Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c9f96af6d233d9d304c59b9643aa52b85f72b13e07491f5379e9e1662d6bba73
+oid sha256:99b3e3c760e32d29e569c3b424cea368587450300225a55a8014a3efd35da2a9
 size 23159290

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bf0b8f8ffa55b7767699fa4939b6efada3f1f84754107a5e73442530d2c0e2ef
+oid sha256:383926143ae71eb8356d446138d63ca482634206b203024857d484429b7d7c2e
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6a946ba862c9290cf73cbdcd016309ecac1eb5b3695453bc8a42a8a259a1c695
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.03590798578642229,
+  "epoch": 0.037404151860856556,
   "eval_steps": 4,
-  "global_step": 48,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -447,6 +447,20 @@
       "eval_samples_per_second": 43.626,
       "eval_steps_per_second": 21.852,
       "step": 48
+    },
+    {
+      "epoch": 0.03665606882363942,
+      "grad_norm": NaN,
+      "learning_rate": 3.0826662668720364e-07,
+      "loss": 0.0,
+      "step": 49
+    },
+    {
+      "epoch": 0.037404151860856556,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 1,
@@ -461,12 +475,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2322534166953984.0,
+  "total_flos": 2419306423910400.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null