{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "global_step": 2040,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.49,
      "learning_rate": 6.824120603015075e-06,
      "loss": 1.2787,
      "step": 100
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 0.48663100600242615,
      "eval_loss": 1.1127219200134277,
      "eval_runtime": 2.143,
      "eval_samples_per_second": 174.524,
      "eval_steps_per_second": 11.199,
      "step": 100
    },
    {
      "epoch": 0.98,
      "learning_rate": 6.472361809045226e-06,
      "loss": 1.089,
      "step": 200
    },
    {
      "epoch": 0.98,
      "eval_accuracy": 0.7139037251472473,
      "eval_loss": 0.9668397903442383,
      "eval_runtime": 2.1362,
      "eval_samples_per_second": 175.077,
      "eval_steps_per_second": 11.235,
      "step": 200
    },
    {
      "epoch": 1.47,
      "learning_rate": 6.1206030150753765e-06,
      "loss": 0.9134,
      "step": 300
    },
    {
      "epoch": 1.47,
      "eval_accuracy": 0.7834224700927734,
      "eval_loss": 0.8720457553863525,
      "eval_runtime": 2.1335,
      "eval_samples_per_second": 175.301,
      "eval_steps_per_second": 11.249,
      "step": 300
    },
    {
      "epoch": 1.96,
      "learning_rate": 5.7688442211055275e-06,
      "loss": 0.8618,
      "step": 400
    },
    {
      "epoch": 1.96,
      "eval_accuracy": 0.7941176295280457,
      "eval_loss": 0.772637665271759,
      "eval_runtime": 2.1363,
      "eval_samples_per_second": 175.072,
      "eval_steps_per_second": 11.235,
      "step": 400
    },
    {
      "epoch": 2.45,
      "learning_rate": 5.4170854271356785e-06,
      "loss": 0.686,
      "step": 500
    },
    {
      "epoch": 2.45,
      "eval_accuracy": 0.8208556175231934,
      "eval_loss": 0.7337380647659302,
      "eval_runtime": 2.1375,
      "eval_samples_per_second": 174.975,
      "eval_steps_per_second": 11.228,
      "step": 500
    },
    {
      "epoch": 2.94,
      "learning_rate": 5.0653266331658295e-06,
      "loss": 0.6333,
      "step": 600
    },
    {
      "epoch": 2.94,
      "eval_accuracy": 0.8235294222831726,
      "eval_loss": 0.7350101470947266,
      "eval_runtime": 2.1343,
      "eval_samples_per_second": 175.234,
      "eval_steps_per_second": 11.245,
      "step": 600
    },
    {
      "epoch": 3.43,
      "learning_rate": 4.71356783919598e-06,
      "loss": 0.5765,
      "step": 700
    },
    {
      "epoch": 3.43,
      "eval_accuracy": 0.8235294222831726,
      "eval_loss": 0.7560638785362244,
      "eval_runtime": 2.1248,
      "eval_samples_per_second": 176.019,
      "eval_steps_per_second": 11.295,
      "step": 700
    },
    {
      "epoch": 3.92,
      "learning_rate": 4.361809045226131e-06,
      "loss": 0.5502,
      "step": 800
    },
    {
      "epoch": 3.92,
      "eval_accuracy": 0.8475936055183411,
      "eval_loss": 0.727317750453949,
      "eval_runtime": 2.1509,
      "eval_samples_per_second": 173.882,
      "eval_steps_per_second": 11.158,
      "step": 800
    },
    {
      "epoch": 4.41,
      "learning_rate": 4.010050251256282e-06,
      "loss": 0.5049,
      "step": 900
    },
    {
      "epoch": 4.41,
      "eval_accuracy": 0.8101603984832764,
      "eval_loss": 0.8136795163154602,
      "eval_runtime": 2.1343,
      "eval_samples_per_second": 175.233,
      "eval_steps_per_second": 11.245,
      "step": 900
    },
    {
      "epoch": 4.9,
      "learning_rate": 3.6582914572864323e-06,
      "loss": 0.4695,
      "step": 1000
    },
    {
      "epoch": 4.9,
      "eval_accuracy": 0.8288770318031311,
      "eval_loss": 0.7581244707107544,
      "eval_runtime": 2.1366,
      "eval_samples_per_second": 175.041,
      "eval_steps_per_second": 11.233,
      "step": 1000
    },
    {
      "epoch": 5.39,
      "learning_rate": 3.306532663316583e-06,
      "loss": 0.4657,
      "step": 1100
    },
    {
      "epoch": 5.39,
      "eval_accuracy": 0.8048128485679626,
      "eval_loss": 0.8404039144515991,
      "eval_runtime": 2.1382,
      "eval_samples_per_second": 174.912,
      "eval_steps_per_second": 11.224,
      "step": 1100
    },
    {
      "epoch": 5.88,
      "learning_rate": 2.9547738693467334e-06,
      "loss": 0.4549,
      "step": 1200
    },
    {
      "epoch": 5.88,
      "eval_accuracy": 0.8368983864784241,
      "eval_loss": 0.7800447940826416,
      "eval_runtime": 2.143,
      "eval_samples_per_second": 174.523,
      "eval_steps_per_second": 11.199,
      "step": 1200
    },
    {
      "epoch": 6.37,
      "learning_rate": 2.6030150753768844e-06,
      "loss": 0.4305,
      "step": 1300
    },
    {
      "epoch": 6.37,
      "eval_accuracy": 0.8235294222831726,
      "eval_loss": 0.8575029969215393,
      "eval_runtime": 2.1375,
      "eval_samples_per_second": 174.967,
      "eval_steps_per_second": 11.228,
      "step": 1300
    },
    {
      "epoch": 6.86,
      "learning_rate": 2.251256281407035e-06,
      "loss": 0.4209,
      "step": 1400
    },
    {
      "epoch": 6.86,
      "eval_accuracy": 0.8101603984832764,
      "eval_loss": 0.8572390675544739,
      "eval_runtime": 2.1484,
      "eval_samples_per_second": 174.083,
      "eval_steps_per_second": 11.171,
      "step": 1400
    },
    {
      "epoch": 7.35,
      "learning_rate": 1.899497487437186e-06,
      "loss": 0.3983,
      "step": 1500
    },
    {
      "epoch": 7.35,
      "eval_accuracy": 0.8315507769584656,
      "eval_loss": 0.8391810655593872,
      "eval_runtime": 2.1399,
      "eval_samples_per_second": 174.771,
      "eval_steps_per_second": 11.215,
      "step": 1500
    },
    {
      "epoch": 7.84,
      "learning_rate": 1.5477386934673368e-06,
      "loss": 0.4139,
      "step": 1600
    },
    {
      "epoch": 7.84,
      "eval_accuracy": 0.8208556175231934,
      "eval_loss": 0.8151516318321228,
      "eval_runtime": 2.1644,
      "eval_samples_per_second": 172.797,
      "eval_steps_per_second": 11.089,
      "step": 1600
    },
    {
      "epoch": 8.33,
      "learning_rate": 1.1959798994974873e-06,
      "loss": 0.393,
      "step": 1700
    },
    {
      "epoch": 8.33,
      "eval_accuracy": 0.8288770318031311,
      "eval_loss": 0.8261328935623169,
      "eval_runtime": 2.171,
      "eval_samples_per_second": 172.27,
      "eval_steps_per_second": 11.055,
      "step": 1700
    },
    {
      "epoch": 8.82,
      "learning_rate": 8.442211055276381e-07,
      "loss": 0.3979,
      "step": 1800
    },
    {
      "epoch": 8.82,
      "eval_accuracy": 0.8235294222831726,
      "eval_loss": 0.8327566385269165,
      "eval_runtime": 2.1392,
      "eval_samples_per_second": 174.828,
      "eval_steps_per_second": 11.219,
      "step": 1800
    },
    {
      "epoch": 9.31,
      "learning_rate": 4.924623115577889e-07,
      "loss": 0.3928,
      "step": 1900
    },
    {
      "epoch": 9.31,
      "eval_accuracy": 0.8208556175231934,
      "eval_loss": 0.8364331126213074,
      "eval_runtime": 2.138,
      "eval_samples_per_second": 174.931,
      "eval_steps_per_second": 11.226,
      "step": 1900
    },
    {
      "epoch": 9.8,
      "learning_rate": 1.4070351758793969e-07,
      "loss": 0.3848,
      "step": 2000
    },
    {
      "epoch": 9.8,
      "eval_accuracy": 0.8235294222831726,
      "eval_loss": 0.8322352170944214,
      "eval_runtime": 2.142,
      "eval_samples_per_second": 174.602,
      "eval_steps_per_second": 11.204,
      "step": 2000
    },
    {
      "epoch": 10.0,
      "step": 2040,
      "total_flos": 1.517670726457344e+16,
      "train_loss": 0.5818920486113605,
      "train_runtime": 787.9964,
      "train_samples_per_second": 41.333,
      "train_steps_per_second": 2.589
    }
  ],
  "max_steps": 2040,
  "num_train_epochs": 10,
  "total_flos": 1.517670726457344e+16,
  "trial_name": null,
  "trial_params": null
}