{
  "best_metric": 1.1056212186813354,
  "best_model_checkpoint": "/kaggle/output/checkpoint-6000",
  "epoch": 208.0,
  "eval_steps": 1000,
  "global_step": 13000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "learning_rate": 2.7777777777777777e-11,
      "loss": 1.5477,
      "step": 1
    },
    {
      "epoch": 16.0,
      "learning_rate": 2.7750000000000004e-08,
      "loss": 1.2028,
      "step": 1000
    },
    {
      "epoch": 16.0,
      "eval_accuracy": 0.3387225548902196,
      "eval_loss": 1.1078879833221436,
      "eval_runtime": 54.1057,
      "eval_samples_per_second": 92.596,
      "eval_steps_per_second": 11.588,
      "step": 1000
    },
    {
      "epoch": 32.0,
      "learning_rate": 5.5527777777777784e-08,
      "loss": 1.1152,
      "step": 2000
    },
    {
      "epoch": 32.0,
      "eval_accuracy": 0.3349301397205589,
      "eval_loss": 1.1080944538116455,
      "eval_runtime": 54.2029,
      "eval_samples_per_second": 92.43,
      "eval_steps_per_second": 11.568,
      "step": 2000
    },
    {
      "epoch": 48.0,
      "learning_rate": 8.327777777777778e-08,
      "loss": 1.1036,
      "step": 3000
    },
    {
      "epoch": 48.0,
      "eval_accuracy": 0.3377245508982036,
      "eval_loss": 1.1081210374832153,
      "eval_runtime": 54.0467,
      "eval_samples_per_second": 92.698,
      "eval_steps_per_second": 11.601,
      "step": 3000
    },
    {
      "epoch": 64.0,
      "learning_rate": 1.1105555555555557e-07,
      "loss": 1.0895,
      "step": 4000
    },
    {
      "epoch": 64.0,
      "eval_accuracy": 0.33912175648702597,
      "eval_loss": 1.1072543859481812,
      "eval_runtime": 54.1318,
      "eval_samples_per_second": 92.552,
      "eval_steps_per_second": 11.583,
      "step": 4000
    },
    {
      "epoch": 80.0,
      "learning_rate": 1.3880555555555558e-07,
      "loss": 1.0748,
      "step": 5000
    },
    {
      "epoch": 80.0,
      "eval_accuracy": 0.3435129740518962,
      "eval_loss": 1.1071943044662476,
      "eval_runtime": 54.4121,
      "eval_samples_per_second": 92.075,
      "eval_steps_per_second": 11.523,
      "step": 5000
    },
    {
      "epoch": 96.0,
      "learning_rate": 1.6658333333333335e-07,
      "loss": 1.055,
      "step": 6000
    },
    {
      "epoch": 96.0,
      "eval_accuracy": 0.3459081836327345,
      "eval_loss": 1.1056212186813354,
      "eval_runtime": 54.092,
      "eval_samples_per_second": 92.62,
      "eval_steps_per_second": 11.591,
      "step": 6000
    },
    {
      "epoch": 112.0,
      "learning_rate": 1.9433333333333334e-07,
      "loss": 1.0352,
      "step": 7000
    },
    {
      "epoch": 112.0,
      "eval_accuracy": 0.3469061876247505,
      "eval_loss": 1.1121071577072144,
      "eval_runtime": 53.9318,
      "eval_samples_per_second": 92.895,
      "eval_steps_per_second": 11.626,
      "step": 7000
    },
    {
      "epoch": 128.0,
      "learning_rate": 2.2211111111111114e-07,
      "loss": 1.0085,
      "step": 8000
    },
    {
      "epoch": 128.0,
      "eval_accuracy": 0.3534930139720559,
      "eval_loss": 1.1201248168945312,
      "eval_runtime": 54.0094,
      "eval_samples_per_second": 92.762,
      "eval_steps_per_second": 11.609,
      "step": 8000
    },
    {
      "epoch": 144.0,
      "learning_rate": 2.4986111111111113e-07,
      "loss": 0.9772,
      "step": 9000
    },
    {
      "epoch": 144.0,
      "eval_accuracy": 0.3568862275449102,
      "eval_loss": 1.1434961557388306,
      "eval_runtime": 54.0639,
      "eval_samples_per_second": 92.668,
      "eval_steps_per_second": 11.597,
      "step": 9000
    },
    {
      "epoch": 160.0,
      "learning_rate": 2.7761111111111115e-07,
      "loss": 0.9323,
      "step": 10000
    },
    {
      "epoch": 160.0,
      "eval_accuracy": 0.36087824351297404,
      "eval_loss": 1.1742260456085205,
      "eval_runtime": 54.7624,
      "eval_samples_per_second": 91.486,
      "eval_steps_per_second": 11.449,
      "step": 10000
    },
    {
      "epoch": 176.0,
      "learning_rate": 3.053888888888889e-07,
      "loss": 0.8779,
      "step": 11000
    },
    {
      "epoch": 176.0,
      "eval_accuracy": 0.3568862275449102,
      "eval_loss": 1.2272026538848877,
      "eval_runtime": 54.0934,
      "eval_samples_per_second": 92.618,
      "eval_steps_per_second": 11.591,
      "step": 11000
    },
    {
      "epoch": 192.0,
      "learning_rate": 3.331388888888889e-07,
      "loss": 0.8276,
      "step": 12000
    },
    {
      "epoch": 192.0,
      "eval_accuracy": 0.3562874251497006,
      "eval_loss": 1.3099753856658936,
      "eval_runtime": 54.3996,
      "eval_samples_per_second": 92.096,
      "eval_steps_per_second": 11.526,
      "step": 12000
    },
    {
      "epoch": 208.0,
      "learning_rate": 3.608888888888889e-07,
      "loss": 0.7716,
      "step": 13000
    },
    {
      "epoch": 208.0,
      "eval_accuracy": 0.3588822355289421,
      "eval_loss": 1.4230743646621704,
      "eval_runtime": 54.193,
      "eval_samples_per_second": 92.447,
      "eval_steps_per_second": 11.57,
      "step": 13000
    }
  ],
  "logging_steps": 1000,
  "max_steps": 10000000,
  "num_train_epochs": 161291,
  "save_steps": 1000,
  "total_flos": 2.7174616694784e+16,
  "trial_name": null,
  "trial_params": null
}