Training in progress, step 10, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:bddc5c22b349e86f6fa67078fa341ee526a5f1a7e2952bfaf73e20a4ce1544a5
+oid sha256:9b9a75f32be63387c28153328a1b0691f9e49ee128269c6ff2216dcfebb420ad
 size 41119636

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:ffe0152387846c1162de177cdc53167a9183696b149d3eb20d4cf5fbd6b53e78
+oid sha256:557fadda68f81af2c774a79a4c369bd061cd88e6452778324e57a9edcd611ffb
 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": 0.024866171645657055,
+  "epoch": 0.027629079606285616,
   "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": 41.75,
       "eval_steps_per_second": 20.875,
       "step": 9
+    },
+    {
+      "epoch": 0.027629079606285616,
+      "grad_norm": NaN,
+      "learning_rate": 0.0001,
+      "loss": 0.0,
+      "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": 6392840775008256.0,
+  "total_flos": 7166496664977408.0,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null