{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0885783179961616,
  "eval_steps": 500,
  "global_step": 225,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0019683102056884164,
      "grad_norm": 0.15222452580928802,
      "learning_rate": 4e-05,
      "loss": 1.5145992279052733,
      "step": 5
    },
    {
      "epoch": 0.003936620411376833,
      "grad_norm": 0.25713402032852173,
      "learning_rate": 9e-05,
      "loss": 1.4644563674926758,
      "step": 10
    },
    {
      "epoch": 0.00590493061706525,
      "grad_norm": 0.18192017078399658,
      "learning_rate": 0.00014,
      "loss": 1.2352377891540527,
      "step": 15
    },
    {
      "epoch": 0.007873240822753666,
      "grad_norm": 0.2997220456600189,
      "learning_rate": 0.00019,
      "loss": 1.059535598754883,
      "step": 20
    },
    {
      "epoch": 0.009841551028442082,
      "grad_norm": 0.2566224932670593,
      "learning_rate": 0.00019555555555555556,
      "loss": 0.7871951103210449,
      "step": 25
    },
    {
      "epoch": 0.0118098612341305,
      "grad_norm": 0.27674880623817444,
      "learning_rate": 0.00019,
      "loss": 0.5399114608764648,
      "step": 30
    },
    {
      "epoch": 0.013778171439818916,
      "grad_norm": 0.23078280687332153,
      "learning_rate": 0.00018444444444444446,
      "loss": 0.3415979385375977,
      "step": 35
    },
    {
      "epoch": 0.01574648164550733,
      "grad_norm": 0.30523088574409485,
      "learning_rate": 0.0001788888888888889,
      "loss": 0.2282104015350342,
      "step": 40
    },
    {
      "epoch": 0.01771479185119575,
      "grad_norm": 0.173019140958786,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.15973645448684692,
      "step": 45
    },
    {
      "epoch": 0.019683102056884165,
      "grad_norm": 0.13935033977031708,
      "learning_rate": 0.0001677777777777778,
      "loss": 0.07095953226089477,
      "step": 50
    },
    {
      "epoch": 0.02165141226257258,
      "grad_norm": 0.18054886162281036,
      "learning_rate": 0.00016222222222222224,
      "loss": 0.1123568058013916,
      "step": 55
    },
    {
      "epoch": 0.023619722468261,
      "grad_norm": 0.24172309041023254,
      "learning_rate": 0.00015666666666666666,
      "loss": 0.10775176286697388,
      "step": 60
    },
    {
      "epoch": 0.025588032673949414,
      "grad_norm": 0.3667204678058624,
      "learning_rate": 0.0001511111111111111,
      "loss": 0.10995625257492066,
      "step": 65
    },
    {
      "epoch": 0.027556342879637832,
      "grad_norm": 0.11734714359045029,
      "learning_rate": 0.00014555555555555556,
      "loss": 0.06654936075210571,
      "step": 70
    },
    {
      "epoch": 0.029524653085326247,
      "grad_norm": 0.12473294883966446,
      "learning_rate": 0.00014,
      "loss": 0.12400143146514893,
      "step": 75
    },
    {
      "epoch": 0.03149296329101466,
      "grad_norm": 0.07316447794437408,
      "learning_rate": 0.00013444444444444447,
      "loss": 0.04965262711048126,
      "step": 80
    },
    {
      "epoch": 0.03346127349670308,
      "grad_norm": 0.05375482887029648,
      "learning_rate": 0.00012888888888888892,
      "loss": 0.05626271367073059,
      "step": 85
    },
    {
      "epoch": 0.0354295837023915,
      "grad_norm": 0.08668103069067001,
      "learning_rate": 0.00012333333333333334,
      "loss": 0.04172733426094055,
      "step": 90
    },
    {
      "epoch": 0.03739789390807991,
      "grad_norm": 0.05760786682367325,
      "learning_rate": 0.00011777777777777779,
      "loss": 0.04003114104270935,
      "step": 95
    },
    {
      "epoch": 0.03936620411376833,
      "grad_norm": 0.07841235399246216,
      "learning_rate": 0.00011222222222222223,
      "loss": 0.05856711864471435,
      "step": 100
    },
    {
      "epoch": 0.04133451431945675,
      "grad_norm": 0.08126020431518555,
      "learning_rate": 0.00010666666666666667,
      "loss": 0.07549648880958557,
      "step": 105
    },
    {
      "epoch": 0.04330282452514516,
      "grad_norm": 0.07693538069725037,
      "learning_rate": 0.00010111111111111112,
      "loss": 0.05478605628013611,
      "step": 110
    },
    {
      "epoch": 0.04527113473083358,
      "grad_norm": 0.08111221343278885,
      "learning_rate": 9.555555555555557e-05,
      "loss": 0.042981699109077454,
      "step": 115
    },
    {
      "epoch": 0.047239444936522,
      "grad_norm": 0.059269264340400696,
      "learning_rate": 9e-05,
      "loss": 0.047053870558738706,
      "step": 120
    },
    {
      "epoch": 0.04920775514221041,
      "grad_norm": 0.1270105242729187,
      "learning_rate": 8.444444444444444e-05,
      "loss": 0.04052863121032715,
      "step": 125
    },
    {
      "epoch": 0.05117606534789883,
      "grad_norm": 0.12631726264953613,
      "learning_rate": 4e-05,
      "loss": 0.03758008480072021,
      "step": 130
    },
    {
      "epoch": 0.053144375553587246,
      "grad_norm": 0.1927873194217682,
      "learning_rate": 9e-05,
      "loss": 0.04368264079093933,
      "step": 135
    },
    {
      "epoch": 0.055112685759275665,
      "grad_norm": 0.0689581036567688,
      "learning_rate": 0.00014,
      "loss": 0.049501892924308774,
      "step": 140
    },
    {
      "epoch": 0.057080995964964076,
      "grad_norm": 0.10839821398258209,
      "learning_rate": 0.00019,
      "loss": 0.04906965792179108,
      "step": 145
    },
    {
      "epoch": 0.059049306170652495,
      "grad_norm": 0.09603235125541687,
      "learning_rate": 0.00019555555555555556,
      "loss": 0.032542136311531064,
      "step": 150
    },
    {
      "epoch": 0.061017616376340914,
      "grad_norm": 0.12639078497886658,
      "learning_rate": 0.00019,
      "loss": 0.052462565898895266,
      "step": 155
    },
    {
      "epoch": 0.06298592658202933,
      "grad_norm": 0.07529020309448242,
      "learning_rate": 0.00018444444444444446,
      "loss": 0.03453230857849121,
      "step": 160
    },
    {
      "epoch": 0.06495423678771775,
      "grad_norm": 0.07132653892040253,
      "learning_rate": 0.0001788888888888889,
      "loss": 0.035509389638900754,
      "step": 165
    },
    {
      "epoch": 0.06692254699340616,
      "grad_norm": 0.1096048653125763,
      "learning_rate": 0.00017333333333333334,
      "loss": 0.034902679920196536,
      "step": 170
    },
    {
      "epoch": 0.06889085719909457,
      "grad_norm": 0.13892512023448944,
      "learning_rate": 0.0001677777777777778,
      "loss": 0.046495720744132996,
      "step": 175
    },
    {
      "epoch": 0.070859167404783,
      "grad_norm": 0.07194061577320099,
      "learning_rate": 0.00016222222222222224,
      "loss": 0.09309906363487244,
      "step": 180
    },
    {
      "epoch": 0.07282747761047141,
      "grad_norm": 0.17113636434078217,
      "learning_rate": 0.00015666666666666666,
      "loss": 0.0954027771949768,
      "step": 185
    },
    {
      "epoch": 0.07479578781615982,
      "grad_norm": 0.06981978565454483,
      "learning_rate": 0.0001511111111111111,
      "loss": 0.030196136236190795,
      "step": 190
    },
    {
      "epoch": 0.07676409802184825,
      "grad_norm": 0.06941649317741394,
      "learning_rate": 0.00014555555555555556,
      "loss": 0.040055733919143674,
      "step": 195
    },
    {
      "epoch": 0.07873240822753666,
      "grad_norm": 0.06938308477401733,
      "learning_rate": 0.00014,
      "loss": 0.031933313608169554,
      "step": 200
    },
    {
      "epoch": 0.08070468972983613,
      "grad_norm": 0.08689229935407639,
      "learning_rate": 4e-05,
      "loss": 0.06567999720573425,
      "step": 205
    },
    {
      "epoch": 0.0826730967964175,
      "grad_norm": 0.15433841943740845,
      "learning_rate": 9e-05,
      "loss": 0.08210374116897583,
      "step": 210
    },
    {
      "epoch": 0.08464150386299887,
      "grad_norm": 0.07927189767360687,
      "learning_rate": 0.00014,
      "loss": 0.08322054743766785,
      "step": 215
    },
    {
      "epoch": 0.08660991092958023,
      "grad_norm": 0.2075062394142151,
      "learning_rate": 0.00019,
      "loss": 0.05775731205940247,
      "step": 220
    },
    {
      "epoch": 0.0885783179961616,
      "grad_norm": 0.16508708894252777,
      "learning_rate": 0.0001998360655737705,
      "loss": 0.07884831428527832,
      "step": 225
    }
  ],
  "logging_steps": 5,
  "max_steps": 4900,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.511864096096379e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}