Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:fe6761db302d71b032c9f7d45329ea3f0288ae940e638bcaaf42d7ee0af58561
+oid sha256:16e9353f754dc20cf77ef7626d29c2c848a1e0d3596071fa01d0d59ff344ff74
 size 150486964

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:b953f866251e427e44ebe6e7ea847b5fd232ef47dc17bde3f2df9f1ccd4c636b
+oid sha256:5d789fa52b543d6c3dd3d3bad33aff3492a9afcb02eb4b7e87a4d13f60f96291
 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": 2.769230769230769,
+  "epoch": 3.076923076923077,
   "eval_steps": 1,
-  "global_step": 9,
+  "global_step": 10,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -100,6 +100,14 @@
       "eval_samples_per_second": 34.979,
       "eval_steps_per_second": 5.83,
       "step": 9
+    },
+    {
+      "epoch": 3.076923076923077,
+      "eval_loss": NaN,
+      "eval_runtime": 0.1688,
+      "eval_samples_per_second": 35.538,
+      "eval_steps_per_second": 5.923,
+      "step": 10
     }
   ],
   "logging_steps": 3,
@@ -114,12 +122,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2364257347829760.0,
+  "total_flos": 2593879464345600.0,
   "train_batch_size": 8,
   "trial_name": null,
   "trial_params": null