{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.12610340479192939,
  "eval_steps": 50,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0025220680958385876,
      "grad_norm": 83.50857543945312,
      "learning_rate": 0.0,
      "loss": 3.3887,
      "step": 1
    },
    {
      "epoch": 0.005044136191677175,
      "grad_norm": 71.31573486328125,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 3.4305,
      "step": 2
    },
    {
      "epoch": 0.007566204287515763,
      "grad_norm": 66.55958557128906,
      "learning_rate": 4.000000000000001e-06,
      "loss": 3.0425,
      "step": 3
    },
    {
      "epoch": 0.01008827238335435,
      "grad_norm": 67.16094207763672,
      "learning_rate": 6e-06,
      "loss": 3.1193,
      "step": 4
    },
    {
      "epoch": 0.012610340479192938,
      "grad_norm": 58.159088134765625,
      "learning_rate": 8.000000000000001e-06,
      "loss": 2.7595,
      "step": 5
    },
    {
      "epoch": 0.015132408575031526,
      "grad_norm": 39.46601867675781,
      "learning_rate": 1e-05,
      "loss": 2.3184,
      "step": 6
    },
    {
      "epoch": 0.017654476670870115,
      "grad_norm": 45.5927734375,
      "learning_rate": 9.987325728770595e-06,
      "loss": 2.1763,
      "step": 7
    },
    {
      "epoch": 0.0201765447667087,
      "grad_norm": 20.798906326293945,
      "learning_rate": 9.974651457541193e-06,
      "loss": 2.1835,
      "step": 8
    },
    {
      "epoch": 0.02269861286254729,
      "grad_norm": 15.517325401306152,
      "learning_rate": 9.961977186311787e-06,
      "loss": 2.1354,
      "step": 9
    },
    {
      "epoch": 0.025220680958385876,
      "grad_norm": 15.667418479919434,
      "learning_rate": 9.949302915082384e-06,
      "loss": 1.9287,
      "step": 10
    },
    {
      "epoch": 0.027742749054224466,
      "grad_norm": 13.178864479064941,
      "learning_rate": 9.93662864385298e-06,
      "loss": 1.9898,
      "step": 11
    },
    {
      "epoch": 0.03026481715006305,
      "grad_norm": 10.053223609924316,
      "learning_rate": 9.923954372623576e-06,
      "loss": 2.0013,
      "step": 12
    },
    {
      "epoch": 0.03278688524590164,
      "grad_norm": 14.007344245910645,
      "learning_rate": 9.91128010139417e-06,
      "loss": 2.0559,
      "step": 13
    },
    {
      "epoch": 0.03530895334174023,
      "grad_norm": 11.14796257019043,
      "learning_rate": 9.898605830164766e-06,
      "loss": 2.0379,
      "step": 14
    },
    {
      "epoch": 0.03783102143757881,
      "grad_norm": 13.28112506866455,
      "learning_rate": 9.885931558935362e-06,
      "loss": 1.9854,
      "step": 15
    },
    {
      "epoch": 0.0403530895334174,
      "grad_norm": 11.45155143737793,
      "learning_rate": 9.873257287705957e-06,
      "loss": 2.1884,
      "step": 16
    },
    {
      "epoch": 0.04287515762925599,
      "grad_norm": 10.636513710021973,
      "learning_rate": 9.860583016476553e-06,
      "loss": 1.9676,
      "step": 17
    },
    {
      "epoch": 0.04539722572509458,
      "grad_norm": 10.700081825256348,
      "learning_rate": 9.847908745247149e-06,
      "loss": 1.9426,
      "step": 18
    },
    {
      "epoch": 0.04791929382093316,
      "grad_norm": 10.350312232971191,
      "learning_rate": 9.835234474017745e-06,
      "loss": 1.931,
      "step": 19
    },
    {
      "epoch": 0.05044136191677175,
      "grad_norm": 11.60483455657959,
      "learning_rate": 9.822560202788341e-06,
      "loss": 1.9397,
      "step": 20
    },
    {
      "epoch": 0.05296343001261034,
      "grad_norm": 10.923288345336914,
      "learning_rate": 9.809885931558936e-06,
      "loss": 1.8861,
      "step": 21
    },
    {
      "epoch": 0.05548549810844893,
      "grad_norm": 10.222322463989258,
      "learning_rate": 9.797211660329532e-06,
      "loss": 1.8154,
      "step": 22
    },
    {
      "epoch": 0.058007566204287514,
      "grad_norm": 9.665061950683594,
      "learning_rate": 9.784537389100128e-06,
      "loss": 1.9885,
      "step": 23
    },
    {
      "epoch": 0.0605296343001261,
      "grad_norm": 10.544888496398926,
      "learning_rate": 9.771863117870724e-06,
      "loss": 1.9728,
      "step": 24
    },
    {
      "epoch": 0.06305170239596469,
      "grad_norm": 9.924367904663086,
      "learning_rate": 9.759188846641318e-06,
      "loss": 1.9665,
      "step": 25
    },
    {
      "epoch": 0.06557377049180328,
      "grad_norm": 9.470415115356445,
      "learning_rate": 9.746514575411914e-06,
      "loss": 1.8872,
      "step": 26
    },
    {
      "epoch": 0.06809583858764187,
      "grad_norm": 9.330588340759277,
      "learning_rate": 9.73384030418251e-06,
      "loss": 1.9458,
      "step": 27
    },
    {
      "epoch": 0.07061790668348046,
      "grad_norm": 9.101158142089844,
      "learning_rate": 9.721166032953105e-06,
      "loss": 2.0452,
      "step": 28
    },
    {
      "epoch": 0.07313997477931904,
      "grad_norm": 9.63065242767334,
      "learning_rate": 9.708491761723701e-06,
      "loss": 1.9648,
      "step": 29
    },
    {
      "epoch": 0.07566204287515763,
      "grad_norm": 9.038743019104004,
      "learning_rate": 9.695817490494297e-06,
      "loss": 1.9469,
      "step": 30
    },
    {
      "epoch": 0.07818411097099622,
      "grad_norm": 9.375469207763672,
      "learning_rate": 9.683143219264893e-06,
      "loss": 2.0387,
      "step": 31
    },
    {
      "epoch": 0.0807061790668348,
      "grad_norm": 9.170827865600586,
      "learning_rate": 9.670468948035488e-06,
      "loss": 2.0396,
      "step": 32
    },
    {
      "epoch": 0.0832282471626734,
      "grad_norm": 9.155048370361328,
      "learning_rate": 9.657794676806086e-06,
      "loss": 2.1346,
      "step": 33
    },
    {
      "epoch": 0.08575031525851198,
      "grad_norm": 9.660133361816406,
      "learning_rate": 9.64512040557668e-06,
      "loss": 1.814,
      "step": 34
    },
    {
      "epoch": 0.08827238335435057,
      "grad_norm": 9.577939987182617,
      "learning_rate": 9.632446134347276e-06,
      "loss": 1.9353,
      "step": 35
    },
    {
      "epoch": 0.09079445145018916,
      "grad_norm": 9.347375869750977,
      "learning_rate": 9.619771863117872e-06,
      "loss": 1.8748,
      "step": 36
    },
    {
      "epoch": 0.09331651954602774,
      "grad_norm": 9.635443687438965,
      "learning_rate": 9.607097591888467e-06,
      "loss": 2.0299,
      "step": 37
    },
    {
      "epoch": 0.09583858764186633,
      "grad_norm": 9.470548629760742,
      "learning_rate": 9.594423320659063e-06,
      "loss": 1.966,
      "step": 38
    },
    {
      "epoch": 0.09836065573770492,
      "grad_norm": 9.292247772216797,
      "learning_rate": 9.581749049429659e-06,
      "loss": 1.8779,
      "step": 39
    },
    {
      "epoch": 0.1008827238335435,
      "grad_norm": 9.822443962097168,
      "learning_rate": 9.569074778200255e-06,
      "loss": 1.8484,
      "step": 40
    },
    {
      "epoch": 0.1034047919293821,
      "grad_norm": 8.519198417663574,
      "learning_rate": 9.55640050697085e-06,
      "loss": 1.7622,
      "step": 41
    },
    {
      "epoch": 0.10592686002522068,
      "grad_norm": 9.220460891723633,
      "learning_rate": 9.543726235741445e-06,
      "loss": 1.8659,
      "step": 42
    },
    {
      "epoch": 0.10844892812105927,
      "grad_norm": 8.564704895019531,
      "learning_rate": 9.531051964512042e-06,
      "loss": 1.8478,
      "step": 43
    },
    {
      "epoch": 0.11097099621689786,
      "grad_norm": 9.696242332458496,
      "learning_rate": 9.518377693282636e-06,
      "loss": 1.8625,
      "step": 44
    },
    {
      "epoch": 0.11349306431273644,
      "grad_norm": 9.121529579162598,
      "learning_rate": 9.505703422053234e-06,
      "loss": 1.9736,
      "step": 45
    },
    {
      "epoch": 0.11601513240857503,
      "grad_norm": 9.0239896774292,
      "learning_rate": 9.493029150823828e-06,
      "loss": 1.8687,
      "step": 46
    },
    {
      "epoch": 0.11853720050441362,
      "grad_norm": 8.566268920898438,
      "learning_rate": 9.480354879594424e-06,
      "loss": 1.7855,
      "step": 47
    },
    {
      "epoch": 0.1210592686002522,
      "grad_norm": 9.728326797485352,
      "learning_rate": 9.46768060836502e-06,
      "loss": 2.0394,
      "step": 48
    },
    {
      "epoch": 0.1235813366960908,
      "grad_norm": 8.644201278686523,
      "learning_rate": 9.455006337135616e-06,
      "loss": 1.8265,
      "step": 49
    },
    {
      "epoch": 0.12610340479192939,
      "grad_norm": 9.00877857208252,
      "learning_rate": 9.442332065906211e-06,
      "loss": 1.9655,
      "step": 50
    },
    {
      "epoch": 0.12610340479192939,
      "eval_loss": 1.8593257665634155,
      "eval_runtime": 19.3972,
      "eval_samples_per_second": 36.345,
      "eval_steps_per_second": 18.198,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 794,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 267147834912768.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}