Training in progress, step 50, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:71d8d14ba1f9a055eacb4624c664b7e9d2dd0741081affb76e710800221283d7
+oid sha256:a754ce524b3ddeafc09b93740ed507a617409c5c21c5b262310af50a67575a85
 size 10251668

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f7f9d5190350ad708c686673ab1c35280e35c0982927bf58b2dcb47471742285
+oid sha256:86af7b1fc47796ed18ffd9cd875ba7360388371865d580a574d91e2798d05773
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:216e1a9a1c53e7de93f56319b4855910155cb98dd7ebb5fa08b3717fd303059f
+oid sha256:e69e2b49ea642509f0c688c16fb190b7cf27dac0a18903a5e2d1467d0343d8b8
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.07854984894259819,
+  "epoch": 0.10070493454179255,
   "eval_steps": 13,
-  "global_step": 39,
+  "global_step": 50,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -60,6 +60,20 @@
       "eval_samples_per_second": 50.197,
       "eval_steps_per_second": 25.098,
       "step": 39
+    },
+    {
+      "epoch": 0.08056394763343404,
+      "grad_norm": NaN,
+      "learning_rate": 2.339555568810221e-05,
+      "loss": 0.0,
+      "step": 40
+    },
+    {
+      "epoch": 0.10070493454179255,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -74,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 317486699642880.0,
+  "total_flos": 407637243985920.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null