{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.45,
  "eval_steps": 100,
  "global_step": 900,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0125,
      "grad_norm": 0.14176353812217712,
      "learning_rate": 0.0004,
      "loss": 1.1525,
      "step": 25
    },
    {
      "epoch": 0.025,
      "grad_norm": 0.1460508555173874,
      "learning_rate": 0.0004998852503731983,
      "loss": 1.047,
      "step": 50
    },
    {
      "epoch": 0.0375,
      "grad_norm": 0.2368021011352539,
      "learning_rate": 0.0004993848168027977,
      "loss": 0.8529,
      "step": 75
    },
    {
      "epoch": 0.05,
      "grad_norm": 0.14488168060779572,
      "learning_rate": 0.0004984880506341147,
      "loss": 0.9756,
      "step": 100
    },
    {
      "epoch": 0.05,
      "eval_loss": 0.9470569491386414,
      "eval_runtime": 845.9115,
      "eval_samples_per_second": 1.297,
      "eval_steps_per_second": 0.021,
      "step": 100
    },
    {
      "epoch": 0.0625,
      "grad_norm": 0.1415175348520279,
      "learning_rate": 0.0004971963770447935,
      "loss": 0.9564,
      "step": 125
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.1751064509153366,
      "learning_rate": 0.0004955118488155782,
      "loss": 0.711,
      "step": 150
    },
    {
      "epoch": 0.0875,
      "grad_norm": 0.1439943015575409,
      "learning_rate": 0.0004934371430679492,
      "loss": 0.9409,
      "step": 175
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.15947112441062927,
      "learning_rate": 0.0004909755570095319,
      "loss": 0.8979,
      "step": 200
    },
    {
      "epoch": 0.1,
      "eval_loss": 0.9711233973503113,
      "eval_runtime": 845.6433,
      "eval_samples_per_second": 1.297,
      "eval_steps_per_second": 0.021,
      "step": 200
    },
    {
      "epoch": 0.1125,
      "grad_norm": 0.14685837924480438,
      "learning_rate": 0.0004881310026940389,
      "loss": 0.6376,
      "step": 225
    },
    {
      "epoch": 0.125,
      "grad_norm": 0.15040776133537292,
      "learning_rate": 0.0004849080008040734,
      "loss": 0.927,
      "step": 250
    },
    {
      "epoch": 0.1375,
      "grad_norm": 0.16087745130062103,
      "learning_rate": 0.00048131167346667446,
      "loss": 0.8456,
      "step": 275
    },
    {
      "epoch": 0.15,
      "grad_norm": 0.15025638043880463,
      "learning_rate": 0.00047734773611302284,
      "loss": 0.6029,
      "step": 300
    },
    {
      "epoch": 0.15,
      "eval_loss": 1.0056413412094116,
      "eval_runtime": 848.447,
      "eval_samples_per_second": 1.293,
      "eval_steps_per_second": 0.021,
      "step": 300
    },
    {
      "epoch": 0.1625,
      "grad_norm": 0.15893957018852234,
      "learning_rate": 0.0004730224883952422,
      "loss": 0.9036,
      "step": 325
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.1535714715719223,
      "learning_rate": 0.0004683428041747334,
      "loss": 0.828,
      "step": 350
    },
    {
      "epoch": 0.1875,
      "grad_norm": 0.1718970686197281,
      "learning_rate": 0.0004633161205979517,
      "loss": 0.5944,
      "step": 375
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.17664535343647003,
      "learning_rate": 0.0004579504262769877,
      "loss": 0.8654,
      "step": 400
    },
    {
      "epoch": 0.2,
      "eval_loss": 1.0151112079620361,
      "eval_runtime": 839.7482,
      "eval_samples_per_second": 1.306,
      "eval_steps_per_second": 0.021,
      "step": 400
    },
    {
      "epoch": 0.2125,
      "grad_norm": 0.17122088372707367,
      "learning_rate": 0.0004522542485937369,
      "loss": 0.8078,
      "step": 425
    },
    {
      "epoch": 0.225,
      "grad_norm": 0.19420970976352692,
      "learning_rate": 0.00044623664014783386,
      "loss": 0.5735,
      "step": 450
    },
    {
      "epoch": 0.2375,
      "grad_norm": 0.18166953325271606,
      "learning_rate": 0.00043990716436988924,
      "loss": 0.8604,
      "step": 475
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.1502382755279541,
      "learning_rate": 0.0004332758803228925,
      "loss": 0.7673,
      "step": 500
    },
    {
      "epoch": 0.25,
      "eval_loss": 1.0454745292663574,
      "eval_runtime": 841.3951,
      "eval_samples_per_second": 1.304,
      "eval_steps_per_second": 0.021,
      "step": 500
    },
    {
      "epoch": 0.2625,
      "grad_norm": 0.16875839233398438,
      "learning_rate": 0.00042635332671593575,
      "loss": 0.5882,
      "step": 525
    },
    {
      "epoch": 0.275,
      "grad_norm": 0.16070039570331573,
      "learning_rate": 0.00041915050515566445,
      "loss": 0.8175,
      "step": 550
    },
    {
      "epoch": 0.2875,
      "grad_norm": 0.16584184765815735,
      "learning_rate": 0.00041167886266207167,
      "loss": 0.7795,
      "step": 575
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.15345798432826996,
      "learning_rate": 0.0004039502734764241,
      "loss": 0.7331,
      "step": 600
    },
    {
      "epoch": 0.3,
      "eval_loss": 1.0627943277359009,
      "eval_runtime": 849.4944,
      "eval_samples_per_second": 1.291,
      "eval_steps_per_second": 0.021,
      "step": 600
    },
    {
      "epoch": 0.3125,
      "grad_norm": 0.16241031885147095,
      "learning_rate": 0.0003959770201902294,
      "loss": 0.7436,
      "step": 625
    },
    {
      "epoch": 0.325,
      "grad_norm": 0.1531112939119339,
      "learning_rate": 0.0003877717742252371,
      "loss": 0.6345,
      "step": 650
    },
    {
      "epoch": 0.3375,
      "grad_norm": 0.15790140628814697,
      "learning_rate": 0.00037934757569549495,
      "loss": 0.7351,
      "step": 675
    },
    {
      "epoch": 0.35,
      "grad_norm": 0.1822807490825653,
      "learning_rate": 0.00037071781268346345,
      "loss": 0.745,
      "step": 700
    },
    {
      "epoch": 0.35,
      "eval_loss": 1.07315993309021,
      "eval_runtime": 837.5276,
      "eval_samples_per_second": 1.31,
      "eval_steps_per_second": 0.021,
      "step": 700
    },
    {
      "epoch": 0.3625,
      "grad_norm": 0.15983282029628754,
      "learning_rate": 0.00036189619996312495,
      "loss": 0.5972,
      "step": 725
    },
    {
      "epoch": 0.375,
      "grad_norm": 0.18202389776706696,
      "learning_rate": 0.00035289675720390174,
      "loss": 0.759,
      "step": 750
    },
    {
      "epoch": 0.3875,
      "grad_norm": 0.16057106852531433,
      "learning_rate": 0.00034373378669002105,
      "loss": 0.7358,
      "step": 775
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.1680625081062317,
      "learning_rate": 0.00033442185059073706,
      "loss": 0.5636,
      "step": 800
    },
    {
      "epoch": 0.4,
      "eval_loss": 1.0932456254959106,
      "eval_runtime": 840.1331,
      "eval_samples_per_second": 1.306,
      "eval_steps_per_second": 0.021,
      "step": 800
    },
    {
      "epoch": 0.4125,
      "grad_norm": 0.15613198280334473,
      "learning_rate": 0.00032497574781753367,
      "loss": 0.7596,
      "step": 825
    },
    {
      "epoch": 0.425,
      "grad_norm": 0.1628854125738144,
      "learning_rate": 0.000315410490505086,
      "loss": 0.7282,
      "step": 850
    },
    {
      "epoch": 0.4375,
      "grad_norm": 0.16740979254245758,
      "learning_rate": 0.0003057412801533589,
      "loss": 0.5325,
      "step": 875
    },
    {
      "epoch": 0.45,
      "grad_norm": 0.1634828895330429,
      "learning_rate": 0.0002959834834687587,
      "loss": 0.778,
      "step": 900
    },
    {
      "epoch": 0.45,
      "eval_loss": 1.0952215194702148,
      "eval_runtime": 836.473,
      "eval_samples_per_second": 1.311,
      "eval_steps_per_second": 0.022,
      "step": 900
    }
  ],
  "logging_steps": 25,
  "max_steps": 2000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 9.07138389025751e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}