Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -0,0 +1,213 @@
+{
+  "best_global_step": 1740,
+  "best_metric": 0.5872700637508189,
+  "best_model_checkpoint": "outputs/phobert-v2/checkpoint-1740",
+  "epoch": 10.0,
+  "eval_steps": 500,
+  "global_step": 1740,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9942528735632183,
+      "grad_norm": 10.429289817810059,
+      "learning_rate": 6.88e-06,
+      "loss": 1.8471,
+      "step": 173
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.3746355685131195,
+      "eval_loss": 1.6570643186569214,
+      "eval_macro_f1": 0.14434482728193657,
+      "eval_runtime": 2.3848,
+      "eval_samples_per_second": 287.655,
+      "eval_steps_per_second": 9.225,
+      "step": 174
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 4.976310729980469,
+      "learning_rate": 1.38e-05,
+      "loss": 1.527,
+      "step": 346
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.5568513119533528,
+      "eval_loss": 1.307194709777832,
+      "eval_macro_f1": 0.3319217550450094,
+      "eval_runtime": 2.3807,
+      "eval_samples_per_second": 288.151,
+      "eval_steps_per_second": 9.241,
+      "step": 348
+    },
+    {
+      "epoch": 2.9827586206896552,
+      "grad_norm": 15.020604133605957,
+      "learning_rate": 1.999994401896218e-05,
+      "loss": 1.2266,
+      "step": 519
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.5991253644314869,
+      "eval_loss": 1.1421139240264893,
+      "eval_macro_f1": 0.44220855453833874,
+      "eval_runtime": 2.3441,
+      "eval_samples_per_second": 292.645,
+      "eval_steps_per_second": 9.385,
+      "step": 522
+    },
+    {
+      "epoch": 3.9770114942528734,
+      "grad_norm": 10.641494750976562,
+      "learning_rate": 1.9993697433304146e-05,
+      "loss": 0.9848,
+      "step": 692
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.597667638483965,
+      "eval_loss": 1.1232401132583618,
+      "eval_macro_f1": 0.5090589987778544,
+      "eval_runtime": 2.3684,
+      "eval_samples_per_second": 289.65,
+      "eval_steps_per_second": 9.289,
+      "step": 696
+    },
+    {
+      "epoch": 4.971264367816092,
+      "grad_norm": 50.000247955322266,
+      "learning_rate": 1.9977115923137912e-05,
+      "loss": 0.7954,
+      "step": 865
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.6268221574344023,
+      "eval_loss": 1.1033910512924194,
+      "eval_macro_f1": 0.5464276091084106,
+      "eval_runtime": 2.3903,
+      "eval_samples_per_second": 286.991,
+      "eval_steps_per_second": 9.204,
+      "step": 870
+    },
+    {
+      "epoch": 5.9655172413793105,
+      "grad_norm": 11.679581642150879,
+      "learning_rate": 1.995021663613649e-05,
+      "loss": 0.6331,
+      "step": 1038
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6282798833819242,
+      "eval_loss": 1.1012190580368042,
+      "eval_macro_f1": 0.5559355350042673,
+      "eval_runtime": 2.3747,
+      "eval_samples_per_second": 288.875,
+      "eval_steps_per_second": 9.264,
+      "step": 1044
+    },
+    {
+      "epoch": 6.959770114942529,
+      "grad_norm": 18.876968383789062,
+      "learning_rate": 1.991302739004225e-05,
+      "loss": 0.5026,
+      "step": 1211
+    },
+    {
+      "epoch": 7.0,
+      "eval_accuracy": 0.6166180758017493,
+      "eval_loss": 1.155078411102295,
+      "eval_macro_f1": 0.5442508367488053,
+      "eval_runtime": 2.3826,
+      "eval_samples_per_second": 287.918,
+      "eval_steps_per_second": 9.234,
+      "step": 1218
+    },
+    {
+      "epoch": 7.954022988505747,
+      "grad_norm": 26.72658920288086,
+      "learning_rate": 1.9865586643899352e-05,
+      "loss": 0.3975,
+      "step": 1384
+    },
+    {
+      "epoch": 8.0,
+      "eval_accuracy": 0.6282798833819242,
+      "eval_loss": 1.2925310134887695,
+      "eval_macro_f1": 0.5741099300421252,
+      "eval_runtime": 2.3814,
+      "eval_samples_per_second": 288.06,
+      "eval_steps_per_second": 9.238,
+      "step": 1392
+    },
+    {
+      "epoch": 8.948275862068966,
+      "grad_norm": 12.882652282714844,
+      "learning_rate": 1.9807943458281543e-05,
+      "loss": 0.3211,
+      "step": 1557
+    },
+    {
+      "epoch": 9.0,
+      "eval_accuracy": 0.6180758017492711,
+      "eval_loss": 1.3261842727661133,
+      "eval_macro_f1": 0.5540305128995968,
+      "eval_runtime": 2.4018,
+      "eval_samples_per_second": 285.618,
+      "eval_steps_per_second": 9.16,
+      "step": 1566
+    },
+    {
+      "epoch": 9.942528735632184,
+      "grad_norm": 19.935659408569336,
+      "learning_rate": 1.974015744455647e-05,
+      "loss": 0.2817,
+      "step": 1730
+    },
+    {
+      "epoch": 10.0,
+      "eval_accuracy": 0.641399416909621,
+      "eval_loss": 1.345000147819519,
+      "eval_macro_f1": 0.5872700637508189,
+      "eval_runtime": 2.3829,
+      "eval_samples_per_second": 287.882,
+      "eval_steps_per_second": 9.232,
+      "step": 1740
+    }
+  ],
+  "logging_steps": 173,
+  "max_steps": 17400,
+  "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": 5160641128278000.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}