{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 268,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.018656716417910446,
      "grad_norm": 1.8354408972918559,
      "learning_rate": 1.785714285714286e-05,
      "loss": 0.8456,
      "step": 5
    },
    {
      "epoch": 0.03731343283582089,
      "grad_norm": 0.7881826286086709,
      "learning_rate": 3.571428571428572e-05,
      "loss": 0.7682,
      "step": 10
    },
    {
      "epoch": 0.055970149253731345,
      "grad_norm": 0.507320301810873,
      "learning_rate": 4.999827900623038e-05,
      "loss": 0.7025,
      "step": 15
    },
    {
      "epoch": 0.07462686567164178,
      "grad_norm": 0.39661236951302037,
      "learning_rate": 4.993807186343243e-05,
      "loss": 0.6745,
      "step": 20
    },
    {
      "epoch": 0.09328358208955224,
      "grad_norm": 0.3829746749453088,
      "learning_rate": 4.979207812402531e-05,
      "loss": 0.6435,
      "step": 25
    },
    {
      "epoch": 0.11194029850746269,
      "grad_norm": 0.2970943748532379,
      "learning_rate": 4.956085596012407e-05,
      "loss": 0.6362,
      "step": 30
    },
    {
      "epoch": 0.13059701492537312,
      "grad_norm": 0.28161066021376685,
      "learning_rate": 4.924528939432311e-05,
      "loss": 0.6199,
      "step": 35
    },
    {
      "epoch": 0.14925373134328357,
      "grad_norm": 0.2458908088562114,
      "learning_rate": 4.884658491984735e-05,
      "loss": 0.6105,
      "step": 40
    },
    {
      "epoch": 0.16791044776119404,
      "grad_norm": 0.21077705935451713,
      "learning_rate": 4.8366266887814235e-05,
      "loss": 0.6112,
      "step": 45
    },
    {
      "epoch": 0.1865671641791045,
      "grad_norm": 0.24988007188567507,
      "learning_rate": 4.780617167924209e-05,
      "loss": 0.5938,
      "step": 50
    },
    {
      "epoch": 0.20522388059701493,
      "grad_norm": 0.2618040985514504,
      "learning_rate": 4.716844068408693e-05,
      "loss": 0.5964,
      "step": 55
    },
    {
      "epoch": 0.22388059701492538,
      "grad_norm": 0.27593082311896716,
      "learning_rate": 4.6455512114150546e-05,
      "loss": 0.5918,
      "step": 60
    },
    {
      "epoch": 0.24253731343283583,
      "grad_norm": 0.5514318957648608,
      "learning_rate": 4.5670111681161296e-05,
      "loss": 0.583,
      "step": 65
    },
    {
      "epoch": 0.26119402985074625,
      "grad_norm": 0.46209061856878686,
      "learning_rate": 4.481524217566783e-05,
      "loss": 0.58,
      "step": 70
    },
    {
      "epoch": 0.2798507462686567,
      "grad_norm": 0.4276426373565151,
      "learning_rate": 4.3894171986588217e-05,
      "loss": 0.5784,
      "step": 75
    },
    {
      "epoch": 0.29850746268656714,
      "grad_norm": 0.4469191387827957,
      "learning_rate": 4.29104226053073e-05,
      "loss": 0.5774,
      "step": 80
    },
    {
      "epoch": 0.31716417910447764,
      "grad_norm": 0.31315910087255616,
      "learning_rate": 4.186775516209732e-05,
      "loss": 0.5728,
      "step": 85
    },
    {
      "epoch": 0.3358208955223881,
      "grad_norm": 0.32522440022737154,
      "learning_rate": 4.077015604633669e-05,
      "loss": 0.5753,
      "step": 90
    },
    {
      "epoch": 0.35447761194029853,
      "grad_norm": 0.3366119368298097,
      "learning_rate": 3.962182166550441e-05,
      "loss": 0.5738,
      "step": 95
    },
    {
      "epoch": 0.373134328358209,
      "grad_norm": 0.2587846057192818,
      "learning_rate": 3.8427142401220634e-05,
      "loss": 0.5696,
      "step": 100
    },
    {
      "epoch": 0.3917910447761194,
      "grad_norm": 0.2227770689821787,
      "learning_rate": 3.71906858236735e-05,
      "loss": 0.5659,
      "step": 105
    },
    {
      "epoch": 0.41044776119402987,
      "grad_norm": 0.2459159767997945,
      "learning_rate": 3.591717922860785e-05,
      "loss": 0.5732,
      "step": 110
    },
    {
      "epoch": 0.4291044776119403,
      "grad_norm": 0.22732893260395456,
      "learning_rate": 3.46114915636416e-05,
      "loss": 0.5641,
      "step": 115
    },
    {
      "epoch": 0.44776119402985076,
      "grad_norm": 0.2539929741274319,
      "learning_rate": 3.3278614813010034e-05,
      "loss": 0.5651,
      "step": 120
    },
    {
      "epoch": 0.4664179104477612,
      "grad_norm": 0.24660530938234346,
      "learning_rate": 3.1923644911909e-05,
      "loss": 0.5619,
      "step": 125
    },
    {
      "epoch": 0.48507462686567165,
      "grad_norm": 0.21933651293884215,
      "learning_rate": 3.0551762263406576e-05,
      "loss": 0.5606,
      "step": 130
    },
    {
      "epoch": 0.503731343283582,
      "grad_norm": 0.223999216160582,
      "learning_rate": 2.9168211932412042e-05,
      "loss": 0.5578,
      "step": 135
    },
    {
      "epoch": 0.5223880597014925,
      "grad_norm": 0.20693415659710301,
      "learning_rate": 2.777828359242567e-05,
      "loss": 0.5632,
      "step": 140
    },
    {
      "epoch": 0.5410447761194029,
      "grad_norm": 0.23425392132945205,
      "learning_rate": 2.6387291301738377e-05,
      "loss": 0.5558,
      "step": 145
    },
    {
      "epoch": 0.5597014925373134,
      "grad_norm": 0.22487318136750217,
      "learning_rate": 2.50005531864019e-05,
      "loss": 0.5537,
      "step": 150
    },
    {
      "epoch": 0.5783582089552238,
      "grad_norm": 0.1856721249310053,
      "learning_rate": 2.362337110764688e-05,
      "loss": 0.554,
      "step": 155
    },
    {
      "epoch": 0.5970149253731343,
      "grad_norm": 0.20126227551169606,
      "learning_rate": 2.226101039148557e-05,
      "loss": 0.5522,
      "step": 160
    },
    {
      "epoch": 0.6156716417910447,
      "grad_norm": 0.22438521570745706,
      "learning_rate": 2.0918679697998252e-05,
      "loss": 0.5511,
      "step": 165
    },
    {
      "epoch": 0.6343283582089553,
      "grad_norm": 0.20731039058659614,
      "learning_rate": 1.9601511107268255e-05,
      "loss": 0.5515,
      "step": 170
    },
    {
      "epoch": 0.6529850746268657,
      "grad_norm": 0.19797903832823752,
      "learning_rate": 1.8314540498102216e-05,
      "loss": 0.5511,
      "step": 175
    },
    {
      "epoch": 0.6716417910447762,
      "grad_norm": 0.17221585069011683,
      "learning_rate": 1.7062688294552992e-05,
      "loss": 0.5432,
      "step": 180
    },
    {
      "epoch": 0.6902985074626866,
      "grad_norm": 0.19322724560845156,
      "learning_rate": 1.5850740653856096e-05,
      "loss": 0.5467,
      "step": 185
    },
    {
      "epoch": 0.7089552238805971,
      "grad_norm": 0.17969131342750516,
      "learning_rate": 1.4683331167703218e-05,
      "loss": 0.5503,
      "step": 190
    },
    {
      "epoch": 0.7276119402985075,
      "grad_norm": 0.16836784689351517,
      "learning_rate": 1.356492314681356e-05,
      "loss": 0.553,
      "step": 195
    },
    {
      "epoch": 0.746268656716418,
      "grad_norm": 0.16669098051097167,
      "learning_rate": 1.2499792556533716e-05,
      "loss": 0.5474,
      "step": 200
    },
    {
      "epoch": 0.7649253731343284,
      "grad_norm": 0.17875185793657875,
      "learning_rate": 1.1492011668707753e-05,
      "loss": 0.5449,
      "step": 205
    },
    {
      "epoch": 0.7835820895522388,
      "grad_norm": 0.17087648305035483,
      "learning_rate": 1.0545433492320603e-05,
      "loss": 0.55,
      "step": 210
    },
    {
      "epoch": 0.8022388059701493,
      "grad_norm": 0.16026141311106246,
      "learning_rate": 9.663677042440537e-06,
      "loss": 0.5444,
      "step": 215
    },
    {
      "epoch": 0.8208955223880597,
      "grad_norm": 0.1610817206359273,
      "learning_rate": 8.850113503781367e-06,
      "loss": 0.5443,
      "step": 220
    },
    {
      "epoch": 0.8395522388059702,
      "grad_norm": 0.14265059464924393,
      "learning_rate": 8.107853341784671e-06,
      "loss": 0.5506,
      "step": 225
    },
    {
      "epoch": 0.8582089552238806,
      "grad_norm": 0.15560245721767546,
      "learning_rate": 7.439734410499752e-06,
      "loss": 0.547,
      "step": 230
    },
    {
      "epoch": 0.8768656716417911,
      "grad_norm": 0.18280465957063508,
      "learning_rate": 6.848311102728011e-06,
      "loss": 0.5471,
      "step": 235
    },
    {
      "epoch": 0.8955223880597015,
      "grad_norm": 0.1757059406671393,
      "learning_rate": 6.335844583913515e-06,
      "loss": 0.5433,
      "step": 240
    },
    {
      "epoch": 0.914179104477612,
      "grad_norm": 0.14421002534207897,
      "learning_rate": 5.904294147118193e-06,
      "loss": 0.5471,
      "step": 245
    },
    {
      "epoch": 0.9328358208955224,
      "grad_norm": 0.14770223717857597,
      "learning_rate": 5.555309722133842e-06,
      "loss": 0.5435,
      "step": 250
    },
    {
      "epoch": 0.9514925373134329,
      "grad_norm": 0.1415694728852703,
      "learning_rate": 5.290225567370509e-06,
      "loss": 0.5396,
      "step": 255
    },
    {
      "epoch": 0.9701492537313433,
      "grad_norm": 0.14950581262234355,
      "learning_rate": 5.110055168638854e-06,
      "loss": 0.5432,
      "step": 260
    },
    {
      "epoch": 0.9888059701492538,
      "grad_norm": 0.1432292679703526,
      "learning_rate": 5.0154873643297575e-06,
      "loss": 0.547,
      "step": 265
    },
    {
      "epoch": 1.0,
      "step": 268,
      "total_flos": 488621249396736.0,
      "train_loss": 0.5792782279982496,
      "train_runtime": 6428.403,
      "train_samples_per_second": 5.336,
      "train_steps_per_second": 0.042
    }
  ],
  "logging_steps": 5,
  "max_steps": 268,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 488621249396736.0,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}