{
  "best_metric": 1.0962979793548584,
  "best_model_checkpoint": "/kaggle/output/checkpoint-13000",
  "epoch": 0.5704041720990873,
  "eval_steps": 1000,
  "global_step": 14000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0,
      "learning_rate": 2.7777777777777777e-11,
      "loss": 1.029,
      "step": 1
    },
    {
      "epoch": 0.04,
      "learning_rate": 2.7638888888888893e-08,
      "loss": 1.181,
      "step": 1000
    },
    {
      "epoch": 0.04,
      "eval_accuracy": 0.3273453093812375,
      "eval_loss": 1.1529844999313354,
      "eval_runtime": 54.2837,
      "eval_samples_per_second": 92.293,
      "eval_steps_per_second": 11.55,
      "step": 1000
    },
    {
      "epoch": 0.08,
      "learning_rate": 5.541666666666667e-08,
      "loss": 1.1527,
      "step": 2000
    },
    {
      "epoch": 0.08,
      "eval_accuracy": 0.33013972055888224,
      "eval_loss": 1.1351025104522705,
      "eval_runtime": 54.0518,
      "eval_samples_per_second": 92.689,
      "eval_steps_per_second": 11.6,
      "step": 2000
    },
    {
      "epoch": 0.12,
      "learning_rate": 8.316666666666666e-08,
      "loss": 1.142,
      "step": 3000
    },
    {
      "epoch": 0.12,
      "eval_accuracy": 0.3317365269461078,
      "eval_loss": 1.127414345741272,
      "eval_runtime": 54.0871,
      "eval_samples_per_second": 92.628,
      "eval_steps_per_second": 11.592,
      "step": 3000
    },
    {
      "epoch": 0.16,
      "learning_rate": 1.1091666666666668e-07,
      "loss": 1.1371,
      "step": 4000
    },
    {
      "epoch": 0.16,
      "eval_accuracy": 0.331936127744511,
      "eval_loss": 1.1194497346878052,
      "eval_runtime": 54.3907,
      "eval_samples_per_second": 92.111,
      "eval_steps_per_second": 11.528,
      "step": 4000
    },
    {
      "epoch": 0.2,
      "learning_rate": 1.3869444444444447e-07,
      "loss": 1.1246,
      "step": 5000
    },
    {
      "epoch": 0.2,
      "eval_accuracy": 0.3345309381237525,
      "eval_loss": 1.1131775379180908,
      "eval_runtime": 54.3492,
      "eval_samples_per_second": 92.182,
      "eval_steps_per_second": 11.537,
      "step": 5000
    },
    {
      "epoch": 0.24,
      "learning_rate": 1.664722222222222e-07,
      "loss": 1.1201,
      "step": 6000
    },
    {
      "epoch": 0.24,
      "eval_accuracy": 0.34151696606786425,
      "eval_loss": 1.1093512773513794,
      "eval_runtime": 54.3536,
      "eval_samples_per_second": 92.174,
      "eval_steps_per_second": 11.536,
      "step": 6000
    },
    {
      "epoch": 0.29,
      "learning_rate": 1.9425e-07,
      "loss": 1.115,
      "step": 7000
    },
    {
      "epoch": 0.29,
      "eval_accuracy": 0.34510978043912177,
      "eval_loss": 1.1066845655441284,
      "eval_runtime": 53.9977,
      "eval_samples_per_second": 92.782,
      "eval_steps_per_second": 11.612,
      "step": 7000
    },
    {
      "epoch": 0.33,
      "learning_rate": 2.2202777777777778e-07,
      "loss": 1.1125,
      "step": 8000
    },
    {
      "epoch": 0.33,
      "eval_accuracy": 0.3449101796407186,
      "eval_loss": 1.1031057834625244,
      "eval_runtime": 54.2562,
      "eval_samples_per_second": 92.34,
      "eval_steps_per_second": 11.556,
      "step": 8000
    },
    {
      "epoch": 0.37,
      "learning_rate": 2.498055555555556e-07,
      "loss": 1.1072,
      "step": 9000
    },
    {
      "epoch": 0.37,
      "eval_accuracy": 0.34870259481037924,
      "eval_loss": 1.1044224500656128,
      "eval_runtime": 54.0795,
      "eval_samples_per_second": 92.641,
      "eval_steps_per_second": 11.594,
      "step": 9000
    },
    {
      "epoch": 0.41,
      "learning_rate": 2.7755555555555554e-07,
      "loss": 1.1064,
      "step": 10000
    },
    {
      "epoch": 0.41,
      "eval_accuracy": 0.3499001996007984,
      "eval_loss": 1.1001031398773193,
      "eval_runtime": 54.0869,
      "eval_samples_per_second": 92.629,
      "eval_steps_per_second": 11.592,
      "step": 10000
    },
    {
      "epoch": 0.45,
      "learning_rate": 3.053333333333333e-07,
      "loss": 1.1053,
      "step": 11000
    },
    {
      "epoch": 0.45,
      "eval_accuracy": 0.36087824351297404,
      "eval_loss": 1.0987293720245361,
      "eval_runtime": 53.9688,
      "eval_samples_per_second": 92.831,
      "eval_steps_per_second": 11.618,
      "step": 11000
    },
    {
      "epoch": 0.49,
      "learning_rate": 3.3311111111111114e-07,
      "loss": 1.104,
      "step": 12000
    },
    {
      "epoch": 0.49,
      "eval_accuracy": 0.3594810379241517,
      "eval_loss": 1.0968631505966187,
      "eval_runtime": 54.0936,
      "eval_samples_per_second": 92.617,
      "eval_steps_per_second": 11.591,
      "step": 12000
    },
    {
      "epoch": 0.53,
      "learning_rate": 3.608888888888889e-07,
      "loss": 1.1022,
      "step": 13000
    },
    {
      "epoch": 0.53,
      "eval_accuracy": 0.36087824351297404,
      "eval_loss": 1.0962979793548584,
      "eval_runtime": 54.0403,
      "eval_samples_per_second": 92.709,
      "eval_steps_per_second": 11.602,
      "step": 13000
    },
    {
      "epoch": 0.57,
      "learning_rate": 3.886666666666667e-07,
      "loss": 1.1029,
      "step": 14000
    },
    {
      "epoch": 0.57,
      "eval_accuracy": 0.3528942115768463,
      "eval_loss": 1.0987964868545532,
      "eval_runtime": 54.06,
      "eval_samples_per_second": 92.675,
      "eval_steps_per_second": 11.598,
      "step": 14000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 408,
  "save_steps": 1000,
  "total_flos": 2.9264971825152e+16,
  "trial_name": null,
  "trial_params": null
}