{
  "best_metric": 2.214895725250244,
  "best_model_checkpoint": "dq158/pingusPongus/checkpoint-15810",
  "epoch": 11.0,
  "eval_steps": 500,
  "global_step": 17391,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.32,
      "learning_rate": 0.0001,
      "loss": 3.1034,
      "step": 500
    },
    {
      "epoch": 0.63,
      "learning_rate": 9.993631921956987e-05,
      "loss": 2.6893,
      "step": 1000
    },
    {
      "epoch": 0.95,
      "learning_rate": 9.974543908795133e-05,
      "loss": 2.5782,
      "step": 1500
    },
    {
      "epoch": 1.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.409773349761963,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 52663,
      "eval_runtime": 589.2444,
      "eval_samples_per_second": 4.771,
      "eval_steps_per_second": 0.597,
      "eval_translation_length": 52663,
      "step": 1581
    },
    {
      "epoch": 1.27,
      "learning_rate": 9.942784582097439e-05,
      "loss": 2.4939,
      "step": 2000
    },
    {
      "epoch": 1.58,
      "learning_rate": 9.898434840212306e-05,
      "loss": 2.4615,
      "step": 2500
    },
    {
      "epoch": 1.9,
      "learning_rate": 9.841607652186736e-05,
      "loss": 2.4147,
      "step": 3000
    },
    {
      "epoch": 2.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.320283889770508,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 53341,
      "eval_runtime": 585.7187,
      "eval_samples_per_second": 4.799,
      "eval_steps_per_second": 0.601,
      "eval_translation_length": 53341,
      "step": 3162
    },
    {
      "epoch": 2.21,
      "learning_rate": 9.772447770008058e-05,
      "loss": 2.3609,
      "step": 3500
    },
    {
      "epoch": 2.53,
      "learning_rate": 9.691131359887135e-05,
      "loss": 2.3422,
      "step": 4000
    },
    {
      "epoch": 2.85,
      "learning_rate": 9.597865553522297e-05,
      "loss": 2.3484,
      "step": 4500
    },
    {
      "epoch": 3.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.2784500122070312,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 52556,
      "eval_runtime": 583.4704,
      "eval_samples_per_second": 4.818,
      "eval_steps_per_second": 0.603,
      "eval_translation_length": 52556,
      "step": 4743
    },
    {
      "epoch": 3.16,
      "learning_rate": 9.492887920487015e-05,
      "loss": 2.2993,
      "step": 5000
    },
    {
      "epoch": 3.48,
      "learning_rate": 9.376465863085263e-05,
      "loss": 2.2738,
      "step": 5500
    },
    {
      "epoch": 3.8,
      "learning_rate": 9.24889593521603e-05,
      "loss": 2.2585,
      "step": 6000
    },
    {
      "epoch": 4.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.257721424102783,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 53121,
      "eval_runtime": 580.1345,
      "eval_samples_per_second": 4.845,
      "eval_steps_per_second": 0.607,
      "eval_translation_length": 53121,
      "step": 6324
    },
    {
      "epoch": 4.11,
      "learning_rate": 9.110503086981956e-05,
      "loss": 2.2444,
      "step": 6500
    },
    {
      "epoch": 4.43,
      "learning_rate": 8.961639836966304e-05,
      "loss": 2.2152,
      "step": 7000
    },
    {
      "epoch": 4.74,
      "learning_rate": 8.802685374286608e-05,
      "loss": 2.2,
      "step": 7500
    },
    {
      "epoch": 5.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.240872383117676,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 52857,
      "eval_runtime": 579.7989,
      "eval_samples_per_second": 4.848,
      "eval_steps_per_second": 0.607,
      "eval_translation_length": 52857,
      "step": 7905
    },
    {
      "epoch": 5.06,
      "learning_rate": 8.63404459271232e-05,
      "loss": 2.2021,
      "step": 8000
    },
    {
      "epoch": 5.38,
      "learning_rate": 8.456147059306759e-05,
      "loss": 2.1521,
      "step": 8500
    },
    {
      "epoch": 5.69,
      "learning_rate": 8.26944592022048e-05,
      "loss": 2.1533,
      "step": 9000
    },
    {
      "epoch": 6.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.2270374298095703,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 52650,
      "eval_runtime": 581.0567,
      "eval_samples_per_second": 4.838,
      "eval_steps_per_second": 0.606,
      "eval_translation_length": 52650,
      "step": 9486
    },
    {
      "epoch": 6.01,
      "learning_rate": 8.07441674642325e-05,
      "loss": 2.1582,
      "step": 9500
    },
    {
      "epoch": 6.33,
      "learning_rate": 7.871556322314834e-05,
      "loss": 2.1203,
      "step": 10000
    },
    {
      "epoch": 6.64,
      "learning_rate": 7.661381380300255e-05,
      "loss": 2.1193,
      "step": 10500
    },
    {
      "epoch": 6.96,
      "learning_rate": 7.444427284552887e-05,
      "loss": 2.106,
      "step": 11000
    },
    {
      "epoch": 7.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.2215259075164795,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 53190,
      "eval_runtime": 584.4443,
      "eval_samples_per_second": 4.81,
      "eval_steps_per_second": 0.602,
      "eval_translation_length": 53190,
      "step": 11067
    },
    {
      "epoch": 7.27,
      "learning_rate": 7.221246667318116e-05,
      "loss": 2.0653,
      "step": 11500
    },
    {
      "epoch": 7.59,
      "learning_rate": 6.992408021231241e-05,
      "loss": 2.0783,
      "step": 12000
    },
    {
      "epoch": 7.91,
      "learning_rate": 6.758494251235275e-05,
      "loss": 2.0813,
      "step": 12500
    },
    {
      "epoch": 8.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.219463586807251,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 52305,
      "eval_runtime": 583.0366,
      "eval_samples_per_second": 4.821,
      "eval_steps_per_second": 0.604,
      "eval_translation_length": 52305,
      "step": 12648
    },
    {
      "epoch": 8.22,
      "learning_rate": 6.520101189787285e-05,
      "loss": 2.0482,
      "step": 13000
    },
    {
      "epoch": 8.54,
      "learning_rate": 6.27783607913536e-05,
      "loss": 2.0496,
      "step": 13500
    },
    {
      "epoch": 8.86,
      "learning_rate": 6.03231602453219e-05,
      "loss": 2.0406,
      "step": 14000
    },
    {
      "epoch": 9.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.215216636657715,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 52546,
      "eval_runtime": 581.8998,
      "eval_samples_per_second": 4.831,
      "eval_steps_per_second": 0.605,
      "eval_translation_length": 52546,
      "step": 14229
    },
    {
      "epoch": 9.17,
      "learning_rate": 5.784166422325311e-05,
      "loss": 2.0341,
      "step": 14500
    },
    {
      "epoch": 9.49,
      "learning_rate": 5.534019366928e-05,
      "loss": 2.0094,
      "step": 15000
    },
    {
      "epoch": 9.8,
      "learning_rate": 5.282512040728659e-05,
      "loss": 2.0032,
      "step": 15500
    },
    {
      "epoch": 10.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.214895725250244,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 52363,
      "eval_runtime": 584.3355,
      "eval_samples_per_second": 4.811,
      "eval_steps_per_second": 0.602,
      "eval_translation_length": 52363,
      "step": 15810
    },
    {
      "epoch": 10.12,
      "learning_rate": 5.030285091039936e-05,
      "loss": 1.9783,
      "step": 16000
    },
    {
      "epoch": 10.44,
      "learning_rate": 4.777980998221901e-05,
      "loss": 1.9852,
      "step": 16500
    },
    {
      "epoch": 10.75,
      "learning_rate": 4.5262424391360075e-05,
      "loss": 1.9982,
      "step": 17000
    },
    {
      "epoch": 11.0,
      "eval_bleu": 1.0,
      "eval_brevity_penalty": 1.0,
      "eval_length_ratio": 1.0,
      "eval_loss": 2.2150418758392334,
      "eval_precisions": [
        1.0,
        1.0,
        1.0,
        1.0
      ],
      "eval_reference_length": 53036,
      "eval_runtime": 587.6164,
      "eval_samples_per_second": 4.784,
      "eval_steps_per_second": 0.599,
      "eval_translation_length": 53036,
      "step": 17391
    }
  ],
  "logging_steps": 500,
  "max_steps": 31620,
  "num_train_epochs": 20,
  "save_steps": 500,
  "total_flos": 1.9050018020838605e+17,
  "trial_name": null,
  "trial_params": null
}