Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -0,0 +1,177 @@
+{
+  "best_global_step": 4460,
+  "best_metric": 0.739004540015325,
+  "best_model_checkpoint": "outputs/bartpho-spam-multiclass/checkpoint-4460",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 4460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.833648393194707,
+      "eval_f1": 0.4157543289084952,
+      "eval_loss": 0.6244890689849854,
+      "eval_precision": 0.4262904071172342,
+      "eval_recall": 0.4149214169597084,
+      "eval_runtime": 7.8402,
+      "eval_samples_per_second": 202.419,
+      "eval_steps_per_second": 25.382,
+      "step": 446
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8153749212350346,
+      "eval_f1": 0.433632041735033,
+      "eval_loss": 0.5630072951316833,
+      "eval_precision": 0.5903702530353774,
+      "eval_recall": 0.4344169022421274,
+      "eval_runtime": 7.8375,
+      "eval_samples_per_second": 202.487,
+      "eval_steps_per_second": 25.391,
+      "step": 892
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.84940138626339,
+      "eval_f1": 0.5653227140092393,
+      "eval_loss": 0.5221616625785828,
+      "eval_precision": 0.564037586544765,
+      "eval_recall": 0.5683028343768871,
+      "eval_runtime": 7.8421,
+      "eval_samples_per_second": 202.369,
+      "eval_steps_per_second": 25.376,
+      "step": 1338
+    },
+    {
+      "epoch": 3.9960740325294446,
+      "grad_norm": 5.466811656951904,
+      "learning_rate": 4.980352910793417e-05,
+      "loss": 0.4889,
+      "step": 1782
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8657844990548205,
+      "eval_f1": 0.6394921110512,
+      "eval_loss": 0.389175683259964,
+      "eval_precision": 0.7853159132821476,
+      "eval_recall": 0.6047426591200951,
+      "eval_runtime": 7.844,
+      "eval_samples_per_second": 202.319,
+      "eval_steps_per_second": 25.37,
+      "step": 1784
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8733459357277883,
+      "eval_f1": 0.7016823872753396,
+      "eval_loss": 0.40175092220306396,
+      "eval_precision": 0.8087821759079243,
+      "eval_recall": 0.6612857479378891,
+      "eval_runtime": 7.8493,
+      "eval_samples_per_second": 202.184,
+      "eval_steps_per_second": 25.353,
+      "step": 2230
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.8701953371140516,
+      "eval_f1": 0.6859172237887332,
+      "eval_loss": 0.4602343738079071,
+      "eval_precision": 0.791916408814219,
+      "eval_recall": 0.6336586619369521,
+      "eval_runtime": 7.852,
+      "eval_samples_per_second": 202.114,
+      "eval_steps_per_second": 25.344,
+      "step": 2676
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.868935097668557,
+      "eval_f1": 0.7067813869499413,
+      "eval_loss": 0.43884512782096863,
+      "eval_precision": 0.7673674771583133,
+      "eval_recall": 0.667951619723433,
+      "eval_runtime": 7.8341,
+      "eval_samples_per_second": 202.576,
+      "eval_steps_per_second": 25.402,
+      "step": 3122
+    },
+    {
+      "epoch": 7.991587212563096,
+      "grad_norm": 7.460344314575195,
+      "learning_rate": 4.9216767218961726e-05,
+      "loss": 0.2743,
+      "step": 3564
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.851291745431632,
+      "eval_f1": 0.6902022867115422,
+      "eval_loss": 0.4710412323474884,
+      "eval_precision": 0.7215256835990624,
+      "eval_recall": 0.6790999625989841,
+      "eval_runtime": 7.8278,
+      "eval_samples_per_second": 202.74,
+      "eval_steps_per_second": 25.422,
+      "step": 3568
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.8739760554505356,
+      "eval_f1": 0.7387557061187268,
+      "eval_loss": 0.4174262285232544,
+      "eval_precision": 0.8044350156954325,
+      "eval_recall": 0.6986304092198873,
+      "eval_runtime": 7.848,
+      "eval_samples_per_second": 202.218,
+      "eval_steps_per_second": 25.357,
+      "step": 4014
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.872715816005041,
+      "eval_f1": 0.739004540015325,
+      "eval_loss": 0.4741021692752838,
+      "eval_precision": 0.7711173278560965,
+      "eval_recall": 0.7137098204729126,
+      "eval_runtime": 7.8585,
+      "eval_samples_per_second": 201.947,
+      "eval_steps_per_second": 25.323,
+      "step": 4460
+    }
+  ],
+  "logging_steps": 1782,
+  "max_steps": 44600,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 100,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "EarlyStoppingCallback": {
+      "args": {
+        "early_stopping_patience": 5,
+        "early_stopping_threshold": 0.0
+      },
+      "attributes": {
+        "early_stopping_patience_counter": 0
+      }
+    },
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}