Training in progress, step 90, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2dd77812dea3ced1ab33526d0dde926a099ad85f063b12af5d8369288f18cf5b
+oid sha256:a101c402afaf74f956b89a827bf8901a0ab5d7c8c859c32d66cb04672e72516d
 size 240145026

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d18ca3d25ec89aa366b5c10e91c7e0eceb8609e7d059e580505d96a31b0d3bdf
+oid sha256:172aeb48af9586a198746bc68bf5d4bdd20f0201d148d0a93190535d1641e37b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:4967fab956f007beafd6b8bc5c5dee4d86950ea055e4ab46c9a7cdc66a69112d
+oid sha256:f6b7babead6c4be4368caff2650e543461856d401ff242b042a60fc57cd3bcca
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.007277730201738007,
+  "epoch": 0.008086366890820007,
   "eval_steps": 9,
-  "global_step": 81,
+  "global_step": 90,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -276,6 +276,35 @@
       "eval_samples_per_second": 26.813,
       "eval_steps_per_second": 13.407,
       "step": 81
+    },
+    {
+      "epoch": 0.007547275764765341,
+      "grad_norm": NaN,
+      "learning_rate": 1.9098300562505266e-05,
+      "loss": 0.0,
+      "step": 84
+    },
+    {
+      "epoch": 0.007816821327792675,
+      "grad_norm": NaN,
+      "learning_rate": 1.2750399292720283e-05,
+      "loss": 0.0,
+      "step": 87
+    },
+    {
+      "epoch": 0.008086366890820007,
+      "grad_norm": NaN,
+      "learning_rate": 7.612046748871327e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.008086366890820007,
+      "eval_loss": NaN,
+      "eval_runtime": 1397.6994,
+      "eval_samples_per_second": 26.823,
+      "eval_steps_per_second": 13.411,
+      "step": 90
     }
   ],
   "logging_steps": 3,
@@ -295,7 +324,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 8.459891270221824e+16,
+  "total_flos": 9.409536599261184e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null