Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2a54c22f7979a7e29404c8001f24a0a2613650b3b8e6075655254ee2c5200856
+oid sha256:1d6658178aa8505baab812bdb9b1f6c8c527b166017dfef2e09fdd868e32c5a3
 size 1279641042

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:83eafbac03a7476b4d49b130d5ab2826387f76bc6958b712aec2504a5656c396
+oid sha256:27f51750ae8f732e53152795257053c08f61a635a331fbbf438ff56de7f64bd3
 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": 0.03173076923076923,
+  "epoch": 0.03205128205128205,
   "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": 10.389,
       "eval_steps_per_second": 1.299,
       "step": 99
+    },
+    {
+      "epoch": 0.03205128205128205,
+      "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": 2.634381633037271e+17,
+  "total_flos": 2.660991548522496e+17,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null