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": 0.7351252010107971,
+  "epoch": 0.9189065012634965,
   "eval_steps": 500,
-  "global_step": 200,
+  "global_step": 250,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -148,6 +148,41 @@
       "learning_rate": 4.504523224581762e-05,
       "loss": 0.864,
       "step": 200
+    },
+    {
+      "epoch": 0.771881461061337,
+      "grad_norm": 0.38919857144355774,
+      "learning_rate": 4.442333322822028e-05,
+      "loss": 0.8375,
+      "step": 210
+    },
+    {
+      "epoch": 0.8086377211118768,
+      "grad_norm": 0.3908405303955078,
+      "learning_rate": 4.376952172513046e-05,
+      "loss": 0.8642,
+      "step": 220
+    },
+    {
+      "epoch": 0.8453939811624167,
+      "grad_norm": 0.37455061078071594,
+      "learning_rate": 4.308487194713097e-05,
+      "loss": 0.8775,
+      "step": 230
+    },
+    {
+      "epoch": 0.8821502412129566,
+      "grad_norm": 0.3894438147544861,
+      "learning_rate": 4.2370508772009334e-05,
+      "loss": 0.8454,
+      "step": 240
+    },
+    {
+      "epoch": 0.9189065012634965,
+      "grad_norm": 0.40810340642929077,
+      "learning_rate": 4.162760589658649e-05,
+      "loss": 0.8399,
+      "step": 250
     }
   ],
   "logging_steps": 10,
@@ -167,7 +202,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 6662970335559680.0,
+  "total_flos": 8336347341258752.0,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null