{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9908256880733948,
  "eval_steps": 500,
  "global_step": 243,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.06116207951070336,
      "grad_norm": 1.7883533239364624,
      "learning_rate": 0.00019986631570270832,
      "loss": 2.3883,
      "num_input_tokens_seen": 4016,
      "step": 5
    },
    {
      "epoch": 0.12232415902140673,
      "grad_norm": 2.9251019954681396,
      "learning_rate": 0.00019932383577419432,
      "loss": 1.4752,
      "num_input_tokens_seen": 7952,
      "step": 10
    },
    {
      "epoch": 0.1834862385321101,
      "grad_norm": 5.290874004364014,
      "learning_rate": 0.0001983664691986601,
      "loss": 1.1174,
      "num_input_tokens_seen": 11936,
      "step": 15
    },
    {
      "epoch": 0.24464831804281345,
      "grad_norm": 6.394321918487549,
      "learning_rate": 0.00019699821500217434,
      "loss": 0.7815,
      "num_input_tokens_seen": 15808,
      "step": 20
    },
    {
      "epoch": 0.3058103975535168,
      "grad_norm": 1.3936750888824463,
      "learning_rate": 0.00019522478853384155,
      "loss": 0.632,
      "num_input_tokens_seen": 19888,
      "step": 25
    },
    {
      "epoch": 0.3669724770642202,
      "grad_norm": 0.6125549674034119,
      "learning_rate": 0.00019305359759215685,
      "loss": 0.4603,
      "num_input_tokens_seen": 23856,
      "step": 30
    },
    {
      "epoch": 0.42813455657492355,
      "grad_norm": 0.8421280980110168,
      "learning_rate": 0.00019049371148181253,
      "loss": 0.4761,
      "num_input_tokens_seen": 27936,
      "step": 35
    },
    {
      "epoch": 0.4892966360856269,
      "grad_norm": 0.7261258959770203,
      "learning_rate": 0.0001875558231302091,
      "loss": 0.4525,
      "num_input_tokens_seen": 31872,
      "step": 40
    },
    {
      "epoch": 0.5504587155963303,
      "grad_norm": 0.8600367903709412,
      "learning_rate": 0.00018425220442191495,
      "loss": 0.4803,
      "num_input_tokens_seen": 35696,
      "step": 45
    },
    {
      "epoch": 0.6116207951070336,
      "grad_norm": 0.8055685758590698,
      "learning_rate": 0.00018059665493764743,
      "loss": 0.3933,
      "num_input_tokens_seen": 39680,
      "step": 50
    },
    {
      "epoch": 0.672782874617737,
      "grad_norm": 0.7538366317749023,
      "learning_rate": 0.0001766044443118978,
      "loss": 0.3919,
      "num_input_tokens_seen": 43920,
      "step": 55
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 0.8907052874565125,
      "learning_rate": 0.00017229224844997928,
      "loss": 0.3804,
      "num_input_tokens_seen": 48160,
      "step": 60
    },
    {
      "epoch": 0.7951070336391437,
      "grad_norm": 0.7426741123199463,
      "learning_rate": 0.00016767807987092621,
      "loss": 0.3576,
      "num_input_tokens_seen": 52080,
      "step": 65
    },
    {
      "epoch": 0.8562691131498471,
      "grad_norm": 0.6457409262657166,
      "learning_rate": 0.00016278121246720987,
      "loss": 0.3343,
      "num_input_tokens_seen": 56128,
      "step": 70
    },
    {
      "epoch": 0.9174311926605505,
      "grad_norm": 0.9887730479240417,
      "learning_rate": 0.00015762210099555803,
      "loss": 0.4526,
      "num_input_tokens_seen": 59952,
      "step": 75
    },
    {
      "epoch": 0.9785932721712538,
      "grad_norm": 0.9649442434310913,
      "learning_rate": 0.00015222229563517385,
      "loss": 0.4048,
      "num_input_tokens_seen": 63840,
      "step": 80
    },
    {
      "epoch": 1.0489296636085628,
      "grad_norm": 0.8496802449226379,
      "learning_rate": 0.0001466043519702539,
      "loss": 0.3599,
      "num_input_tokens_seen": 68176,
      "step": 85
    },
    {
      "epoch": 1.110091743119266,
      "grad_norm": 0.6206537485122681,
      "learning_rate": 0.00014079173677281837,
      "loss": 0.2197,
      "num_input_tokens_seen": 72336,
      "step": 90
    },
    {
      "epoch": 1.1712538226299694,
      "grad_norm": 0.7237979173660278,
      "learning_rate": 0.00013480872997940905,
      "loss": 0.1816,
      "num_input_tokens_seen": 76384,
      "step": 95
    },
    {
      "epoch": 1.2324159021406729,
      "grad_norm": 1.0752713680267334,
      "learning_rate": 0.00012868032327110904,
      "loss": 0.1839,
      "num_input_tokens_seen": 80368,
      "step": 100
    },
    {
      "epoch": 1.2935779816513762,
      "grad_norm": 1.0526070594787598,
      "learning_rate": 0.00012243211568052677,
      "loss": 0.21,
      "num_input_tokens_seen": 84400,
      "step": 105
    },
    {
      "epoch": 1.3547400611620795,
      "grad_norm": 1.073427677154541,
      "learning_rate": 0.00011609020666180575,
      "loss": 0.2568,
      "num_input_tokens_seen": 88352,
      "step": 110
    },
    {
      "epoch": 1.4159021406727827,
      "grad_norm": 0.8212242722511292,
      "learning_rate": 0.00010968108707031792,
      "loss": 0.2049,
      "num_input_tokens_seen": 92464,
      "step": 115
    },
    {
      "epoch": 1.4770642201834863,
      "grad_norm": 1.1588611602783203,
      "learning_rate": 0.00010323152850743107,
      "loss": 0.2213,
      "num_input_tokens_seen": 96432,
      "step": 120
    },
    {
      "epoch": 1.5382262996941896,
      "grad_norm": 1.08698308467865,
      "learning_rate": 9.676847149256895e-05,
      "loss": 0.2836,
      "num_input_tokens_seen": 100416,
      "step": 125
    },
    {
      "epoch": 1.599388379204893,
      "grad_norm": 1.1150074005126953,
      "learning_rate": 9.03189129296821e-05,
      "loss": 0.228,
      "num_input_tokens_seen": 104432,
      "step": 130
    },
    {
      "epoch": 1.6605504587155964,
      "grad_norm": 0.7235325574874878,
      "learning_rate": 8.390979333819426e-05,
      "loss": 0.1778,
      "num_input_tokens_seen": 108432,
      "step": 135
    },
    {
      "epoch": 1.7217125382262997,
      "grad_norm": 0.8855745196342468,
      "learning_rate": 7.756788431947326e-05,
      "loss": 0.1871,
      "num_input_tokens_seen": 112320,
      "step": 140
    },
    {
      "epoch": 1.782874617737003,
      "grad_norm": 1.3950036764144897,
      "learning_rate": 7.131967672889101e-05,
      "loss": 0.2289,
      "num_input_tokens_seen": 116272,
      "step": 145
    },
    {
      "epoch": 1.8440366972477065,
      "grad_norm": 1.182417392730713,
      "learning_rate": 6.519127002059095e-05,
      "loss": 0.2889,
      "num_input_tokens_seen": 120224,
      "step": 150
    },
    {
      "epoch": 1.9051987767584098,
      "grad_norm": 1.020156741142273,
      "learning_rate": 5.920826322718165e-05,
      "loss": 0.2724,
      "num_input_tokens_seen": 124176,
      "step": 155
    },
    {
      "epoch": 1.9663608562691133,
      "grad_norm": 0.8830191493034363,
      "learning_rate": 5.339564802974615e-05,
      "loss": 0.2359,
      "num_input_tokens_seen": 128256,
      "step": 160
    },
    {
      "epoch": 2.036697247706422,
      "grad_norm": 0.8336369395256042,
      "learning_rate": 4.777770436482617e-05,
      "loss": 0.1864,
      "num_input_tokens_seen": 132576,
      "step": 165
    },
    {
      "epoch": 2.0978593272171255,
      "grad_norm": 0.583479106426239,
      "learning_rate": 4.2377899004441966e-05,
      "loss": 0.0671,
      "num_input_tokens_seen": 136608,
      "step": 170
    },
    {
      "epoch": 2.159021406727829,
      "grad_norm": 0.686152994632721,
      "learning_rate": 3.721878753279017e-05,
      "loss": 0.1465,
      "num_input_tokens_seen": 140416,
      "step": 175
    },
    {
      "epoch": 2.220183486238532,
      "grad_norm": 0.6811323761940002,
      "learning_rate": 3.2321920129073816e-05,
      "loss": 0.091,
      "num_input_tokens_seen": 144336,
      "step": 180
    },
    {
      "epoch": 2.2813455657492354,
      "grad_norm": 0.5875197052955627,
      "learning_rate": 2.770775155002071e-05,
      "loss": 0.114,
      "num_input_tokens_seen": 148256,
      "step": 185
    },
    {
      "epoch": 2.3425076452599387,
      "grad_norm": 0.6630216836929321,
      "learning_rate": 2.339555568810221e-05,
      "loss": 0.1381,
      "num_input_tokens_seen": 152416,
      "step": 190
    },
    {
      "epoch": 2.4036697247706424,
      "grad_norm": 0.7730478644371033,
      "learning_rate": 1.9403345062352573e-05,
      "loss": 0.0799,
      "num_input_tokens_seen": 156400,
      "step": 195
    },
    {
      "epoch": 2.4648318042813457,
      "grad_norm": 0.7855842709541321,
      "learning_rate": 1.5747795578085046e-05,
      "loss": 0.0722,
      "num_input_tokens_seen": 160528,
      "step": 200
    },
    {
      "epoch": 2.525993883792049,
      "grad_norm": 0.7239196300506592,
      "learning_rate": 1.2444176869790925e-05,
      "loss": 0.1003,
      "num_input_tokens_seen": 164720,
      "step": 205
    },
    {
      "epoch": 2.5871559633027523,
      "grad_norm": 0.8815809488296509,
      "learning_rate": 9.506288518187467e-06,
      "loss": 0.1155,
      "num_input_tokens_seen": 168560,
      "step": 210
    },
    {
      "epoch": 2.6483180428134556,
      "grad_norm": 1.0388275384902954,
      "learning_rate": 6.946402407843155e-06,
      "loss": 0.0962,
      "num_input_tokens_seen": 172608,
      "step": 215
    },
    {
      "epoch": 2.709480122324159,
      "grad_norm": 0.9285043478012085,
      "learning_rate": 4.775211466158469e-06,
      "loss": 0.0808,
      "num_input_tokens_seen": 176656,
      "step": 220
    },
    {
      "epoch": 2.770642201834862,
      "grad_norm": 0.9785643815994263,
      "learning_rate": 3.0017849978256516e-06,
      "loss": 0.1206,
      "num_input_tokens_seen": 180608,
      "step": 225
    },
    {
      "epoch": 2.8318042813455655,
      "grad_norm": 0.9847484827041626,
      "learning_rate": 1.6335308013398886e-06,
      "loss": 0.1259,
      "num_input_tokens_seen": 184592,
      "step": 230
    },
    {
      "epoch": 2.8929663608562692,
      "grad_norm": 1.2911163568496704,
      "learning_rate": 6.761642258056978e-07,
      "loss": 0.158,
      "num_input_tokens_seen": 188496,
      "step": 235
    },
    {
      "epoch": 2.9541284403669725,
      "grad_norm": 0.7206448912620544,
      "learning_rate": 1.3368429729168076e-07,
      "loss": 0.062,
      "num_input_tokens_seen": 192368,
      "step": 240
    },
    {
      "epoch": 2.9908256880733948,
      "num_input_tokens_seen": 194864,
      "step": 243,
      "total_flos": 7611007265931264.0,
      "train_loss": 0.34003226710445106,
      "train_runtime": 5382.7216,
      "train_samples_per_second": 0.728,
      "train_steps_per_second": 0.045
    }
  ],
  "logging_steps": 5,
  "max_steps": 243,
  "num_input_tokens_seen": 194864,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7611007265931264.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}