{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15278838808250572,
  "eval_steps": 10,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0015278838808250573,
      "grad_norm": 0.32149291038513184,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.665,
      "step": 1
    },
    {
      "epoch": 0.0030557677616501145,
      "grad_norm": 0.34995731711387634,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.6434,
      "step": 2
    },
    {
      "epoch": 0.004583651642475172,
      "grad_norm": 0.3517548739910126,
      "learning_rate": 6e-06,
      "loss": 2.7358,
      "step": 3
    },
    {
      "epoch": 0.006111535523300229,
      "grad_norm": 0.3041296601295471,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.5857,
      "step": 4
    },
    {
      "epoch": 0.007639419404125287,
      "grad_norm": 0.3146103620529175,
      "learning_rate": 1e-05,
      "loss": 2.6509,
      "step": 5
    },
    {
      "epoch": 0.009167303284950344,
      "grad_norm": 0.3501134216785431,
      "learning_rate": 1.2e-05,
      "loss": 2.6375,
      "step": 6
    },
    {
      "epoch": 0.0106951871657754,
      "grad_norm": 0.3118212819099426,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.685,
      "step": 7
    },
    {
      "epoch": 0.012223071046600458,
      "grad_norm": 0.33596929907798767,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.7284,
      "step": 8
    },
    {
      "epoch": 0.013750954927425516,
      "grad_norm": 0.32165855169296265,
      "learning_rate": 1.8e-05,
      "loss": 2.7919,
      "step": 9
    },
    {
      "epoch": 0.015278838808250574,
      "grad_norm": 0.3280738592147827,
      "learning_rate": 2e-05,
      "loss": 2.6194,
      "step": 10
    },
    {
      "epoch": 0.015278838808250574,
      "eval_loss": 2.6943862438201904,
      "eval_runtime": 97.4489,
      "eval_samples_per_second": 2.175,
      "eval_steps_per_second": 0.544,
      "step": 10
    },
    {
      "epoch": 0.01680672268907563,
      "grad_norm": 0.3205621838569641,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 2.6964,
      "step": 11
    },
    {
      "epoch": 0.01833460656990069,
      "grad_norm": 0.3181299567222595,
      "learning_rate": 2.4e-05,
      "loss": 2.6889,
      "step": 12
    },
    {
      "epoch": 0.019862490450725745,
      "grad_norm": 0.3135446012020111,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 2.6606,
      "step": 13
    },
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 0.34573134779930115,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 2.6154,
      "step": 14
    },
    {
      "epoch": 0.02291825821237586,
      "grad_norm": 0.3248574137687683,
      "learning_rate": 3e-05,
      "loss": 2.6702,
      "step": 15
    },
    {
      "epoch": 0.024446142093200916,
      "grad_norm": 0.304574579000473,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 2.6536,
      "step": 16
    },
    {
      "epoch": 0.025974025974025976,
      "grad_norm": 0.31393641233444214,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 2.5807,
      "step": 17
    },
    {
      "epoch": 0.02750190985485103,
      "grad_norm": 0.34099656343460083,
      "learning_rate": 3.6e-05,
      "loss": 2.7321,
      "step": 18
    },
    {
      "epoch": 0.029029793735676088,
      "grad_norm": 0.30074265599250793,
      "learning_rate": 3.8e-05,
      "loss": 2.5924,
      "step": 19
    },
    {
      "epoch": 0.030557677616501147,
      "grad_norm": 0.3261857032775879,
      "learning_rate": 4e-05,
      "loss": 2.6013,
      "step": 20
    },
    {
      "epoch": 0.030557677616501147,
      "eval_loss": 2.6393423080444336,
      "eval_runtime": 97.6877,
      "eval_samples_per_second": 2.17,
      "eval_steps_per_second": 0.543,
      "step": 20
    },
    {
      "epoch": 0.03208556149732621,
      "grad_norm": 0.32320329546928406,
      "learning_rate": 4.2e-05,
      "loss": 2.5175,
      "step": 21
    },
    {
      "epoch": 0.03361344537815126,
      "grad_norm": 0.32611727714538574,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 2.7366,
      "step": 22
    },
    {
      "epoch": 0.03514132925897632,
      "grad_norm": 0.3132462501525879,
      "learning_rate": 4.600000000000001e-05,
      "loss": 2.4918,
      "step": 23
    },
    {
      "epoch": 0.03666921313980138,
      "grad_norm": 0.3301452398300171,
      "learning_rate": 4.8e-05,
      "loss": 2.6077,
      "step": 24
    },
    {
      "epoch": 0.03819709702062643,
      "grad_norm": 0.3712747097015381,
      "learning_rate": 5e-05,
      "loss": 2.5816,
      "step": 25
    },
    {
      "epoch": 0.03972498090145149,
      "grad_norm": 0.33991169929504395,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 2.6139,
      "step": 26
    },
    {
      "epoch": 0.04125286478227655,
      "grad_norm": 0.3331744372844696,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 2.6106,
      "step": 27
    },
    {
      "epoch": 0.0427807486631016,
      "grad_norm": 0.34741106629371643,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 2.5478,
      "step": 28
    },
    {
      "epoch": 0.04430863254392666,
      "grad_norm": 0.34006839990615845,
      "learning_rate": 5.8e-05,
      "loss": 2.4678,
      "step": 29
    },
    {
      "epoch": 0.04583651642475172,
      "grad_norm": 0.30897256731987,
      "learning_rate": 6e-05,
      "loss": 2.5094,
      "step": 30
    },
    {
      "epoch": 0.04583651642475172,
      "eval_loss": 2.56597638130188,
      "eval_runtime": 97.2121,
      "eval_samples_per_second": 2.181,
      "eval_steps_per_second": 0.545,
      "step": 30
    },
    {
      "epoch": 0.04736440030557677,
      "grad_norm": 0.3237461745738983,
      "learning_rate": 6.2e-05,
      "loss": 2.4556,
      "step": 31
    },
    {
      "epoch": 0.04889228418640183,
      "grad_norm": 0.31788715720176697,
      "learning_rate": 6.400000000000001e-05,
      "loss": 2.308,
      "step": 32
    },
    {
      "epoch": 0.05042016806722689,
      "grad_norm": 0.3567247986793518,
      "learning_rate": 6.6e-05,
      "loss": 2.4991,
      "step": 33
    },
    {
      "epoch": 0.05194805194805195,
      "grad_norm": 0.38980555534362793,
      "learning_rate": 6.800000000000001e-05,
      "loss": 2.4502,
      "step": 34
    },
    {
      "epoch": 0.053475935828877004,
      "grad_norm": 0.3469444215297699,
      "learning_rate": 7e-05,
      "loss": 2.5429,
      "step": 35
    },
    {
      "epoch": 0.05500381970970206,
      "grad_norm": 0.385903000831604,
      "learning_rate": 7.2e-05,
      "loss": 2.6139,
      "step": 36
    },
    {
      "epoch": 0.05653170359052712,
      "grad_norm": 0.37668120861053467,
      "learning_rate": 7.4e-05,
      "loss": 2.5119,
      "step": 37
    },
    {
      "epoch": 0.058059587471352175,
      "grad_norm": 0.3561411201953888,
      "learning_rate": 7.6e-05,
      "loss": 2.5083,
      "step": 38
    },
    {
      "epoch": 0.059587471352177235,
      "grad_norm": 0.3774603009223938,
      "learning_rate": 7.800000000000001e-05,
      "loss": 2.5935,
      "step": 39
    },
    {
      "epoch": 0.061115355233002294,
      "grad_norm": 0.37734416127204895,
      "learning_rate": 8e-05,
      "loss": 2.5097,
      "step": 40
    },
    {
      "epoch": 0.061115355233002294,
      "eval_loss": 2.525169610977173,
      "eval_runtime": 97.2448,
      "eval_samples_per_second": 2.18,
      "eval_steps_per_second": 0.545,
      "step": 40
    },
    {
      "epoch": 0.06264323911382735,
      "grad_norm": 0.37569305300712585,
      "learning_rate": 8.2e-05,
      "loss": 2.5988,
      "step": 41
    },
    {
      "epoch": 0.06417112299465241,
      "grad_norm": 0.38874006271362305,
      "learning_rate": 8.4e-05,
      "loss": 2.3542,
      "step": 42
    },
    {
      "epoch": 0.06569900687547746,
      "grad_norm": 0.40507742762565613,
      "learning_rate": 8.6e-05,
      "loss": 2.5079,
      "step": 43
    },
    {
      "epoch": 0.06722689075630252,
      "grad_norm": 0.38088974356651306,
      "learning_rate": 8.800000000000001e-05,
      "loss": 2.4938,
      "step": 44
    },
    {
      "epoch": 0.06875477463712758,
      "grad_norm": 0.393225759267807,
      "learning_rate": 9e-05,
      "loss": 2.5691,
      "step": 45
    },
    {
      "epoch": 0.07028265851795264,
      "grad_norm": 0.39259836077690125,
      "learning_rate": 9.200000000000001e-05,
      "loss": 2.491,
      "step": 46
    },
    {
      "epoch": 0.0718105423987777,
      "grad_norm": 0.38004833459854126,
      "learning_rate": 9.4e-05,
      "loss": 2.3911,
      "step": 47
    },
    {
      "epoch": 0.07333842627960276,
      "grad_norm": 0.41154587268829346,
      "learning_rate": 9.6e-05,
      "loss": 2.3079,
      "step": 48
    },
    {
      "epoch": 0.0748663101604278,
      "grad_norm": 0.4159567058086395,
      "learning_rate": 9.8e-05,
      "loss": 2.4623,
      "step": 49
    },
    {
      "epoch": 0.07639419404125286,
      "grad_norm": 0.39570435881614685,
      "learning_rate": 0.0001,
      "loss": 2.5313,
      "step": 50
    },
    {
      "epoch": 0.07639419404125286,
      "eval_loss": 2.4937703609466553,
      "eval_runtime": 97.1689,
      "eval_samples_per_second": 2.182,
      "eval_steps_per_second": 0.545,
      "step": 50
    },
    {
      "epoch": 0.07792207792207792,
      "grad_norm": 0.3842063248157501,
      "learning_rate": 0.0001,
      "loss": 2.3827,
      "step": 51
    },
    {
      "epoch": 0.07944996180290298,
      "grad_norm": 0.3905870020389557,
      "learning_rate": 0.0001,
      "loss": 2.3705,
      "step": 52
    },
    {
      "epoch": 0.08097784568372804,
      "grad_norm": 0.408173531293869,
      "learning_rate": 0.0001,
      "loss": 2.4771,
      "step": 53
    },
    {
      "epoch": 0.0825057295645531,
      "grad_norm": 0.3941194415092468,
      "learning_rate": 0.0001,
      "loss": 2.4952,
      "step": 54
    },
    {
      "epoch": 0.08403361344537816,
      "grad_norm": 0.3991928696632385,
      "learning_rate": 0.0001,
      "loss": 2.4954,
      "step": 55
    },
    {
      "epoch": 0.0855614973262032,
      "grad_norm": 0.42234569787979126,
      "learning_rate": 0.0001,
      "loss": 2.3436,
      "step": 56
    },
    {
      "epoch": 0.08708938120702826,
      "grad_norm": 0.4667830169200897,
      "learning_rate": 0.0001,
      "loss": 2.4344,
      "step": 57
    },
    {
      "epoch": 0.08861726508785332,
      "grad_norm": 0.44776275753974915,
      "learning_rate": 0.0001,
      "loss": 2.4326,
      "step": 58
    },
    {
      "epoch": 0.09014514896867838,
      "grad_norm": 0.42618316411972046,
      "learning_rate": 0.0001,
      "loss": 2.3055,
      "step": 59
    },
    {
      "epoch": 0.09167303284950344,
      "grad_norm": 0.4447256624698639,
      "learning_rate": 0.0001,
      "loss": 2.5108,
      "step": 60
    },
    {
      "epoch": 0.09167303284950344,
      "eval_loss": 2.4696223735809326,
      "eval_runtime": 98.5528,
      "eval_samples_per_second": 2.151,
      "eval_steps_per_second": 0.538,
      "step": 60
    },
    {
      "epoch": 0.0932009167303285,
      "grad_norm": 0.44445377588272095,
      "learning_rate": 0.0001,
      "loss": 2.4297,
      "step": 61
    },
    {
      "epoch": 0.09472880061115355,
      "grad_norm": 0.40467268228530884,
      "learning_rate": 0.0001,
      "loss": 2.2947,
      "step": 62
    },
    {
      "epoch": 0.0962566844919786,
      "grad_norm": 0.4658174216747284,
      "learning_rate": 0.0001,
      "loss": 2.5242,
      "step": 63
    },
    {
      "epoch": 0.09778456837280367,
      "grad_norm": 0.44855207204818726,
      "learning_rate": 0.0001,
      "loss": 2.3913,
      "step": 64
    },
    {
      "epoch": 0.09931245225362872,
      "grad_norm": 0.4550195634365082,
      "learning_rate": 0.0001,
      "loss": 2.3403,
      "step": 65
    },
    {
      "epoch": 0.10084033613445378,
      "grad_norm": 0.4837151765823364,
      "learning_rate": 0.0001,
      "loss": 2.4951,
      "step": 66
    },
    {
      "epoch": 0.10236822001527884,
      "grad_norm": 0.4518112242221832,
      "learning_rate": 0.0001,
      "loss": 2.432,
      "step": 67
    },
    {
      "epoch": 0.1038961038961039,
      "grad_norm": 0.43797725439071655,
      "learning_rate": 0.0001,
      "loss": 2.3761,
      "step": 68
    },
    {
      "epoch": 0.10542398777692895,
      "grad_norm": 0.4753503203392029,
      "learning_rate": 0.0001,
      "loss": 2.3425,
      "step": 69
    },
    {
      "epoch": 0.10695187165775401,
      "grad_norm": 0.4559343159198761,
      "learning_rate": 0.0001,
      "loss": 2.4907,
      "step": 70
    },
    {
      "epoch": 0.10695187165775401,
      "eval_loss": 2.4506397247314453,
      "eval_runtime": 96.9403,
      "eval_samples_per_second": 2.187,
      "eval_steps_per_second": 0.547,
      "step": 70
    },
    {
      "epoch": 0.10847975553857907,
      "grad_norm": 0.43265870213508606,
      "learning_rate": 0.0001,
      "loss": 2.3957,
      "step": 71
    },
    {
      "epoch": 0.11000763941940413,
      "grad_norm": 0.49019816517829895,
      "learning_rate": 0.0001,
      "loss": 2.3443,
      "step": 72
    },
    {
      "epoch": 0.11153552330022919,
      "grad_norm": 0.46558165550231934,
      "learning_rate": 0.0001,
      "loss": 2.4487,
      "step": 73
    },
    {
      "epoch": 0.11306340718105425,
      "grad_norm": 0.4491911232471466,
      "learning_rate": 0.0001,
      "loss": 2.4371,
      "step": 74
    },
    {
      "epoch": 0.11459129106187929,
      "grad_norm": 0.4462290108203888,
      "learning_rate": 0.0001,
      "loss": 2.3225,
      "step": 75
    },
    {
      "epoch": 0.11611917494270435,
      "grad_norm": 0.4684162437915802,
      "learning_rate": 0.0001,
      "loss": 2.3301,
      "step": 76
    },
    {
      "epoch": 0.11764705882352941,
      "grad_norm": 0.4510643780231476,
      "learning_rate": 0.0001,
      "loss": 2.3803,
      "step": 77
    },
    {
      "epoch": 0.11917494270435447,
      "grad_norm": 0.45720160007476807,
      "learning_rate": 0.0001,
      "loss": 2.1956,
      "step": 78
    },
    {
      "epoch": 0.12070282658517953,
      "grad_norm": 0.5116860866546631,
      "learning_rate": 0.0001,
      "loss": 2.3297,
      "step": 79
    },
    {
      "epoch": 0.12223071046600459,
      "grad_norm": 0.49560126662254333,
      "learning_rate": 0.0001,
      "loss": 2.3534,
      "step": 80
    },
    {
      "epoch": 0.12223071046600459,
      "eval_loss": 2.431182861328125,
      "eval_runtime": 97.315,
      "eval_samples_per_second": 2.178,
      "eval_steps_per_second": 0.545,
      "step": 80
    },
    {
      "epoch": 0.12375859434682965,
      "grad_norm": 0.5099540948867798,
      "learning_rate": 0.0001,
      "loss": 2.3705,
      "step": 81
    },
    {
      "epoch": 0.1252864782276547,
      "grad_norm": 0.5318695902824402,
      "learning_rate": 0.0001,
      "loss": 2.433,
      "step": 82
    },
    {
      "epoch": 0.12681436210847977,
      "grad_norm": 0.5086469054222107,
      "learning_rate": 0.0001,
      "loss": 2.3501,
      "step": 83
    },
    {
      "epoch": 0.12834224598930483,
      "grad_norm": 0.5173415541648865,
      "learning_rate": 0.0001,
      "loss": 2.5133,
      "step": 84
    },
    {
      "epoch": 0.12987012987012986,
      "grad_norm": 0.5070729851722717,
      "learning_rate": 0.0001,
      "loss": 2.3097,
      "step": 85
    },
    {
      "epoch": 0.13139801375095492,
      "grad_norm": 0.5236591100692749,
      "learning_rate": 0.0001,
      "loss": 2.4274,
      "step": 86
    },
    {
      "epoch": 0.13292589763177998,
      "grad_norm": 0.4986536502838135,
      "learning_rate": 0.0001,
      "loss": 2.319,
      "step": 87
    },
    {
      "epoch": 0.13445378151260504,
      "grad_norm": 0.5196006894111633,
      "learning_rate": 0.0001,
      "loss": 2.3206,
      "step": 88
    },
    {
      "epoch": 0.1359816653934301,
      "grad_norm": 0.5313082337379456,
      "learning_rate": 0.0001,
      "loss": 2.3236,
      "step": 89
    },
    {
      "epoch": 0.13750954927425516,
      "grad_norm": 0.5488006472587585,
      "learning_rate": 0.0001,
      "loss": 2.4561,
      "step": 90
    },
    {
      "epoch": 0.13750954927425516,
      "eval_loss": 2.418342113494873,
      "eval_runtime": 97.2483,
      "eval_samples_per_second": 2.18,
      "eval_steps_per_second": 0.545,
      "step": 90
    },
    {
      "epoch": 0.13903743315508021,
      "grad_norm": 0.4645894169807434,
      "learning_rate": 0.0001,
      "loss": 2.2276,
      "step": 91
    },
    {
      "epoch": 0.14056531703590527,
      "grad_norm": 0.5012871623039246,
      "learning_rate": 0.0001,
      "loss": 2.2207,
      "step": 92
    },
    {
      "epoch": 0.14209320091673033,
      "grad_norm": 0.530411422252655,
      "learning_rate": 0.0001,
      "loss": 2.562,
      "step": 93
    },
    {
      "epoch": 0.1436210847975554,
      "grad_norm": 0.5485709309577942,
      "learning_rate": 0.0001,
      "loss": 2.3263,
      "step": 94
    },
    {
      "epoch": 0.14514896867838045,
      "grad_norm": 0.6266875863075256,
      "learning_rate": 0.0001,
      "loss": 2.6683,
      "step": 95
    },
    {
      "epoch": 0.1466768525592055,
      "grad_norm": 0.5087680220603943,
      "learning_rate": 0.0001,
      "loss": 2.4218,
      "step": 96
    },
    {
      "epoch": 0.14820473644003057,
      "grad_norm": 0.5369350910186768,
      "learning_rate": 0.0001,
      "loss": 2.3236,
      "step": 97
    },
    {
      "epoch": 0.1497326203208556,
      "grad_norm": 0.5454537272453308,
      "learning_rate": 0.0001,
      "loss": 2.3474,
      "step": 98
    },
    {
      "epoch": 0.15126050420168066,
      "grad_norm": 0.5537680387496948,
      "learning_rate": 0.0001,
      "loss": 2.3792,
      "step": 99
    },
    {
      "epoch": 0.15278838808250572,
      "grad_norm": 0.5667999982833862,
      "learning_rate": 0.0001,
      "loss": 2.3371,
      "step": 100
    },
    {
      "epoch": 0.15278838808250572,
      "eval_loss": 2.405158519744873,
      "eval_runtime": 96.774,
      "eval_samples_per_second": 2.191,
      "eval_steps_per_second": 0.548,
      "step": 100
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "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": 2.188069974338765e+16,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}