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": 1.8022598870056497,
+  "epoch": 2.0,
   "eval_steps": 10,
-  "global_step": 160,
+  "global_step": 178,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -344,6 +344,27 @@
       "eval_samples_per_second": 4.337,
       "eval_steps_per_second": 1.084,
       "step": 160
+    },
+    {
+      "entropy": 6.240383183956146,
+      "epoch": 1.9152542372881356,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.0465116279069768e-05,
+      "loss": 6.1943107604980465,
+      "mean_token_accuracy": 0.2432584844529629,
+      "num_tokens": 2869517.0,
+      "step": 170
+    },
+    {
+      "epoch": 1.9152542372881356,
+      "eval_entropy": 6.599712918202083,
+      "eval_loss": 6.369909763336182,
+      "eval_mean_token_accuracy": 0.20116472554703554,
+      "eval_num_tokens": 2869517.0,
+      "eval_runtime": 43.9021,
+      "eval_samples_per_second": 4.373,
+      "eval_steps_per_second": 1.093,
+      "step": 170
     }
   ],
   "logging_steps": 10,
@@ -358,12 +379,12 @@
         "should_evaluate": false,
         "should_log": false,
         "should_save": true,
-        "should_training_stop": false
+        "should_training_stop": true
       },
       "attributes": {}
     }
   },
-  "total_flos": 1.931435674847908e+17,
+  "total_flos": 2.1389497039169126e+17,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null