{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8942544153811759,
  "eval_steps": 50,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.017885088307623517,
      "grad_norm": 0.27167433500289917,
      "learning_rate": 5.9523809523809525e-06,
      "loss": 1.9206,
      "step": 10
    },
    {
      "epoch": 0.035770176615247035,
      "grad_norm": 0.2490677386522293,
      "learning_rate": 1.1904761904761905e-05,
      "loss": 1.8864,
      "step": 20
    },
    {
      "epoch": 0.05365526492287056,
      "grad_norm": 0.23479315638542175,
      "learning_rate": 1.785714285714286e-05,
      "loss": 1.8092,
      "step": 30
    },
    {
      "epoch": 0.07154035323049407,
      "grad_norm": 0.2516893446445465,
      "learning_rate": 2.380952380952381e-05,
      "loss": 1.6878,
      "step": 40
    },
    {
      "epoch": 0.0894254415381176,
      "grad_norm": 0.30081456899642944,
      "learning_rate": 2.9761904761904762e-05,
      "loss": 1.4673,
      "step": 50
    },
    {
      "epoch": 0.0894254415381176,
      "eval_loss": 1.3079078197479248,
      "eval_runtime": 340.2145,
      "eval_samples_per_second": 5.843,
      "eval_steps_per_second": 2.922,
      "step": 50
    },
    {
      "epoch": 0.10731052984574112,
      "grad_norm": 0.40885159373283386,
      "learning_rate": 3.571428571428572e-05,
      "loss": 1.1216,
      "step": 60
    },
    {
      "epoch": 0.12519561815336464,
      "grad_norm": 0.34105631709098816,
      "learning_rate": 4.166666666666667e-05,
      "loss": 0.623,
      "step": 70
    },
    {
      "epoch": 0.14308070646098814,
      "grad_norm": 0.08575189858675003,
      "learning_rate": 4.761904761904762e-05,
      "loss": 0.321,
      "step": 80
    },
    {
      "epoch": 0.16096579476861167,
      "grad_norm": 0.06351594626903534,
      "learning_rate": 5.3571428571428575e-05,
      "loss": 0.2671,
      "step": 90
    },
    {
      "epoch": 0.1788508830762352,
      "grad_norm": 0.044943634420633316,
      "learning_rate": 5.9523809523809524e-05,
      "loss": 0.2634,
      "step": 100
    },
    {
      "epoch": 0.1788508830762352,
      "eval_loss": 0.2529277801513672,
      "eval_runtime": 340.0791,
      "eval_samples_per_second": 5.846,
      "eval_steps_per_second": 2.923,
      "step": 100
    },
    {
      "epoch": 0.1967359713838587,
      "grad_norm": 0.04525942727923393,
      "learning_rate": 6.547619047619048e-05,
      "loss": 0.2476,
      "step": 110
    },
    {
      "epoch": 0.21462105969148224,
      "grad_norm": 0.03497561439871788,
      "learning_rate": 7.142857142857143e-05,
      "loss": 0.2364,
      "step": 120
    },
    {
      "epoch": 0.23250614799910574,
      "grad_norm": 0.03806141018867493,
      "learning_rate": 7.738095238095239e-05,
      "loss": 0.2375,
      "step": 130
    },
    {
      "epoch": 0.25039123630672927,
      "grad_norm": 0.03912373259663582,
      "learning_rate": 8.333333333333334e-05,
      "loss": 0.2458,
      "step": 140
    },
    {
      "epoch": 0.2682763246143528,
      "grad_norm": 0.038528475910425186,
      "learning_rate": 8.92857142857143e-05,
      "loss": 0.2356,
      "step": 150
    },
    {
      "epoch": 0.2682763246143528,
      "eval_loss": 0.2338634878396988,
      "eval_runtime": 340.1092,
      "eval_samples_per_second": 5.845,
      "eval_steps_per_second": 2.923,
      "step": 150
    },
    {
      "epoch": 0.2861614129219763,
      "grad_norm": 0.033717814832925797,
      "learning_rate": 9.523809523809524e-05,
      "loss": 0.2328,
      "step": 160
    },
    {
      "epoch": 0.3040465012295998,
      "grad_norm": 0.034611135721206665,
      "learning_rate": 9.98674618952949e-05,
      "loss": 0.232,
      "step": 170
    },
    {
      "epoch": 0.32193158953722334,
      "grad_norm": 0.03772770240902901,
      "learning_rate": 9.920477137176939e-05,
      "loss": 0.2321,
      "step": 180
    },
    {
      "epoch": 0.33981667784484687,
      "grad_norm": 0.03764208406209946,
      "learning_rate": 9.854208084824388e-05,
      "loss": 0.2252,
      "step": 190
    },
    {
      "epoch": 0.3577017661524704,
      "grad_norm": 0.04233132675290108,
      "learning_rate": 9.787939032471835e-05,
      "loss": 0.2255,
      "step": 200
    },
    {
      "epoch": 0.3577017661524704,
      "eval_loss": 0.22211842238903046,
      "eval_runtime": 340.2159,
      "eval_samples_per_second": 5.843,
      "eval_steps_per_second": 2.922,
      "step": 200
    },
    {
      "epoch": 0.3755868544600939,
      "grad_norm": 0.04666154831647873,
      "learning_rate": 9.721669980119285e-05,
      "loss": 0.2221,
      "step": 210
    },
    {
      "epoch": 0.3934719427677174,
      "grad_norm": 0.05546770244836807,
      "learning_rate": 9.655400927766734e-05,
      "loss": 0.2241,
      "step": 220
    },
    {
      "epoch": 0.41135703107534094,
      "grad_norm": 0.04022465646266937,
      "learning_rate": 9.589131875414182e-05,
      "loss": 0.2144,
      "step": 230
    },
    {
      "epoch": 0.42924211938296447,
      "grad_norm": 0.041572101414203644,
      "learning_rate": 9.52286282306163e-05,
      "loss": 0.2113,
      "step": 240
    },
    {
      "epoch": 0.44712720769058795,
      "grad_norm": 0.039912398904561996,
      "learning_rate": 9.45659377070908e-05,
      "loss": 0.2143,
      "step": 250
    },
    {
      "epoch": 0.44712720769058795,
      "eval_loss": 0.21348513662815094,
      "eval_runtime": 339.9419,
      "eval_samples_per_second": 5.848,
      "eval_steps_per_second": 2.924,
      "step": 250
    },
    {
      "epoch": 0.4650122959982115,
      "grad_norm": 0.04531717300415039,
      "learning_rate": 9.390324718356528e-05,
      "loss": 0.2078,
      "step": 260
    },
    {
      "epoch": 0.482897384305835,
      "grad_norm": 0.05076432228088379,
      "learning_rate": 9.324055666003977e-05,
      "loss": 0.2105,
      "step": 270
    },
    {
      "epoch": 0.5007824726134585,
      "grad_norm": 0.05077740550041199,
      "learning_rate": 9.257786613651425e-05,
      "loss": 0.2102,
      "step": 280
    },
    {
      "epoch": 0.518667560921082,
      "grad_norm": 0.05294053629040718,
      "learning_rate": 9.191517561298874e-05,
      "loss": 0.2116,
      "step": 290
    },
    {
      "epoch": 0.5365526492287056,
      "grad_norm": 0.04222816973924637,
      "learning_rate": 9.125248508946323e-05,
      "loss": 0.2004,
      "step": 300
    },
    {
      "epoch": 0.5365526492287056,
      "eval_loss": 0.205940380692482,
      "eval_runtime": 340.0032,
      "eval_samples_per_second": 5.847,
      "eval_steps_per_second": 2.924,
      "step": 300
    },
    {
      "epoch": 0.5544377375363291,
      "grad_norm": 0.06563922017812729,
      "learning_rate": 9.058979456593771e-05,
      "loss": 0.2024,
      "step": 310
    },
    {
      "epoch": 0.5723228258439526,
      "grad_norm": 0.06504207849502563,
      "learning_rate": 8.99271040424122e-05,
      "loss": 0.2076,
      "step": 320
    },
    {
      "epoch": 0.5902079141515761,
      "grad_norm": 0.055658888071775436,
      "learning_rate": 8.926441351888669e-05,
      "loss": 0.2026,
      "step": 330
    },
    {
      "epoch": 0.6080930024591996,
      "grad_norm": 0.0635204091668129,
      "learning_rate": 8.860172299536117e-05,
      "loss": 0.199,
      "step": 340
    },
    {
      "epoch": 0.6259780907668232,
      "grad_norm": 0.06404862552881241,
      "learning_rate": 8.793903247183566e-05,
      "loss": 0.2048,
      "step": 350
    },
    {
      "epoch": 0.6259780907668232,
      "eval_loss": 0.1987379640340805,
      "eval_runtime": 339.7556,
      "eval_samples_per_second": 5.851,
      "eval_steps_per_second": 2.926,
      "step": 350
    },
    {
      "epoch": 0.6438631790744467,
      "grad_norm": 0.061456065624952316,
      "learning_rate": 8.727634194831014e-05,
      "loss": 0.2002,
      "step": 360
    },
    {
      "epoch": 0.6617482673820702,
      "grad_norm": 0.059758663177490234,
      "learning_rate": 8.661365142478463e-05,
      "loss": 0.1928,
      "step": 370
    },
    {
      "epoch": 0.6796333556896937,
      "grad_norm": 0.07035389542579651,
      "learning_rate": 8.595096090125912e-05,
      "loss": 0.1982,
      "step": 380
    },
    {
      "epoch": 0.6975184439973172,
      "grad_norm": 0.05884738266468048,
      "learning_rate": 8.52882703777336e-05,
      "loss": 0.199,
      "step": 390
    },
    {
      "epoch": 0.7154035323049408,
      "grad_norm": 0.07666763663291931,
      "learning_rate": 8.462557985420809e-05,
      "loss": 0.1901,
      "step": 400
    },
    {
      "epoch": 0.7154035323049408,
      "eval_loss": 0.19112130999565125,
      "eval_runtime": 339.7085,
      "eval_samples_per_second": 5.852,
      "eval_steps_per_second": 2.926,
      "step": 400
    },
    {
      "epoch": 0.7332886206125643,
      "grad_norm": 0.07783893495798111,
      "learning_rate": 8.396288933068258e-05,
      "loss": 0.1903,
      "step": 410
    },
    {
      "epoch": 0.7511737089201878,
      "grad_norm": 0.06356322020292282,
      "learning_rate": 8.330019880715706e-05,
      "loss": 0.189,
      "step": 420
    },
    {
      "epoch": 0.7690587972278113,
      "grad_norm": 0.06573337316513062,
      "learning_rate": 8.263750828363155e-05,
      "loss": 0.1921,
      "step": 430
    },
    {
      "epoch": 0.7869438855354348,
      "grad_norm": 0.0807296559214592,
      "learning_rate": 8.197481776010603e-05,
      "loss": 0.1826,
      "step": 440
    },
    {
      "epoch": 0.8048289738430584,
      "grad_norm": 0.07666200399398804,
      "learning_rate": 8.131212723658052e-05,
      "loss": 0.1835,
      "step": 450
    },
    {
      "epoch": 0.8048289738430584,
      "eval_loss": 0.18313755095005035,
      "eval_runtime": 340.1916,
      "eval_samples_per_second": 5.844,
      "eval_steps_per_second": 2.922,
      "step": 450
    },
    {
      "epoch": 0.8227140621506819,
      "grad_norm": 0.09144561737775803,
      "learning_rate": 8.064943671305501e-05,
      "loss": 0.1813,
      "step": 460
    },
    {
      "epoch": 0.8405991504583054,
      "grad_norm": 0.10572754591703415,
      "learning_rate": 7.99867461895295e-05,
      "loss": 0.1776,
      "step": 470
    },
    {
      "epoch": 0.8584842387659289,
      "grad_norm": 0.08453221619129181,
      "learning_rate": 7.932405566600398e-05,
      "loss": 0.1809,
      "step": 480
    },
    {
      "epoch": 0.8763693270735524,
      "grad_norm": 0.08854762464761734,
      "learning_rate": 7.866136514247847e-05,
      "loss": 0.176,
      "step": 490
    },
    {
      "epoch": 0.8942544153811759,
      "grad_norm": 0.09418456256389618,
      "learning_rate": 7.799867461895295e-05,
      "loss": 0.1749,
      "step": 500
    },
    {
      "epoch": 0.8942544153811759,
      "eval_loss": 0.17343606054782867,
      "eval_runtime": 340.1945,
      "eval_samples_per_second": 5.844,
      "eval_steps_per_second": 2.922,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 1677,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.571356521652814e+18,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}