Training in progress, step 10, checkpoint

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ab4032206871f76f267774b23b5210fddd18559968f207e84376a2a9e45c5846
+oid sha256:c5364d09e27bdf541cc4080b011a0a833388b061da2ef703197275a4e77a4aa4
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.006015037593984963,
+  "epoch": 0.006683375104427736,
   "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": 25.243,
       "eval_steps_per_second": 25.243,
       "step": 9
+    },
+    {
+      "epoch": 0.006683375104427736,
+      "grad_norm": NaN,
+      "learning_rate": 0.0,
+      "loss": 6.3319,
+      "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": 230212780425216.0,
+  "total_flos": 255791978250240.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null