{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.999973032011003,
  "eval_steps": 500,
  "global_step": 18540,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.026967988997060488,
      "grad_norm": 0.8829220533370972,
      "learning_rate": 4.9910325182530915e-05,
      "loss": 0.6808,
      "step": 500
    },
    {
      "epoch": 0.053935977994120976,
      "grad_norm": 1.0129338502883911,
      "learning_rate": 4.9641944055954695e-05,
      "loss": 0.458,
      "step": 1000
    },
    {
      "epoch": 0.08090396699118146,
      "grad_norm": 0.8441129326820374,
      "learning_rate": 4.9196781982554374e-05,
      "loss": 0.4483,
      "step": 1500
    },
    {
      "epoch": 0.10787195598824195,
      "grad_norm": 0.3246585726737976,
      "learning_rate": 4.857803254854406e-05,
      "loss": 0.45,
      "step": 2000
    },
    {
      "epoch": 0.13483994498530244,
      "grad_norm": 0.44776633381843567,
      "learning_rate": 4.7790134653328074e-05,
      "loss": 0.4444,
      "step": 2500
    },
    {
      "epoch": 0.16180793398236293,
      "grad_norm": 0.49329063296318054,
      "learning_rate": 4.6838740664901435e-05,
      "loss": 0.438,
      "step": 3000
    },
    {
      "epoch": 0.18877592297942342,
      "grad_norm": 0.47724494338035583,
      "learning_rate": 4.573067586984441e-05,
      "loss": 0.4406,
      "step": 3500
    },
    {
      "epoch": 0.2157439119764839,
      "grad_norm": 0.5984110236167908,
      "learning_rate": 4.447388950881625e-05,
      "loss": 0.4293,
      "step": 4000
    },
    {
      "epoch": 0.2427119009735444,
      "grad_norm": 0.29806196689605713,
      "learning_rate": 4.307739774881878e-05,
      "loss": 0.4347,
      "step": 4500
    },
    {
      "epoch": 0.2696798899706049,
      "grad_norm": 0.5836197137832642,
      "learning_rate": 4.1551219001346e-05,
      "loss": 0.4303,
      "step": 5000
    },
    {
      "epoch": 0.29664787896766537,
      "grad_norm": 0.35174188017845154,
      "learning_rate": 3.990630205044629e-05,
      "loss": 0.4335,
      "step": 5500
    },
    {
      "epoch": 0.32361586796472586,
      "grad_norm": 0.529833197593689,
      "learning_rate": 3.815804970461473e-05,
      "loss": 0.4307,
      "step": 6000
    },
    {
      "epoch": 0.35058385696178634,
      "grad_norm": 0.2829456329345703,
      "learning_rate": 3.6312001077632294e-05,
      "loss": 0.433,
      "step": 6500
    },
    {
      "epoch": 0.37755184595884683,
      "grad_norm": 0.3882625102996826,
      "learning_rate": 3.438480032010211e-05,
      "loss": 0.4305,
      "step": 7000
    },
    {
      "epoch": 0.4045198349559073,
      "grad_norm": 0.4895012378692627,
      "learning_rate": 3.2390273142116814e-05,
      "loss": 0.4292,
      "step": 7500
    },
    {
      "epoch": 0.4314878239529678,
      "grad_norm": 0.4984913468360901,
      "learning_rate": 3.034272825252622e-05,
      "loss": 0.4271,
      "step": 8000
    },
    {
      "epoch": 0.4584558129500283,
      "grad_norm": 0.4299156367778778,
      "learning_rate": 2.8256854708469055e-05,
      "loss": 0.4265,
      "step": 8500
    },
    {
      "epoch": 0.4854238019470888,
      "grad_norm": 0.44763749837875366,
      "learning_rate": 2.6147616536291464e-05,
      "loss": 0.425,
      "step": 9000
    },
    {
      "epoch": 0.5123917909441493,
      "grad_norm": 0.6412510275840759,
      "learning_rate": 2.4030145379840563e-05,
      "loss": 0.4263,
      "step": 9500
    },
    {
      "epoch": 0.5393597799412098,
      "grad_norm": 0.884003758430481,
      "learning_rate": 2.1919631946272402e-05,
      "loss": 0.4225,
      "step": 10000
    },
    {
      "epoch": 0.5663277689382703,
      "grad_norm": 0.4416724443435669,
      "learning_rate": 1.9831217028140688e-05,
      "loss": 0.4264,
      "step": 10500
    },
    {
      "epoch": 0.5932957579353307,
      "grad_norm": 0.5343862175941467,
      "learning_rate": 1.777988288357209e-05,
      "loss": 0.4242,
      "step": 11000
    },
    {
      "epoch": 0.6202637469323913,
      "grad_norm": 0.5542997717857361,
      "learning_rate": 1.578034575376518e-05,
      "loss": 0.4223,
      "step": 11500
    },
    {
      "epoch": 0.6472317359294517,
      "grad_norm": 0.8904162049293518,
      "learning_rate": 1.3850741762328944e-05,
      "loss": 0.4209,
      "step": 12000
    },
    {
      "epoch": 0.6741997249265123,
      "grad_norm": 0.4040282368659973,
      "learning_rate": 1.1997184612520374e-05,
      "loss": 0.4232,
      "step": 12500
    },
    {
      "epoch": 0.7011677139235727,
      "grad_norm": 0.5565162897109985,
      "learning_rate": 1.0236909470428333e-05,
      "loss": 0.4229,
      "step": 13000
    },
    {
      "epoch": 0.7281357029206332,
      "grad_norm": 0.6723429560661316,
      "learning_rate": 8.585739531996178e-06,
      "loss": 0.4187,
      "step": 13500
    },
    {
      "epoch": 0.7551036919176937,
      "grad_norm": 0.35649460554122925,
      "learning_rate": 7.048906317823642e-06,
      "loss": 0.4244,
      "step": 14000
    },
    {
      "epoch": 0.7820716809147542,
      "grad_norm": 0.3733614683151245,
      "learning_rate": 5.640853987596667e-06,
      "loss": 0.4178,
      "step": 14500
    },
    {
      "epoch": 0.8090396699118146,
      "grad_norm": 0.889401912689209,
      "learning_rate": 4.371683888171277e-06,
      "loss": 0.4195,
      "step": 15000
    },
    {
      "epoch": 0.8360076589088752,
      "grad_norm": 0.4235946536064148,
      "learning_rate": 3.250501027307715e-06,
      "loss": 0.4203,
      "step": 15500
    },
    {
      "epoch": 0.8629756479059356,
      "grad_norm": 0.5250910520553589,
      "learning_rate": 2.287118546736572e-06,
      "loss": 0.4187,
      "step": 16000
    },
    {
      "epoch": 0.8899436369029962,
      "grad_norm": 0.5213350057601929,
      "learning_rate": 1.4845888005343062e-06,
      "loss": 0.4202,
      "step": 16500
    },
    {
      "epoch": 0.9169116259000566,
      "grad_norm": 0.4989272356033325,
      "learning_rate": 8.507582708938533e-07,
      "loss": 0.4221,
      "step": 17000
    },
    {
      "epoch": 0.9438796148971171,
      "grad_norm": 0.4094185531139374,
      "learning_rate": 3.901740487793598e-07,
      "loss": 0.4217,
      "step": 17500
    },
    {
      "epoch": 0.9708476038941776,
      "grad_norm": 0.5710214972496033,
      "learning_rate": 1.0614035867460847e-07,
      "loss": 0.4209,
      "step": 18000
    },
    {
      "epoch": 0.9978155928912381,
      "grad_norm": 0.5618287920951843,
      "learning_rate": 6.94854124816402e-10,
      "loss": 0.4205,
      "step": 18500
    },
    {
      "epoch": 0.999973032011003,
      "step": 18540,
      "total_flos": 7.616663384064e+17,
      "train_loss": 0.3924344686242755,
      "train_runtime": 20071.1732,
      "train_samples_per_second": 3.695,
      "train_steps_per_second": 0.924
    }
  ],
  "logging_steps": 500,
  "max_steps": 18540,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 7.616663384064e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}