{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.0,
  "eval_steps": 30,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 0.318470299243927,
      "learning_rate": 9.987820251299122e-05,
      "loss": 0.4455,
      "step": 10
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 0.02355371043086052,
      "learning_rate": 9.951340343707852e-05,
      "loss": 0.0053,
      "step": 20
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 0.036702342331409454,
      "learning_rate": 9.890738003669029e-05,
      "loss": 0.004,
      "step": 30
    },
    {
      "epoch": 0.13333333333333333,
      "eval_loss": 0.0037715784274041653,
      "eval_runtime": 108.061,
      "eval_samples_per_second": 9.254,
      "eval_steps_per_second": 0.231,
      "step": 30
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 0.07428745925426483,
      "learning_rate": 9.806308479691595e-05,
      "loss": 0.0038,
      "step": 40
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 0.07172686606645584,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.0038,
      "step": 50
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 0.03130387142300606,
      "learning_rate": 9.567727288213005e-05,
      "loss": 0.0036,
      "step": 60
    },
    {
      "epoch": 0.26666666666666666,
      "eval_loss": 0.0035628757905215025,
      "eval_runtime": 108.1607,
      "eval_samples_per_second": 9.246,
      "eval_steps_per_second": 0.231,
      "step": 60
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 0.02135792188346386,
      "learning_rate": 9.414737964294636e-05,
      "loss": 0.0036,
      "step": 70
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 0.1094546914100647,
      "learning_rate": 9.24024048078213e-05,
      "loss": 0.0033,
      "step": 80
    },
    {
      "epoch": 0.4,
      "grad_norm": 0.15919151902198792,
      "learning_rate": 9.045084971874738e-05,
      "loss": 0.0035,
      "step": 90
    },
    {
      "epoch": 0.4,
      "eval_loss": 0.003310541156679392,
      "eval_runtime": 108.1107,
      "eval_samples_per_second": 9.25,
      "eval_steps_per_second": 0.231,
      "step": 90
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 0.024381157010793686,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.0029,
      "step": 100
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 0.05485767126083374,
      "learning_rate": 8.596699001693255e-05,
      "loss": 0.002,
      "step": 110
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 0.08088912814855576,
      "learning_rate": 8.345653031794292e-05,
      "loss": 0.0024,
      "step": 120
    },
    {
      "epoch": 0.5333333333333333,
      "eval_loss": 0.0021427080500870943,
      "eval_runtime": 108.1623,
      "eval_samples_per_second": 9.245,
      "eval_steps_per_second": 0.231,
      "step": 120
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 0.09581312537193298,
      "learning_rate": 8.07830737662829e-05,
      "loss": 0.0019,
      "step": 130
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 0.06600484997034073,
      "learning_rate": 7.795964517353735e-05,
      "loss": 0.0012,
      "step": 140
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 0.08135157078504562,
      "learning_rate": 7.500000000000001e-05,
      "loss": 0.0011,
      "step": 150
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.0011440212838351727,
      "eval_runtime": 108.1819,
      "eval_samples_per_second": 9.244,
      "eval_steps_per_second": 0.231,
      "step": 150
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 0.0257169920951128,
      "learning_rate": 7.191855733945387e-05,
      "loss": 0.0018,
      "step": 160
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 0.02252952568233013,
      "learning_rate": 6.873032967079561e-05,
      "loss": 0.0013,
      "step": 170
    },
    {
      "epoch": 0.8,
      "grad_norm": 0.015104785561561584,
      "learning_rate": 6.545084971874738e-05,
      "loss": 0.0011,
      "step": 180
    },
    {
      "epoch": 0.8,
      "eval_loss": 0.0008804052486084402,
      "eval_runtime": 108.241,
      "eval_samples_per_second": 9.239,
      "eval_steps_per_second": 0.231,
      "step": 180
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 0.037444427609443665,
      "learning_rate": 6.209609477998338e-05,
      "loss": 0.0009,
      "step": 190
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 0.041397638618946075,
      "learning_rate": 5.868240888334653e-05,
      "loss": 0.0009,
      "step": 200
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 0.04828115180134773,
      "learning_rate": 5.522642316338268e-05,
      "loss": 0.001,
      "step": 210
    },
    {
      "epoch": 0.9333333333333333,
      "eval_loss": 0.0008426142740063369,
      "eval_runtime": 108.1605,
      "eval_samples_per_second": 9.246,
      "eval_steps_per_second": 0.231,
      "step": 210
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 0.09075287729501724,
      "learning_rate": 5.174497483512506e-05,
      "loss": 0.0011,
      "step": 220
    },
    {
      "epoch": 1.0222222222222221,
      "grad_norm": 0.025804603472352028,
      "learning_rate": 4.825502516487497e-05,
      "loss": 0.0009,
      "step": 230
    },
    {
      "epoch": 1.0666666666666667,
      "grad_norm": 0.04228019714355469,
      "learning_rate": 4.477357683661734e-05,
      "loss": 0.0008,
      "step": 240
    },
    {
      "epoch": 1.0666666666666667,
      "eval_loss": 0.000761281349696219,
      "eval_runtime": 108.2466,
      "eval_samples_per_second": 9.238,
      "eval_steps_per_second": 0.231,
      "step": 240
    },
    {
      "epoch": 1.1111111111111112,
      "grad_norm": 0.07708187401294708,
      "learning_rate": 4.131759111665349e-05,
      "loss": 0.0008,
      "step": 250
    },
    {
      "epoch": 1.1555555555555554,
      "grad_norm": 0.090398870408535,
      "learning_rate": 3.790390522001662e-05,
      "loss": 0.0007,
      "step": 260
    },
    {
      "epoch": 1.2,
      "grad_norm": 0.10483791679143906,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 0.0009,
      "step": 270
    },
    {
      "epoch": 1.2,
      "eval_loss": 0.0007036189781501889,
      "eval_runtime": 108.3447,
      "eval_samples_per_second": 9.23,
      "eval_steps_per_second": 0.231,
      "step": 270
    },
    {
      "epoch": 1.2444444444444445,
      "grad_norm": 0.046087298542261124,
      "learning_rate": 3.12696703292044e-05,
      "loss": 0.0008,
      "step": 280
    },
    {
      "epoch": 1.2888888888888888,
      "grad_norm": 0.016715016216039658,
      "learning_rate": 2.8081442660546125e-05,
      "loss": 0.0007,
      "step": 290
    },
    {
      "epoch": 1.3333333333333333,
      "grad_norm": 0.0191776305437088,
      "learning_rate": 2.500000000000001e-05,
      "loss": 0.0006,
      "step": 300
    },
    {
      "epoch": 1.3333333333333333,
      "eval_loss": 0.0006860981229692698,
      "eval_runtime": 108.3015,
      "eval_samples_per_second": 9.233,
      "eval_steps_per_second": 0.231,
      "step": 300
    },
    {
      "epoch": 1.3777777777777778,
      "grad_norm": 0.03184030205011368,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 0.0007,
      "step": 310
    },
    {
      "epoch": 1.4222222222222223,
      "grad_norm": 0.025107963010668755,
      "learning_rate": 1.9216926233717085e-05,
      "loss": 0.0007,
      "step": 320
    },
    {
      "epoch": 1.4666666666666668,
      "grad_norm": 0.023573119193315506,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 0.0006,
      "step": 330
    },
    {
      "epoch": 1.4666666666666668,
      "eval_loss": 0.0006219326751306653,
      "eval_runtime": 108.2828,
      "eval_samples_per_second": 9.235,
      "eval_steps_per_second": 0.231,
      "step": 330
    },
    {
      "epoch": 1.511111111111111,
      "grad_norm": 0.04575636237859726,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 0.0007,
      "step": 340
    },
    {
      "epoch": 1.5555555555555556,
      "grad_norm": 0.1070500984787941,
      "learning_rate": 1.1697777844051105e-05,
      "loss": 0.0007,
      "step": 350
    },
    {
      "epoch": 1.6,
      "grad_norm": 0.03425155580043793,
      "learning_rate": 9.549150281252633e-06,
      "loss": 0.0004,
      "step": 360
    },
    {
      "epoch": 1.6,
      "eval_loss": 0.0006177299073897302,
      "eval_runtime": 108.3475,
      "eval_samples_per_second": 9.23,
      "eval_steps_per_second": 0.231,
      "step": 360
    },
    {
      "epoch": 1.6444444444444444,
      "grad_norm": 0.030520088970661163,
      "learning_rate": 7.597595192178702e-06,
      "loss": 0.0006,
      "step": 370
    },
    {
      "epoch": 1.6888888888888889,
      "grad_norm": 0.010435817763209343,
      "learning_rate": 5.852620357053651e-06,
      "loss": 0.0005,
      "step": 380
    },
    {
      "epoch": 1.7333333333333334,
      "grad_norm": 0.020339515060186386,
      "learning_rate": 4.322727117869951e-06,
      "loss": 0.0007,
      "step": 390
    },
    {
      "epoch": 1.7333333333333334,
      "eval_loss": 0.0006012282683514059,
      "eval_runtime": 108.2882,
      "eval_samples_per_second": 9.235,
      "eval_steps_per_second": 0.231,
      "step": 390
    },
    {
      "epoch": 1.7777777777777777,
      "grad_norm": 0.10952532291412354,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 0.0008,
      "step": 400
    },
    {
      "epoch": 1.8222222222222222,
      "grad_norm": 0.017915133386850357,
      "learning_rate": 1.9369152030840556e-06,
      "loss": 0.0007,
      "step": 410
    },
    {
      "epoch": 1.8666666666666667,
      "grad_norm": 0.04453803971409798,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 0.0005,
      "step": 420
    },
    {
      "epoch": 1.8666666666666667,
      "eval_loss": 0.0006457158015109599,
      "eval_runtime": 108.2276,
      "eval_samples_per_second": 9.24,
      "eval_steps_per_second": 0.231,
      "step": 420
    },
    {
      "epoch": 1.911111111111111,
      "grad_norm": 0.02466416358947754,
      "learning_rate": 4.865965629214819e-07,
      "loss": 0.0006,
      "step": 430
    },
    {
      "epoch": 1.9555555555555557,
      "grad_norm": 0.030644970014691353,
      "learning_rate": 1.2179748700879012e-07,
      "loss": 0.0005,
      "step": 440
    },
    {
      "epoch": 2.0,
      "grad_norm": 0.01875125616788864,
      "learning_rate": 0.0,
      "loss": 0.0005,
      "step": 450
    },
    {
      "epoch": 2.0,
      "eval_loss": 0.0005785770481452346,
      "eval_runtime": 108.2462,
      "eval_samples_per_second": 9.238,
      "eval_steps_per_second": 0.231,
      "step": 450
    },
    {
      "epoch": 2.0,
      "step": 450,
      "total_flos": 1.6644589041987092e+18,
      "train_loss": 0.01136111196440955,
      "train_runtime": 7966.0994,
      "train_samples_per_second": 2.26,
      "train_steps_per_second": 0.056
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.6644589041987092e+18,
  "train_batch_size": 10,
  "trial_name": null,
  "trial_params": null
}