{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9848908785674314,
  "eval_steps": 500,
  "global_step": 55,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.01790710688304421,
      "grad_norm": 9.154049089173217,
      "learning_rate": 0.0,
      "loss": 1.8388,
      "step": 1
    },
    {
      "epoch": 0.03581421376608842,
      "grad_norm": 9.137176514972408,
      "learning_rate": 1.6666666666666667e-06,
      "loss": 1.7621,
      "step": 2
    },
    {
      "epoch": 0.053721320649132626,
      "grad_norm": 8.5343147738079,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 1.7087,
      "step": 3
    },
    {
      "epoch": 0.07162842753217684,
      "grad_norm": 6.3146031385642205,
      "learning_rate": 5e-06,
      "loss": 1.707,
      "step": 4
    },
    {
      "epoch": 0.08953553441522104,
      "grad_norm": 4.390788179209801,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.5855,
      "step": 5
    },
    {
      "epoch": 0.10744264129826525,
      "grad_norm": 4.103715813570343,
      "learning_rate": 8.333333333333334e-06,
      "loss": 1.4669,
      "step": 6
    },
    {
      "epoch": 0.12534974818130945,
      "grad_norm": 4.258081836604545,
      "learning_rate": 1e-05,
      "loss": 1.3811,
      "step": 7
    },
    {
      "epoch": 0.14325685506435368,
      "grad_norm": 4.394719037154525,
      "learning_rate": 9.989726963751683e-06,
      "loss": 1.196,
      "step": 8
    },
    {
      "epoch": 0.16116396194739788,
      "grad_norm": 4.387678851831427,
      "learning_rate": 9.95895006911623e-06,
      "loss": 1.192,
      "step": 9
    },
    {
      "epoch": 0.17907106883044208,
      "grad_norm": 3.266903233723893,
      "learning_rate": 9.907795784955327e-06,
      "loss": 1.1589,
      "step": 10
    },
    {
      "epoch": 0.1969781757134863,
      "grad_norm": 2.9600105157057004,
      "learning_rate": 9.836474315195148e-06,
      "loss": 1.1848,
      "step": 11
    },
    {
      "epoch": 0.2148852825965305,
      "grad_norm": 2.794372521189197,
      "learning_rate": 9.745278735053345e-06,
      "loss": 1.2283,
      "step": 12
    },
    {
      "epoch": 0.2327923894795747,
      "grad_norm": 2.3393492159358313,
      "learning_rate": 9.63458378673011e-06,
      "loss": 1.035,
      "step": 13
    },
    {
      "epoch": 0.2506994963626189,
      "grad_norm": 2.9175786704630813,
      "learning_rate": 9.504844339512096e-06,
      "loss": 1.1845,
      "step": 14
    },
    {
      "epoch": 0.2686066032456631,
      "grad_norm": 2.730923033140476,
      "learning_rate": 9.356593520616948e-06,
      "loss": 1.1604,
      "step": 15
    },
    {
      "epoch": 0.28651371012870736,
      "grad_norm": 2.3983376743034657,
      "learning_rate": 9.190440524459203e-06,
      "loss": 1.0337,
      "step": 16
    },
    {
      "epoch": 0.30442081701175155,
      "grad_norm": 2.2413641873757024,
      "learning_rate": 9.007068109339783e-06,
      "loss": 1.0432,
      "step": 17
    },
    {
      "epoch": 0.32232792389479575,
      "grad_norm": 1.7600228823774702,
      "learning_rate": 8.807229791845673e-06,
      "loss": 1.0112,
      "step": 18
    },
    {
      "epoch": 0.34023503077783995,
      "grad_norm": 2.0117426133601835,
      "learning_rate": 8.591746750488639e-06,
      "loss": 1.1059,
      "step": 19
    },
    {
      "epoch": 0.35814213766088415,
      "grad_norm": 2.060473679270181,
      "learning_rate": 8.361504451306585e-06,
      "loss": 0.9571,
      "step": 20
    },
    {
      "epoch": 0.37604924454392835,
      "grad_norm": 2.0723918915090516,
      "learning_rate": 8.117449009293668e-06,
      "loss": 1.049,
      "step": 21
    },
    {
      "epoch": 0.3939563514269726,
      "grad_norm": 2.0555716704589826,
      "learning_rate": 7.860583300610849e-06,
      "loss": 1.071,
      "step": 22
    },
    {
      "epoch": 0.4118634583100168,
      "grad_norm": 1.901749073039597,
      "learning_rate": 7.591962841552627e-06,
      "loss": 0.993,
      "step": 23
    },
    {
      "epoch": 0.429770565193061,
      "grad_norm": 2.2773682705145792,
      "learning_rate": 7.312691451204178e-06,
      "loss": 1.0638,
      "step": 24
    },
    {
      "epoch": 0.4476776720761052,
      "grad_norm": 1.8553489638041873,
      "learning_rate": 7.023916715611969e-06,
      "loss": 1.0701,
      "step": 25
    },
    {
      "epoch": 0.4655847789591494,
      "grad_norm": 1.8296309651772127,
      "learning_rate": 6.726825272106539e-06,
      "loss": 1.0457,
      "step": 26
    },
    {
      "epoch": 0.4834918858421936,
      "grad_norm": 1.951377844511212,
      "learning_rate": 6.4226379331551625e-06,
      "loss": 0.979,
      "step": 27
    },
    {
      "epoch": 0.5013989927252378,
      "grad_norm": 2.131073321825185,
      "learning_rate": 6.112604669781572e-06,
      "loss": 1.0516,
      "step": 28
    },
    {
      "epoch": 0.519306099608282,
      "grad_norm": 1.9236940939367049,
      "learning_rate": 5.797999475166897e-06,
      "loss": 0.9174,
      "step": 29
    },
    {
      "epoch": 0.5372132064913262,
      "grad_norm": 1.8594780822897603,
      "learning_rate": 5.480115129538409e-06,
      "loss": 1.0256,
      "step": 30
    },
    {
      "epoch": 0.5551203133743704,
      "grad_norm": 1.9789880146462748,
      "learning_rate": 5.160257887858278e-06,
      "loss": 1.0618,
      "step": 31
    },
    {
      "epoch": 0.5730274202574147,
      "grad_norm": 1.7424889796134264,
      "learning_rate": 4.839742112141725e-06,
      "loss": 0.947,
      "step": 32
    },
    {
      "epoch": 0.5909345271404589,
      "grad_norm": 1.5718805251413062,
      "learning_rate": 4.5198848704615915e-06,
      "loss": 0.9008,
      "step": 33
    },
    {
      "epoch": 0.6088416340235031,
      "grad_norm": 1.8168721829454335,
      "learning_rate": 4.2020005248331056e-06,
      "loss": 1.0493,
      "step": 34
    },
    {
      "epoch": 0.6267487409065473,
      "grad_norm": 1.5926497298103737,
      "learning_rate": 3.887395330218429e-06,
      "loss": 0.9912,
      "step": 35
    },
    {
      "epoch": 0.6446558477895915,
      "grad_norm": 1.6787356670246831,
      "learning_rate": 3.5773620668448384e-06,
      "loss": 0.9277,
      "step": 36
    },
    {
      "epoch": 0.6625629546726357,
      "grad_norm": 1.7504857895226833,
      "learning_rate": 3.273174727893463e-06,
      "loss": 0.9374,
      "step": 37
    },
    {
      "epoch": 0.6804700615556799,
      "grad_norm": 1.8855358371917814,
      "learning_rate": 2.976083284388031e-06,
      "loss": 1.0638,
      "step": 38
    },
    {
      "epoch": 0.6983771684387241,
      "grad_norm": 2.079981422104126,
      "learning_rate": 2.687308548795825e-06,
      "loss": 1.0418,
      "step": 39
    },
    {
      "epoch": 0.7162842753217683,
      "grad_norm": 1.825444504742724,
      "learning_rate": 2.408037158447375e-06,
      "loss": 0.9922,
      "step": 40
    },
    {
      "epoch": 0.7341913822048125,
      "grad_norm": 1.5244894733584424,
      "learning_rate": 2.139416699389153e-06,
      "loss": 0.8983,
      "step": 41
    },
    {
      "epoch": 0.7520984890878567,
      "grad_norm": 1.5240784478870684,
      "learning_rate": 1.8825509907063328e-06,
      "loss": 0.9511,
      "step": 42
    },
    {
      "epoch": 0.7700055959709009,
      "grad_norm": 1.7893289750375283,
      "learning_rate": 1.6384955486934157e-06,
      "loss": 1.0381,
      "step": 43
    },
    {
      "epoch": 0.7879127028539452,
      "grad_norm": 1.6071325493161637,
      "learning_rate": 1.4082532495113627e-06,
      "loss": 0.9741,
      "step": 44
    },
    {
      "epoch": 0.8058198097369894,
      "grad_norm": 1.5427190294804947,
      "learning_rate": 1.1927702081543279e-06,
      "loss": 0.8816,
      "step": 45
    },
    {
      "epoch": 0.8237269166200336,
      "grad_norm": 1.6398520351491825,
      "learning_rate": 9.929318906602176e-07,
      "loss": 0.9024,
      "step": 46
    },
    {
      "epoch": 0.8416340235030778,
      "grad_norm": 1.7080546088158608,
      "learning_rate": 8.095594755407971e-07,
      "loss": 1.0991,
      "step": 47
    },
    {
      "epoch": 0.859541130386122,
      "grad_norm": 1.676808577271218,
      "learning_rate": 6.43406479383053e-07,
      "loss": 1.0762,
      "step": 48
    },
    {
      "epoch": 0.8774482372691662,
      "grad_norm": 1.7910684633127532,
      "learning_rate": 4.951556604879049e-07,
      "loss": 1.0304,
      "step": 49
    },
    {
      "epoch": 0.8953553441522104,
      "grad_norm": 1.6360492284728316,
      "learning_rate": 3.6541621326989183e-07,
      "loss": 0.9294,
      "step": 50
    },
    {
      "epoch": 0.9132624510352546,
      "grad_norm": 1.4569649164177891,
      "learning_rate": 2.547212649466568e-07,
      "loss": 0.9019,
      "step": 51
    },
    {
      "epoch": 0.9311695579182988,
      "grad_norm": 1.6323528961043134,
      "learning_rate": 1.6352568480485277e-07,
      "loss": 0.963,
      "step": 52
    },
    {
      "epoch": 0.949076664801343,
      "grad_norm": 1.6005257490464857,
      "learning_rate": 9.22042150446728e-08,
      "loss": 0.8996,
      "step": 53
    },
    {
      "epoch": 0.9669837716843872,
      "grad_norm": 1.5664108489842672,
      "learning_rate": 4.104993088376974e-08,
      "loss": 0.9621,
      "step": 54
    },
    {
      "epoch": 0.9848908785674314,
      "grad_norm": 1.4809268609667965,
      "learning_rate": 1.0273036248318325e-08,
      "loss": 0.9323,
      "step": 55
    },
    {
      "epoch": 0.9848908785674314,
      "step": 55,
      "total_flos": 6936212070400.0,
      "train_loss": 1.1010965683243492,
      "train_runtime": 842.7134,
      "train_samples_per_second": 2.121,
      "train_steps_per_second": 0.065
    }
  ],
  "logging_steps": 1,
  "max_steps": 55,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6936212070400.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}