{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.04153973968429798,
  "eval_steps": 13,
  "global_step": 150,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00027693159789531985,
      "eval_loss": 6.243055820465088,
      "eval_runtime": 457.8006,
      "eval_samples_per_second": 13.285,
      "eval_steps_per_second": 1.662,
      "step": 1
    },
    {
      "epoch": 0.0008307947936859596,
      "grad_norm": 27.681867599487305,
      "learning_rate": 3e-05,
      "loss": 24.6744,
      "step": 3
    },
    {
      "epoch": 0.001661589587371919,
      "grad_norm": 27.828317642211914,
      "learning_rate": 6e-05,
      "loss": 22.5088,
      "step": 6
    },
    {
      "epoch": 0.0024923843810578787,
      "grad_norm": 29.053722381591797,
      "learning_rate": 9e-05,
      "loss": 17.9623,
      "step": 9
    },
    {
      "epoch": 0.003323179174743838,
      "grad_norm": 19.01649284362793,
      "learning_rate": 9.994965332706573e-05,
      "loss": 11.8099,
      "step": 12
    },
    {
      "epoch": 0.003600110772639158,
      "eval_loss": 1.6348825693130493,
      "eval_runtime": 460.8045,
      "eval_samples_per_second": 13.199,
      "eval_steps_per_second": 1.651,
      "step": 13
    },
    {
      "epoch": 0.004153973968429798,
      "grad_norm": 18.268274307250977,
      "learning_rate": 9.968561049466214e-05,
      "loss": 6.9041,
      "step": 15
    },
    {
      "epoch": 0.004984768762115757,
      "grad_norm": 9.425353050231934,
      "learning_rate": 9.919647942993148e-05,
      "loss": 3.1179,
      "step": 18
    },
    {
      "epoch": 0.005815563555801717,
      "grad_norm": 13.245735168457031,
      "learning_rate": 9.848447601883435e-05,
      "loss": 2.4225,
      "step": 21
    },
    {
      "epoch": 0.006646358349487676,
      "grad_norm": 7.058098793029785,
      "learning_rate": 9.755282581475769e-05,
      "loss": 1.7562,
      "step": 24
    },
    {
      "epoch": 0.007200221545278316,
      "eval_loss": 0.40671274065971375,
      "eval_runtime": 461.0952,
      "eval_samples_per_second": 13.19,
      "eval_steps_per_second": 1.65,
      "step": 26
    },
    {
      "epoch": 0.007477153143173636,
      "grad_norm": 5.528973579406738,
      "learning_rate": 9.640574942595196e-05,
      "loss": 1.6548,
      "step": 27
    },
    {
      "epoch": 0.008307947936859596,
      "grad_norm": 5.370375156402588,
      "learning_rate": 9.504844339512095e-05,
      "loss": 1.6354,
      "step": 30
    },
    {
      "epoch": 0.009138742730545555,
      "grad_norm": 4.518975257873535,
      "learning_rate": 9.348705665778478e-05,
      "loss": 1.5657,
      "step": 33
    },
    {
      "epoch": 0.009969537524231515,
      "grad_norm": 3.3204827308654785,
      "learning_rate": 9.172866268606513e-05,
      "loss": 1.445,
      "step": 36
    },
    {
      "epoch": 0.010800332317917475,
      "grad_norm": 5.033892631530762,
      "learning_rate": 8.978122744408906e-05,
      "loss": 1.8423,
      "step": 39
    },
    {
      "epoch": 0.010800332317917475,
      "eval_loss": 0.37738242745399475,
      "eval_runtime": 460.9405,
      "eval_samples_per_second": 13.195,
      "eval_steps_per_second": 1.651,
      "step": 39
    },
    {
      "epoch": 0.011631127111603435,
      "grad_norm": 2.9625065326690674,
      "learning_rate": 8.765357330018056e-05,
      "loss": 1.5417,
      "step": 42
    },
    {
      "epoch": 0.012461921905289393,
      "grad_norm": 2.775251865386963,
      "learning_rate": 8.535533905932738e-05,
      "loss": 1.4174,
      "step": 45
    },
    {
      "epoch": 0.013292716698975353,
      "grad_norm": 3.418978214263916,
      "learning_rate": 8.289693629698564e-05,
      "loss": 1.444,
      "step": 48
    },
    {
      "epoch": 0.014123511492661313,
      "grad_norm": 2.627183437347412,
      "learning_rate": 8.0289502192041e-05,
      "loss": 1.3904,
      "step": 51
    },
    {
      "epoch": 0.014400443090556632,
      "eval_loss": 0.3832974135875702,
      "eval_runtime": 461.0753,
      "eval_samples_per_second": 13.191,
      "eval_steps_per_second": 1.65,
      "step": 52
    },
    {
      "epoch": 0.014954306286347273,
      "grad_norm": 3.195793628692627,
      "learning_rate": 7.754484907260513e-05,
      "loss": 1.4893,
      "step": 54
    },
    {
      "epoch": 0.015785101080033233,
      "grad_norm": 2.969637393951416,
      "learning_rate": 7.467541090321735e-05,
      "loss": 1.5184,
      "step": 57
    },
    {
      "epoch": 0.016615895873719193,
      "grad_norm": 2.318040609359741,
      "learning_rate": 7.169418695587791e-05,
      "loss": 1.5243,
      "step": 60
    },
    {
      "epoch": 0.01744669066740515,
      "grad_norm": 3.390565872192383,
      "learning_rate": 6.861468292009727e-05,
      "loss": 1.4535,
      "step": 63
    },
    {
      "epoch": 0.01800055386319579,
      "eval_loss": 0.36983951926231384,
      "eval_runtime": 461.0103,
      "eval_samples_per_second": 13.193,
      "eval_steps_per_second": 1.651,
      "step": 65
    },
    {
      "epoch": 0.01827748546109111,
      "grad_norm": 26.79857063293457,
      "learning_rate": 6.545084971874738e-05,
      "loss": 1.5632,
      "step": 66
    },
    {
      "epoch": 0.01910828025477707,
      "grad_norm": 1.9956955909729004,
      "learning_rate": 6.22170203068947e-05,
      "loss": 1.4358,
      "step": 69
    },
    {
      "epoch": 0.01993907504846303,
      "grad_norm": 4.290536403656006,
      "learning_rate": 5.8927844739931834e-05,
      "loss": 1.3875,
      "step": 72
    },
    {
      "epoch": 0.02076986984214899,
      "grad_norm": 2.6607825756073,
      "learning_rate": 5.559822380516539e-05,
      "loss": 1.5102,
      "step": 75
    },
    {
      "epoch": 0.02160066463583495,
      "grad_norm": 3.075331687927246,
      "learning_rate": 5.2243241517525754e-05,
      "loss": 1.3868,
      "step": 78
    },
    {
      "epoch": 0.02160066463583495,
      "eval_loss": 0.3655809164047241,
      "eval_runtime": 461.183,
      "eval_samples_per_second": 13.188,
      "eval_steps_per_second": 1.65,
      "step": 78
    },
    {
      "epoch": 0.02243145942952091,
      "grad_norm": 2.3494913578033447,
      "learning_rate": 4.887809678520976e-05,
      "loss": 1.4743,
      "step": 81
    },
    {
      "epoch": 0.02326225422320687,
      "grad_norm": 1.7049707174301147,
      "learning_rate": 4.551803455482833e-05,
      "loss": 1.3911,
      "step": 84
    },
    {
      "epoch": 0.024093049016892826,
      "grad_norm": 2.5893452167510986,
      "learning_rate": 4.2178276747988446e-05,
      "loss": 1.3843,
      "step": 87
    },
    {
      "epoch": 0.024923843810578786,
      "grad_norm": 2.1799535751342773,
      "learning_rate": 3.887395330218429e-05,
      "loss": 1.4394,
      "step": 90
    },
    {
      "epoch": 0.025200775408474107,
      "eval_loss": 0.3514753580093384,
      "eval_runtime": 460.8437,
      "eval_samples_per_second": 13.198,
      "eval_steps_per_second": 1.651,
      "step": 91
    },
    {
      "epoch": 0.025754638604264746,
      "grad_norm": 1.784736156463623,
      "learning_rate": 3.562003362839914e-05,
      "loss": 1.3904,
      "step": 93
    },
    {
      "epoch": 0.026585433397950706,
      "grad_norm": 1.4629104137420654,
      "learning_rate": 3.243125879593286e-05,
      "loss": 1.4639,
      "step": 96
    },
    {
      "epoch": 0.027416228191636666,
      "grad_norm": 1.478938102722168,
      "learning_rate": 2.932207475167398e-05,
      "loss": 1.4463,
      "step": 99
    },
    {
      "epoch": 0.028247022985322626,
      "grad_norm": 1.7279759645462036,
      "learning_rate": 2.630656687635007e-05,
      "loss": 1.3153,
      "step": 102
    },
    {
      "epoch": 0.028800886181113265,
      "eval_loss": 0.3473006784915924,
      "eval_runtime": 460.803,
      "eval_samples_per_second": 13.199,
      "eval_steps_per_second": 1.651,
      "step": 104
    },
    {
      "epoch": 0.029077817779008586,
      "grad_norm": 2.075512647628784,
      "learning_rate": 2.3398396174233178e-05,
      "loss": 1.4585,
      "step": 105
    },
    {
      "epoch": 0.029908612572694546,
      "grad_norm": 2.6266424655914307,
      "learning_rate": 2.061073738537635e-05,
      "loss": 1.4344,
      "step": 108
    },
    {
      "epoch": 0.030739407366380506,
      "grad_norm": 1.5184435844421387,
      "learning_rate": 1.7956219300748793e-05,
      "loss": 1.387,
      "step": 111
    },
    {
      "epoch": 0.031570202160066466,
      "grad_norm": 2.3101930618286133,
      "learning_rate": 1.544686755065677e-05,
      "loss": 1.3772,
      "step": 114
    },
    {
      "epoch": 0.032400996953752426,
      "grad_norm": 2.4926693439483643,
      "learning_rate": 1.3094050125632972e-05,
      "loss": 1.339,
      "step": 117
    },
    {
      "epoch": 0.032400996953752426,
      "eval_loss": 0.3452422320842743,
      "eval_runtime": 460.5584,
      "eval_samples_per_second": 13.206,
      "eval_steps_per_second": 1.652,
      "step": 117
    },
    {
      "epoch": 0.033231791747438386,
      "grad_norm": 2.4200942516326904,
      "learning_rate": 1.090842587659851e-05,
      "loss": 1.3846,
      "step": 120
    },
    {
      "epoch": 0.034062586541124346,
      "grad_norm": 2.8469035625457764,
      "learning_rate": 8.899896227604509e-06,
      "loss": 1.4455,
      "step": 123
    },
    {
      "epoch": 0.0348933813348103,
      "grad_norm": 1.944390892982483,
      "learning_rate": 7.077560319906695e-06,
      "loss": 1.419,
      "step": 126
    },
    {
      "epoch": 0.03572417612849626,
      "grad_norm": 2.8275833129882812,
      "learning_rate": 5.449673790581611e-06,
      "loss": 1.3674,
      "step": 129
    },
    {
      "epoch": 0.03600110772639158,
      "eval_loss": 0.34357109665870667,
      "eval_runtime": 460.8114,
      "eval_samples_per_second": 13.198,
      "eval_steps_per_second": 1.651,
      "step": 130
    },
    {
      "epoch": 0.03655497092218222,
      "grad_norm": 2.236476421356201,
      "learning_rate": 4.023611372427471e-06,
      "loss": 1.3822,
      "step": 132
    },
    {
      "epoch": 0.03738576571586818,
      "grad_norm": 2.308274507522583,
      "learning_rate": 2.8058334845816213e-06,
      "loss": 1.3381,
      "step": 135
    },
    {
      "epoch": 0.03821656050955414,
      "grad_norm": 1.7674018144607544,
      "learning_rate": 1.8018569652073381e-06,
      "loss": 1.396,
      "step": 138
    },
    {
      "epoch": 0.0390473553032401,
      "grad_norm": 2.1131505966186523,
      "learning_rate": 1.016230078838226e-06,
      "loss": 1.3624,
      "step": 141
    },
    {
      "epoch": 0.03960121849903074,
      "eval_loss": 0.3427909314632416,
      "eval_runtime": 460.8668,
      "eval_samples_per_second": 13.197,
      "eval_steps_per_second": 1.651,
      "step": 143
    },
    {
      "epoch": 0.03987815009692606,
      "grad_norm": 2.2642595767974854,
      "learning_rate": 4.52511911603265e-07,
      "loss": 1.3243,
      "step": 144
    },
    {
      "epoch": 0.04070894489061202,
      "grad_norm": 2.4517059326171875,
      "learning_rate": 1.132562476771959e-07,
      "loss": 1.3393,
      "step": 147
    },
    {
      "epoch": 0.04153973968429798,
      "grad_norm": 2.226973533630371,
      "learning_rate": 0.0,
      "loss": 1.3837,
      "step": 150
    }
  ],
  "logging_steps": 3,
  "max_steps": 150,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4048711119772058e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}