{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 10.0,
  "eval_steps": 500,
  "global_step": 1580,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.15822784810126583,
      "grad_norm": 2.233290195465088,
      "learning_rate": 0.0002,
      "loss": 3.0567,
      "step": 25
    },
    {
      "epoch": 0.31645569620253167,
      "grad_norm": 1.9256885051727295,
      "learning_rate": 0.0002,
      "loss": 2.6434,
      "step": 50
    },
    {
      "epoch": 0.47468354430379744,
      "grad_norm": 4.249744415283203,
      "learning_rate": 0.0002,
      "loss": 2.0778,
      "step": 75
    },
    {
      "epoch": 0.6329113924050633,
      "grad_norm": 1.954801082611084,
      "learning_rate": 0.0002,
      "loss": 2.1352,
      "step": 100
    },
    {
      "epoch": 0.7911392405063291,
      "grad_norm": 1.9269670248031616,
      "learning_rate": 0.0002,
      "loss": 1.8299,
      "step": 125
    },
    {
      "epoch": 0.9493670886075949,
      "grad_norm": 4.059688091278076,
      "learning_rate": 0.0002,
      "loss": 1.6206,
      "step": 150
    },
    {
      "epoch": 1.1075949367088607,
      "grad_norm": 2.5162670612335205,
      "learning_rate": 0.0002,
      "loss": 1.7301,
      "step": 175
    },
    {
      "epoch": 1.2658227848101267,
      "grad_norm": 2.2635657787323,
      "learning_rate": 0.0002,
      "loss": 1.3103,
      "step": 200
    },
    {
      "epoch": 1.4240506329113924,
      "grad_norm": 2.5782394409179688,
      "learning_rate": 0.0002,
      "loss": 1.2166,
      "step": 225
    },
    {
      "epoch": 1.5822784810126582,
      "grad_norm": 2.443361282348633,
      "learning_rate": 0.0002,
      "loss": 1.4792,
      "step": 250
    },
    {
      "epoch": 1.740506329113924,
      "grad_norm": 4.522688388824463,
      "learning_rate": 0.0002,
      "loss": 1.2199,
      "step": 275
    },
    {
      "epoch": 1.8987341772151898,
      "grad_norm": 3.9393839836120605,
      "learning_rate": 0.0002,
      "loss": 1.3172,
      "step": 300
    },
    {
      "epoch": 2.0569620253164556,
      "grad_norm": 1.763312816619873,
      "learning_rate": 0.0002,
      "loss": 1.1909,
      "step": 325
    },
    {
      "epoch": 2.2151898734177213,
      "grad_norm": 2.383930206298828,
      "learning_rate": 0.0002,
      "loss": 0.9682,
      "step": 350
    },
    {
      "epoch": 2.3734177215189876,
      "grad_norm": 3.6665306091308594,
      "learning_rate": 0.0002,
      "loss": 1.1693,
      "step": 375
    },
    {
      "epoch": 2.5316455696202533,
      "grad_norm": 1.7745016813278198,
      "learning_rate": 0.0002,
      "loss": 1.0193,
      "step": 400
    },
    {
      "epoch": 2.689873417721519,
      "grad_norm": 1.569421410560608,
      "learning_rate": 0.0002,
      "loss": 0.9753,
      "step": 425
    },
    {
      "epoch": 2.848101265822785,
      "grad_norm": 2.2681877613067627,
      "learning_rate": 0.0002,
      "loss": 1.0567,
      "step": 450
    },
    {
      "epoch": 3.0063291139240507,
      "grad_norm": 1.752241849899292,
      "learning_rate": 0.0002,
      "loss": 1.0343,
      "step": 475
    },
    {
      "epoch": 3.1645569620253164,
      "grad_norm": 0.7529569268226624,
      "learning_rate": 0.0002,
      "loss": 0.8624,
      "step": 500
    },
    {
      "epoch": 3.3227848101265822,
      "grad_norm": 2.013693332672119,
      "learning_rate": 0.0002,
      "loss": 0.9729,
      "step": 525
    },
    {
      "epoch": 3.481012658227848,
      "grad_norm": 2.212862730026245,
      "learning_rate": 0.0002,
      "loss": 0.8433,
      "step": 550
    },
    {
      "epoch": 3.6392405063291138,
      "grad_norm": 2.6525330543518066,
      "learning_rate": 0.0002,
      "loss": 0.9046,
      "step": 575
    },
    {
      "epoch": 3.7974683544303796,
      "grad_norm": 1.9108997583389282,
      "learning_rate": 0.0002,
      "loss": 0.9368,
      "step": 600
    },
    {
      "epoch": 3.9556962025316453,
      "grad_norm": 1.4593428373336792,
      "learning_rate": 0.0002,
      "loss": 0.8079,
      "step": 625
    },
    {
      "epoch": 4.113924050632911,
      "grad_norm": 1.0320943593978882,
      "learning_rate": 0.0002,
      "loss": 0.8961,
      "step": 650
    },
    {
      "epoch": 4.272151898734177,
      "grad_norm": 2.041616439819336,
      "learning_rate": 0.0002,
      "loss": 0.7348,
      "step": 675
    },
    {
      "epoch": 4.430379746835443,
      "grad_norm": 2.494473457336426,
      "learning_rate": 0.0002,
      "loss": 0.7822,
      "step": 700
    },
    {
      "epoch": 4.588607594936709,
      "grad_norm": 1.134831428527832,
      "learning_rate": 0.0002,
      "loss": 0.8666,
      "step": 725
    },
    {
      "epoch": 4.746835443037975,
      "grad_norm": 1.860443353652954,
      "learning_rate": 0.0002,
      "loss": 0.7721,
      "step": 750
    },
    {
      "epoch": 4.905063291139241,
      "grad_norm": 3.339151620864868,
      "learning_rate": 0.0002,
      "loss": 0.8407,
      "step": 775
    },
    {
      "epoch": 5.063291139240507,
      "grad_norm": 1.3228943347930908,
      "learning_rate": 0.0002,
      "loss": 0.833,
      "step": 800
    },
    {
      "epoch": 5.2215189873417724,
      "grad_norm": 2.0199851989746094,
      "learning_rate": 0.0002,
      "loss": 0.6558,
      "step": 825
    },
    {
      "epoch": 5.379746835443038,
      "grad_norm": 1.0233032703399658,
      "learning_rate": 0.0002,
      "loss": 0.7571,
      "step": 850
    },
    {
      "epoch": 5.537974683544304,
      "grad_norm": 1.8455493450164795,
      "learning_rate": 0.0002,
      "loss": 0.7673,
      "step": 875
    },
    {
      "epoch": 5.69620253164557,
      "grad_norm": 1.3019192218780518,
      "learning_rate": 0.0002,
      "loss": 0.6765,
      "step": 900
    },
    {
      "epoch": 5.8544303797468356,
      "grad_norm": 1.6968228816986084,
      "learning_rate": 0.0002,
      "loss": 0.8249,
      "step": 925
    },
    {
      "epoch": 6.012658227848101,
      "grad_norm": 1.5166069269180298,
      "learning_rate": 0.0002,
      "loss": 0.765,
      "step": 950
    },
    {
      "epoch": 6.170886075949367,
      "grad_norm": 1.438341498374939,
      "learning_rate": 0.0002,
      "loss": 0.628,
      "step": 975
    },
    {
      "epoch": 6.329113924050633,
      "grad_norm": 1.4135054349899292,
      "learning_rate": 0.0002,
      "loss": 0.7128,
      "step": 1000
    },
    {
      "epoch": 6.487341772151899,
      "grad_norm": 1.8510311841964722,
      "learning_rate": 0.0002,
      "loss": 0.6726,
      "step": 1025
    },
    {
      "epoch": 6.6455696202531644,
      "grad_norm": 0.8984973430633545,
      "learning_rate": 0.0002,
      "loss": 0.7169,
      "step": 1050
    },
    {
      "epoch": 6.80379746835443,
      "grad_norm": 1.762295126914978,
      "learning_rate": 0.0002,
      "loss": 0.7315,
      "step": 1075
    },
    {
      "epoch": 6.962025316455696,
      "grad_norm": 1.3354698419570923,
      "learning_rate": 0.0002,
      "loss": 0.6275,
      "step": 1100
    },
    {
      "epoch": 7.120253164556962,
      "grad_norm": 1.680066466331482,
      "learning_rate": 0.0002,
      "loss": 0.6706,
      "step": 1125
    },
    {
      "epoch": 7.2784810126582276,
      "grad_norm": 1.5245403051376343,
      "learning_rate": 0.0002,
      "loss": 0.6232,
      "step": 1150
    },
    {
      "epoch": 7.436708860759493,
      "grad_norm": 1.4877965450286865,
      "learning_rate": 0.0002,
      "loss": 0.5902,
      "step": 1175
    },
    {
      "epoch": 7.594936708860759,
      "grad_norm": 0.7956791520118713,
      "learning_rate": 0.0002,
      "loss": 0.6998,
      "step": 1200
    },
    {
      "epoch": 7.753164556962025,
      "grad_norm": 2.1762688159942627,
      "learning_rate": 0.0002,
      "loss": 0.7275,
      "step": 1225
    },
    {
      "epoch": 7.911392405063291,
      "grad_norm": 1.2218317985534668,
      "learning_rate": 0.0002,
      "loss": 0.6267,
      "step": 1250
    },
    {
      "epoch": 8.069620253164556,
      "grad_norm": 1.339480996131897,
      "learning_rate": 0.0002,
      "loss": 0.6799,
      "step": 1275
    },
    {
      "epoch": 8.227848101265822,
      "grad_norm": 1.3387433290481567,
      "learning_rate": 0.0002,
      "loss": 0.577,
      "step": 1300
    },
    {
      "epoch": 8.386075949367088,
      "grad_norm": 1.0354127883911133,
      "learning_rate": 0.0002,
      "loss": 0.6526,
      "step": 1325
    },
    {
      "epoch": 8.544303797468354,
      "grad_norm": 1.4868078231811523,
      "learning_rate": 0.0002,
      "loss": 0.6638,
      "step": 1350
    },
    {
      "epoch": 8.70253164556962,
      "grad_norm": 0.7492271065711975,
      "learning_rate": 0.0002,
      "loss": 0.5833,
      "step": 1375
    },
    {
      "epoch": 8.860759493670885,
      "grad_norm": 1.3193756341934204,
      "learning_rate": 0.0002,
      "loss": 0.6851,
      "step": 1400
    },
    {
      "epoch": 9.018987341772151,
      "grad_norm": 1.924387812614441,
      "learning_rate": 0.0002,
      "loss": 0.6335,
      "step": 1425
    },
    {
      "epoch": 9.177215189873417,
      "grad_norm": 1.1999796628952026,
      "learning_rate": 0.0002,
      "loss": 0.4827,
      "step": 1450
    },
    {
      "epoch": 9.335443037974684,
      "grad_norm": 1.647176742553711,
      "learning_rate": 0.0002,
      "loss": 0.6423,
      "step": 1475
    },
    {
      "epoch": 9.49367088607595,
      "grad_norm": 1.3660459518432617,
      "learning_rate": 0.0002,
      "loss": 0.6176,
      "step": 1500
    },
    {
      "epoch": 9.651898734177216,
      "grad_norm": 0.9778301119804382,
      "learning_rate": 0.0002,
      "loss": 0.5802,
      "step": 1525
    },
    {
      "epoch": 9.810126582278482,
      "grad_norm": 1.5528557300567627,
      "learning_rate": 0.0002,
      "loss": 0.6645,
      "step": 1550
    },
    {
      "epoch": 9.968354430379748,
      "grad_norm": 1.8788762092590332,
      "learning_rate": 0.0002,
      "loss": 0.5932,
      "step": 1575
    }
  ],
  "logging_steps": 25,
  "max_steps": 1580,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 5358729709043712.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}