{
  "best_metric": 0.4348618984222412,
  "best_model_checkpoint": "mobilebert_sa_GLUE_Experiment_qqp_256/checkpoint-19901",
  "epoch": 12.0,
  "global_step": 34116,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 1.0,
      "learning_rate": 4.9e-05,
      "loss": 0.526,
      "step": 2843
    },
    {
      "epoch": 1.0,
      "eval_accuracy": 0.7492208755874351,
      "eval_combined_score": 0.7082937159013911,
      "eval_f1": 0.6673665562153472,
      "eval_loss": 0.5088046193122864,
      "eval_runtime": 91.1135,
      "eval_samples_per_second": 443.732,
      "eval_steps_per_second": 3.468,
      "step": 2843
    },
    {
      "epoch": 2.0,
      "learning_rate": 4.8e-05,
      "loss": 0.4762,
      "step": 5686
    },
    {
      "epoch": 2.0,
      "eval_accuracy": 0.7695028444224585,
      "eval_combined_score": 0.7139173250526591,
      "eval_f1": 0.6583318056828598,
      "eval_loss": 0.47822895646095276,
      "eval_runtime": 90.2309,
      "eval_samples_per_second": 448.073,
      "eval_steps_per_second": 3.502,
      "step": 5686
    },
    {
      "epoch": 3.0,
      "learning_rate": 4.7e-05,
      "loss": 0.4438,
      "step": 8529
    },
    {
      "epoch": 3.0,
      "eval_accuracy": 0.7846648528320554,
      "eval_combined_score": 0.7337878459964473,
      "eval_f1": 0.6829108391608393,
      "eval_loss": 0.4531722366809845,
      "eval_runtime": 91.3155,
      "eval_samples_per_second": 442.751,
      "eval_steps_per_second": 3.461,
      "step": 8529
    },
    {
      "epoch": 4.0,
      "learning_rate": 4.600000000000001e-05,
      "loss": 0.4161,
      "step": 11372
    },
    {
      "epoch": 4.0,
      "eval_accuracy": 0.7869156566905763,
      "eval_combined_score": 0.7502325581873497,
      "eval_f1": 0.7135494596841232,
      "eval_loss": 0.46022653579711914,
      "eval_runtime": 91.2781,
      "eval_samples_per_second": 442.932,
      "eval_steps_per_second": 3.462,
      "step": 11372
    },
    {
      "epoch": 5.0,
      "learning_rate": 4.5e-05,
      "loss": 0.3968,
      "step": 14215
    },
    {
      "epoch": 5.0,
      "eval_accuracy": 0.7955231263912936,
      "eval_combined_score": 0.7583470804137655,
      "eval_f1": 0.7211710344362373,
      "eval_loss": 0.4394775331020355,
      "eval_runtime": 91.1289,
      "eval_samples_per_second": 443.657,
      "eval_steps_per_second": 3.468,
      "step": 14215
    },
    {
      "epoch": 6.0,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 0.3815,
      "step": 17058
    },
    {
      "epoch": 6.0,
      "eval_accuracy": 0.7984664852832055,
      "eval_combined_score": 0.7587117194627948,
      "eval_f1": 0.7189569536423841,
      "eval_loss": 0.4391535222530365,
      "eval_runtime": 91.087,
      "eval_samples_per_second": 443.861,
      "eval_steps_per_second": 3.469,
      "step": 17058
    },
    {
      "epoch": 7.0,
      "learning_rate": 4.3e-05,
      "loss": 0.3659,
      "step": 19901
    },
    {
      "epoch": 7.0,
      "eval_accuracy": 0.7976007914914668,
      "eval_combined_score": 0.7636558870752131,
      "eval_f1": 0.7297109826589595,
      "eval_loss": 0.4348618984222412,
      "eval_runtime": 91.0131,
      "eval_samples_per_second": 444.222,
      "eval_steps_per_second": 3.472,
      "step": 19901
    },
    {
      "epoch": 8.0,
      "learning_rate": 4.2e-05,
      "loss": 0.352,
      "step": 22744
    },
    {
      "epoch": 8.0,
      "eval_accuracy": 0.8005194162750433,
      "eval_combined_score": 0.7652354322292678,
      "eval_f1": 0.7299514481834923,
      "eval_loss": 0.44193214178085327,
      "eval_runtime": 91.0887,
      "eval_samples_per_second": 443.853,
      "eval_steps_per_second": 3.469,
      "step": 22744
    },
    {
      "epoch": 9.0,
      "learning_rate": 4.1e-05,
      "loss": 0.3399,
      "step": 25587
    },
    {
      "epoch": 9.0,
      "eval_accuracy": 0.7998268612416523,
      "eval_combined_score": 0.7657590030108403,
      "eval_f1": 0.7316911447800285,
      "eval_loss": 0.445422887802124,
      "eval_runtime": 90.9942,
      "eval_samples_per_second": 444.314,
      "eval_steps_per_second": 3.473,
      "step": 25587
    },
    {
      "epoch": 10.0,
      "learning_rate": 4e-05,
      "loss": 0.327,
      "step": 28430
    },
    {
      "epoch": 10.0,
      "eval_accuracy": 0.7994805837249567,
      "eval_combined_score": 0.7677087619448861,
      "eval_f1": 0.7359369401648156,
      "eval_loss": 0.4613562524318695,
      "eval_runtime": 91.0773,
      "eval_samples_per_second": 443.909,
      "eval_steps_per_second": 3.47,
      "step": 28430
    },
    {
      "epoch": 11.0,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 0.3157,
      "step": 31273
    },
    {
      "epoch": 11.0,
      "eval_accuracy": 0.7999505317833292,
      "eval_combined_score": 0.7622743669540454,
      "eval_f1": 0.7245982021247616,
      "eval_loss": 0.47330302000045776,
      "eval_runtime": 90.9948,
      "eval_samples_per_second": 444.311,
      "eval_steps_per_second": 3.473,
      "step": 31273
    },
    {
      "epoch": 12.0,
      "learning_rate": 3.8e-05,
      "loss": 0.3041,
      "step": 34116
    },
    {
      "epoch": 12.0,
      "eval_accuracy": 0.8041305960920109,
      "eval_combined_score": 0.766191443339578,
      "eval_f1": 0.7282522905871452,
      "eval_loss": 0.473808228969574,
      "eval_runtime": 90.9998,
      "eval_samples_per_second": 444.287,
      "eval_steps_per_second": 3.473,
      "step": 34116
    },
    {
      "epoch": 12.0,
      "step": 34116,
      "total_flos": 1.150094617262162e+17,
      "train_loss": 0.3870812057260752,
      "train_runtime": 30982.1918,
      "train_samples_per_second": 587.186,
      "train_steps_per_second": 4.588
    }
  ],
  "max_steps": 142150,
  "num_train_epochs": 50,
  "total_flos": 1.150094617262162e+17,
  "trial_name": null,
  "trial_params": null
}