{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.308411214953271,
  "eval_steps": 9,
  "global_step": 99,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003115264797507788,
      "eval_loss": 2.8396923542022705,
      "eval_runtime": 35.2524,
      "eval_samples_per_second": 15.346,
      "eval_steps_per_second": 1.929,
      "step": 1
    },
    {
      "epoch": 0.009345794392523364,
      "grad_norm": 0.6679688692092896,
      "learning_rate": 3e-05,
      "loss": 2.9378,
      "step": 3
    },
    {
      "epoch": 0.018691588785046728,
      "grad_norm": 0.6512870788574219,
      "learning_rate": 6e-05,
      "loss": 2.6626,
      "step": 6
    },
    {
      "epoch": 0.028037383177570093,
      "grad_norm": 0.5187833905220032,
      "learning_rate": 9e-05,
      "loss": 2.508,
      "step": 9
    },
    {
      "epoch": 0.028037383177570093,
      "eval_loss": 2.6647448539733887,
      "eval_runtime": 35.78,
      "eval_samples_per_second": 15.12,
      "eval_steps_per_second": 1.901,
      "step": 9
    },
    {
      "epoch": 0.037383177570093455,
      "grad_norm": 0.5416520237922668,
      "learning_rate": 9.987820251299122e-05,
      "loss": 2.6302,
      "step": 12
    },
    {
      "epoch": 0.04672897196261682,
      "grad_norm": 0.5842136144638062,
      "learning_rate": 9.924038765061042e-05,
      "loss": 2.6649,
      "step": 15
    },
    {
      "epoch": 0.056074766355140186,
      "grad_norm": 0.681281566619873,
      "learning_rate": 9.806308479691595e-05,
      "loss": 2.6358,
      "step": 18
    },
    {
      "epoch": 0.056074766355140186,
      "eval_loss": 2.4967315196990967,
      "eval_runtime": 35.8589,
      "eval_samples_per_second": 15.087,
      "eval_steps_per_second": 1.896,
      "step": 18
    },
    {
      "epoch": 0.06542056074766354,
      "grad_norm": 0.44981229305267334,
      "learning_rate": 9.635919272833938e-05,
      "loss": 2.5723,
      "step": 21
    },
    {
      "epoch": 0.07476635514018691,
      "grad_norm": 0.5177224278450012,
      "learning_rate": 9.414737964294636e-05,
      "loss": 2.4427,
      "step": 24
    },
    {
      "epoch": 0.08411214953271028,
      "grad_norm": 0.45180022716522217,
      "learning_rate": 9.145187862775209e-05,
      "loss": 2.7195,
      "step": 27
    },
    {
      "epoch": 0.08411214953271028,
      "eval_loss": 2.473558187484741,
      "eval_runtime": 35.8529,
      "eval_samples_per_second": 15.089,
      "eval_steps_per_second": 1.897,
      "step": 27
    },
    {
      "epoch": 0.09345794392523364,
      "grad_norm": 0.36055752635002136,
      "learning_rate": 8.83022221559489e-05,
      "loss": 2.3665,
      "step": 30
    },
    {
      "epoch": 0.102803738317757,
      "grad_norm": 0.360610693693161,
      "learning_rate": 8.473291852294987e-05,
      "loss": 2.2944,
      "step": 33
    },
    {
      "epoch": 0.11214953271028037,
      "grad_norm": 0.3996005952358246,
      "learning_rate": 8.07830737662829e-05,
      "loss": 2.5749,
      "step": 36
    },
    {
      "epoch": 0.11214953271028037,
      "eval_loss": 2.4603617191314697,
      "eval_runtime": 35.8629,
      "eval_samples_per_second": 15.085,
      "eval_steps_per_second": 1.896,
      "step": 36
    },
    {
      "epoch": 0.12149532710280374,
      "grad_norm": 0.4377972185611725,
      "learning_rate": 7.649596321166024e-05,
      "loss": 2.4763,
      "step": 39
    },
    {
      "epoch": 0.1308411214953271,
      "grad_norm": 0.3858930170536041,
      "learning_rate": 7.191855733945387e-05,
      "loss": 2.3667,
      "step": 42
    },
    {
      "epoch": 0.14018691588785046,
      "grad_norm": 0.49132058024406433,
      "learning_rate": 6.710100716628344e-05,
      "loss": 2.4215,
      "step": 45
    },
    {
      "epoch": 0.14018691588785046,
      "eval_loss": 2.4540045261383057,
      "eval_runtime": 35.8336,
      "eval_samples_per_second": 15.098,
      "eval_steps_per_second": 1.898,
      "step": 45
    },
    {
      "epoch": 0.14953271028037382,
      "grad_norm": 0.46008965373039246,
      "learning_rate": 6.209609477998338e-05,
      "loss": 2.4564,
      "step": 48
    },
    {
      "epoch": 0.1588785046728972,
      "grad_norm": 0.3996325135231018,
      "learning_rate": 5.695865504800327e-05,
      "loss": 2.6137,
      "step": 51
    },
    {
      "epoch": 0.16822429906542055,
      "grad_norm": 0.3991493880748749,
      "learning_rate": 5.174497483512506e-05,
      "loss": 2.5113,
      "step": 54
    },
    {
      "epoch": 0.16822429906542055,
      "eval_loss": 2.449310302734375,
      "eval_runtime": 35.8846,
      "eval_samples_per_second": 15.076,
      "eval_steps_per_second": 1.895,
      "step": 54
    },
    {
      "epoch": 0.17757009345794392,
      "grad_norm": 0.39731472730636597,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 2.2348,
      "step": 57
    },
    {
      "epoch": 0.18691588785046728,
      "grad_norm": 0.3915022611618042,
      "learning_rate": 4.131759111665349e-05,
      "loss": 2.358,
      "step": 60
    },
    {
      "epoch": 0.19626168224299065,
      "grad_norm": 0.518890917301178,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 2.4009,
      "step": 63
    },
    {
      "epoch": 0.19626168224299065,
      "eval_loss": 2.4464268684387207,
      "eval_runtime": 35.8347,
      "eval_samples_per_second": 15.097,
      "eval_steps_per_second": 1.898,
      "step": 63
    },
    {
      "epoch": 0.205607476635514,
      "grad_norm": 0.39004433155059814,
      "learning_rate": 3.12696703292044e-05,
      "loss": 2.5475,
      "step": 66
    },
    {
      "epoch": 0.21495327102803738,
      "grad_norm": 0.32779279351234436,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 2.2946,
      "step": 69
    },
    {
      "epoch": 0.22429906542056074,
      "grad_norm": 0.34863942861557007,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 2.3909,
      "step": 72
    },
    {
      "epoch": 0.22429906542056074,
      "eval_loss": 2.4445815086364746,
      "eval_runtime": 35.8489,
      "eval_samples_per_second": 15.091,
      "eval_steps_per_second": 1.897,
      "step": 72
    },
    {
      "epoch": 0.2336448598130841,
      "grad_norm": 0.31984978914260864,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 2.459,
      "step": 75
    },
    {
      "epoch": 0.24299065420560748,
      "grad_norm": 0.34642836451530457,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 2.5152,
      "step": 78
    },
    {
      "epoch": 0.2523364485981308,
      "grad_norm": 0.3397381901741028,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 2.346,
      "step": 81
    },
    {
      "epoch": 0.2523364485981308,
      "eval_loss": 2.4437313079833984,
      "eval_runtime": 35.8474,
      "eval_samples_per_second": 15.092,
      "eval_steps_per_second": 1.897,
      "step": 81
    },
    {
      "epoch": 0.2616822429906542,
      "grad_norm": 0.36524611711502075,
      "learning_rate": 7.597595192178702e-06,
      "loss": 2.4189,
      "step": 84
    },
    {
      "epoch": 0.27102803738317754,
      "grad_norm": 0.3941788077354431,
      "learning_rate": 5.060297685041659e-06,
      "loss": 2.5074,
      "step": 87
    },
    {
      "epoch": 0.2803738317757009,
      "grad_norm": 0.4242384731769562,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 2.2093,
      "step": 90
    },
    {
      "epoch": 0.2803738317757009,
      "eval_loss": 2.443415880203247,
      "eval_runtime": 35.8185,
      "eval_samples_per_second": 15.104,
      "eval_steps_per_second": 1.898,
      "step": 90
    },
    {
      "epoch": 0.2897196261682243,
      "grad_norm": 0.30537888407707214,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 2.468,
      "step": 93
    },
    {
      "epoch": 0.29906542056074764,
      "grad_norm": 0.4237378239631653,
      "learning_rate": 4.865965629214819e-07,
      "loss": 2.4167,
      "step": 96
    },
    {
      "epoch": 0.308411214953271,
      "grad_norm": 0.3696635067462921,
      "learning_rate": 3.04586490452119e-08,
      "loss": 2.4373,
      "step": 99
    },
    {
      "epoch": 0.308411214953271,
      "eval_loss": 2.4432592391967773,
      "eval_runtime": 35.843,
      "eval_samples_per_second": 15.094,
      "eval_steps_per_second": 1.897,
      "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.293847239768146e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}