{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 3.0,
  "eval_steps": 500,
  "global_step": 24591,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0609979260705136,
      "grad_norm": 2.1482937335968018,
      "learning_rate": 4.8985401163027127e-05,
      "loss": 5.1096,
      "step": 500
    },
    {
      "epoch": 0.1219958521410272,
      "grad_norm": 1.8602643013000488,
      "learning_rate": 4.79687690618519e-05,
      "loss": 4.2904,
      "step": 1000
    },
    {
      "epoch": 0.1829937782115408,
      "grad_norm": 2.2239928245544434,
      "learning_rate": 4.6952136960676673e-05,
      "loss": 3.9507,
      "step": 1500
    },
    {
      "epoch": 0.2439917042820544,
      "grad_norm": 1.9908227920532227,
      "learning_rate": 4.593550485950145e-05,
      "loss": 3.7767,
      "step": 2000
    },
    {
      "epoch": 0.304989630352568,
      "grad_norm": 2.2968549728393555,
      "learning_rate": 4.491887275832622e-05,
      "loss": 3.6462,
      "step": 2500
    },
    {
      "epoch": 0.3659875564230816,
      "grad_norm": 1.7772067785263062,
      "learning_rate": 4.3902240657150994e-05,
      "loss": 3.5216,
      "step": 3000
    },
    {
      "epoch": 0.4269854824935952,
      "grad_norm": 1.9565205574035645,
      "learning_rate": 4.288560855597577e-05,
      "loss": 3.4266,
      "step": 3500
    },
    {
      "epoch": 0.4879834085641088,
      "grad_norm": 2.3488683700561523,
      "learning_rate": 4.186897645480054e-05,
      "loss": 3.348,
      "step": 4000
    },
    {
      "epoch": 0.5489813346346224,
      "grad_norm": 2.3590667247772217,
      "learning_rate": 4.085234435362531e-05,
      "loss": 3.2803,
      "step": 4500
    },
    {
      "epoch": 0.609979260705136,
      "grad_norm": 1.8940634727478027,
      "learning_rate": 3.983571225245009e-05,
      "loss": 3.2199,
      "step": 5000
    },
    {
      "epoch": 0.6709771867756497,
      "grad_norm": 2.2232987880706787,
      "learning_rate": 3.8819080151274854e-05,
      "loss": 3.1632,
      "step": 5500
    },
    {
      "epoch": 0.7319751128461632,
      "grad_norm": 1.9332739114761353,
      "learning_rate": 3.7802448050099634e-05,
      "loss": 3.1074,
      "step": 6000
    },
    {
      "epoch": 0.7929730389166768,
      "grad_norm": 1.869598150253296,
      "learning_rate": 3.678581594892441e-05,
      "loss": 3.0732,
      "step": 6500
    },
    {
      "epoch": 0.8539709649871904,
      "grad_norm": 1.6995704174041748,
      "learning_rate": 3.5769183847749174e-05,
      "loss": 3.0224,
      "step": 7000
    },
    {
      "epoch": 0.9149688910577041,
      "grad_norm": 2.039504051208496,
      "learning_rate": 3.4752551746573955e-05,
      "loss": 2.9645,
      "step": 7500
    },
    {
      "epoch": 0.9759668171282176,
      "grad_norm": 1.8474594354629517,
      "learning_rate": 3.373591964539872e-05,
      "loss": 2.9575,
      "step": 8000
    },
    {
      "epoch": 1.0369647431987312,
      "grad_norm": 1.9620344638824463,
      "learning_rate": 3.2719287544223495e-05,
      "loss": 2.8944,
      "step": 8500
    },
    {
      "epoch": 1.0979626692692448,
      "grad_norm": 1.8038884401321411,
      "learning_rate": 3.1702655443048275e-05,
      "loss": 2.877,
      "step": 9000
    },
    {
      "epoch": 1.1589605953397584,
      "grad_norm": 1.9445528984069824,
      "learning_rate": 3.068602334187304e-05,
      "loss": 2.8539,
      "step": 9500
    },
    {
      "epoch": 1.219958521410272,
      "grad_norm": 1.7721298933029175,
      "learning_rate": 2.966939124069782e-05,
      "loss": 2.8176,
      "step": 10000
    },
    {
      "epoch": 1.2809564474807855,
      "grad_norm": 2.3092963695526123,
      "learning_rate": 2.865275913952259e-05,
      "loss": 2.7872,
      "step": 10500
    },
    {
      "epoch": 1.3419543735512993,
      "grad_norm": 2.0396852493286133,
      "learning_rate": 2.7636127038347365e-05,
      "loss": 2.7764,
      "step": 11000
    },
    {
      "epoch": 1.402952299621813,
      "grad_norm": 1.755911946296692,
      "learning_rate": 2.6619494937172135e-05,
      "loss": 2.7607,
      "step": 11500
    },
    {
      "epoch": 1.4639502256923265,
      "grad_norm": 2.1026928424835205,
      "learning_rate": 2.560286283599691e-05,
      "loss": 2.7469,
      "step": 12000
    },
    {
      "epoch": 1.52494815176284,
      "grad_norm": 1.655788540840149,
      "learning_rate": 2.4586230734821682e-05,
      "loss": 2.7264,
      "step": 12500
    },
    {
      "epoch": 1.5859460778333536,
      "grad_norm": 2.534583568572998,
      "learning_rate": 2.3569598633646456e-05,
      "loss": 2.7102,
      "step": 13000
    },
    {
      "epoch": 1.6469440039038674,
      "grad_norm": 1.9951140880584717,
      "learning_rate": 2.2552966532471232e-05,
      "loss": 2.7136,
      "step": 13500
    },
    {
      "epoch": 1.707941929974381,
      "grad_norm": 2.0365281105041504,
      "learning_rate": 2.1536334431296002e-05,
      "loss": 2.6968,
      "step": 14000
    },
    {
      "epoch": 1.7689398560448946,
      "grad_norm": 1.7324215173721313,
      "learning_rate": 2.0519702330120776e-05,
      "loss": 2.6767,
      "step": 14500
    },
    {
      "epoch": 1.8299377821154081,
      "grad_norm": 1.9328315258026123,
      "learning_rate": 1.950307022894555e-05,
      "loss": 2.6868,
      "step": 15000
    },
    {
      "epoch": 1.8909357081859217,
      "grad_norm": 1.9608515501022339,
      "learning_rate": 1.8486438127770323e-05,
      "loss": 2.6585,
      "step": 15500
    },
    {
      "epoch": 1.9519336342564353,
      "grad_norm": 2.448692560195923,
      "learning_rate": 1.7469806026595096e-05,
      "loss": 2.6456,
      "step": 16000
    },
    {
      "epoch": 2.012931560326949,
      "grad_norm": 2.166044235229492,
      "learning_rate": 1.645317392541987e-05,
      "loss": 2.6379,
      "step": 16500
    },
    {
      "epoch": 2.0739294863974624,
      "grad_norm": 2.6067957878112793,
      "learning_rate": 1.5436541824244643e-05,
      "loss": 2.6017,
      "step": 17000
    },
    {
      "epoch": 2.134927412467976,
      "grad_norm": 2.173795700073242,
      "learning_rate": 1.4419909723069416e-05,
      "loss": 2.6037,
      "step": 17500
    },
    {
      "epoch": 2.1959253385384896,
      "grad_norm": 2.3912558555603027,
      "learning_rate": 1.340327762189419e-05,
      "loss": 2.5863,
      "step": 18000
    },
    {
      "epoch": 2.256923264609003,
      "grad_norm": 2.6069979667663574,
      "learning_rate": 1.2386645520718963e-05,
      "loss": 2.5806,
      "step": 18500
    },
    {
      "epoch": 2.3179211906795167,
      "grad_norm": 2.0667498111724854,
      "learning_rate": 1.1370013419543737e-05,
      "loss": 2.5738,
      "step": 19000
    },
    {
      "epoch": 2.3789191167500303,
      "grad_norm": 2.186269760131836,
      "learning_rate": 1.0353381318368509e-05,
      "loss": 2.5831,
      "step": 19500
    },
    {
      "epoch": 2.439917042820544,
      "grad_norm": 1.7841541767120361,
      "learning_rate": 9.336749217193284e-06,
      "loss": 2.561,
      "step": 20000
    },
    {
      "epoch": 2.500914968891058,
      "grad_norm": 2.1247878074645996,
      "learning_rate": 8.320117116018055e-06,
      "loss": 2.5534,
      "step": 20500
    },
    {
      "epoch": 2.561912894961571,
      "grad_norm": 1.7261439561843872,
      "learning_rate": 7.303485014842829e-06,
      "loss": 2.5288,
      "step": 21000
    },
    {
      "epoch": 2.622910821032085,
      "grad_norm": 1.6930060386657715,
      "learning_rate": 6.286852913667603e-06,
      "loss": 2.5449,
      "step": 21500
    },
    {
      "epoch": 2.6839087471025986,
      "grad_norm": 1.9172097444534302,
      "learning_rate": 5.270220812492376e-06,
      "loss": 2.5482,
      "step": 22000
    },
    {
      "epoch": 2.744906673173112,
      "grad_norm": 1.56685209274292,
      "learning_rate": 4.253588711317149e-06,
      "loss": 2.5493,
      "step": 22500
    },
    {
      "epoch": 2.805904599243626,
      "grad_norm": 2.165651321411133,
      "learning_rate": 3.2369566101419217e-06,
      "loss": 2.5481,
      "step": 23000
    },
    {
      "epoch": 2.8669025253141394,
      "grad_norm": 2.2414863109588623,
      "learning_rate": 2.220324508966695e-06,
      "loss": 2.5216,
      "step": 23500
    },
    {
      "epoch": 2.927900451384653,
      "grad_norm": 2.2040302753448486,
      "learning_rate": 1.2036924077914685e-06,
      "loss": 2.5239,
      "step": 24000
    },
    {
      "epoch": 2.9888983774551665,
      "grad_norm": 2.3587329387664795,
      "learning_rate": 1.8706030661624173e-07,
      "loss": 2.5358,
      "step": 24500
    },
    {
      "epoch": 3.0,
      "step": 24591,
      "total_flos": 4.51806634222551e+16,
      "train_loss": 2.926649949844495,
      "train_runtime": 7468.4511,
      "train_samples_per_second": 26.34,
      "train_steps_per_second": 3.293
    }
  ],
  "logging_steps": 500,
  "max_steps": 24591,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.51806634222551e+16,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}