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:d350fb63629b5bbbb1b6067754fd294bad8dde900daee7588c8d726fa5fb4835
+oid sha256:a43ddc14c7ec51649c402ce4d44c026af80252540e3350ce764c94187f06272c
 size 14244

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.00012525442304681385,
+  "epoch": 0.0001391715811631265,
   "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": 9.839,
       "eval_steps_per_second": 9.839,
       "step": 9
+    },
+    {
+      "epoch": 0.0001391715811631265,
+      "grad_norm": NaN,
+      "learning_rate": 0.00014,
+      "loss": 6.5318,
+      "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": 2855961781862400.0,
+  "total_flos": 3173290868736000.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null