Training in progress, step 100, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bda070ce8697c300bbcd60d0635b8325887f21fdcc6715ad16e17bcfe2c59e4a
+oid sha256:8f5821ef7ab41bd6f9c2685b0841c6a9fbd8d5787f6afbc7ad1da85983167fbe
 size 25986148

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:0104cd3a39a39e7efe96d4368d017e590c56f84656f77b6c2e0cc8bfebf6aafb
+oid sha256:e2ee64302c2e6d99452e0846f387608fbc785131d28043c874888db195b7f800
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:dd09e47b42474af18ba1772930aac1db12bb0a5a5868e68e151935c59da27a51
+oid sha256:3a60c7d771c1fd156acee762fba03c724cb41829a3f71df370ecd1d20b134982
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.04133611691022965,
+  "epoch": 0.04175365344467641,
   "eval_steps": 17,
-  "global_step": 99,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -748,6 +748,13 @@
       "learning_rate": 6.09172980904238e-08,
       "loss": 3.1884,
       "step": 99
+    },
+    {
+      "epoch": 0.04175365344467641,
+      "grad_norm": Infinity,
+      "learning_rate": 0.0,
+      "loss": 3.0133,
+      "step": 100
     }
   ],
   "logging_steps": 1,
@@ -762,12 +769,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 4.076300337256858e+16,
+  "total_flos": 4.11747508813824e+16,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null