Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 2.3822651045256147,
+  "epoch": 2.749827705031013,
   "eval_steps": 500,
-  "global_step": 650,
+  "global_step": 750,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -463,6 +463,76 @@
       "learning_rate": 5.5130235322263634e-06,
       "loss": 0.4155,
       "step": 650
+    },
+    {
+      "epoch": 2.4190213645761545,
+      "grad_norm": 0.40967750549316406,
+      "learning_rate": 4.894372840954112e-06,
+      "loss": 0.433,
+      "step": 660
+    },
+    {
+      "epoch": 2.4557776246266942,
+      "grad_norm": 0.3949553370475769,
+      "learning_rate": 4.3087556423111186e-06,
+      "loss": 0.4262,
+      "step": 670
+    },
+    {
+      "epoch": 2.492533884677234,
+      "grad_norm": 0.3676910698413849,
+      "learning_rate": 3.757134103817053e-06,
+      "loss": 0.4306,
+      "step": 680
+    },
+    {
+      "epoch": 2.529290144727774,
+      "grad_norm": 0.4114847481250763,
+      "learning_rate": 3.2404145382112254e-06,
+      "loss": 0.4351,
+      "step": 690
+    },
+    {
+      "epoch": 2.566046404778314,
+      "grad_norm": 0.38977691531181335,
+      "learning_rate": 2.759445914383135e-06,
+      "loss": 0.4293,
+      "step": 700
+    },
+    {
+      "epoch": 2.602802664828854,
+      "grad_norm": 0.39468637108802795,
+      "learning_rate": 2.315018462518803e-06,
+      "loss": 0.422,
+      "step": 710
+    },
+    {
+      "epoch": 2.6395589248793936,
+      "grad_norm": 0.3883320093154907,
+      "learning_rate": 1.9078623757546767e-06,
+      "loss": 0.418,
+      "step": 720
+    },
+    {
+      "epoch": 2.6763151849299334,
+      "grad_norm": 0.4122566878795624,
+      "learning_rate": 1.5386466104722053e-06,
+      "loss": 0.4268,
+      "step": 730
+    },
+    {
+      "epoch": 2.713071444980473,
+      "grad_norm": 0.40187907218933105,
+      "learning_rate": 1.2079777872042592e-06,
+      "loss": 0.4256,
+      "step": 740
+    },
+    {
+      "epoch": 2.749827705031013,
+      "grad_norm": 0.3951718211174011,
+      "learning_rate": 9.163991939592081e-07,
+      "loss": 0.4315,
+      "step": 750
     }
   ],
   "logging_steps": 10,
@@ -482,7 +552,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 2.163261743877325e+16,
+  "total_flos": 2.496191032773837e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null