{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.07836990595611286,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0007836990595611285,
      "eval_loss": 1.8189666271209717,
      "eval_runtime": 154.0325,
      "eval_samples_per_second": 13.952,
      "eval_steps_per_second": 1.746,
      "step": 1
    },
    {
      "epoch": 0.0023510971786833857,
      "grad_norm": 0.19960135221481323,
      "learning_rate": 3e-05,
      "loss": 1.6224,
      "step": 3
    },
    {
      "epoch": 0.004702194357366771,
      "grad_norm": 0.20366176962852478,
      "learning_rate": 6e-05,
      "loss": 1.788,
      "step": 6
    },
    {
      "epoch": 0.007053291536050157,
      "grad_norm": 0.24395181238651276,
      "learning_rate": 9e-05,
      "loss": 1.7563,
      "step": 9
    },
    {
      "epoch": 0.007053291536050157,
      "eval_loss": 1.7944647073745728,
      "eval_runtime": 155.6578,
      "eval_samples_per_second": 13.806,
      "eval_steps_per_second": 1.728,
      "step": 9
    },
    {
      "epoch": 0.009404388714733543,
      "grad_norm": 0.22205477952957153,
      "learning_rate": 9.987820251299122e-05,
      "loss": 1.6841,
      "step": 12
    },
    {
      "epoch": 0.011755485893416929,
      "grad_norm": 0.2233169674873352,
      "learning_rate": 9.924038765061042e-05,
      "loss": 1.7981,
      "step": 15
    },
    {
      "epoch": 0.014106583072100314,
      "grad_norm": 0.21325641870498657,
      "learning_rate": 9.806308479691595e-05,
      "loss": 1.7515,
      "step": 18
    },
    {
      "epoch": 0.014106583072100314,
      "eval_loss": 1.7263827323913574,
      "eval_runtime": 155.6956,
      "eval_samples_per_second": 13.803,
      "eval_steps_per_second": 1.728,
      "step": 18
    },
    {
      "epoch": 0.016457680250783698,
      "grad_norm": 0.21644531190395355,
      "learning_rate": 9.635919272833938e-05,
      "loss": 1.6503,
      "step": 21
    },
    {
      "epoch": 0.018808777429467086,
      "grad_norm": 0.1924390196800232,
      "learning_rate": 9.414737964294636e-05,
      "loss": 1.5309,
      "step": 24
    },
    {
      "epoch": 0.02115987460815047,
      "grad_norm": 0.23553432524204254,
      "learning_rate": 9.145187862775209e-05,
      "loss": 1.4196,
      "step": 27
    },
    {
      "epoch": 0.02115987460815047,
      "eval_loss": 1.6870815753936768,
      "eval_runtime": 155.6773,
      "eval_samples_per_second": 13.804,
      "eval_steps_per_second": 1.728,
      "step": 27
    },
    {
      "epoch": 0.023510971786833857,
      "grad_norm": 0.2909448742866516,
      "learning_rate": 8.83022221559489e-05,
      "loss": 1.5234,
      "step": 30
    },
    {
      "epoch": 0.02586206896551724,
      "grad_norm": 0.2146679311990738,
      "learning_rate": 8.473291852294987e-05,
      "loss": 1.4488,
      "step": 33
    },
    {
      "epoch": 0.02821316614420063,
      "grad_norm": 0.2212241291999817,
      "learning_rate": 8.07830737662829e-05,
      "loss": 1.4463,
      "step": 36
    },
    {
      "epoch": 0.02821316614420063,
      "eval_loss": 1.6592437028884888,
      "eval_runtime": 155.6643,
      "eval_samples_per_second": 13.805,
      "eval_steps_per_second": 1.728,
      "step": 36
    },
    {
      "epoch": 0.030564263322884012,
      "grad_norm": 0.31677696108818054,
      "learning_rate": 7.649596321166024e-05,
      "loss": 1.7469,
      "step": 39
    },
    {
      "epoch": 0.032915360501567396,
      "grad_norm": 0.23331013321876526,
      "learning_rate": 7.191855733945387e-05,
      "loss": 1.6296,
      "step": 42
    },
    {
      "epoch": 0.03526645768025078,
      "grad_norm": 0.27310678362846375,
      "learning_rate": 6.710100716628344e-05,
      "loss": 1.5908,
      "step": 45
    },
    {
      "epoch": 0.03526645768025078,
      "eval_loss": 1.6446130275726318,
      "eval_runtime": 155.692,
      "eval_samples_per_second": 13.803,
      "eval_steps_per_second": 1.728,
      "step": 45
    },
    {
      "epoch": 0.03761755485893417,
      "grad_norm": 0.2733047604560852,
      "learning_rate": 6.209609477998338e-05,
      "loss": 1.6959,
      "step": 48
    },
    {
      "epoch": 0.039968652037617555,
      "grad_norm": 0.24993999302387238,
      "learning_rate": 5.695865504800327e-05,
      "loss": 1.6182,
      "step": 51
    },
    {
      "epoch": 0.04231974921630094,
      "grad_norm": 0.25631314516067505,
      "learning_rate": 5.174497483512506e-05,
      "loss": 1.5026,
      "step": 54
    },
    {
      "epoch": 0.04231974921630094,
      "eval_loss": 1.6353027820587158,
      "eval_runtime": 155.6626,
      "eval_samples_per_second": 13.806,
      "eval_steps_per_second": 1.728,
      "step": 54
    },
    {
      "epoch": 0.04467084639498432,
      "grad_norm": 0.23046250641345978,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 1.5225,
      "step": 57
    },
    {
      "epoch": 0.047021943573667714,
      "grad_norm": 0.2635563910007477,
      "learning_rate": 4.131759111665349e-05,
      "loss": 1.6317,
      "step": 60
    },
    {
      "epoch": 0.0493730407523511,
      "grad_norm": 0.272748738527298,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 1.6508,
      "step": 63
    },
    {
      "epoch": 0.0493730407523511,
      "eval_loss": 1.628738284111023,
      "eval_runtime": 155.6556,
      "eval_samples_per_second": 13.806,
      "eval_steps_per_second": 1.728,
      "step": 63
    },
    {
      "epoch": 0.05172413793103448,
      "grad_norm": 0.31287166476249695,
      "learning_rate": 3.12696703292044e-05,
      "loss": 1.5983,
      "step": 66
    },
    {
      "epoch": 0.054075235109717866,
      "grad_norm": 0.2865971028804779,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 1.5986,
      "step": 69
    },
    {
      "epoch": 0.05642633228840126,
      "grad_norm": 0.24794569611549377,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 1.6311,
      "step": 72
    },
    {
      "epoch": 0.05642633228840126,
      "eval_loss": 1.624565839767456,
      "eval_runtime": 155.6863,
      "eval_samples_per_second": 13.803,
      "eval_steps_per_second": 1.728,
      "step": 72
    },
    {
      "epoch": 0.05877742946708464,
      "grad_norm": 0.30881521105766296,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 1.5812,
      "step": 75
    },
    {
      "epoch": 0.061128526645768025,
      "grad_norm": 0.3214222490787506,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 1.5031,
      "step": 78
    },
    {
      "epoch": 0.06347962382445141,
      "grad_norm": 0.9007675647735596,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 1.6133,
      "step": 81
    },
    {
      "epoch": 0.06347962382445141,
      "eval_loss": 1.6222409009933472,
      "eval_runtime": 155.6887,
      "eval_samples_per_second": 13.803,
      "eval_steps_per_second": 1.728,
      "step": 81
    },
    {
      "epoch": 0.06583072100313479,
      "grad_norm": 0.27317968010902405,
      "learning_rate": 7.597595192178702e-06,
      "loss": 1.5434,
      "step": 84
    },
    {
      "epoch": 0.06818181818181818,
      "grad_norm": 0.3382052481174469,
      "learning_rate": 5.060297685041659e-06,
      "loss": 1.5874,
      "step": 87
    },
    {
      "epoch": 0.07053291536050156,
      "grad_norm": 0.2950480878353119,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 1.5417,
      "step": 90
    },
    {
      "epoch": 0.07053291536050156,
      "eval_loss": 1.6213549375534058,
      "eval_runtime": 155.6058,
      "eval_samples_per_second": 13.811,
      "eval_steps_per_second": 1.729,
      "step": 90
    },
    {
      "epoch": 0.07288401253918496,
      "grad_norm": 0.27879786491394043,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 1.7045,
      "step": 93
    },
    {
      "epoch": 0.07523510971786834,
      "grad_norm": 0.2570805847644806,
      "learning_rate": 4.865965629214819e-07,
      "loss": 1.4772,
      "step": 96
    },
    {
      "epoch": 0.07758620689655173,
      "grad_norm": 0.23328937590122223,
      "learning_rate": 3.04586490452119e-08,
      "loss": 1.6005,
      "step": 99
    },
    {
      "epoch": 0.07758620689655173,
      "eval_loss": 1.6211639642715454,
      "eval_runtime": 155.6403,
      "eval_samples_per_second": 13.807,
      "eval_steps_per_second": 1.728,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.444156864022446e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}