749476,
+      "loss": 0.0,
+      "step": 18
     }
   ],
   "logging_steps": 3,
@@ -63,7 +92,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 653134418411520.0,
+  "total_flos": 1306268836823040.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null