{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.05335289606188936,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.001333822401547234,
      "grad_norm": 5.80256772259428,
      "learning_rate": 4e-06,
      "loss": 1.0498,
      "step": 10
    },
    {
      "epoch": 0.002667644803094468,
      "grad_norm": 33.895696082107904,
      "learning_rate": 8e-06,
      "loss": 1.0653,
      "step": 20
    },
    {
      "epoch": 0.004001467204641702,
      "grad_norm": 5.523348234283539,
      "learning_rate": 1.2e-05,
      "loss": 1.0341,
      "step": 30
    },
    {
      "epoch": 0.005335289606188936,
      "grad_norm": 11.1556403156453,
      "learning_rate": 1.6e-05,
      "loss": 0.9692,
      "step": 40
    },
    {
      "epoch": 0.00666911200773617,
      "grad_norm": 3.7375231126561825,
      "learning_rate": 1.9999999999999998e-05,
      "loss": 0.9554,
      "step": 50
    },
    {
      "epoch": 0.008002934409283404,
      "grad_norm": 8.43538339698909,
      "learning_rate": 2.4e-05,
      "loss": 0.8965,
      "step": 60
    },
    {
      "epoch": 0.009336756810830639,
      "grad_norm": 13.403454896011478,
      "learning_rate": 2.8e-05,
      "loss": 0.8273,
      "step": 70
    },
    {
      "epoch": 0.010670579212377872,
      "grad_norm": 3.95522050766088,
      "learning_rate": 2.9999966406213696e-05,
      "loss": 0.7837,
      "step": 80
    },
    {
      "epoch": 0.012004401613925107,
      "grad_norm": 36.799552052300854,
      "learning_rate": 2.9999697656826056e-05,
      "loss": 0.8288,
      "step": 90
    },
    {
      "epoch": 0.01333822401547234,
      "grad_norm": 1.6305479563258536,
      "learning_rate": 2.9999160162865885e-05,
      "loss": 0.7778,
      "step": 100
    },
    {
      "epoch": 0.014672046417019574,
      "grad_norm": 2.159536648784889,
      "learning_rate": 2.9998353933963273e-05,
      "loss": 0.7616,
      "step": 110
    },
    {
      "epoch": 0.016005868818566808,
      "grad_norm": 3.397321425707004,
      "learning_rate": 2.999727898456315e-05,
      "loss": 0.7594,
      "step": 120
    },
    {
      "epoch": 0.017339691220114042,
      "grad_norm": 4.772220837365037,
      "learning_rate": 2.999593533392503e-05,
      "loss": 0.756,
      "step": 130
    },
    {
      "epoch": 0.018673513621661277,
      "grad_norm": 2.4845945633126885,
      "learning_rate": 2.9994323006122654e-05,
      "loss": 0.7601,
      "step": 140
    },
    {
      "epoch": 0.02000733602320851,
      "grad_norm": 3.591682569169127,
      "learning_rate": 2.9992442030043557e-05,
      "loss": 0.7894,
      "step": 150
    },
    {
      "epoch": 0.021341158424755743,
      "grad_norm": 2.5679458807474416,
      "learning_rate": 2.9990292439388565e-05,
      "loss": 0.7093,
      "step": 160
    },
    {
      "epoch": 0.022674980826302978,
      "grad_norm": 1.9412569107551652,
      "learning_rate": 2.9987874272671168e-05,
      "loss": 0.706,
      "step": 170
    },
    {
      "epoch": 0.024008803227850213,
      "grad_norm": 3.2667097270489,
      "learning_rate": 2.9985187573216855e-05,
      "loss": 0.7586,
      "step": 180
    },
    {
      "epoch": 0.025342625629397444,
      "grad_norm": 4.4208737375400675,
      "learning_rate": 2.998223238916232e-05,
      "loss": 0.6985,
      "step": 190
    },
    {
      "epoch": 0.02667644803094468,
      "grad_norm": 5.515966302183704,
      "learning_rate": 2.9979008773454618e-05,
      "loss": 0.7323,
      "step": 200
    },
    {
      "epoch": 0.028010270432491914,
      "grad_norm": 2.964165450396077,
      "learning_rate": 2.997551678385019e-05,
      "loss": 0.7603,
      "step": 210
    },
    {
      "epoch": 0.02934409283403915,
      "grad_norm": 3.0952916783456197,
      "learning_rate": 2.997175648291384e-05,
      "loss": 0.7421,
      "step": 220
    },
    {
      "epoch": 0.03067791523558638,
      "grad_norm": 4.213588693904103,
      "learning_rate": 2.996772793801763e-05,
      "loss": 0.7322,
      "step": 230
    },
    {
      "epoch": 0.032011737637133615,
      "grad_norm": 1.8568586103139084,
      "learning_rate": 2.996343122133965e-05,
      "loss": 0.6922,
      "step": 240
    },
    {
      "epoch": 0.033345560038680847,
      "grad_norm": 4.494146778909846,
      "learning_rate": 2.9958866409862745e-05,
      "loss": 0.7244,
      "step": 250
    },
    {
      "epoch": 0.034679382440228085,
      "grad_norm": 7.438170074282725,
      "learning_rate": 2.9954033585373108e-05,
      "loss": 0.7093,
      "step": 260
    },
    {
      "epoch": 0.036013204841775316,
      "grad_norm": 2.3744787346857015,
      "learning_rate": 2.994893283445885e-05,
      "loss": 0.6983,
      "step": 270
    },
    {
      "epoch": 0.037347027243322554,
      "grad_norm": 1.4722011682616383,
      "learning_rate": 2.9943564248508415e-05,
      "loss": 0.6781,
      "step": 280
    },
    {
      "epoch": 0.038680849644869786,
      "grad_norm": 3.3397620832486075,
      "learning_rate": 2.9937927923708966e-05,
      "loss": 0.7399,
      "step": 290
    },
    {
      "epoch": 0.04001467204641702,
      "grad_norm": 5.05063397044549,
      "learning_rate": 2.993202396104465e-05,
      "loss": 0.7671,
      "step": 300
    },
    {
      "epoch": 0.041348494447964255,
      "grad_norm": 3.0128431385936767,
      "learning_rate": 2.9925852466294795e-05,
      "loss": 0.7015,
      "step": 310
    },
    {
      "epoch": 0.04268231684951149,
      "grad_norm": 2.0161342716764237,
      "learning_rate": 2.9919413550032014e-05,
      "loss": 0.7009,
      "step": 320
    },
    {
      "epoch": 0.04401613925105872,
      "grad_norm": 1.3114004070324985,
      "learning_rate": 2.991270732762022e-05,
      "loss": 0.7153,
      "step": 330
    },
    {
      "epoch": 0.045349961652605957,
      "grad_norm": 18.493625676806268,
      "learning_rate": 2.990573391921255e-05,
      "loss": 0.7518,
      "step": 340
    },
    {
      "epoch": 0.04668378405415319,
      "grad_norm": 2.9526764059703567,
      "learning_rate": 2.989849344974924e-05,
      "loss": 0.7133,
      "step": 350
    },
    {
      "epoch": 0.048017606455700426,
      "grad_norm": 5.26274958582726,
      "learning_rate": 2.9890986048955368e-05,
      "loss": 0.7139,
      "step": 360
    },
    {
      "epoch": 0.04935142885724766,
      "grad_norm": 3.5319788357887933,
      "learning_rate": 2.9883211851338516e-05,
      "loss": 0.7084,
      "step": 370
    },
    {
      "epoch": 0.05068525125879489,
      "grad_norm": 7.607269935902469,
      "learning_rate": 2.9875170996186392e-05,
      "loss": 0.7309,
      "step": 380
    },
    {
      "epoch": 0.05201907366034213,
      "grad_norm": 2.3456663308287253,
      "learning_rate": 2.986686362756431e-05,
      "loss": 0.6827,
      "step": 390
    },
    {
      "epoch": 0.05335289606188936,
      "grad_norm": 2.176182050789012,
      "learning_rate": 2.9858289894312617e-05,
      "loss": 0.6995,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 7497,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0934282360979456e+18,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}