Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a7b032fac5374b0c83707d1727da500ec767fda1c335c156c6d066f9bc9f6d43
+oid sha256:4eb5d637bc626773e33df0908a7c9822fc3b6f5ab608e8f7d4647e1211679a4a
 size 4628218

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6c3c636144aec0d964e16b995a92b445c8d1723a01cb1c6ade2ae2a4b3800da5
+oid sha256:d08f5ce0833dd08d8170484854efa6b4436ebd53e47e18cf9f4d0a17914e13a5
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eef4c60eef56c59d148e4191bea64e9a3bf517b29f5a413c536dcdc8e61edf1
+oid sha256:5416093c744b622c4436f38b8545546a70241fb2d36e53a533c7ae67d7ced8b6
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.17942908926144088,
+  "epoch": 0.18124150430448574,
   "eval_steps": 9,
-  "global_step": 99,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -236,6 +236,13 @@
       "eval_samples_per_second": 284.445,
       "eval_steps_per_second": 35.664,
       "step": 99
+    },
+    {
+      "epoch": 0.18124150430448574,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 100
     }
   ],
   "logging_steps": 5,
@@ -250,12 +257,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1772877879705600.0,
+  "total_flos": 1790853827788800.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null