Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:7627004b5709b0660422cbd70c6ac0b419042fef40957dc1b5cf176392fc657a
+oid sha256:83afaf26176540c96ace16c89c5ba3bee1dba9a60f1c9d874b5813d14c82265c
 size 403961210

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6b0ef7915397502015c95bbe7ddaaea74270df10182e3225089e3815cd07e413
+oid sha256:58654d86a9a025b3b3d19760e390ca6010eebdf6667192ab0d5a530f9c3a9144
 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": 1.1647058823529413,
+  "epoch": 1.1764705882352942,
   "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": 69.355,
       "eval_steps_per_second": 8.727,
       "step": 99
+    },
+    {
+      "epoch": 1.1764705882352942,
+      "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": 2.1071501130203136e+16,
+  "total_flos": 2.128481591545037e+16,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null