Upload trainer_state.json

trainer_state.json

@@ -0,0 +1,76 @@
+{
+  "best_metric": 0.8872033047821317,
+  "best_model_checkpoint": "./results1/output/checkpoint-831690",
+  "epoch": 4.0,
+  "global_step": 1108920,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "learning_rate": 4.787836344379806e-06,
+      "loss": 0.4724,
+      "step": 277230
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8809251522860411,
+      "eval_loss": 0.55721116065979,
+      "eval_runtime": 500.703,
+      "eval_samples_per_second": 85.574,
+      "eval_steps_per_second": 21.394,
+      "step": 277230
+    },
+    {
+      "epoch": 2.0,
+      "learning_rate": 3.1926775545288493e-06,
+      "loss": 0.3483,
+      "step": 554460
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8858029733703643,
+      "eval_loss": 0.5279836058616638,
+      "eval_runtime": 500.7272,
+      "eval_samples_per_second": 85.57,
+      "eval_steps_per_second": 21.393,
+      "step": 554460
+    },
+    {
+      "epoch": 3.0,
+      "learning_rate": 1.5975417888225454e-06,
+      "loss": 0.253,
+      "step": 831690
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8872033047821317,
+      "eval_loss": 0.624336838722229,
+      "eval_runtime": 501.4348,
+      "eval_samples_per_second": 85.449,
+      "eval_steps_per_second": 21.363,
+      "step": 831690
+    },
+    {
+      "epoch": 4.0,
+      "learning_rate": 2.3657308630984357e-09,
+      "loss": 0.1594,
+      "step": 1108920
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8861297173664434,
+      "eval_loss": 0.7563027143478394,
+      "eval_runtime": 500.2671,
+      "eval_samples_per_second": 85.648,
+      "eval_steps_per_second": 21.413,
+      "step": 1108920
+    }
+  ],
+  "max_steps": 1108920,
+  "num_train_epochs": 4,
+  "total_flos": 5.3327480440765914e+17,
+  "trial_name": null,
+  "trial_params": null
+}