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": 2.749827705031013,
+  "epoch": 2.9924190213645763,
   "eval_steps": 500,
-  "global_step": 750,
+  "global_step": 816,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -533,6 +533,48 @@
       "learning_rate": 9.163991939592081e-07,
       "loss": 0.4315,
       "step": 750
+    },
+    {
+      "epoch": 2.7865839650815527,
+      "grad_norm": 0.39825597405433655,
+      "learning_rate": 6.643898936001369e-07,
+      "loss": 0.4214,
+      "step": 760
+    },
+    {
+      "epoch": 2.823340225132093,
+      "grad_norm": 0.38193032145500183,
+      "learning_rate": 4.5236393674580324e-07,
+      "loss": 0.4221,
+      "step": 770
+    },
+    {
+      "epoch": 2.8600964851826327,
+      "grad_norm": 0.4201795160770416,
+      "learning_rate": 2.8066968148658945e-07,
+      "loss": 0.428,
+      "step": 780
+    },
+    {
+      "epoch": 2.8968527452331725,
+      "grad_norm": 0.3711008131504059,
+      "learning_rate": 1.4958922103305574e-07,
+      "loss": 0.4211,
+      "step": 790
+    },
+    {
+      "epoch": 2.9336090052837123,
+      "grad_norm": 0.39392825961112976,
+      "learning_rate": 5.9337920237534375e-08,
+      "loss": 0.4295,
+      "step": 800
+    },
+    {
+      "epoch": 2.9703652653342525,
+      "grad_norm": 0.3807792067527771,
+      "learning_rate": 1.0064061750253429e-08,
+      "loss": 0.4133,
+      "step": 810
     }
   ],
   "logging_steps": 10,
@@ -547,12 +589,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 2.496191032773837e+16,
+  "total_flos": 2.716624724636467e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null