{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.20036315822428152,
  "eval_steps": 500,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005009078955607038,
      "grad_norm": 3.8452577590942383,
      "learning_rate": 0.0001,
      "loss": 3.7141,
      "step": 10
    },
    {
      "epoch": 0.010018157911214076,
      "grad_norm": 1.3136709928512573,
      "learning_rate": 0.0002,
      "loss": 2.5276,
      "step": 20
    },
    {
      "epoch": 0.015027236866821113,
      "grad_norm": 1.7088837623596191,
      "learning_rate": 0.000199658449300667,
      "loss": 1.5061,
      "step": 30
    },
    {
      "epoch": 0.020036315822428152,
      "grad_norm": 1.5081887245178223,
      "learning_rate": 0.00019863613034027224,
      "loss": 1.3611,
      "step": 40
    },
    {
      "epoch": 0.02504539477803519,
      "grad_norm": 1.4680248498916626,
      "learning_rate": 0.00019694002659393305,
      "loss": 1.2824,
      "step": 50
    },
    {
      "epoch": 0.030054473733642225,
      "grad_norm": 1.4349300861358643,
      "learning_rate": 0.00019458172417006347,
      "loss": 1.2862,
      "step": 60
    },
    {
      "epoch": 0.03506355268924927,
      "grad_norm": 1.3822752237319946,
      "learning_rate": 0.00019157733266550575,
      "loss": 1.2418,
      "step": 70
    },
    {
      "epoch": 0.040072631644856305,
      "grad_norm": 1.3204342126846313,
      "learning_rate": 0.0001879473751206489,
      "loss": 1.1863,
      "step": 80
    },
    {
      "epoch": 0.04508171060046334,
      "grad_norm": 1.6619811058044434,
      "learning_rate": 0.00018371664782625287,
      "loss": 1.292,
      "step": 90
    },
    {
      "epoch": 0.05009078955607038,
      "grad_norm": 1.519755482673645,
      "learning_rate": 0.00017891405093963938,
      "loss": 1.3015,
      "step": 100
    },
    {
      "epoch": 0.05509986851167741,
      "grad_norm": 1.11312997341156,
      "learning_rate": 0.00017357239106731317,
      "loss": 0.9784,
      "step": 110
    },
    {
      "epoch": 0.06010894746728445,
      "grad_norm": 1.171500563621521,
      "learning_rate": 0.00016772815716257412,
      "loss": 1.0728,
      "step": 120
    },
    {
      "epoch": 0.0651180264228915,
      "grad_norm": 1.573570728302002,
      "learning_rate": 0.0001614212712689668,
      "loss": 1.0383,
      "step": 130
    },
    {
      "epoch": 0.07012710537849853,
      "grad_norm": 1.2490291595458984,
      "learning_rate": 0.00015469481581224272,
      "loss": 0.9686,
      "step": 140
    },
    {
      "epoch": 0.07513618433410557,
      "grad_norm": 1.2631878852844238,
      "learning_rate": 0.00014759473930370736,
      "loss": 0.8221,
      "step": 150
    },
    {
      "epoch": 0.08014526328971261,
      "grad_norm": 1.264460802078247,
      "learning_rate": 0.00014016954246529696,
      "loss": 1.0505,
      "step": 160
    },
    {
      "epoch": 0.08515434224531965,
      "grad_norm": 1.6487361192703247,
      "learning_rate": 0.00013246994692046836,
      "loss": 0.9273,
      "step": 170
    },
    {
      "epoch": 0.09016342120092669,
      "grad_norm": 1.2811675071716309,
      "learning_rate": 0.00012454854871407994,
      "loss": 1.0738,
      "step": 180
    },
    {
      "epoch": 0.09517250015653372,
      "grad_norm": 1.3107404708862305,
      "learning_rate": 0.00011645945902807341,
      "loss": 1.0617,
      "step": 190
    },
    {
      "epoch": 0.10018157911214076,
      "grad_norm": 1.3991544246673584,
      "learning_rate": 0.00010825793454723325,
      "loss": 1.0279,
      "step": 200
    },
    {
      "epoch": 0.1051906580677478,
      "grad_norm": 0.982639491558075,
      "learning_rate": 0.0001,
      "loss": 0.6177,
      "step": 210
    },
    {
      "epoch": 0.11019973702335482,
      "grad_norm": 1.3960201740264893,
      "learning_rate": 9.174206545276677e-05,
      "loss": 1.1537,
      "step": 220
    },
    {
      "epoch": 0.11520881597896186,
      "grad_norm": 1.1508264541625977,
      "learning_rate": 8.35405409719266e-05,
      "loss": 1.0193,
      "step": 230
    },
    {
      "epoch": 0.1202178949345689,
      "grad_norm": 1.4218165874481201,
      "learning_rate": 7.54514512859201e-05,
      "loss": 0.9139,
      "step": 240
    },
    {
      "epoch": 0.12522697389017595,
      "grad_norm": 1.4765474796295166,
      "learning_rate": 6.753005307953167e-05,
      "loss": 1.0649,
      "step": 250
    },
    {
      "epoch": 0.130236052845783,
      "grad_norm": 1.854028344154358,
      "learning_rate": 5.983045753470308e-05,
      "loss": 1.0795,
      "step": 260
    },
    {
      "epoch": 0.13524513180139003,
      "grad_norm": 1.1793019771575928,
      "learning_rate": 5.240526069629265e-05,
      "loss": 1.0884,
      "step": 270
    },
    {
      "epoch": 0.14025421075699707,
      "grad_norm": 1.3754643201828003,
      "learning_rate": 4.530518418775733e-05,
      "loss": 1.0449,
      "step": 280
    },
    {
      "epoch": 0.1452632897126041,
      "grad_norm": 1.337937831878662,
      "learning_rate": 3.857872873103322e-05,
      "loss": 0.7611,
      "step": 290
    },
    {
      "epoch": 0.15027236866821114,
      "grad_norm": 1.337849497795105,
      "learning_rate": 3.227184283742591e-05,
      "loss": 1.1993,
      "step": 300
    },
    {
      "epoch": 0.15528144762381818,
      "grad_norm": 1.6689127683639526,
      "learning_rate": 2.6427608932686843e-05,
      "loss": 1.0456,
      "step": 310
    },
    {
      "epoch": 0.16029052657942522,
      "grad_norm": 1.2203370332717896,
      "learning_rate": 2.1085949060360654e-05,
      "loss": 0.869,
      "step": 320
    },
    {
      "epoch": 0.16529960553503226,
      "grad_norm": 1.5624113082885742,
      "learning_rate": 1.6283352173747145e-05,
      "loss": 0.9677,
      "step": 330
    },
    {
      "epoch": 0.1703086844906393,
      "grad_norm": 1.4291284084320068,
      "learning_rate": 1.2052624879351104e-05,
      "loss": 0.9613,
      "step": 340
    },
    {
      "epoch": 0.17531776344624633,
      "grad_norm": 1.324217677116394,
      "learning_rate": 8.422667334494249e-06,
      "loss": 0.8151,
      "step": 350
    },
    {
      "epoch": 0.18032684240185337,
      "grad_norm": 1.0875211954116821,
      "learning_rate": 5.418275829936537e-06,
      "loss": 0.8445,
      "step": 360
    },
    {
      "epoch": 0.1853359213574604,
      "grad_norm": 1.5346405506134033,
      "learning_rate": 3.059973406066963e-06,
      "loss": 0.8916,
      "step": 370
    },
    {
      "epoch": 0.19034500031306745,
      "grad_norm": 1.3770543336868286,
      "learning_rate": 1.3638696597277679e-06,
      "loss": 0.9675,
      "step": 380
    },
    {
      "epoch": 0.19535407926867449,
      "grad_norm": 1.5972645282745361,
      "learning_rate": 3.415506993330153e-07,
      "loss": 0.7615,
      "step": 390
    },
    {
      "epoch": 0.20036315822428152,
      "grad_norm": 1.0311360359191895,
      "learning_rate": 0.0,
      "loss": 0.7726,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 400,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 7.30567126488384e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}