{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 500,
  "global_step": 410,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04878048780487805,
      "grad_norm": 0.4036892056465149,
      "learning_rate": 0.00019999478113897612,
      "loss": 1.0282,
      "step": 10
    },
    {
      "epoch": 0.0975609756097561,
      "grad_norm": 0.3629762828350067,
      "learning_rate": 0.0001999791251006346,
      "loss": 0.7875,
      "step": 20
    },
    {
      "epoch": 0.14634146341463414,
      "grad_norm": 0.4877622425556183,
      "learning_rate": 0.0001999530335191093,
      "loss": 0.5942,
      "step": 30
    },
    {
      "epoch": 0.1951219512195122,
      "grad_norm": 0.4466260075569153,
      "learning_rate": 0.00019991650911776695,
      "loss": 0.3866,
      "step": 40
    },
    {
      "epoch": 0.24390243902439024,
      "grad_norm": 0.649118959903717,
      "learning_rate": 0.000199869555708923,
      "loss": 0.3928,
      "step": 50
    },
    {
      "epoch": 0.2926829268292683,
      "grad_norm": 0.8762800097465515,
      "learning_rate": 0.0001998121781934438,
      "loss": 0.3258,
      "step": 60
    },
    {
      "epoch": 0.34146341463414637,
      "grad_norm": 0.9195622801780701,
      "learning_rate": 0.0001997443825602349,
      "loss": 0.2885,
      "step": 70
    },
    {
      "epoch": 0.3902439024390244,
      "grad_norm": 0.5856262445449829,
      "learning_rate": 0.00019966617588561609,
      "loss": 0.2888,
      "step": 80
    },
    {
      "epoch": 0.43902439024390244,
      "grad_norm": 0.5520443320274353,
      "learning_rate": 0.00019957756633258265,
      "loss": 0.2242,
      "step": 90
    },
    {
      "epoch": 0.4878048780487805,
      "grad_norm": 0.9435800909996033,
      "learning_rate": 0.00019947856314995349,
      "loss": 0.1629,
      "step": 100
    },
    {
      "epoch": 0.5365853658536586,
      "grad_norm": 0.9416623115539551,
      "learning_rate": 0.00019936917667140555,
      "loss": 0.1555,
      "step": 110
    },
    {
      "epoch": 0.5853658536585366,
      "grad_norm": 0.802065372467041,
      "learning_rate": 0.0001992494183143955,
      "loss": 0.1339,
      "step": 120
    },
    {
      "epoch": 0.6341463414634146,
      "grad_norm": 0.7007794380187988,
      "learning_rate": 0.00019911930057896774,
      "loss": 0.1191,
      "step": 130
    },
    {
      "epoch": 0.6829268292682927,
      "grad_norm": 0.6755990386009216,
      "learning_rate": 0.00019897883704644983,
      "loss": 0.1571,
      "step": 140
    },
    {
      "epoch": 0.7317073170731707,
      "grad_norm": 1.6951078176498413,
      "learning_rate": 0.00019882804237803488,
      "loss": 0.1309,
      "step": 150
    },
    {
      "epoch": 0.7804878048780488,
      "grad_norm": 0.567158579826355,
      "learning_rate": 0.0001986669323132512,
      "loss": 0.0766,
      "step": 160
    },
    {
      "epoch": 0.8292682926829268,
      "grad_norm": 0.8820038437843323,
      "learning_rate": 0.0001984955236683196,
      "loss": 0.0839,
      "step": 170
    },
    {
      "epoch": 0.8780487804878049,
      "grad_norm": 0.6520794034004211,
      "learning_rate": 0.00019831383433439797,
      "loss": 0.0863,
      "step": 180
    },
    {
      "epoch": 0.926829268292683,
      "grad_norm": 0.45519864559173584,
      "learning_rate": 0.00019812188327571399,
      "loss": 0.0889,
      "step": 190
    },
    {
      "epoch": 0.975609756097561,
      "grad_norm": 0.614235520362854,
      "learning_rate": 0.00019791969052758562,
      "loss": 0.0725,
      "step": 200
    },
    {
      "epoch": 1.024390243902439,
      "grad_norm": 0.2764686644077301,
      "learning_rate": 0.00019770727719432994,
      "loss": 0.0407,
      "step": 210
    },
    {
      "epoch": 1.0731707317073171,
      "grad_norm": 0.6082726716995239,
      "learning_rate": 0.00019748466544706022,
      "loss": 0.044,
      "step": 220
    },
    {
      "epoch": 1.1219512195121952,
      "grad_norm": 0.9295619130134583,
      "learning_rate": 0.00019725187852137195,
      "loss": 0.0675,
      "step": 230
    },
    {
      "epoch": 1.170731707317073,
      "grad_norm": 0.3758924603462219,
      "learning_rate": 0.00019700894071491732,
      "loss": 0.0439,
      "step": 240
    },
    {
      "epoch": 1.2195121951219512,
      "grad_norm": 0.46514585614204407,
      "learning_rate": 0.00019675587738486936,
      "loss": 0.0398,
      "step": 250
    },
    {
      "epoch": 1.2682926829268293,
      "grad_norm": 0.5870018005371094,
      "learning_rate": 0.0001964927149452751,
      "loss": 0.0406,
      "step": 260
    },
    {
      "epoch": 1.3170731707317074,
      "grad_norm": 0.30292996764183044,
      "learning_rate": 0.00019621948086429844,
      "loss": 0.028,
      "step": 270
    },
    {
      "epoch": 1.3658536585365852,
      "grad_norm": 0.47037121653556824,
      "learning_rate": 0.00019593620366135337,
      "loss": 0.0239,
      "step": 280
    },
    {
      "epoch": 1.4146341463414633,
      "grad_norm": 0.4176475405693054,
      "learning_rate": 0.00019564291290412688,
      "loss": 0.0281,
      "step": 290
    },
    {
      "epoch": 1.4634146341463414,
      "grad_norm": 0.3179157078266144,
      "learning_rate": 0.00019533963920549306,
      "loss": 0.0281,
      "step": 300
    },
    {
      "epoch": 1.5121951219512195,
      "grad_norm": 0.5817562937736511,
      "learning_rate": 0.00019502641422031763,
      "loss": 0.0296,
      "step": 310
    },
    {
      "epoch": 1.5609756097560976,
      "grad_norm": 0.7409655451774597,
      "learning_rate": 0.00019470327064215383,
      "loss": 0.029,
      "step": 320
    },
    {
      "epoch": 1.6097560975609757,
      "grad_norm": 0.4418310225009918,
      "learning_rate": 0.00019437024219983028,
      "loss": 0.0583,
      "step": 330
    },
    {
      "epoch": 1.6585365853658538,
      "grad_norm": 0.31637728214263916,
      "learning_rate": 0.0001940273636539301,
      "loss": 0.0354,
      "step": 340
    },
    {
      "epoch": 1.7073170731707317,
      "grad_norm": 0.22175493836402893,
      "learning_rate": 0.00019367467079316279,
      "loss": 0.0514,
      "step": 350
    },
    {
      "epoch": 1.7560975609756098,
      "grad_norm": 0.6636152267456055,
      "learning_rate": 0.00019331220043062894,
      "loss": 0.034,
      "step": 360
    },
    {
      "epoch": 1.8048780487804879,
      "grad_norm": 0.8424332141876221,
      "learning_rate": 0.00019293999039997746,
      "loss": 0.0299,
      "step": 370
    },
    {
      "epoch": 1.8536585365853657,
      "grad_norm": 0.6435155272483826,
      "learning_rate": 0.00019255807955145677,
      "loss": 0.0508,
      "step": 380
    },
    {
      "epoch": 1.9024390243902438,
      "grad_norm": 0.7734220027923584,
      "learning_rate": 0.00019216650774785972,
      "loss": 0.035,
      "step": 390
    },
    {
      "epoch": 1.951219512195122,
      "grad_norm": 0.2854250967502594,
      "learning_rate": 0.0001917653158603628,
      "loss": 0.0339,
      "step": 400
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.6165639758110046,
      "learning_rate": 0.0001913545457642601,
      "loss": 0.0323,
      "step": 410
    }
  ],
  "logging_steps": 10,
  "max_steps": 3075,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 15,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.64317874233344e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}