trainer_state.json

{
  "best_metric": 0.735576923076923,
  "best_model_checkpoint": "/bigwork/nhwpziet/appropriateness-style-transfer/data/models/binary-debertav3-conservative/fold0/0/checkpoint-600",
  "epoch": 9.375,
  "global_step": 1800,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.78,
      "eval_Appropriateness_binaryF1": 0.24193548387096772,
      "eval_Inappropriateness_binaryF1": 0.7025316455696202,
      "eval_Inappropriateness_macroF1": 0.472233564720294,
      "eval_Inappropriateness_microF1": 0.5727272727272728,
      "eval_loss": 0.6738538146018982,
      "eval_runtime": 2.8905,
      "eval_samples_per_second": 76.112,
      "eval_steps_per_second": 9.687,
      "step": 150
    },
    {
      "epoch": 1.56,
      "eval_Appropriateness_binaryF1": 0.6870229007633587,
      "eval_Inappropriateness_binaryF1": 0.5393258426966292,
      "eval_Inappropriateness_macroF1": 0.613174371729994,
      "eval_Inappropriateness_microF1": 0.6272727272727273,
      "eval_loss": 0.6069997549057007,
      "eval_runtime": 2.9102,
      "eval_samples_per_second": 75.596,
      "eval_steps_per_second": 9.621,
      "step": 300
    },
    {
      "epoch": 2.34,
      "eval_Appropriateness_binaryF1": 0.696078431372549,
      "eval_Inappropriateness_binaryF1": 0.7372881355932204,
      "eval_Inappropriateness_macroF1": 0.7166832834828847,
      "eval_Inappropriateness_microF1": 0.7181818181818181,
      "eval_loss": 0.6120564341545105,
      "eval_runtime": 2.9124,
      "eval_samples_per_second": 75.539,
      "eval_steps_per_second": 9.614,
      "step": 450
    },
    {
      "epoch": 2.6,
      "learning_rate": 2.483101851851852e-06,
      "loss": 0.5884,
      "step": 500
    },
    {
      "epoch": 3.12,
      "eval_Appropriateness_binaryF1": 0.721153846153846,
      "eval_Inappropriateness_binaryF1": 0.75,
      "eval_Inappropriateness_macroF1": 0.735576923076923,
      "eval_Inappropriateness_microF1": 0.7363636363636363,
      "eval_loss": 0.698798418045044,
      "eval_runtime": 2.9139,
      "eval_samples_per_second": 75.501,
      "eval_steps_per_second": 9.609,
      "step": 600
    },
    {
      "epoch": 3.91,
      "eval_Appropriateness_binaryF1": 0.6995515695067265,
      "eval_Inappropriateness_binaryF1": 0.6912442396313364,
      "eval_Inappropriateness_macroF1": 0.6953979045690315,
      "eval_Inappropriateness_microF1": 0.6954545454545454,
      "eval_loss": 0.7792043089866638,
      "eval_runtime": 2.9114,
      "eval_samples_per_second": 75.565,
      "eval_steps_per_second": 9.617,
      "step": 750
    },
    {
      "epoch": 4.69,
      "eval_Appropriateness_binaryF1": 0.6986899563318776,
      "eval_Inappropriateness_binaryF1": 0.6729857819905214,
      "eval_Inappropriateness_macroF1": 0.6858378691611995,
      "eval_Inappropriateness_microF1": 0.6863636363636364,
      "eval_loss": 0.9839176535606384,
      "eval_runtime": 2.9088,
      "eval_samples_per_second": 75.632,
      "eval_steps_per_second": 9.626,
      "step": 900
    },
    {
      "epoch": 5.21,
      "learning_rate": 1.6439814814814818e-06,
      "loss": 0.3639,
      "step": 1000
    },
    {
      "epoch": 5.47,
      "eval_Appropriateness_binaryF1": 0.7130434782608694,
      "eval_Inappropriateness_binaryF1": 0.6857142857142857,
      "eval_Inappropriateness_macroF1": 0.6993788819875776,
      "eval_Inappropriateness_microF1": 0.7,
      "eval_loss": 1.1842643022537231,
      "eval_runtime": 2.9105,
      "eval_samples_per_second": 75.589,
      "eval_steps_per_second": 9.62,
      "step": 1050
    },
    {
      "epoch": 6.25,
      "eval_Appropriateness_binaryF1": 0.7074235807860262,
      "eval_Inappropriateness_binaryF1": 0.6824644549763034,
      "eval_Inappropriateness_macroF1": 0.6949440178811648,
      "eval_Inappropriateness_microF1": 0.6954545454545454,
      "eval_loss": 1.3936840295791626,
      "eval_runtime": 2.9081,
      "eval_samples_per_second": 75.652,
      "eval_steps_per_second": 9.628,
      "step": 1200
    },
    {
      "epoch": 7.03,
      "eval_Appropriateness_binaryF1": 0.7079646017699115,
      "eval_Inappropriateness_binaryF1": 0.6915887850467289,
      "eval_Inappropriateness_macroF1": 0.6997766934083203,
      "eval_Inappropriateness_microF1": 0.7,
      "eval_loss": 1.534929871559143,
      "eval_runtime": 2.9065,
      "eval_samples_per_second": 75.692,
      "eval_steps_per_second": 9.634,
      "step": 1350
    },
    {
      "epoch": 7.81,
      "learning_rate": 8.048611111111111e-07,
      "loss": 0.2237,
      "step": 1500
    },
    {
      "epoch": 7.81,
      "eval_Appropriateness_binaryF1": 0.7048458149779735,
      "eval_Inappropriateness_binaryF1": 0.6854460093896714,
      "eval_Inappropriateness_macroF1": 0.6951459121838224,
      "eval_Inappropriateness_microF1": 0.6954545454545454,
      "eval_loss": 1.604066014289856,
      "eval_runtime": 2.9577,
      "eval_samples_per_second": 74.383,
      "eval_steps_per_second": 9.467,
      "step": 1500
    },
    {
      "epoch": 8.59,
      "eval_Appropriateness_binaryF1": 0.706896551724138,
      "eval_Inappropriateness_binaryF1": 0.6730769230769231,
      "eval_Inappropriateness_macroF1": 0.6899867374005306,
      "eval_Inappropriateness_microF1": 0.6909090909090909,
      "eval_loss": 1.6559981107711792,
      "eval_runtime": 2.9142,
      "eval_samples_per_second": 75.494,
      "eval_steps_per_second": 9.608,
      "step": 1650
    },
    {
      "epoch": 9.38,
      "eval_Appropriateness_binaryF1": 0.7136563876651982,
      "eval_Inappropriateness_binaryF1": 0.6948356807511736,
      "eval_Inappropriateness_macroF1": 0.704246034208186,
      "eval_Inappropriateness_microF1": 0.7045454545454546,
      "eval_loss": 1.6468514204025269,
      "eval_runtime": 2.9039,
      "eval_samples_per_second": 75.759,
      "eval_steps_per_second": 9.642,
      "step": 1800
    }
  ],
  "max_steps": 1920,
  "num_train_epochs": 10,
  "total_flos": 5135315033335992.0,
  "trial_name": null,
  "trial_params": null
}