{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 15228,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.03283425269240872,
      "grad_norm": 2.148223638534546,
      "learning_rate": 4.8358287365379566e-05,
      "loss": 7.8532,
      "step": 500
    },
    {
      "epoch": 0.06566850538481744,
      "grad_norm": 1.8999865055084229,
      "learning_rate": 4.671657473075913e-05,
      "loss": 7.2619,
      "step": 1000
    },
    {
      "epoch": 0.09850275807722617,
      "grad_norm": 1.8169187307357788,
      "learning_rate": 4.5074862096138694e-05,
      "loss": 7.078,
      "step": 1500
    },
    {
      "epoch": 0.1313370107696349,
      "grad_norm": 2.516470193862915,
      "learning_rate": 4.343314946151826e-05,
      "loss": 6.9502,
      "step": 2000
    },
    {
      "epoch": 0.1641712634620436,
      "grad_norm": 2.3785781860351562,
      "learning_rate": 4.179143682689782e-05,
      "loss": 6.8573,
      "step": 2500
    },
    {
      "epoch": 0.19700551615445233,
      "grad_norm": 2.1694188117980957,
      "learning_rate": 4.0149724192277385e-05,
      "loss": 6.8,
      "step": 3000
    },
    {
      "epoch": 0.22983976884686105,
      "grad_norm": 2.474036455154419,
      "learning_rate": 3.850801155765695e-05,
      "loss": 6.744,
      "step": 3500
    },
    {
      "epoch": 0.2626740215392698,
      "grad_norm": 2.19565749168396,
      "learning_rate": 3.686629892303651e-05,
      "loss": 6.6814,
      "step": 4000
    },
    {
      "epoch": 0.29550827423167847,
      "grad_norm": 2.747317314147949,
      "learning_rate": 3.522458628841608e-05,
      "loss": 6.5869,
      "step": 4500
    },
    {
      "epoch": 0.3283425269240872,
      "grad_norm": 3.399601936340332,
      "learning_rate": 3.358287365379564e-05,
      "loss": 6.4711,
      "step": 5000
    },
    {
      "epoch": 0.3611767796164959,
      "grad_norm": 2.9853923320770264,
      "learning_rate": 3.1941161019175205e-05,
      "loss": 6.3167,
      "step": 5500
    },
    {
      "epoch": 0.39401103230890466,
      "grad_norm": 3.57155704498291,
      "learning_rate": 3.029944838455477e-05,
      "loss": 6.2061,
      "step": 6000
    },
    {
      "epoch": 0.42684528500131336,
      "grad_norm": 3.53355073928833,
      "learning_rate": 2.8657735749934332e-05,
      "loss": 6.0795,
      "step": 6500
    },
    {
      "epoch": 0.4596795376937221,
      "grad_norm": 3.1891579627990723,
      "learning_rate": 2.70160231153139e-05,
      "loss": 5.9704,
      "step": 7000
    },
    {
      "epoch": 0.4925137903861308,
      "grad_norm": 3.8728067874908447,
      "learning_rate": 2.5374310480693457e-05,
      "loss": 5.8494,
      "step": 7500
    },
    {
      "epoch": 0.5253480430785396,
      "grad_norm": 3.752729654312134,
      "learning_rate": 2.3732597846073024e-05,
      "loss": 5.7467,
      "step": 8000
    },
    {
      "epoch": 0.5581822957709482,
      "grad_norm": 3.093104124069214,
      "learning_rate": 2.2090885211452588e-05,
      "loss": 5.6585,
      "step": 8500
    },
    {
      "epoch": 0.5910165484633569,
      "grad_norm": 3.5485284328460693,
      "learning_rate": 2.0449172576832152e-05,
      "loss": 5.5876,
      "step": 9000
    },
    {
      "epoch": 0.6238508011557657,
      "grad_norm": 3.3730971813201904,
      "learning_rate": 1.8807459942211716e-05,
      "loss": 5.5165,
      "step": 9500
    },
    {
      "epoch": 0.6566850538481744,
      "grad_norm": 3.767274856567383,
      "learning_rate": 1.716574730759128e-05,
      "loss": 5.4677,
      "step": 10000
    },
    {
      "epoch": 0.6895193065405831,
      "grad_norm": 3.7977945804595947,
      "learning_rate": 1.5524034672970843e-05,
      "loss": 5.4096,
      "step": 10500
    },
    {
      "epoch": 0.7223535592329918,
      "grad_norm": 3.5391793251037598,
      "learning_rate": 1.3882322038350407e-05,
      "loss": 5.3555,
      "step": 11000
    },
    {
      "epoch": 0.7551878119254006,
      "grad_norm": 3.8988144397735596,
      "learning_rate": 1.2240609403729971e-05,
      "loss": 5.3476,
      "step": 11500
    },
    {
      "epoch": 0.7880220646178093,
      "grad_norm": 4.032622337341309,
      "learning_rate": 1.0598896769109535e-05,
      "loss": 5.2971,
      "step": 12000
    },
    {
      "epoch": 0.820856317310218,
      "grad_norm": 3.8639235496520996,
      "learning_rate": 8.957184134489099e-06,
      "loss": 5.2853,
      "step": 12500
    },
    {
      "epoch": 0.8536905700026267,
      "grad_norm": 4.275233268737793,
      "learning_rate": 7.315471499868663e-06,
      "loss": 5.2745,
      "step": 13000
    },
    {
      "epoch": 0.8865248226950354,
      "grad_norm": 3.4154789447784424,
      "learning_rate": 5.673758865248227e-06,
      "loss": 5.2396,
      "step": 13500
    },
    {
      "epoch": 0.9193590753874442,
      "grad_norm": 3.5738344192504883,
      "learning_rate": 4.032046230627791e-06,
      "loss": 5.2383,
      "step": 14000
    },
    {
      "epoch": 0.9521933280798529,
      "grad_norm": 3.526001214981079,
      "learning_rate": 2.390333596007355e-06,
      "loss": 5.2186,
      "step": 14500
    },
    {
      "epoch": 0.9850275807722616,
      "grad_norm": 3.600189208984375,
      "learning_rate": 7.486209613869189e-07,
      "loss": 5.2131,
      "step": 15000
    }
  ],
  "logging_steps": 500,
  "max_steps": 15228,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.231269529606144e+16,
  "train_batch_size": 64,
  "trial_name": null,
  "trial_params": null
}