Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:521a0d7eaae4e907f7fd69650050c9a3451db74c95a4db6219a2739aee1ccd19
+oid sha256:bc20014b0620344b3d5b5258a4ee83d13b6326a3a1b9e2d9785a9fd4e1f62fb0
 size 18763860

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:c7d68fceb13086e9892e1c9c3203d31df35fd3183cd6aac7813303ae766d2416
+oid sha256:05657592c9b81e5d630624065304f66deb1555f06d5f390bd8dc245592c6eb8b
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9c8e6b04902f17ae368c3e6cfd97a31ad4de2f025d673daea8c033ce0e260946
+oid sha256:bb578e75c11a81e85dda67a691f96ba4793a02960f1409fd3e1511aac873491a
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0005421278518183872,
+  "epoch": 0.0006023642797982079,
   "eval_steps": 3,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -102,6 +102,13 @@
       "eval_samples_per_second": 49.945,
       "eval_steps_per_second": 24.972,
       "step": 9
+    },
+    {
+      "epoch": 0.0006023642797982079,
+      "grad_norm": NaN,
+      "learning_rate": 0.0002,
+      "loss": 0.0,
+      "step": 10
     }
   ],
   "logging_steps": 1,
@@ -116,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 507541154955264.0,
+  "total_flos": 587155453771776.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null