Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6504cfbd1dd963b655dd975f320308f8e764b37597448e504e8ea559cc339936
+oid sha256:c956afbc7d95e23b03d314666ec35401fd1949a5bb9faffbc17f5f0fd23cb1e5
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:756f5354e70cf8ea389a55b973a7a83a0698ead411ced9a550dad53863f8e805
+oid sha256:85d7dcb82cc9c8edaa0c5feb250680d2ea54a2f1b97d0e9fe9ea7b25c22b72c1
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:1eca0ddb3ec890c90e8e6e7325bec40cdb8b59e4bebf5c0da8473b02809de875
+oid sha256:b4849a6ac0a1d895740f1ab4eba9d346b8d898008d0cfe93dd108cd928d7c63e
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0007027304004099261,
+  "epoch": 0.000780811556011029,
   "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": 30.918,
       "eval_steps_per_second": 15.459,
       "step": 9
+    },
+    {
+      "epoch": 0.000780811556011029,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 2221.7275,
+      "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": 9552061305716736.0,
+  "total_flos": 1.073511477018624e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null