Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -0,0 +1,139 @@
+{
+  "best_global_step": 1044,
+  "best_metric": 0.6268221574344023,
+  "best_model_checkpoint": "outputs/phobert-emotion/checkpoint-best/checkpoint-1044",
+  "epoch": 6.0,
+  "eval_steps": 500,
+  "global_step": 1044,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.9942528735632183,
+      "grad_norm": 20.47917366027832,
+      "learning_rate": 4.9987945942675096e-05,
+      "loss": 1.4743,
+      "step": 173
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.577259475218659,
+      "eval_loss": 1.1560364961624146,
+      "eval_runtime": 3.0884,
+      "eval_samples_per_second": 222.123,
+      "eval_steps_per_second": 7.123,
+      "step": 174
+    },
+    {
+      "epoch": 1.9885057471264367,
+      "grad_norm": 7.539226531982422,
+      "learning_rate": 4.995151481879383e-05,
+      "loss": 0.9909,
+      "step": 346
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.565597667638484,
+      "eval_loss": 1.2476938962936401,
+      "eval_runtime": 3.0856,
+      "eval_samples_per_second": 222.325,
+      "eval_steps_per_second": 7.13,
+      "step": 348
+    },
+    {
+      "epoch": 2.9827586206896552,
+      "grad_norm": 11.198332786560059,
+      "learning_rate": 4.989074176195917e-05,
+      "loss": 0.7107,
+      "step": 519
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.6122448979591837,
+      "eval_loss": 1.123983383178711,
+      "eval_runtime": 3.0996,
+      "eval_samples_per_second": 221.317,
+      "eval_steps_per_second": 7.098,
+      "step": 522
+    },
+    {
+      "epoch": 3.9770114942528734,
+      "grad_norm": 12.280202865600586,
+      "learning_rate": 4.9805686060502335e-05,
+      "loss": 0.4713,
+      "step": 692
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.6107871720116618,
+      "eval_loss": 1.3784441947937012,
+      "eval_runtime": 3.1106,
+      "eval_samples_per_second": 220.539,
+      "eval_steps_per_second": 7.073,
+      "step": 696
+    },
+    {
+      "epoch": 4.971264367816092,
+      "grad_norm": 21.99969482421875,
+      "learning_rate": 4.9696430692158234e-05,
+      "loss": 0.3164,
+      "step": 865
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.5991253644314869,
+      "eval_loss": 1.6089521646499634,
+      "eval_runtime": 3.0948,
+      "eval_samples_per_second": 221.66,
+      "eval_steps_per_second": 7.109,
+      "step": 870
+    },
+    {
+      "epoch": 5.9655172413793105,
+      "grad_norm": 10.548605918884277,
+      "learning_rate": 4.956308224311493e-05,
+      "loss": 0.2366,
+      "step": 1038
+    },
+    {
+      "epoch": 6.0,
+      "eval_accuracy": 0.6268221574344023,
+      "eval_loss": 1.54556143283844,
+      "eval_runtime": 3.1112,
+      "eval_samples_per_second": 220.491,
+      "eval_steps_per_second": 7.071,
+      "step": 1044
+    }
+  ],
+  "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": 3096384676966800.0,
+  "train_batch_size": 32,
+  "trial_name": null,
+  "trial_params": null
+}