Training in progress, step 81, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e1101ae4a140d8c48d78c060b5b1a82992299967e2d9bafce48d694ba81133f
+oid sha256:2dd77812dea3ced1ab33526d0dde926a099ad85f063b12af5d8369288f18cf5b
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ee9627d324fa9d9eaa4cfb33dcf81f82b5bc2076fb94fc413cc20a4173caed78
+oid sha256:d18ca3d25ec89aa366b5c10e91c7e0eceb8609e7d059e580505d96a31b0d3bdf
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3f9245597e5014ecf432f2646dbac4f88c26cbc6ab1676ee7be71281b45d826d
+oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006469093512656007,
+  "epoch": 0.007277730201738007,
   "eval_steps": 9,
-  "global_step": 72,
+  "global_step": 81,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -247,6 +247,35 @@
       "eval_samples_per_second": 26.822,
       "eval_steps_per_second": 13.411,
       "step": 72
+    },
+    {
+      "epoch": 0.00673863907568334,
+      "grad_norm": NaN,
+      "learning_rate": 4.444297669803981e-05,
+      "loss": 0.0,
+      "step": 75
+    },
+    {
+      "epoch": 0.0070081846387106735,
+      "grad_norm": NaN,
+      "learning_rate": 3.5055195166981645e-05,
+      "loss": 0.0,
+      "step": 78
+    },
+    {
+      "epoch": 0.007277730201738007,
+      "grad_norm": NaN,
+      "learning_rate": 2.6567749056431467e-05,
+      "loss": 0.0,
+      "step": 81
+    },
+    {
+      "epoch": 0.007277730201738007,
+      "eval_loss": NaN,
+      "eval_runtime": 1398.2001,
+      "eval_samples_per_second": 26.813,
+      "eval_steps_per_second": 13.407,
+      "step": 81
     }
   ],
   "logging_steps": 3,
@@ -266,7 +295,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 7.510245941182464e+16,
+  "total_flos": 8.459891270221824e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null