Upload trainer_state.json with huggingface_hub

trainer_state.json

@@ -0,0 +1,138 @@
+{
+  "best_global_step": 2230,
+  "best_metric": 0.7546993962446734,
+  "best_model_checkpoint": "outputs/sphobert-spam-multiclass/checkpoint-2230",
+  "epoch": 5.0,
+  "eval_steps": 500,
+  "global_step": 2230,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.6658368110656738,
+      "learning_rate": 4.998771926094749e-05,
+      "loss": 0.4255,
+      "step": 446
+    },
+    {
+      "epoch": 1.0,
+      "eval_accuracy": 0.8998109640831758,
+      "eval_f1": 0.6118838653499583,
+      "eval_loss": 0.34767210483551025,
+      "eval_precision": 0.6318427168394549,
+      "eval_recall": 0.5963543333375183,
+      "eval_runtime": 6.1035,
+      "eval_samples_per_second": 260.013,
+      "eval_steps_per_second": 8.192,
+      "step": 446
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 11.896188735961914,
+      "learning_rate": 4.995077872180951e-05,
+      "loss": 0.3055,
+      "step": 892
+    },
+    {
+      "epoch": 2.0,
+      "eval_accuracy": 0.8878386893509767,
+      "eval_f1": 0.6971747573302647,
+      "eval_loss": 0.3667740523815155,
+      "eval_precision": 0.7437863231955785,
+      "eval_recall": 0.6636150532565848,
+      "eval_runtime": 6.1145,
+      "eval_samples_per_second": 259.547,
+      "eval_steps_per_second": 8.177,
+      "step": 892
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 1.1215373277664185,
+      "learning_rate": 4.988921477641713e-05,
+      "loss": 0.2304,
+      "step": 1338
+    },
+    {
+      "epoch": 3.0,
+      "eval_accuracy": 0.8783868935097668,
+      "eval_f1": 0.7278806363421748,
+      "eval_loss": 0.4099155366420746,
+      "eval_precision": 0.7379081778941136,
+      "eval_recall": 0.7258881101303292,
+      "eval_runtime": 6.126,
+      "eval_samples_per_second": 259.06,
+      "eval_steps_per_second": 8.162,
+      "step": 1338
+    },
+    {
+      "epoch": 4.0,
+      "grad_norm": 12.53381633758545,
+      "learning_rate": 4.980308818095173e-05,
+      "loss": 0.1789,
+      "step": 1784
+    },
+    {
+      "epoch": 4.0,
+      "eval_accuracy": 0.8821676118462508,
+      "eval_f1": 0.745408246325706,
+      "eval_loss": 0.36882126331329346,
+      "eval_precision": 0.7883722081909573,
+      "eval_recall": 0.7290027987005978,
+      "eval_runtime": 6.1181,
+      "eval_samples_per_second": 259.395,
+      "eval_steps_per_second": 8.173,
+      "step": 1784
+    },
+    {
+      "epoch": 5.0,
+      "grad_norm": 2.6861891746520996,
+      "learning_rate": 4.9692483931964865e-05,
+      "loss": 0.1579,
+      "step": 2230
+    },
+    {
+      "epoch": 5.0,
+      "eval_accuracy": 0.8954001260239446,
+      "eval_f1": 0.7546993962446734,
+      "eval_loss": 0.4157574772834778,
+      "eval_precision": 0.77789212019109,
+      "eval_recall": 0.735742306116222,
+      "eval_runtime": 6.1208,
+      "eval_samples_per_second": 259.28,
+      "eval_steps_per_second": 8.169,
+      "step": 2230
+    }
+  ],
+  "logging_steps": 446,
+  "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": 32,
+  "trial_name": null,
+  "trial_params": null
+}