{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.35727045373347627,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.007145409074669525,
      "grad_norm": 4.4086809158325195,
      "learning_rate": 2.3809523809523808e-06,
      "loss": 1.0969,
      "step": 10
    },
    {
      "epoch": 0.01429081814933905,
      "grad_norm": 5.687011241912842,
      "learning_rate": 4.7619047619047615e-06,
      "loss": 1.0795,
      "step": 20
    },
    {
      "epoch": 0.021436227224008574,
      "grad_norm": 1.976590633392334,
      "learning_rate": 7.142857142857143e-06,
      "loss": 0.7536,
      "step": 30
    },
    {
      "epoch": 0.0285816362986781,
      "grad_norm": 3.1355409622192383,
      "learning_rate": 9.523809523809523e-06,
      "loss": 0.5564,
      "step": 40
    },
    {
      "epoch": 0.03572704537334762,
      "grad_norm": 2.6710309982299805,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 0.623,
      "step": 50
    },
    {
      "epoch": 0.04287245444801715,
      "grad_norm": 2.8567938804626465,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 0.5322,
      "step": 60
    },
    {
      "epoch": 0.050017863522686674,
      "grad_norm": 3.4388861656188965,
      "learning_rate": 1.6666666666666667e-05,
      "loss": 0.5102,
      "step": 70
    },
    {
      "epoch": 0.0571632725973562,
      "grad_norm": 3.093275308609009,
      "learning_rate": 1.9047619047619046e-05,
      "loss": 0.568,
      "step": 80
    },
    {
      "epoch": 0.06430868167202572,
      "grad_norm": 2.3798677921295166,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 0.4883,
      "step": 90
    },
    {
      "epoch": 0.07145409074669525,
      "grad_norm": 2.846259117126465,
      "learning_rate": 2.380952380952381e-05,
      "loss": 0.417,
      "step": 100
    },
    {
      "epoch": 0.07145409074669525,
      "eval_news_finetune_val_loss": 0.48679304122924805,
      "eval_news_finetune_val_runtime": 1001.9158,
      "eval_news_finetune_val_samples_per_second": 1.397,
      "eval_news_finetune_val_steps_per_second": 1.397,
      "step": 100
    },
    {
      "epoch": 0.07859949982136477,
      "grad_norm": 1.9387887716293335,
      "learning_rate": 2.6190476190476192e-05,
      "loss": 0.4595,
      "step": 110
    },
    {
      "epoch": 0.0857449088960343,
      "grad_norm": 2.3232853412628174,
      "learning_rate": 2.857142857142857e-05,
      "loss": 0.4658,
      "step": 120
    },
    {
      "epoch": 0.09289031797070382,
      "grad_norm": 2.813093423843384,
      "learning_rate": 3.095238095238095e-05,
      "loss": 0.4122,
      "step": 130
    },
    {
      "epoch": 0.10003572704537335,
      "grad_norm": 1.9588465690612793,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 0.4878,
      "step": 140
    },
    {
      "epoch": 0.10718113612004287,
      "grad_norm": 1.4838117361068726,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.4168,
      "step": 150
    },
    {
      "epoch": 0.1143265451947124,
      "grad_norm": 3.020738124847412,
      "learning_rate": 3.809523809523809e-05,
      "loss": 0.4298,
      "step": 160
    },
    {
      "epoch": 0.12147195426938193,
      "grad_norm": 2.097656011581421,
      "learning_rate": 4.047619047619048e-05,
      "loss": 0.4413,
      "step": 170
    },
    {
      "epoch": 0.12861736334405144,
      "grad_norm": 1.6332950592041016,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 0.3734,
      "step": 180
    },
    {
      "epoch": 0.13576277241872098,
      "grad_norm": 2.1570417881011963,
      "learning_rate": 4.523809523809524e-05,
      "loss": 0.4015,
      "step": 190
    },
    {
      "epoch": 0.1429081814933905,
      "grad_norm": 1.6941479444503784,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.4411,
      "step": 200
    },
    {
      "epoch": 0.1429081814933905,
      "eval_news_finetune_val_loss": 0.4338369369506836,
      "eval_news_finetune_val_runtime": 1002.1695,
      "eval_news_finetune_val_samples_per_second": 1.397,
      "eval_news_finetune_val_steps_per_second": 1.397,
      "step": 200
    },
    {
      "epoch": 0.15005359056806003,
      "grad_norm": 2.3582301139831543,
      "learning_rate": 5e-05,
      "loss": 0.3697,
      "step": 210
    },
    {
      "epoch": 0.15719899964272954,
      "grad_norm": 2.0517632961273193,
      "learning_rate": 5.2380952380952384e-05,
      "loss": 0.4076,
      "step": 220
    },
    {
      "epoch": 0.16434440871739908,
      "grad_norm": 1.3338748216629028,
      "learning_rate": 5.4761904761904766e-05,
      "loss": 0.3307,
      "step": 230
    },
    {
      "epoch": 0.1714898177920686,
      "grad_norm": 3.0515363216400146,
      "learning_rate": 5.714285714285714e-05,
      "loss": 0.4227,
      "step": 240
    },
    {
      "epoch": 0.17863522686673813,
      "grad_norm": 2.4899113178253174,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 0.4689,
      "step": 250
    },
    {
      "epoch": 0.18578063594140765,
      "grad_norm": 1.6197255849838257,
      "learning_rate": 6.19047619047619e-05,
      "loss": 0.3618,
      "step": 260
    },
    {
      "epoch": 0.19292604501607716,
      "grad_norm": 1.654628872871399,
      "learning_rate": 6.428571428571429e-05,
      "loss": 0.4668,
      "step": 270
    },
    {
      "epoch": 0.2000714540907467,
      "grad_norm": 1.6470831632614136,
      "learning_rate": 6.666666666666667e-05,
      "loss": 0.3525,
      "step": 280
    },
    {
      "epoch": 0.2072168631654162,
      "grad_norm": 2.640536308288574,
      "learning_rate": 6.904761904761905e-05,
      "loss": 0.3707,
      "step": 290
    },
    {
      "epoch": 0.21436227224008575,
      "grad_norm": 2.3426971435546875,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.4461,
      "step": 300
    },
    {
      "epoch": 0.21436227224008575,
      "eval_news_finetune_val_loss": 0.40391305088996887,
      "eval_news_finetune_val_runtime": 1002.5797,
      "eval_news_finetune_val_samples_per_second": 1.396,
      "eval_news_finetune_val_steps_per_second": 1.396,
      "step": 300
    },
    {
      "epoch": 0.22150768131475526,
      "grad_norm": 1.0351321697235107,
      "learning_rate": 7.380952380952382e-05,
      "loss": 0.3439,
      "step": 310
    },
    {
      "epoch": 0.2286530903894248,
      "grad_norm": 3.062483549118042,
      "learning_rate": 7.619047619047618e-05,
      "loss": 0.4492,
      "step": 320
    },
    {
      "epoch": 0.2357984994640943,
      "grad_norm": 2.095825672149658,
      "learning_rate": 7.857142857142858e-05,
      "loss": 0.3399,
      "step": 330
    },
    {
      "epoch": 0.24294390853876385,
      "grad_norm": 1.700642704963684,
      "learning_rate": 8.095238095238096e-05,
      "loss": 0.4336,
      "step": 340
    },
    {
      "epoch": 0.2500893176134334,
      "grad_norm": 1.6802127361297607,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.3628,
      "step": 350
    },
    {
      "epoch": 0.2572347266881029,
      "grad_norm": 1.1725817918777466,
      "learning_rate": 8.571428571428571e-05,
      "loss": 0.4113,
      "step": 360
    },
    {
      "epoch": 0.2643801357627724,
      "grad_norm": 1.0182325839996338,
      "learning_rate": 8.80952380952381e-05,
      "loss": 0.4009,
      "step": 370
    },
    {
      "epoch": 0.27152554483744196,
      "grad_norm": 2.5762252807617188,
      "learning_rate": 9.047619047619048e-05,
      "loss": 0.3399,
      "step": 380
    },
    {
      "epoch": 0.27867095391211144,
      "grad_norm": 1.5393809080123901,
      "learning_rate": 9.285714285714286e-05,
      "loss": 0.326,
      "step": 390
    },
    {
      "epoch": 0.285816362986781,
      "grad_norm": 2.3259921073913574,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.4228,
      "step": 400
    },
    {
      "epoch": 0.285816362986781,
      "eval_news_finetune_val_loss": 0.39322975277900696,
      "eval_news_finetune_val_runtime": 1002.8865,
      "eval_news_finetune_val_samples_per_second": 1.396,
      "eval_news_finetune_val_steps_per_second": 1.396,
      "step": 400
    },
    {
      "epoch": 0.2929617720614505,
      "grad_norm": 0.9278184771537781,
      "learning_rate": 9.761904761904762e-05,
      "loss": 0.3184,
      "step": 410
    },
    {
      "epoch": 0.30010718113612006,
      "grad_norm": 1.4571782350540161,
      "learning_rate": 0.0001,
      "loss": 0.473,
      "step": 420
    },
    {
      "epoch": 0.30725259021078954,
      "grad_norm": 1.6199829578399658,
      "learning_rate": 9.99982704095424e-05,
      "loss": 0.392,
      "step": 430
    },
    {
      "epoch": 0.3143979992854591,
      "grad_norm": 1.302309513092041,
      "learning_rate": 9.999308175782893e-05,
      "loss": 0.3824,
      "step": 440
    },
    {
      "epoch": 0.3215434083601286,
      "grad_norm": 1.438289761543274,
      "learning_rate": 9.998443440382927e-05,
      "loss": 0.4001,
      "step": 450
    },
    {
      "epoch": 0.32868881743479816,
      "grad_norm": 1.7557189464569092,
      "learning_rate": 9.997232894579868e-05,
      "loss": 0.4144,
      "step": 460
    },
    {
      "epoch": 0.33583422650946765,
      "grad_norm": 0.9362027645111084,
      "learning_rate": 9.995676622123655e-05,
      "loss": 0.3094,
      "step": 470
    },
    {
      "epoch": 0.3429796355841372,
      "grad_norm": 1.7850221395492554,
      "learning_rate": 9.993774730682845e-05,
      "loss": 0.2966,
      "step": 480
    },
    {
      "epoch": 0.35012504465880673,
      "grad_norm": 1.705842137336731,
      "learning_rate": 9.991527351837174e-05,
      "loss": 0.3274,
      "step": 490
    },
    {
      "epoch": 0.35727045373347627,
      "grad_norm": 1.0722746849060059,
      "learning_rate": 9.988934641068436e-05,
      "loss": 0.4301,
      "step": 500
    },
    {
      "epoch": 0.35727045373347627,
      "eval_news_finetune_val_loss": 0.3787713646888733,
      "eval_news_finetune_val_runtime": 1002.8588,
      "eval_news_finetune_val_samples_per_second": 1.396,
      "eval_news_finetune_val_steps_per_second": 1.396,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 4197,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.392907957026816e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}