{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 25000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02,
      "grad_norm": 1.1523245573043823,
      "learning_rate": 0.00019959999999999997,
      "loss": 0.4793,
      "step": 500
    },
    {
      "epoch": 0.04,
      "grad_norm": 1.207442283630371,
      "learning_rate": 0.0002999219633608753,
      "loss": 0.365,
      "step": 1000
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.608832836151123,
      "learning_rate": 0.0002992943970692375,
      "loss": 0.3408,
      "step": 1500
    },
    {
      "epoch": 0.08,
      "grad_norm": 1.6748807430267334,
      "learning_rate": 0.0002980406381928192,
      "loss": 0.3432,
      "step": 2000
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.1549451351165771,
      "learning_rate": 0.0002961659454320601,
      "loss": 0.3337,
      "step": 2500
    },
    {
      "epoch": 0.12,
      "grad_norm": 1.3943244218826294,
      "learning_rate": 0.0002936781818999006,
      "loss": 0.328,
      "step": 3000
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.8221294283866882,
      "learning_rate": 0.0002905877821411536,
      "loss": 0.3184,
      "step": 3500
    },
    {
      "epoch": 0.16,
      "grad_norm": 0.8499279022216797,
      "learning_rate": 0.00028690770836639715,
      "loss": 0.312,
      "step": 4000
    },
    {
      "epoch": 0.18,
      "grad_norm": 1.1005589962005615,
      "learning_rate": 0.0002826533960839586,
      "loss": 0.3175,
      "step": 4500
    },
    {
      "epoch": 0.2,
      "grad_norm": 1.239676594734192,
      "learning_rate": 0.0002778426893580286,
      "loss": 0.3139,
      "step": 5000
    },
    {
      "epoch": 0.22,
      "grad_norm": 0.5692813396453857,
      "learning_rate": 0.00027249576596445455,
      "loss": 0.3065,
      "step": 5500
    },
    {
      "epoch": 0.24,
      "grad_norm": 0.6223649382591248,
      "learning_rate": 0.00026663505275813633,
      "loss": 0.3015,
      "step": 6000
    },
    {
      "epoch": 0.26,
      "grad_norm": 1.6326464414596558,
      "learning_rate": 0.0002602851316070032,
      "loss": 0.298,
      "step": 6500
    },
    {
      "epoch": 0.28,
      "grad_norm": 0.44571417570114136,
      "learning_rate": 0.0002534726362871166,
      "loss": 0.3043,
      "step": 7000
    },
    {
      "epoch": 0.3,
      "grad_norm": 0.7266321182250977,
      "learning_rate": 0.00024622614077135773,
      "loss": 0.2949,
      "step": 7500
    },
    {
      "epoch": 0.32,
      "grad_norm": 1.133889079093933,
      "learning_rate": 0.00023857603938025494,
      "loss": 0.2826,
      "step": 8000
    },
    {
      "epoch": 0.34,
      "grad_norm": 0.7410082817077637,
      "learning_rate": 0.00023055441929764077,
      "loss": 0.2836,
      "step": 8500
    },
    {
      "epoch": 0.36,
      "grad_norm": 0.5899648070335388,
      "learning_rate": 0.00022219492598585185,
      "loss": 0.2868,
      "step": 9000
    },
    {
      "epoch": 0.38,
      "grad_norm": 1.3609607219696045,
      "learning_rate": 0.00021353262206496714,
      "loss": 0.3002,
      "step": 9500
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.7143217325210571,
      "learning_rate": 0.0002046038402479944,
      "loss": 0.2734,
      "step": 10000
    },
    {
      "epoch": 0.42,
      "grad_norm": 0.9960472583770752,
      "learning_rate": 0.0001954460309488451,
      "loss": 0.2824,
      "step": 10500
    },
    {
      "epoch": 0.44,
      "grad_norm": 0.9902260899543762,
      "learning_rate": 0.00018609760520228364,
      "loss": 0.2802,
      "step": 11000
    },
    {
      "epoch": 0.46,
      "grad_norm": 1.1902357339859009,
      "learning_rate": 0.00017659777355469886,
      "loss": 0.2848,
      "step": 11500
    },
    {
      "epoch": 0.48,
      "grad_norm": 0.7066996097564697,
      "learning_rate": 0.0001669863816014457,
      "loss": 0.2723,
      "step": 12000
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.8586142063140869,
      "learning_rate": 0.00015730374286057098,
      "loss": 0.2661,
      "step": 12500
    },
    {
      "epoch": 0.52,
      "grad_norm": 1.3139828443527222,
      "learning_rate": 0.00014759046968390891,
      "loss": 0.27,
      "step": 13000
    },
    {
      "epoch": 0.54,
      "grad_norm": 2.092033624649048,
      "learning_rate": 0.00013788730291476348,
      "loss": 0.2626,
      "step": 13500
    },
    {
      "epoch": 0.56,
      "grad_norm": 0.6759353876113892,
      "learning_rate": 0.00012823494100665345,
      "loss": 0.2713,
      "step": 14000
    },
    {
      "epoch": 0.58,
      "grad_norm": 0.7745094299316406,
      "learning_rate": 0.0001186738693198545,
      "loss": 0.2659,
      "step": 14500
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.1789864301681519,
      "learning_rate": 0.00010924419031172836,
      "loss": 0.2621,
      "step": 15000
    },
    {
      "epoch": 0.62,
      "grad_norm": 0.7983564138412476,
      "learning_rate": 9.998545533308028e-05,
      "loss": 0.2485,
      "step": 15500
    },
    {
      "epoch": 0.64,
      "grad_norm": 2.2566275596618652,
      "learning_rate": 9.093649873604878e-05,
      "loss": 0.2499,
      "step": 16000
    },
    {
      "epoch": 0.66,
      "grad_norm": 2.405757188796997,
      "learning_rate": 8.213527498933654e-05,
      "loss": 0.2648,
      "step": 16500
    },
    {
      "epoch": 0.68,
      "grad_norm": 0.706387996673584,
      "learning_rate": 7.361869948397888e-05,
      "loss": 0.248,
      "step": 17000
    },
    {
      "epoch": 0.7,
      "grad_norm": 0.9889776110649109,
      "learning_rate": 6.542249369736452e-05,
      "loss": 0.2533,
      "step": 17500
    },
    {
      "epoch": 0.72,
      "grad_norm": 0.3792021572589874,
      "learning_rate": 5.758103536494548e-05,
      "loss": 0.2464,
      "step": 18000
    },
    {
      "epoch": 0.74,
      "grad_norm": 1.4570865631103516,
      "learning_rate": 5.012721428806742e-05,
      "loss": 0.2469,
      "step": 18500
    },
    {
      "epoch": 0.76,
      "grad_norm": 0.3031163811683655,
      "learning_rate": 4.30922943827128e-05,
      "loss": 0.2563,
      "step": 19000
    },
    {
      "epoch": 0.78,
      "grad_norm": 0.5329792499542236,
      "learning_rate": 3.6505782547772205e-05,
      "loss": 0.2409,
      "step": 19500
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.900152325630188,
      "learning_rate": 3.0395304902856126e-05,
      "loss": 0.2413,
      "step": 20000
    },
    {
      "epoch": 0.82,
      "grad_norm": 0.79344642162323,
      "learning_rate": 2.4786490914748508e-05,
      "loss": 0.241,
      "step": 20500
    },
    {
      "epoch": 0.84,
      "grad_norm": 2.6573524475097656,
      "learning_rate": 1.970286589851618e-05,
      "loss": 0.2447,
      "step": 21000
    },
    {
      "epoch": 0.86,
      "grad_norm": 0.92716383934021,
      "learning_rate": 1.516575234416183e-05,
      "loss": 0.2513,
      "step": 21500
    },
    {
      "epoch": 0.88,
      "grad_norm": 0.8475908041000366,
      "learning_rate": 1.1194180482690935e-05,
      "loss": 0.2425,
      "step": 22000
    },
    {
      "epoch": 0.9,
      "grad_norm": 0.6743385195732117,
      "learning_rate": 7.804808466709245e-06,
      "loss": 0.2372,
      "step": 22500
    },
    {
      "epoch": 0.92,
      "grad_norm": 0.7676027417182922,
      "learning_rate": 5.011852500341956e-06,
      "loss": 0.2429,
      "step": 23000
    },
    {
      "epoch": 0.94,
      "grad_norm": 2.600247621536255,
      "learning_rate": 2.827027211532812e-06,
      "loss": 0.2351,
      "step": 23500
    },
    {
      "epoch": 0.96,
      "grad_norm": 0.2377513349056244,
      "learning_rate": 1.2594965168235604e-06,
      "loss": 0.2464,
      "step": 24000
    },
    {
      "epoch": 0.98,
      "grad_norm": 3.111140012741089,
      "learning_rate": 3.1583518470324476e-07,
      "loss": 0.2387,
      "step": 24500
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.134462833404541,
      "learning_rate": 1.2587443087852533e-12,
      "loss": 0.2547,
      "step": 25000
    },
    {
      "epoch": 1.0,
      "step": 25000,
      "total_flos": 2.8066019659471258e+17,
      "train_loss": 0.2806466256713867,
      "train_runtime": 4375.9007,
      "train_samples_per_second": 5.713,
      "train_steps_per_second": 5.713
    }
  ],
  "logging_steps": 500,
  "max_steps": 25000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 12500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2.8066019659471258e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}