{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 15.0,
  "eval_steps": 500,
  "global_step": 750,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 19.942209243774414,
      "learning_rate": 6.666666666666667e-05,
      "loss": 7.7458,
      "step": 10
    },
    {
      "epoch": 0.4,
      "grad_norm": 3.6758410930633545,
      "learning_rate": 9.896907216494846e-05,
      "loss": 5.6812,
      "step": 20
    },
    {
      "epoch": 0.6,
      "grad_norm": 3.124385356903076,
      "learning_rate": 9.690721649484537e-05,
      "loss": 5.1671,
      "step": 30
    },
    {
      "epoch": 0.8,
      "grad_norm": 3.7686610221862793,
      "learning_rate": 9.484536082474227e-05,
      "loss": 4.7855,
      "step": 40
    },
    {
      "epoch": 1.0,
      "grad_norm": 2.7892873287200928,
      "learning_rate": 9.278350515463918e-05,
      "loss": 4.6247,
      "step": 50
    },
    {
      "epoch": 1.2,
      "grad_norm": 5.682472229003906,
      "learning_rate": 9.072164948453609e-05,
      "loss": 4.4554,
      "step": 60
    },
    {
      "epoch": 1.4,
      "grad_norm": 3.119821786880493,
      "learning_rate": 8.865979381443299e-05,
      "loss": 4.4782,
      "step": 70
    },
    {
      "epoch": 1.6,
      "grad_norm": 3.42207932472229,
      "learning_rate": 8.65979381443299e-05,
      "loss": 4.4169,
      "step": 80
    },
    {
      "epoch": 1.8,
      "grad_norm": 3.197399139404297,
      "learning_rate": 8.453608247422681e-05,
      "loss": 4.248,
      "step": 90
    },
    {
      "epoch": 2.0,
      "grad_norm": 3.766460418701172,
      "learning_rate": 8.247422680412371e-05,
      "loss": 4.3296,
      "step": 100
    },
    {
      "epoch": 2.2,
      "grad_norm": 3.0895087718963623,
      "learning_rate": 8.041237113402063e-05,
      "loss": 4.2014,
      "step": 110
    },
    {
      "epoch": 2.4,
      "grad_norm": 3.011801242828369,
      "learning_rate": 7.835051546391753e-05,
      "loss": 4.1966,
      "step": 120
    },
    {
      "epoch": 2.6,
      "grad_norm": 2.4347891807556152,
      "learning_rate": 7.628865979381443e-05,
      "loss": 4.2682,
      "step": 130
    },
    {
      "epoch": 2.8,
      "grad_norm": 3.443373441696167,
      "learning_rate": 7.422680412371135e-05,
      "loss": 4.2879,
      "step": 140
    },
    {
      "epoch": 3.0,
      "grad_norm": 3.0630757808685303,
      "learning_rate": 7.216494845360825e-05,
      "loss": 4.2395,
      "step": 150
    },
    {
      "epoch": 3.2,
      "grad_norm": 4.507055282592773,
      "learning_rate": 7.010309278350515e-05,
      "loss": 4.2041,
      "step": 160
    },
    {
      "epoch": 3.4,
      "grad_norm": 3.149142265319824,
      "learning_rate": 6.804123711340207e-05,
      "loss": 4.1754,
      "step": 170
    },
    {
      "epoch": 3.6,
      "grad_norm": 3.8777101039886475,
      "learning_rate": 6.597938144329897e-05,
      "loss": 4.1773,
      "step": 180
    },
    {
      "epoch": 3.8,
      "grad_norm": 3.2908365726470947,
      "learning_rate": 6.391752577319587e-05,
      "loss": 4.1004,
      "step": 190
    },
    {
      "epoch": 4.0,
      "grad_norm": 3.825634241104126,
      "learning_rate": 6.185567010309279e-05,
      "loss": 4.1731,
      "step": 200
    },
    {
      "epoch": 4.2,
      "grad_norm": 2.8585126399993896,
      "learning_rate": 5.979381443298969e-05,
      "loss": 4.1421,
      "step": 210
    },
    {
      "epoch": 4.4,
      "grad_norm": 3.541111946105957,
      "learning_rate": 5.7731958762886594e-05,
      "loss": 4.0777,
      "step": 220
    },
    {
      "epoch": 4.6,
      "grad_norm": 4.357095718383789,
      "learning_rate": 5.567010309278351e-05,
      "loss": 4.0769,
      "step": 230
    },
    {
      "epoch": 4.8,
      "grad_norm": 3.1230344772338867,
      "learning_rate": 5.360824742268041e-05,
      "loss": 4.1582,
      "step": 240
    },
    {
      "epoch": 5.0,
      "grad_norm": 3.7142417430877686,
      "learning_rate": 5.1546391752577315e-05,
      "loss": 4.0817,
      "step": 250
    },
    {
      "epoch": 5.2,
      "grad_norm": 3.0471880435943604,
      "learning_rate": 4.948453608247423e-05,
      "loss": 4.118,
      "step": 260
    },
    {
      "epoch": 5.4,
      "grad_norm": 2.6254706382751465,
      "learning_rate": 4.7422680412371134e-05,
      "loss": 4.0025,
      "step": 270
    },
    {
      "epoch": 5.6,
      "grad_norm": 3.170884132385254,
      "learning_rate": 4.536082474226804e-05,
      "loss": 4.0524,
      "step": 280
    },
    {
      "epoch": 5.8,
      "grad_norm": 2.865476369857788,
      "learning_rate": 4.329896907216495e-05,
      "loss": 4.0805,
      "step": 290
    },
    {
      "epoch": 6.0,
      "grad_norm": 3.1281850337982178,
      "learning_rate": 4.1237113402061855e-05,
      "loss": 4.1221,
      "step": 300
    },
    {
      "epoch": 6.2,
      "grad_norm": 3.0519344806671143,
      "learning_rate": 3.9175257731958764e-05,
      "loss": 4.1095,
      "step": 310
    },
    {
      "epoch": 6.4,
      "grad_norm": 3.115818977355957,
      "learning_rate": 3.7113402061855674e-05,
      "loss": 4.1023,
      "step": 320
    },
    {
      "epoch": 6.6,
      "grad_norm": 3.150238275527954,
      "learning_rate": 3.5051546391752576e-05,
      "loss": 4.0486,
      "step": 330
    },
    {
      "epoch": 6.8,
      "grad_norm": 3.5786564350128174,
      "learning_rate": 3.2989690721649485e-05,
      "loss": 3.9712,
      "step": 340
    },
    {
      "epoch": 7.0,
      "grad_norm": 2.9977972507476807,
      "learning_rate": 3.0927835051546395e-05,
      "loss": 4.0619,
      "step": 350
    },
    {
      "epoch": 7.2,
      "grad_norm": 3.5539848804473877,
      "learning_rate": 2.8865979381443297e-05,
      "loss": 4.0779,
      "step": 360
    },
    {
      "epoch": 7.4,
      "grad_norm": 3.2001516819000244,
      "learning_rate": 2.6804123711340206e-05,
      "loss": 3.9964,
      "step": 370
    },
    {
      "epoch": 7.6,
      "grad_norm": 4.163519859313965,
      "learning_rate": 2.4742268041237116e-05,
      "loss": 4.0303,
      "step": 380
    },
    {
      "epoch": 7.8,
      "grad_norm": 2.706822395324707,
      "learning_rate": 2.268041237113402e-05,
      "loss": 4.0643,
      "step": 390
    },
    {
      "epoch": 8.0,
      "grad_norm": 3.3247110843658447,
      "learning_rate": 2.0618556701030927e-05,
      "loss": 3.9944,
      "step": 400
    },
    {
      "epoch": 8.2,
      "grad_norm": 3.692864418029785,
      "learning_rate": 4.676753782668501e-05,
      "loss": 4.0656,
      "step": 410
    },
    {
      "epoch": 8.4,
      "grad_norm": 4.354611873626709,
      "learning_rate": 4.53920220082531e-05,
      "loss": 3.9715,
      "step": 420
    },
    {
      "epoch": 8.6,
      "grad_norm": 5.532437324523926,
      "learning_rate": 4.4016506189821186e-05,
      "loss": 4.0498,
      "step": 430
    },
    {
      "epoch": 8.8,
      "grad_norm": 4.6008758544921875,
      "learning_rate": 4.264099037138927e-05,
      "loss": 4.0479,
      "step": 440
    },
    {
      "epoch": 9.0,
      "grad_norm": 3.6320340633392334,
      "learning_rate": 4.126547455295736e-05,
      "loss": 4.014,
      "step": 450
    },
    {
      "epoch": 9.2,
      "grad_norm": 3.8125405311584473,
      "learning_rate": 3.988995873452545e-05,
      "loss": 4.0399,
      "step": 460
    },
    {
      "epoch": 9.4,
      "grad_norm": 4.067931652069092,
      "learning_rate": 3.8514442916093536e-05,
      "loss": 3.9899,
      "step": 470
    },
    {
      "epoch": 9.6,
      "grad_norm": 4.198885917663574,
      "learning_rate": 3.713892709766162e-05,
      "loss": 4.0051,
      "step": 480
    },
    {
      "epoch": 9.8,
      "grad_norm": 4.0433173179626465,
      "learning_rate": 3.576341127922971e-05,
      "loss": 4.0214,
      "step": 490
    },
    {
      "epoch": 10.0,
      "grad_norm": 3.475057363510132,
      "learning_rate": 3.4387895460797805e-05,
      "loss": 4.0241,
      "step": 500
    },
    {
      "epoch": 10.2,
      "grad_norm": 5.039187431335449,
      "learning_rate": 3.3012379642365886e-05,
      "loss": 3.9914,
      "step": 510
    },
    {
      "epoch": 10.4,
      "grad_norm": 3.2291958332061768,
      "learning_rate": 3.163686382393397e-05,
      "loss": 4.0007,
      "step": 520
    },
    {
      "epoch": 10.6,
      "grad_norm": 4.718263626098633,
      "learning_rate": 3.0261348005502068e-05,
      "loss": 3.99,
      "step": 530
    },
    {
      "epoch": 10.8,
      "grad_norm": 3.466670513153076,
      "learning_rate": 2.8885832187070155e-05,
      "loss": 3.9816,
      "step": 540
    },
    {
      "epoch": 11.0,
      "grad_norm": 4.72723388671875,
      "learning_rate": 2.751031636863824e-05,
      "loss": 4.0284,
      "step": 550
    },
    {
      "epoch": 11.2,
      "grad_norm": 4.0743088722229,
      "learning_rate": 2.613480055020633e-05,
      "loss": 3.9387,
      "step": 560
    },
    {
      "epoch": 11.4,
      "grad_norm": 3.0914433002471924,
      "learning_rate": 2.4759284731774414e-05,
      "loss": 3.9369,
      "step": 570
    },
    {
      "epoch": 11.6,
      "grad_norm": 4.583773136138916,
      "learning_rate": 2.3383768913342505e-05,
      "loss": 4.0302,
      "step": 580
    },
    {
      "epoch": 11.8,
      "grad_norm": 4.720504283905029,
      "learning_rate": 2.2008253094910593e-05,
      "loss": 3.9831,
      "step": 590
    },
    {
      "epoch": 12.0,
      "grad_norm": 5.4584879875183105,
      "learning_rate": 2.063273727647868e-05,
      "loss": 4.0414,
      "step": 600
    },
    {
      "epoch": 12.2,
      "grad_norm": 4.3133015632629395,
      "learning_rate": 1.9257221458046768e-05,
      "loss": 3.9594,
      "step": 610
    },
    {
      "epoch": 12.4,
      "grad_norm": 4.162217617034912,
      "learning_rate": 1.7881705639614855e-05,
      "loss": 3.8796,
      "step": 620
    },
    {
      "epoch": 12.6,
      "grad_norm": 3.863389730453491,
      "learning_rate": 1.6506189821182943e-05,
      "loss": 4.0042,
      "step": 630
    },
    {
      "epoch": 12.8,
      "grad_norm": 4.166849613189697,
      "learning_rate": 1.5130674002751034e-05,
      "loss": 4.0042,
      "step": 640
    },
    {
      "epoch": 13.0,
      "grad_norm": 4.148003101348877,
      "learning_rate": 1.375515818431912e-05,
      "loss": 4.0276,
      "step": 650
    },
    {
      "epoch": 13.2,
      "grad_norm": 4.149908542633057,
      "learning_rate": 1.2379642365887207e-05,
      "loss": 3.9092,
      "step": 660
    },
    {
      "epoch": 13.4,
      "grad_norm": 3.810363292694092,
      "learning_rate": 1.1004126547455296e-05,
      "loss": 3.9163,
      "step": 670
    },
    {
      "epoch": 13.6,
      "grad_norm": 3.7628567218780518,
      "learning_rate": 9.628610729023384e-06,
      "loss": 3.9669,
      "step": 680
    },
    {
      "epoch": 13.8,
      "grad_norm": 4.967076301574707,
      "learning_rate": 8.253094910591471e-06,
      "loss": 4.0309,
      "step": 690
    },
    {
      "epoch": 14.0,
      "grad_norm": 3.6391351222991943,
      "learning_rate": 6.87757909215956e-06,
      "loss": 3.983,
      "step": 700
    },
    {
      "epoch": 14.2,
      "grad_norm": 4.78062105178833,
      "learning_rate": 5.502063273727648e-06,
      "loss": 3.923,
      "step": 710
    },
    {
      "epoch": 14.4,
      "grad_norm": 4.412433624267578,
      "learning_rate": 4.126547455295736e-06,
      "loss": 3.9983,
      "step": 720
    },
    {
      "epoch": 14.6,
      "grad_norm": 3.6161208152770996,
      "learning_rate": 2.751031636863824e-06,
      "loss": 4.0139,
      "step": 730
    },
    {
      "epoch": 14.8,
      "grad_norm": 4.792978286743164,
      "learning_rate": 1.375515818431912e-06,
      "loss": 3.9172,
      "step": 740
    },
    {
      "epoch": 15.0,
      "grad_norm": 3.42587947845459,
      "learning_rate": 0.0,
      "loss": 3.9408,
      "step": 750
    },
    {
      "epoch": 15.0,
      "step": 750,
      "total_flos": 2445756517957632.0,
      "train_loss": 0.26390928649902345,
      "train_runtime": 1983.5688,
      "train_samples_per_second": 9.075,
      "train_steps_per_second": 0.378
    }
  ],
  "logging_steps": 10,
  "max_steps": 750,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2445756517957632.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}