Training in progress, step 102, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:445157a2da3fe723d8d462303238c3345eb0a462630ac50d8231654008e6639e
+oid sha256:983ce9be9febb14c2e07e474cca4865436b733e916adee9366fdfc223b478984
 size 11710970

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8269368413165814a4034deba6289bdc53a41273ac7335b3b55dcfdfdd18a5df
+oid sha256:ebedbcb21887d5e19a46eb3a841d91615a2cda438d048157d9c55d58ff5a6125
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c36d1103f9cf443ef6a8460ca4877e2b01fa05525fe64b908b45ddbdd2a7b862
+oid sha256:55453edc7ae4b6242ad6bf3479593988d77a7dd0d971dd86170c4caeeca3a0e8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.7684729064039408,
+  "epoch": 1.0049261083743843,
   "eval_steps": 26,
-  "global_step": 78,
+  "global_step": 102,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -88,6 +88,27 @@
       "eval_samples_per_second": 80.07,
       "eval_steps_per_second": 40.966,
       "step": 78
+    },
+    {
+      "epoch": 0.7881773399014779,
+      "grad_norm": 0.0,
+      "learning_rate": 2.432871841823047e-05,
+      "loss": 0.0,
+      "step": 80
+    },
+    {
+      "epoch": 0.8866995073891626,
+      "grad_norm": 0.0,
+      "learning_rate": 7.457877035729588e-06,
+      "loss": 0.0,
+      "step": 90
+    },
+    {
+      "epoch": 0.9852216748768473,
+      "grad_norm": 0.0,
+      "learning_rate": 2.0971737622883515e-07,
+      "loss": 0.0,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -102,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1876255020417024.0,
+  "total_flos": 2453564257468416.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null