{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 12.0,
  "eval_steps": 500,
  "global_step": 3000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.2,
      "grad_norm": 2.671468734741211,
      "learning_rate": 6.125e-05,
      "loss": 8.0449,
      "step": 50
    },
    {
      "epoch": 0.4,
      "grad_norm": 1.9384660720825195,
      "learning_rate": 0.00012375,
      "loss": 6.1065,
      "step": 100
    },
    {
      "epoch": 0.6,
      "grad_norm": 1.7404013872146606,
      "learning_rate": 0.00018625,
      "loss": 5.552,
      "step": 150
    },
    {
      "epoch": 0.8,
      "grad_norm": 1.5962367057800293,
      "learning_rate": 0.00024875,
      "loss": 5.3272,
      "step": 200
    },
    {
      "epoch": 1.0,
      "grad_norm": 1.6055867671966553,
      "learning_rate": 0.000245625,
      "loss": 5.1701,
      "step": 250
    },
    {
      "epoch": 1.2,
      "grad_norm": 1.5786716938018799,
      "learning_rate": 0.0002411607142857143,
      "loss": 4.7686,
      "step": 300
    },
    {
      "epoch": 1.4,
      "grad_norm": 1.5948882102966309,
      "learning_rate": 0.00023669642857142856,
      "loss": 4.6684,
      "step": 350
    },
    {
      "epoch": 1.6,
      "grad_norm": 1.5991402864456177,
      "learning_rate": 0.00023223214285714286,
      "loss": 4.6017,
      "step": 400
    },
    {
      "epoch": 1.8,
      "grad_norm": 1.4955918788909912,
      "learning_rate": 0.00022776785714285713,
      "loss": 4.549,
      "step": 450
    },
    {
      "epoch": 2.0,
      "grad_norm": 1.5773422718048096,
      "learning_rate": 0.00022330357142857143,
      "loss": 4.4926,
      "step": 500
    },
    {
      "epoch": 2.2,
      "grad_norm": 1.5831668376922607,
      "learning_rate": 0.00021883928571428572,
      "loss": 4.1386,
      "step": 550
    },
    {
      "epoch": 2.4,
      "grad_norm": 1.3561625480651855,
      "learning_rate": 0.00021437500000000002,
      "loss": 4.1139,
      "step": 600
    },
    {
      "epoch": 2.6,
      "grad_norm": 1.4930239915847778,
      "learning_rate": 0.0002099107142857143,
      "loss": 4.1189,
      "step": 650
    },
    {
      "epoch": 2.8,
      "grad_norm": 1.5223215818405151,
      "learning_rate": 0.00020544642857142856,
      "loss": 4.0464,
      "step": 700
    },
    {
      "epoch": 3.0,
      "grad_norm": 1.6128135919570923,
      "learning_rate": 0.00020098214285714286,
      "loss": 4.0405,
      "step": 750
    },
    {
      "epoch": 3.2,
      "grad_norm": 1.5877256393432617,
      "learning_rate": 0.00019651785714285713,
      "loss": 3.7492,
      "step": 800
    },
    {
      "epoch": 3.4,
      "grad_norm": 1.5449103116989136,
      "learning_rate": 0.00019205357142857143,
      "loss": 3.8028,
      "step": 850
    },
    {
      "epoch": 3.6,
      "grad_norm": 1.4588514566421509,
      "learning_rate": 0.00018758928571428572,
      "loss": 3.752,
      "step": 900
    },
    {
      "epoch": 3.8,
      "grad_norm": 1.4356666803359985,
      "learning_rate": 0.00018312500000000002,
      "loss": 3.7031,
      "step": 950
    },
    {
      "epoch": 4.0,
      "grad_norm": 1.5264209508895874,
      "learning_rate": 0.0001786607142857143,
      "loss": 3.7287,
      "step": 1000
    },
    {
      "epoch": 4.2,
      "grad_norm": 1.351216197013855,
      "learning_rate": 0.00017419642857142856,
      "loss": 3.4962,
      "step": 1050
    },
    {
      "epoch": 4.4,
      "grad_norm": 1.6168186664581299,
      "learning_rate": 0.00016973214285714286,
      "loss": 3.5006,
      "step": 1100
    },
    {
      "epoch": 4.6,
      "grad_norm": 1.6266807317733765,
      "learning_rate": 0.00016526785714285713,
      "loss": 3.4669,
      "step": 1150
    },
    {
      "epoch": 4.8,
      "grad_norm": 1.509149432182312,
      "learning_rate": 0.00016080357142857142,
      "loss": 3.5044,
      "step": 1200
    },
    {
      "epoch": 5.0,
      "grad_norm": 1.610813856124878,
      "learning_rate": 0.00015633928571428572,
      "loss": 3.4626,
      "step": 1250
    },
    {
      "epoch": 5.2,
      "grad_norm": 1.3284097909927368,
      "learning_rate": 0.00015187500000000002,
      "loss": 3.2758,
      "step": 1300
    },
    {
      "epoch": 5.4,
      "grad_norm": 1.5338636636734009,
      "learning_rate": 0.0001474107142857143,
      "loss": 3.3102,
      "step": 1350
    },
    {
      "epoch": 5.6,
      "grad_norm": 1.4522225856781006,
      "learning_rate": 0.00014294642857142856,
      "loss": 3.2593,
      "step": 1400
    },
    {
      "epoch": 5.8,
      "grad_norm": 1.6232526302337646,
      "learning_rate": 0.00013848214285714286,
      "loss": 3.2785,
      "step": 1450
    },
    {
      "epoch": 6.0,
      "grad_norm": 1.6043927669525146,
      "learning_rate": 0.00013401785714285713,
      "loss": 3.3056,
      "step": 1500
    },
    {
      "epoch": 6.2,
      "grad_norm": 1.6095658540725708,
      "learning_rate": 0.00012955357142857142,
      "loss": 3.1076,
      "step": 1550
    },
    {
      "epoch": 6.4,
      "grad_norm": 1.4529067277908325,
      "learning_rate": 0.00012508928571428572,
      "loss": 3.1206,
      "step": 1600
    },
    {
      "epoch": 6.6,
      "grad_norm": 1.7432512044906616,
      "learning_rate": 0.000120625,
      "loss": 3.1245,
      "step": 1650
    },
    {
      "epoch": 6.8,
      "grad_norm": 1.7623839378356934,
      "learning_rate": 0.00011616071428571429,
      "loss": 3.1437,
      "step": 1700
    },
    {
      "epoch": 7.0,
      "grad_norm": 1.537539005279541,
      "learning_rate": 0.00011169642857142857,
      "loss": 3.121,
      "step": 1750
    },
    {
      "epoch": 7.2,
      "grad_norm": 1.4343411922454834,
      "learning_rate": 0.00010723214285714286,
      "loss": 2.9752,
      "step": 1800
    },
    {
      "epoch": 7.4,
      "grad_norm": 1.4659862518310547,
      "learning_rate": 0.00010276785714285715,
      "loss": 2.9755,
      "step": 1850
    },
    {
      "epoch": 7.6,
      "grad_norm": 1.4027365446090698,
      "learning_rate": 9.830357142857144e-05,
      "loss": 2.9823,
      "step": 1900
    },
    {
      "epoch": 7.8,
      "grad_norm": 1.6034783124923706,
      "learning_rate": 9.383928571428571e-05,
      "loss": 2.9971,
      "step": 1950
    },
    {
      "epoch": 8.0,
      "grad_norm": 1.9349607229232788,
      "learning_rate": 8.9375e-05,
      "loss": 3.0408,
      "step": 2000
    },
    {
      "epoch": 8.2,
      "grad_norm": 1.5146081447601318,
      "learning_rate": 8.491071428571429e-05,
      "loss": 2.8761,
      "step": 2050
    },
    {
      "epoch": 8.4,
      "grad_norm": 1.6080121994018555,
      "learning_rate": 8.044642857142857e-05,
      "loss": 2.8688,
      "step": 2100
    },
    {
      "epoch": 8.6,
      "grad_norm": 1.4734200239181519,
      "learning_rate": 7.598214285714286e-05,
      "loss": 2.8778,
      "step": 2150
    },
    {
      "epoch": 8.8,
      "grad_norm": 1.5679528713226318,
      "learning_rate": 7.151785714285715e-05,
      "loss": 2.9088,
      "step": 2200
    },
    {
      "epoch": 9.0,
      "grad_norm": 1.4920151233673096,
      "learning_rate": 6.705357142857144e-05,
      "loss": 2.9162,
      "step": 2250
    },
    {
      "epoch": 9.2,
      "grad_norm": 1.6481536626815796,
      "learning_rate": 6.25892857142857e-05,
      "loss": 2.8056,
      "step": 2300
    },
    {
      "epoch": 9.4,
      "grad_norm": 1.4848685264587402,
      "learning_rate": 5.8125e-05,
      "loss": 2.796,
      "step": 2350
    },
    {
      "epoch": 9.6,
      "grad_norm": 1.376192569732666,
      "learning_rate": 5.366071428571429e-05,
      "loss": 2.7904,
      "step": 2400
    },
    {
      "epoch": 9.8,
      "grad_norm": 1.557061791419983,
      "learning_rate": 4.919642857142857e-05,
      "loss": 2.8336,
      "step": 2450
    },
    {
      "epoch": 10.0,
      "grad_norm": 1.642156958580017,
      "learning_rate": 4.473214285714286e-05,
      "loss": 2.8048,
      "step": 2500
    },
    {
      "epoch": 10.2,
      "grad_norm": 1.7578301429748535,
      "learning_rate": 4.026785714285714e-05,
      "loss": 2.718,
      "step": 2550
    },
    {
      "epoch": 10.4,
      "grad_norm": 1.5210566520690918,
      "learning_rate": 3.580357142857143e-05,
      "loss": 2.733,
      "step": 2600
    },
    {
      "epoch": 10.6,
      "grad_norm": 1.5723469257354736,
      "learning_rate": 3.133928571428572e-05,
      "loss": 2.7494,
      "step": 2650
    },
    {
      "epoch": 10.8,
      "grad_norm": 1.3110719919204712,
      "learning_rate": 2.6875e-05,
      "loss": 2.7616,
      "step": 2700
    },
    {
      "epoch": 11.0,
      "grad_norm": 1.393686056137085,
      "learning_rate": 2.2410714285714286e-05,
      "loss": 2.7552,
      "step": 2750
    },
    {
      "epoch": 11.2,
      "grad_norm": 1.5743101835250854,
      "learning_rate": 1.7946428571428573e-05,
      "loss": 2.6776,
      "step": 2800
    },
    {
      "epoch": 11.4,
      "grad_norm": 1.7243106365203857,
      "learning_rate": 1.3482142857142857e-05,
      "loss": 2.7079,
      "step": 2850
    },
    {
      "epoch": 11.6,
      "grad_norm": 1.5077002048492432,
      "learning_rate": 9.017857142857144e-06,
      "loss": 2.6959,
      "step": 2900
    },
    {
      "epoch": 11.8,
      "grad_norm": 1.3862125873565674,
      "learning_rate": 4.553571428571429e-06,
      "loss": 2.7095,
      "step": 2950
    },
    {
      "epoch": 12.0,
      "grad_norm": 1.383197546005249,
      "learning_rate": 8.928571428571429e-08,
      "loss": 2.7034,
      "step": 3000
    }
  ],
  "logging_steps": 50,
  "max_steps": 3000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 12,
  "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": 2093469401088000.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}