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": 1.8343671031472548,
+  "epoch": 2.014702504020216,
   "eval_steps": 500,
-  "global_step": 500,
+  "global_step": 550,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -358,6 +358,41 @@
       "learning_rate": 1.795226635093226e-05,
       "loss": 0.6666,
       "step": 500
+    },
+    {
+      "epoch": 1.8711233631977946,
+      "grad_norm": 0.3329021632671356,
+      "learning_rate": 1.6986008468871783e-05,
+      "loss": 0.6766,
+      "step": 510
+    },
+    {
+      "epoch": 1.9078796232483346,
+      "grad_norm": 0.3460406959056854,
+      "learning_rate": 1.6032917553853936e-05,
+      "loss": 0.6735,
+      "step": 520
+    },
+    {
+      "epoch": 1.9446358832988744,
+      "grad_norm": 0.3377283215522766,
+      "learning_rate": 1.509455953174948e-05,
+      "loss": 0.669,
+      "step": 530
+    },
+    {
+      "epoch": 1.9813921433494142,
+      "grad_norm": 0.35212215781211853,
+      "learning_rate": 1.4172476122324806e-05,
+      "loss": 0.6608,
+      "step": 540
+    },
+    {
+      "epoch": 2.014702504020216,
+      "grad_norm": 0.4792023003101349,
+      "learning_rate": 1.3268182306200405e-05,
+      "loss": 0.5849,
+      "step": 550
     }
   ],
   "logging_steps": 10,
@@ -377,7 +412,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.6653413265702912e+16,
+  "total_flos": 1.8293318215532544e+16,
   "train_batch_size": 1,
   "trial_name": null,
   "trial_params": null