{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 31,
  "global_step": 63,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.047619047619047616,
      "grad_norm": 1.5399912595748901,
      "learning_rate": 0.0,
      "loss": 3.283,
      "step": 1
    },
    {
      "epoch": 0.09523809523809523,
      "grad_norm": 1.501554012298584,
      "learning_rate": 7.142857142857143e-06,
      "loss": 3.2754,
      "step": 2
    },
    {
      "epoch": 0.14285714285714285,
      "grad_norm": 1.505775809288025,
      "learning_rate": 1.4285714285714285e-05,
      "loss": 3.3013,
      "step": 3
    },
    {
      "epoch": 0.19047619047619047,
      "grad_norm": 1.4625844955444336,
      "learning_rate": 2.1428571428571428e-05,
      "loss": 3.3042,
      "step": 4
    },
    {
      "epoch": 0.23809523809523808,
      "grad_norm": 1.4471248388290405,
      "learning_rate": 2.857142857142857e-05,
      "loss": 3.3036,
      "step": 5
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 1.4996780157089233,
      "learning_rate": 3.571428571428572e-05,
      "loss": 3.2652,
      "step": 6
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 1.4408137798309326,
      "learning_rate": 4.2857142857142856e-05,
      "loss": 3.2442,
      "step": 7
    },
    {
      "epoch": 0.38095238095238093,
      "grad_norm": 1.433519959449768,
      "learning_rate": 5e-05,
      "loss": 3.1897,
      "step": 8
    },
    {
      "epoch": 0.42857142857142855,
      "grad_norm": 1.3208502531051636,
      "learning_rate": 4.984437719485776e-05,
      "loss": 3.178,
      "step": 9
    },
    {
      "epoch": 0.47619047619047616,
      "grad_norm": 1.1709543466567993,
      "learning_rate": 4.937946582650013e-05,
      "loss": 3.068,
      "step": 10
    },
    {
      "epoch": 0.5238095238095238,
      "grad_norm": 1.0242472887039185,
      "learning_rate": 4.8611112425132096e-05,
      "loss": 3.0394,
      "step": 11
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.8732519745826721,
      "learning_rate": 4.754897948058487e-05,
      "loss": 2.9598,
      "step": 12
    },
    {
      "epoch": 0.6190476190476191,
      "grad_norm": 0.7084696888923645,
      "learning_rate": 4.620642393090003e-05,
      "loss": 2.9303,
      "step": 13
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.5961148142814636,
      "learning_rate": 4.460032919108375e-05,
      "loss": 2.8822,
      "step": 14
    },
    {
      "epoch": 0.7142857142857143,
      "grad_norm": 0.4741389751434326,
      "learning_rate": 4.275089283436705e-05,
      "loss": 2.8885,
      "step": 15
    },
    {
      "epoch": 0.7619047619047619,
      "grad_norm": 0.39935019612312317,
      "learning_rate": 4.068137259600366e-05,
      "loss": 2.8291,
      "step": 16
    },
    {
      "epoch": 0.8095238095238095,
      "grad_norm": 0.3459135890007019,
      "learning_rate": 3.8417793893754584e-05,
      "loss": 2.8699,
      "step": 17
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.31277233362197876,
      "learning_rate": 3.598862254315956e-05,
      "loss": 2.8439,
      "step": 18
    },
    {
      "epoch": 0.9047619047619048,
      "grad_norm": 0.2821517884731293,
      "learning_rate": 3.342440678339039e-05,
      "loss": 2.8943,
      "step": 19
    },
    {
      "epoch": 0.9523809523809523,
      "grad_norm": 0.2536486089229584,
      "learning_rate": 3.075739311541878e-05,
      "loss": 2.7845,
      "step": 20
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.2532535493373871,
      "learning_rate": 2.802112078355687e-05,
      "loss": 2.8393,
      "step": 21
    },
    {
      "epoch": 1.0476190476190477,
      "grad_norm": 0.23882344365119934,
      "learning_rate": 2.525e-05,
      "loss": 2.8088,
      "step": 22
    },
    {
      "epoch": 1.0952380952380953,
      "grad_norm": 0.2156551629304886,
      "learning_rate": 2.2478879216443134e-05,
      "loss": 2.8162,
      "step": 23
    },
    {
      "epoch": 1.1428571428571428,
      "grad_norm": 0.21983318030834198,
      "learning_rate": 1.9742606884581223e-05,
      "loss": 2.8142,
      "step": 24
    },
    {
      "epoch": 1.1904761904761905,
      "grad_norm": 0.20587244629859924,
      "learning_rate": 1.7075593216609622e-05,
      "loss": 2.8216,
      "step": 25
    },
    {
      "epoch": 1.2380952380952381,
      "grad_norm": 0.2053506225347519,
      "learning_rate": 1.4511377456840439e-05,
      "loss": 2.7767,
      "step": 26
    },
    {
      "epoch": 1.2857142857142856,
      "grad_norm": 0.2322610467672348,
      "learning_rate": 1.2082206106245424e-05,
      "loss": 2.8262,
      "step": 27
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.19792939722537994,
      "learning_rate": 9.818627403996347e-06,
      "loss": 2.7816,
      "step": 28
    },
    {
      "epoch": 1.380952380952381,
      "grad_norm": 0.19465278089046478,
      "learning_rate": 7.749107165632952e-06,
      "loss": 2.7915,
      "step": 29
    },
    {
      "epoch": 1.4285714285714286,
      "grad_norm": 0.18391038477420807,
      "learning_rate": 5.899670808916262e-06,
      "loss": 2.7661,
      "step": 30
    },
    {
      "epoch": 1.4761904761904763,
      "grad_norm": 0.19500090181827545,
      "learning_rate": 4.293576069099968e-06,
      "loss": 2.8283,
      "step": 31
    },
    {
      "epoch": 1.5238095238095237,
      "grad_norm": 0.19424214959144592,
      "learning_rate": 2.951020519415129e-06,
      "loss": 2.8423,
      "step": 32
    },
    {
      "epoch": 1.5238095238095237,
      "eval_loss": 2.850144147872925,
      "eval_runtime": 6.3675,
      "eval_samples_per_second": 5.811,
      "eval_steps_per_second": 0.471,
      "step": 32
    },
    {
      "checkpoint_runtime": 60.4302
    },
    {
      "epoch": 1.5714285714285714,
      "grad_norm": 0.18892130255699158,
      "learning_rate": 1.8888875748679026e-06,
      "loss": 2.8371,
      "step": 33
    },
    {
      "epoch": 1.619047619047619,
      "grad_norm": 0.1852538287639618,
      "learning_rate": 1.1205341734998656e-06,
      "loss": 2.8181,
      "step": 34
    },
    {
      "epoch": 1.6666666666666665,
      "grad_norm": 0.18096202611923218,
      "learning_rate": 6.556228051422456e-07,
      "loss": 2.8143,
      "step": 35
    },
    {
      "epoch": 1.7142857142857144,
      "grad_norm": 0.19442056119441986,
      "learning_rate": 5.000000000000001e-07,
      "loss": 2.8414,
      "step": 36
    },
    {
      "epoch": 1.7619047619047619,
      "grad_norm": 0.18372127413749695,
      "learning_rate": 6.556228051422483e-07,
      "loss": 2.7839,
      "step": 37
    },
    {
      "epoch": 1.8095238095238095,
      "grad_norm": 0.1797795295715332,
      "learning_rate": 1.1205341734998656e-06,
      "loss": 2.7905,
      "step": 38
    },
    {
      "epoch": 1.8571428571428572,
      "grad_norm": 0.19863928854465485,
      "learning_rate": 1.8888875748679026e-06,
      "loss": 2.8218,
      "step": 39
    },
    {
      "epoch": 1.9047619047619047,
      "grad_norm": 0.18803931772708893,
      "learning_rate": 2.9510205194151264e-06,
      "loss": 2.8117,
      "step": 40
    },
    {
      "epoch": 1.9523809523809523,
      "grad_norm": 0.18814833462238312,
      "learning_rate": 4.293576069099965e-06,
      "loss": 2.8187,
      "step": 41
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.2702404260635376,
      "learning_rate": 5.899670808916255e-06,
      "loss": 2.8326,
      "step": 42
    },
    {
      "epoch": 2.0476190476190474,
      "grad_norm": 0.1897124946117401,
      "learning_rate": 7.749107165632947e-06,
      "loss": 2.8443,
      "step": 43
    },
    {
      "epoch": 2.0952380952380953,
      "grad_norm": 0.1819615513086319,
      "learning_rate": 9.818627403996342e-06,
      "loss": 2.7819,
      "step": 44
    },
    {
      "epoch": 2.142857142857143,
      "grad_norm": 0.1982765793800354,
      "learning_rate": 1.2082206106245419e-05,
      "loss": 2.8554,
      "step": 45
    },
    {
      "epoch": 2.1904761904761907,
      "grad_norm": 0.1766144186258316,
      "learning_rate": 1.4511377456840434e-05,
      "loss": 2.8522,
      "step": 46
    },
    {
      "epoch": 2.238095238095238,
      "grad_norm": 0.20227931439876556,
      "learning_rate": 1.7075593216609612e-05,
      "loss": 2.812,
      "step": 47
    },
    {
      "epoch": 2.2857142857142856,
      "grad_norm": 0.17198063433170319,
      "learning_rate": 1.9742606884581216e-05,
      "loss": 2.7706,
      "step": 48
    },
    {
      "epoch": 2.3333333333333335,
      "grad_norm": 0.16705217957496643,
      "learning_rate": 2.2478879216443127e-05,
      "loss": 2.8095,
      "step": 49
    },
    {
      "epoch": 2.380952380952381,
      "grad_norm": 0.16677793860435486,
      "learning_rate": 2.5249999999999997e-05,
      "loss": 2.7997,
      "step": 50
    },
    {
      "epoch": 2.4285714285714284,
      "grad_norm": 0.15633974969387054,
      "learning_rate": 2.8021120783556864e-05,
      "loss": 2.8168,
      "step": 51
    },
    {
      "epoch": 2.4761904761904763,
      "grad_norm": 0.15532703697681427,
      "learning_rate": 3.075739311541878e-05,
      "loss": 2.8387,
      "step": 52
    },
    {
      "epoch": 2.5238095238095237,
      "grad_norm": 0.14325609803199768,
      "learning_rate": 3.3424406783390376e-05,
      "loss": 2.7807,
      "step": 53
    },
    {
      "epoch": 2.571428571428571,
      "grad_norm": 0.14080756902694702,
      "learning_rate": 3.598862254315956e-05,
      "loss": 2.8254,
      "step": 54
    },
    {
      "epoch": 2.619047619047619,
      "grad_norm": 0.14736731350421906,
      "learning_rate": 3.841779389375458e-05,
      "loss": 2.7002,
      "step": 55
    },
    {
      "epoch": 2.6666666666666665,
      "grad_norm": 0.12847484648227692,
      "learning_rate": 4.068137259600365e-05,
      "loss": 2.7459,
      "step": 56
    },
    {
      "epoch": 2.7142857142857144,
      "grad_norm": 0.1619555950164795,
      "learning_rate": 4.275089283436705e-05,
      "loss": 2.7976,
      "step": 57
    },
    {
      "epoch": 2.761904761904762,
      "grad_norm": 0.120057113468647,
      "learning_rate": 4.460032919108374e-05,
      "loss": 2.7034,
      "step": 58
    },
    {
      "epoch": 2.8095238095238093,
      "grad_norm": 0.11708179116249084,
      "learning_rate": 4.620642393090003e-05,
      "loss": 2.7266,
      "step": 59
    },
    {
      "epoch": 2.857142857142857,
      "grad_norm": 0.11324940621852875,
      "learning_rate": 4.754897948058487e-05,
      "loss": 2.7771,
      "step": 60
    },
    {
      "epoch": 2.9047619047619047,
      "grad_norm": 0.11083745956420898,
      "learning_rate": 4.8611112425132096e-05,
      "loss": 2.7414,
      "step": 61
    },
    {
      "epoch": 2.9523809523809526,
      "grad_norm": 0.10697492212057114,
      "learning_rate": 4.937946582650013e-05,
      "loss": 2.788,
      "step": 62
    },
    {
      "epoch": 3.0,
      "grad_norm": 0.13905638456344604,
      "learning_rate": 4.984437719485776e-05,
      "loss": 2.7459,
      "step": 63
    },
    {
      "epoch": 3.0,
      "eval_loss": 2.797880172729492,
      "eval_runtime": 6.8583,
      "eval_samples_per_second": 5.395,
      "eval_steps_per_second": 0.437,
      "step": 63
    }
  ],
  "logging_steps": 1.0,
  "max_steps": 63,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 31,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.735074652482437e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}