Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -1,9 +1,9 @@
 {
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 6.25,
+  "epoch": 8.333333333333334,
   "eval_steps": 25,
-  "global_step": 75,
+  "global_step": 100,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -80,6 +80,35 @@
       "eval_samples_per_second": 4.529,
       "eval_steps_per_second": 0.755,
       "step": 75
+    },
+    {
+      "epoch": 6.666666666666667,
+      "grad_norm": 1.6201064586639404,
+      "learning_rate": 0.00010101010101010101,
+      "loss": 0.192,
+      "step": 80
+    },
+    {
+      "epoch": 7.5,
+      "grad_norm": 0.38449788093566895,
+      "learning_rate": 5.0505050505050505e-05,
+      "loss": 0.1761,
+      "step": 90
+    },
+    {
+      "epoch": 8.333333333333334,
+      "grad_norm": 0.3587755858898163,
+      "learning_rate": 0.0,
+      "loss": 0.1506,
+      "step": 100
+    },
+    {
+      "epoch": 8.333333333333334,
+      "eval_loss": 1.4150458574295044,
+      "eval_runtime": 2.6483,
+      "eval_samples_per_second": 4.531,
+      "eval_steps_per_second": 0.755,
+      "step": 100
     }
   ],
   "logging_steps": 10,
@@ -94,12 +123,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 480396498591744.0,
+  "total_flos": 642113283710976.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null