Training in progress, step 99, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:5d34e1bb5d8b95a3863d2c949546503729d6ef93d0f1822f1103de1d568ca84a
+oid sha256:a7b032fac5374b0c83707d1727da500ec767fda1c335c156c6d066f9bc9f6d43
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c94712c6df223864e9628cad82028db72f382ca22f7dd490c339b2f303b94547
+oid sha256:6c3c636144aec0d964e16b995a92b445c8d1723a01cb1c6ade2ae2a4b3800da5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:429c9f0a4ff1909f8cc1cafc3bf6eb6ff29e4592139b5344f1aee9b75eae7379
+oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.16311735387403714,
+  "epoch": 0.17942908926144088,
   "eval_steps": 9,
-  "global_step": 90,
+  "global_step": 99,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -221,6 +221,21 @@
       "eval_samples_per_second": 284.559,
       "eval_steps_per_second": 35.679,
       "step": 90
+    },
+    {
+      "epoch": 0.17217942908926145,
+      "grad_norm": NaN,
+      "learning_rate": 1.4411039697577175e-06,
+      "loss": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.17942908926144088,
+      "eval_loss": NaN,
+      "eval_runtime": 6.8976,
+      "eval_samples_per_second": 284.445,
+      "eval_steps_per_second": 35.664,
+      "step": 99
     }
   ],
   "logging_steps": 5,
@@ -240,7 +255,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1611094346956800.0,
+  "total_flos": 1772877879705600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null