{
  "best_metric": 2.269272565841675,
  "best_model_checkpoint": "/kaggle/working/models/checkpoint-3750",
  "epoch": 4.8475055544334475,
  "eval_steps": 750,
  "global_step": 3750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06,
      "grad_norm": 0.10441142320632935,
      "learning_rate": 5e-05,
      "loss": 2.7397,
      "step": 50
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.15981321036815643,
      "learning_rate": 0.0001,
      "loss": 2.6589,
      "step": 100
    },
    {
      "epoch": 0.19,
      "grad_norm": 0.20967262983322144,
      "learning_rate": 9.889819303658e-05,
      "loss": 2.5718,
      "step": 150
    },
    {
      "epoch": 0.26,
      "grad_norm": 0.20717187225818634,
      "learning_rate": 9.779638607315998e-05,
      "loss": 2.5054,
      "step": 200
    },
    {
      "epoch": 0.32,
      "grad_norm": 0.22402256727218628,
      "learning_rate": 9.669457910973999e-05,
      "loss": 2.4717,
      "step": 250
    },
    {
      "epoch": 0.39,
      "grad_norm": 0.27481311559677124,
      "learning_rate": 9.559277214631996e-05,
      "loss": 2.4487,
      "step": 300
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.21997925639152527,
      "learning_rate": 9.449096518289996e-05,
      "loss": 2.4595,
      "step": 350
    },
    {
      "epoch": 0.52,
      "grad_norm": 0.23128151893615723,
      "learning_rate": 9.338915821947995e-05,
      "loss": 2.4498,
      "step": 400
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.2886131703853607,
      "learning_rate": 9.228735125605994e-05,
      "loss": 2.4342,
      "step": 450
    },
    {
      "epoch": 0.65,
      "grad_norm": 0.2664533257484436,
      "learning_rate": 9.118554429263993e-05,
      "loss": 2.41,
      "step": 500
    },
    {
      "epoch": 0.71,
      "grad_norm": 0.2600548267364502,
      "learning_rate": 9.008373732921994e-05,
      "loss": 2.4136,
      "step": 550
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.2559927701950073,
      "learning_rate": 8.898193036579991e-05,
      "loss": 2.4235,
      "step": 600
    },
    {
      "epoch": 0.84,
      "grad_norm": 0.2909291982650757,
      "learning_rate": 8.788012340237991e-05,
      "loss": 2.4128,
      "step": 650
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.3658187687397003,
      "learning_rate": 8.677831643895989e-05,
      "loss": 2.4026,
      "step": 700
    },
    {
      "epoch": 0.97,
      "grad_norm": 0.2849361002445221,
      "learning_rate": 8.567650947553989e-05,
      "loss": 2.4121,
      "step": 750
    },
    {
      "epoch": 0.97,
      "eval_loss": 2.3384921550750732,
      "eval_runtime": 952.2726,
      "eval_samples_per_second": 8.658,
      "eval_steps_per_second": 8.658,
      "step": 750
    },
    {
      "epoch": 1.03,
      "grad_norm": 0.28176233172416687,
      "learning_rate": 8.457470251211988e-05,
      "loss": 2.4043,
      "step": 800
    },
    {
      "epoch": 1.1,
      "grad_norm": 0.3647988736629486,
      "learning_rate": 8.347289554869987e-05,
      "loss": 2.3877,
      "step": 850
    },
    {
      "epoch": 1.16,
      "grad_norm": 0.2923799455165863,
      "learning_rate": 8.237108858527986e-05,
      "loss": 2.4004,
      "step": 900
    },
    {
      "epoch": 1.23,
      "grad_norm": 0.2779831290245056,
      "learning_rate": 8.126928162185985e-05,
      "loss": 2.3928,
      "step": 950
    },
    {
      "epoch": 1.29,
      "grad_norm": 0.29313695430755615,
      "learning_rate": 8.016747465843984e-05,
      "loss": 2.389,
      "step": 1000
    },
    {
      "epoch": 1.36,
      "grad_norm": 0.31519418954849243,
      "learning_rate": 7.906566769501984e-05,
      "loss": 2.3865,
      "step": 1050
    },
    {
      "epoch": 1.42,
      "grad_norm": 0.2636606693267822,
      "learning_rate": 7.796386073159983e-05,
      "loss": 2.3931,
      "step": 1100
    },
    {
      "epoch": 1.49,
      "grad_norm": 0.33571264147758484,
      "learning_rate": 7.686205376817982e-05,
      "loss": 2.3772,
      "step": 1150
    },
    {
      "epoch": 1.55,
      "grad_norm": 0.31720587611198425,
      "learning_rate": 7.576024680475981e-05,
      "loss": 2.3778,
      "step": 1200
    },
    {
      "epoch": 1.62,
      "grad_norm": 0.2712741196155548,
      "learning_rate": 7.46584398413398e-05,
      "loss": 2.3711,
      "step": 1250
    },
    {
      "epoch": 1.68,
      "grad_norm": 0.3407454192638397,
      "learning_rate": 7.35566328779198e-05,
      "loss": 2.3688,
      "step": 1300
    },
    {
      "epoch": 1.75,
      "grad_norm": 0.27811819314956665,
      "learning_rate": 7.245482591449978e-05,
      "loss": 2.3761,
      "step": 1350
    },
    {
      "epoch": 1.81,
      "grad_norm": 0.2932997941970825,
      "learning_rate": 7.135301895107978e-05,
      "loss": 2.385,
      "step": 1400
    },
    {
      "epoch": 1.87,
      "grad_norm": 0.2541429102420807,
      "learning_rate": 7.025121198765977e-05,
      "loss": 2.374,
      "step": 1450
    },
    {
      "epoch": 1.94,
      "grad_norm": 0.2891751527786255,
      "learning_rate": 6.914940502423976e-05,
      "loss": 2.3634,
      "step": 1500
    },
    {
      "epoch": 1.94,
      "eval_loss": 2.3060712814331055,
      "eval_runtime": 954.8022,
      "eval_samples_per_second": 8.635,
      "eval_steps_per_second": 8.635,
      "step": 1500
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.3406051695346832,
      "learning_rate": 6.804759806081975e-05,
      "loss": 2.3682,
      "step": 1550
    },
    {
      "epoch": 2.07,
      "grad_norm": 0.2978401184082031,
      "learning_rate": 6.694579109739974e-05,
      "loss": 2.3646,
      "step": 1600
    },
    {
      "epoch": 2.13,
      "grad_norm": 0.3196316361427307,
      "learning_rate": 6.584398413397973e-05,
      "loss": 2.3536,
      "step": 1650
    },
    {
      "epoch": 2.2,
      "grad_norm": 0.3379887044429779,
      "learning_rate": 6.474217717055973e-05,
      "loss": 2.3637,
      "step": 1700
    },
    {
      "epoch": 2.26,
      "grad_norm": 0.31465980410575867,
      "learning_rate": 6.36403702071397e-05,
      "loss": 2.3652,
      "step": 1750
    },
    {
      "epoch": 2.33,
      "grad_norm": 0.28737229108810425,
      "learning_rate": 6.253856324371971e-05,
      "loss": 2.3477,
      "step": 1800
    },
    {
      "epoch": 2.39,
      "grad_norm": 0.2794209420681,
      "learning_rate": 6.14367562802997e-05,
      "loss": 2.3557,
      "step": 1850
    },
    {
      "epoch": 2.46,
      "grad_norm": 0.2747984230518341,
      "learning_rate": 6.0334949316879686e-05,
      "loss": 2.3772,
      "step": 1900
    },
    {
      "epoch": 2.52,
      "grad_norm": 0.3119751811027527,
      "learning_rate": 5.923314235345968e-05,
      "loss": 2.3551,
      "step": 1950
    },
    {
      "epoch": 2.59,
      "grad_norm": 0.2791976034641266,
      "learning_rate": 5.8131335390039664e-05,
      "loss": 2.3438,
      "step": 2000
    },
    {
      "epoch": 2.65,
      "grad_norm": 0.2925887703895569,
      "learning_rate": 5.702952842661966e-05,
      "loss": 2.3584,
      "step": 2050
    },
    {
      "epoch": 2.71,
      "grad_norm": 0.28244686126708984,
      "learning_rate": 5.592772146319964e-05,
      "loss": 2.352,
      "step": 2100
    },
    {
      "epoch": 2.78,
      "grad_norm": 0.32431092858314514,
      "learning_rate": 5.482591449977964e-05,
      "loss": 2.3538,
      "step": 2150
    },
    {
      "epoch": 2.84,
      "grad_norm": 0.3006184995174408,
      "learning_rate": 5.3724107536359635e-05,
      "loss": 2.3444,
      "step": 2200
    },
    {
      "epoch": 2.91,
      "grad_norm": 0.33126187324523926,
      "learning_rate": 5.262230057293962e-05,
      "loss": 2.3428,
      "step": 2250
    },
    {
      "epoch": 2.91,
      "eval_loss": 2.286065101623535,
      "eval_runtime": 952.0984,
      "eval_samples_per_second": 8.66,
      "eval_steps_per_second": 8.66,
      "step": 2250
    },
    {
      "epoch": 2.97,
      "grad_norm": 0.36009636521339417,
      "learning_rate": 5.152049360951961e-05,
      "loss": 2.357,
      "step": 2300
    },
    {
      "epoch": 3.04,
      "grad_norm": 0.29686203598976135,
      "learning_rate": 5.041868664609961e-05,
      "loss": 2.3503,
      "step": 2350
    },
    {
      "epoch": 3.1,
      "grad_norm": 0.343845397233963,
      "learning_rate": 4.93168796826796e-05,
      "loss": 2.341,
      "step": 2400
    },
    {
      "epoch": 3.17,
      "grad_norm": 0.35624146461486816,
      "learning_rate": 4.821507271925959e-05,
      "loss": 2.3489,
      "step": 2450
    },
    {
      "epoch": 3.23,
      "grad_norm": 0.39963939785957336,
      "learning_rate": 4.7113265755839584e-05,
      "loss": 2.3406,
      "step": 2500
    },
    {
      "epoch": 3.3,
      "grad_norm": 0.31882843375205994,
      "learning_rate": 4.601145879241957e-05,
      "loss": 2.3426,
      "step": 2550
    },
    {
      "epoch": 3.36,
      "grad_norm": 0.30565398931503296,
      "learning_rate": 4.490965182899956e-05,
      "loss": 2.3518,
      "step": 2600
    },
    {
      "epoch": 3.43,
      "grad_norm": 0.3145510256290436,
      "learning_rate": 4.380784486557955e-05,
      "loss": 2.3465,
      "step": 2650
    },
    {
      "epoch": 3.49,
      "grad_norm": 0.31365010142326355,
      "learning_rate": 4.270603790215955e-05,
      "loss": 2.3441,
      "step": 2700
    },
    {
      "epoch": 3.55,
      "grad_norm": 0.2947095036506653,
      "learning_rate": 4.160423093873954e-05,
      "loss": 2.3259,
      "step": 2750
    },
    {
      "epoch": 3.62,
      "grad_norm": 0.32206296920776367,
      "learning_rate": 4.0502423975319526e-05,
      "loss": 2.339,
      "step": 2800
    },
    {
      "epoch": 3.68,
      "grad_norm": 0.31289926171302795,
      "learning_rate": 3.9400617011899515e-05,
      "loss": 2.3377,
      "step": 2850
    },
    {
      "epoch": 3.75,
      "grad_norm": 0.33143824338912964,
      "learning_rate": 3.829881004847951e-05,
      "loss": 2.3388,
      "step": 2900
    },
    {
      "epoch": 3.81,
      "grad_norm": 0.3358709216117859,
      "learning_rate": 3.71970030850595e-05,
      "loss": 2.3288,
      "step": 2950
    },
    {
      "epoch": 3.88,
      "grad_norm": 0.3498934209346771,
      "learning_rate": 3.609519612163949e-05,
      "loss": 2.3438,
      "step": 3000
    },
    {
      "epoch": 3.88,
      "eval_loss": 2.2748169898986816,
      "eval_runtime": 954.0213,
      "eval_samples_per_second": 8.642,
      "eval_steps_per_second": 8.642,
      "step": 3000
    },
    {
      "epoch": 3.94,
      "grad_norm": 0.3428861200809479,
      "learning_rate": 3.499338915821948e-05,
      "loss": 2.3304,
      "step": 3050
    },
    {
      "epoch": 4.01,
      "grad_norm": 0.3780589699745178,
      "learning_rate": 3.389158219479947e-05,
      "loss": 2.3373,
      "step": 3100
    },
    {
      "epoch": 4.07,
      "grad_norm": 0.35940733551979065,
      "learning_rate": 3.2789775231379464e-05,
      "loss": 2.327,
      "step": 3150
    },
    {
      "epoch": 4.14,
      "grad_norm": 0.32163000106811523,
      "learning_rate": 3.1687968267959454e-05,
      "loss": 2.3354,
      "step": 3200
    },
    {
      "epoch": 4.2,
      "grad_norm": 0.4193963408470154,
      "learning_rate": 3.058616130453944e-05,
      "loss": 2.3155,
      "step": 3250
    },
    {
      "epoch": 4.27,
      "grad_norm": 0.32936742901802063,
      "learning_rate": 2.9484354341119435e-05,
      "loss": 2.334,
      "step": 3300
    },
    {
      "epoch": 4.33,
      "grad_norm": 0.34648725390434265,
      "learning_rate": 2.838254737769943e-05,
      "loss": 2.3321,
      "step": 3350
    },
    {
      "epoch": 4.4,
      "grad_norm": 0.3279941976070404,
      "learning_rate": 2.728074041427942e-05,
      "loss": 2.3381,
      "step": 3400
    },
    {
      "epoch": 4.46,
      "grad_norm": 0.29082515835762024,
      "learning_rate": 2.617893345085941e-05,
      "loss": 2.3339,
      "step": 3450
    },
    {
      "epoch": 4.52,
      "grad_norm": 0.33501705527305603,
      "learning_rate": 2.50771264874394e-05,
      "loss": 2.3425,
      "step": 3500
    },
    {
      "epoch": 4.59,
      "grad_norm": 0.3124564290046692,
      "learning_rate": 2.3975319524019392e-05,
      "loss": 2.3257,
      "step": 3550
    },
    {
      "epoch": 4.65,
      "grad_norm": 0.3001866638660431,
      "learning_rate": 2.2873512560599385e-05,
      "loss": 2.3381,
      "step": 3600
    },
    {
      "epoch": 4.72,
      "grad_norm": 0.299400269985199,
      "learning_rate": 2.1771705597179377e-05,
      "loss": 2.3404,
      "step": 3650
    },
    {
      "epoch": 4.78,
      "grad_norm": 0.3362495005130768,
      "learning_rate": 2.0669898633759366e-05,
      "loss": 2.3131,
      "step": 3700
    },
    {
      "epoch": 4.85,
      "grad_norm": 0.31044018268585205,
      "learning_rate": 1.956809167033936e-05,
      "loss": 2.332,
      "step": 3750
    },
    {
      "epoch": 4.85,
      "eval_loss": 2.269272565841675,
      "eval_runtime": 952.7148,
      "eval_samples_per_second": 8.654,
      "eval_steps_per_second": 8.654,
      "step": 3750
    }
  ],
  "logging_steps": 50,
  "max_steps": 4638,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 6,
  "save_steps": 750,
  "total_flos": 1.4703137390592e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}