{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.02957267484844004,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0002957267484844004,
      "eval_loss": 10.55125617980957,
      "eval_runtime": 22.0201,
      "eval_samples_per_second": 258.628,
      "eval_steps_per_second": 32.334,
      "step": 1
    },
    {
      "epoch": 0.0008871802454532013,
      "grad_norm": 0.9051133394241333,
      "learning_rate": 1.5e-05,
      "loss": 10.5652,
      "step": 3
    },
    {
      "epoch": 0.0017743604909064026,
      "grad_norm": 0.9123979806900024,
      "learning_rate": 3e-05,
      "loss": 10.5723,
      "step": 6
    },
    {
      "epoch": 0.002661540736359604,
      "grad_norm": 0.9561561942100525,
      "learning_rate": 4.5e-05,
      "loss": 10.5405,
      "step": 9
    },
    {
      "epoch": 0.002661540736359604,
      "eval_loss": 10.519363403320312,
      "eval_runtime": 21.9544,
      "eval_samples_per_second": 259.401,
      "eval_steps_per_second": 32.431,
      "step": 9
    },
    {
      "epoch": 0.003548720981812805,
      "grad_norm": 1.0936920642852783,
      "learning_rate": 4.993910125649561e-05,
      "loss": 10.5085,
      "step": 12
    },
    {
      "epoch": 0.004435901227266006,
      "grad_norm": 1.1426111459732056,
      "learning_rate": 4.962019382530521e-05,
      "loss": 10.4419,
      "step": 15
    },
    {
      "epoch": 0.005323081472719208,
      "grad_norm": 1.4070194959640503,
      "learning_rate": 4.9031542398457974e-05,
      "loss": 10.3621,
      "step": 18
    },
    {
      "epoch": 0.005323081472719208,
      "eval_loss": 10.309818267822266,
      "eval_runtime": 21.9475,
      "eval_samples_per_second": 259.482,
      "eval_steps_per_second": 32.441,
      "step": 18
    },
    {
      "epoch": 0.006210261718172409,
      "grad_norm": 1.71590256690979,
      "learning_rate": 4.817959636416969e-05,
      "loss": 10.2368,
      "step": 21
    },
    {
      "epoch": 0.00709744196362561,
      "grad_norm": 1.838427186012268,
      "learning_rate": 4.707368982147318e-05,
      "loss": 10.1356,
      "step": 24
    },
    {
      "epoch": 0.007984622209078812,
      "grad_norm": 1.8013561964035034,
      "learning_rate": 4.572593931387604e-05,
      "loss": 10.0861,
      "step": 27
    },
    {
      "epoch": 0.007984622209078812,
      "eval_loss": 9.968961715698242,
      "eval_runtime": 21.66,
      "eval_samples_per_second": 262.927,
      "eval_steps_per_second": 32.872,
      "step": 27
    },
    {
      "epoch": 0.008871802454532013,
      "grad_norm": 2.0989644527435303,
      "learning_rate": 4.415111107797445e-05,
      "loss": 9.9238,
      "step": 30
    },
    {
      "epoch": 0.009758982699985213,
      "grad_norm": 2.026156187057495,
      "learning_rate": 4.2366459261474933e-05,
      "loss": 9.7902,
      "step": 33
    },
    {
      "epoch": 0.010646162945438416,
      "grad_norm": 2.3057544231414795,
      "learning_rate": 4.039153688314145e-05,
      "loss": 9.6303,
      "step": 36
    },
    {
      "epoch": 0.010646162945438416,
      "eval_loss": 9.565936088562012,
      "eval_runtime": 21.9397,
      "eval_samples_per_second": 259.575,
      "eval_steps_per_second": 32.453,
      "step": 36
    },
    {
      "epoch": 0.011533343190891616,
      "grad_norm": 2.221926212310791,
      "learning_rate": 3.824798160583012e-05,
      "loss": 9.4928,
      "step": 39
    },
    {
      "epoch": 0.012420523436344817,
      "grad_norm": 2.357473850250244,
      "learning_rate": 3.5959278669726935e-05,
      "loss": 9.3646,
      "step": 42
    },
    {
      "epoch": 0.013307703681798018,
      "grad_norm": 2.0763473510742188,
      "learning_rate": 3.355050358314172e-05,
      "loss": 9.2398,
      "step": 45
    },
    {
      "epoch": 0.013307703681798018,
      "eval_loss": 9.206684112548828,
      "eval_runtime": 21.8358,
      "eval_samples_per_second": 260.811,
      "eval_steps_per_second": 32.607,
      "step": 45
    },
    {
      "epoch": 0.01419488392725122,
      "grad_norm": 1.9795143604278564,
      "learning_rate": 3.104804738999169e-05,
      "loss": 9.2296,
      "step": 48
    },
    {
      "epoch": 0.015082064172704421,
      "grad_norm": 1.8224148750305176,
      "learning_rate": 2.8479327524001636e-05,
      "loss": 9.087,
      "step": 51
    },
    {
      "epoch": 0.015969244418157624,
      "grad_norm": 1.690493106842041,
      "learning_rate": 2.587248741756253e-05,
      "loss": 8.9913,
      "step": 54
    },
    {
      "epoch": 0.015969244418157624,
      "eval_loss": 8.966434478759766,
      "eval_runtime": 21.8231,
      "eval_samples_per_second": 260.962,
      "eval_steps_per_second": 32.626,
      "step": 54
    },
    {
      "epoch": 0.016856424663610824,
      "grad_norm": 1.7925915718078613,
      "learning_rate": 2.3256088156396868e-05,
      "loss": 9.0067,
      "step": 57
    },
    {
      "epoch": 0.017743604909064025,
      "grad_norm": 1.7501667737960815,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 8.9105,
      "step": 60
    },
    {
      "epoch": 0.018630785154517226,
      "grad_norm": 1.6109447479248047,
      "learning_rate": 1.8109066104575023e-05,
      "loss": 8.8299,
      "step": 63
    },
    {
      "epoch": 0.018630785154517226,
      "eval_loss": 8.807477951049805,
      "eval_runtime": 21.8799,
      "eval_samples_per_second": 260.284,
      "eval_steps_per_second": 32.541,
      "step": 63
    },
    {
      "epoch": 0.019517965399970427,
      "grad_norm": 1.5246303081512451,
      "learning_rate": 1.56348351646022e-05,
      "loss": 8.7661,
      "step": 66
    },
    {
      "epoch": 0.020405145645423627,
      "grad_norm": 1.5019408464431763,
      "learning_rate": 1.3263210930352737e-05,
      "loss": 8.754,
      "step": 69
    },
    {
      "epoch": 0.02129232589087683,
      "grad_norm": 1.5894227027893066,
      "learning_rate": 1.1020177413231334e-05,
      "loss": 8.7077,
      "step": 72
    },
    {
      "epoch": 0.02129232589087683,
      "eval_loss": 8.709175109863281,
      "eval_runtime": 21.6472,
      "eval_samples_per_second": 263.083,
      "eval_steps_per_second": 32.891,
      "step": 72
    },
    {
      "epoch": 0.022179506136330032,
      "grad_norm": 1.444118857383728,
      "learning_rate": 8.930309757836517e-06,
      "loss": 8.7054,
      "step": 75
    },
    {
      "epoch": 0.023066686381783233,
      "grad_norm": 1.4274139404296875,
      "learning_rate": 7.016504991533726e-06,
      "loss": 8.6764,
      "step": 78
    },
    {
      "epoch": 0.023953866627236434,
      "grad_norm": 1.3681466579437256,
      "learning_rate": 5.299731159831953e-06,
      "loss": 8.6759,
      "step": 81
    },
    {
      "epoch": 0.023953866627236434,
      "eval_loss": 8.658232688903809,
      "eval_runtime": 21.8641,
      "eval_samples_per_second": 260.472,
      "eval_steps_per_second": 32.565,
      "step": 81
    },
    {
      "epoch": 0.024841046872689634,
      "grad_norm": 1.3800792694091797,
      "learning_rate": 3.798797596089351e-06,
      "loss": 8.6834,
      "step": 84
    },
    {
      "epoch": 0.025728227118142835,
      "grad_norm": 1.4322713613510132,
      "learning_rate": 2.5301488425208296e-06,
      "loss": 8.5937,
      "step": 87
    },
    {
      "epoch": 0.026615407363596036,
      "grad_norm": 1.4689640998840332,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 8.6467,
      "step": 90
    },
    {
      "epoch": 0.026615407363596036,
      "eval_loss": 8.637799263000488,
      "eval_runtime": 21.7382,
      "eval_samples_per_second": 261.981,
      "eval_steps_per_second": 32.753,
      "step": 90
    },
    {
      "epoch": 0.02750258760904924,
      "grad_norm": 1.3737329244613647,
      "learning_rate": 7.426068431000882e-07,
      "loss": 8.6452,
      "step": 93
    },
    {
      "epoch": 0.02838976785450244,
      "grad_norm": 1.3900516033172607,
      "learning_rate": 2.4329828146074095e-07,
      "loss": 8.6106,
      "step": 96
    },
    {
      "epoch": 0.02927694809995564,
      "grad_norm": 1.3277000188827515,
      "learning_rate": 1.522932452260595e-08,
      "loss": 8.5828,
      "step": 99
    },
    {
      "epoch": 0.02927694809995564,
      "eval_loss": 8.634114265441895,
      "eval_runtime": 21.7633,
      "eval_samples_per_second": 261.678,
      "eval_steps_per_second": 32.716,
      "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": 4457049026985984.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}