Training in progress, step 55, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2c29feb93714190670b2fb92ef70a723f460c9f0f0870090b889f1096cf82463
+oid sha256:930650721c72d23e9fae266c8c5d21a2175e37f2b7d0874884e2c8a3de77c554
 size 43122580

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:a2b3f6b12e0aa9c777494137b728f08bc96c5e3af997823b308e5dae78db59ee
+oid sha256:0a475de96534ac4885cc7c29d3b30cbfb9e96fa54dba429365183e4b0791c182
 size 14244

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:79af33a7cc5e89926792af60c545e28f6f3569216a6e1a04e51a93b6477fd5cc
+oid sha256:59fb9c579d7f7f4aa986f5f762cd9981f0dcd26b5aa72ad6a0ef96ae89405fbd
 size 1064

last-checkpoint/trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 0.0018329805573133742,
+  "epoch": 0.002400331682196085,
   "eval_steps": 14,
-  "global_step": 42,
+  "global_step": 55,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -67,6 +67,13 @@
       "eval_samples_per_second": 30.178,
       "eval_steps_per_second": 15.089,
       "step": 42
+    },
+    {
+      "epoch": 0.00218211971108735,
+      "grad_norm": NaN,
+      "learning_rate": 4.8943483704846475e-06,
+      "loss": 0.0,
+      "step": 50
     }
   ],
   "logging_steps": 10,
@@ -81,12 +88,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 7887027626311680.0,
+  "total_flos": 1.029695273435136e+16,
   "train_batch_size": 2,
   "trial_name": null,
   "trial_params": null