Training in progress, step 10, checkpoint

last-checkpoint/rng_state_0.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:d79213b91105086d030b1e0778fbe7d6283f4c083ba909b2ec62c9e7ab91b108
+oid sha256:21f7eadd2da0fdaa1df31db2f7e4034feec67fc55c23f4bb989d8ad1fbdf25b1
 size 14512

last-checkpoint/rng_state_1.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b610e79daca538339e134160174e96c554fad20f4a4463e6c489c0e388d47d5e
+oid sha256:859887ca88f9fa64e0df0ffa0367098b179fa3861c8d451393be4c1463944f45
 size 14512

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.005389221556886228,
+  "epoch": 0.005988023952095809,
   "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": 14.668,
       "eval_steps_per_second": 7.334,
       "step": 9
+    },
+    {
+      "epoch": 0.005988023952095809,
+      "grad_norm": NaN,
+      "learning_rate": 0.00012,
+      "loss": 8.6476,
+      "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": 3329215646662656.0,
+  "total_flos": 3699128496291840.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null