{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.022222222222222223,
      "grad_norm": 19.91867348365725,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.4702,
      "step": 10
    },
    {
      "epoch": 0.044444444444444446,
      "grad_norm": 15.369207987994029,
      "learning_rate": 4.444444444444444e-06,
      "loss": 1.1769,
      "step": 20
    },
    {
      "epoch": 0.06666666666666667,
      "grad_norm": 10.077294898457161,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1779,
      "step": 30
    },
    {
      "epoch": 0.08888888888888889,
      "grad_norm": 13.411925074069691,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.0874,
      "step": 40
    },
    {
      "epoch": 0.1111111111111111,
      "grad_norm": 9.846880381435538,
      "learning_rate": 9.996239762521152e-06,
      "loss": 1.1229,
      "step": 50
    },
    {
      "epoch": 0.13333333333333333,
      "grad_norm": 12.455219318406405,
      "learning_rate": 9.966191788709716e-06,
      "loss": 1.1688,
      "step": 60
    },
    {
      "epoch": 0.15555555555555556,
      "grad_norm": 12.82232338643187,
      "learning_rate": 9.906276553136924e-06,
      "loss": 1.137,
      "step": 70
    },
    {
      "epoch": 0.17777777777777778,
      "grad_norm": 10.826832471308387,
      "learning_rate": 9.816854393079402e-06,
      "loss": 1.112,
      "step": 80
    },
    {
      "epoch": 0.2,
      "grad_norm": 8.696002929306234,
      "learning_rate": 9.698463103929542e-06,
      "loss": 1.1811,
      "step": 90
    },
    {
      "epoch": 0.2222222222222222,
      "grad_norm": 7.576344795701732,
      "learning_rate": 9.551814704830734e-06,
      "loss": 1.0925,
      "step": 100
    },
    {
      "epoch": 0.2222222222222222,
      "eval_loss": 1.1537069082260132,
      "eval_runtime": 60.79,
      "eval_samples_per_second": 3.29,
      "eval_steps_per_second": 1.645,
      "step": 100
    },
    {
      "epoch": 0.24444444444444444,
      "grad_norm": 7.036698344103777,
      "learning_rate": 9.377791156510456e-06,
      "loss": 1.1117,
      "step": 110
    },
    {
      "epoch": 0.26666666666666666,
      "grad_norm": 9.794639089760656,
      "learning_rate": 9.177439057064684e-06,
      "loss": 1.2063,
      "step": 120
    },
    {
      "epoch": 0.28888888888888886,
      "grad_norm": 9.113232197574831,
      "learning_rate": 8.951963347593797e-06,
      "loss": 1.1618,
      "step": 130
    },
    {
      "epoch": 0.3111111111111111,
      "grad_norm": 8.260077391927412,
      "learning_rate": 8.702720065545024e-06,
      "loss": 1.1175,
      "step": 140
    },
    {
      "epoch": 0.3333333333333333,
      "grad_norm": 8.97610543279449,
      "learning_rate": 8.43120818934367e-06,
      "loss": 1.0677,
      "step": 150
    },
    {
      "epoch": 0.35555555555555557,
      "grad_norm": 8.006182736919792,
      "learning_rate": 8.139060623360494e-06,
      "loss": 1.0995,
      "step": 160
    },
    {
      "epoch": 0.37777777777777777,
      "grad_norm": 9.384324522838584,
      "learning_rate": 7.828034377432694e-06,
      "loss": 1.0736,
      "step": 170
    },
    {
      "epoch": 0.4,
      "grad_norm": 10.15448752865431,
      "learning_rate": 7.500000000000001e-06,
      "loss": 1.1432,
      "step": 180
    },
    {
      "epoch": 0.4222222222222222,
      "grad_norm": 8.557941280285473,
      "learning_rate": 7.156930328406268e-06,
      "loss": 1.1436,
      "step": 190
    },
    {
      "epoch": 0.4444444444444444,
      "grad_norm": 10.30090432341051,
      "learning_rate": 6.800888624023552e-06,
      "loss": 1.0785,
      "step": 200
    },
    {
      "epoch": 0.4444444444444444,
      "eval_loss": 1.0702898502349854,
      "eval_runtime": 60.723,
      "eval_samples_per_second": 3.294,
      "eval_steps_per_second": 1.647,
      "step": 200
    },
    {
      "epoch": 0.4666666666666667,
      "grad_norm": 9.009218386765967,
      "learning_rate": 6.434016163555452e-06,
      "loss": 0.9758,
      "step": 210
    },
    {
      "epoch": 0.4888888888888889,
      "grad_norm": 8.620838411666378,
      "learning_rate": 6.058519361147055e-06,
      "loss": 1.0329,
      "step": 220
    },
    {
      "epoch": 0.5111111111111111,
      "grad_norm": 6.809783534022497,
      "learning_rate": 5.6766564987506564e-06,
      "loss": 1.0221,
      "step": 230
    },
    {
      "epoch": 0.5333333333333333,
      "grad_norm": 8.12528298286036,
      "learning_rate": 5.290724144552379e-06,
      "loss": 0.9376,
      "step": 240
    },
    {
      "epoch": 0.5555555555555556,
      "grad_norm": 7.180263100676318,
      "learning_rate": 4.903043341140879e-06,
      "loss": 1.0662,
      "step": 250
    },
    {
      "epoch": 0.5777777777777777,
      "grad_norm": 8.326903297447247,
      "learning_rate": 4.515945646484105e-06,
      "loss": 1.0622,
      "step": 260
    },
    {
      "epoch": 0.6,
      "grad_norm": 8.000283583921108,
      "learning_rate": 4.131759111665349e-06,
      "loss": 1.0203,
      "step": 270
    },
    {
      "epoch": 0.6222222222222222,
      "grad_norm": 6.726114069645646,
      "learning_rate": 3.752794279710094e-06,
      "loss": 0.9931,
      "step": 280
    },
    {
      "epoch": 0.6444444444444445,
      "grad_norm": 8.620432402570843,
      "learning_rate": 3.3813302897083955e-06,
      "loss": 1.0236,
      "step": 290
    },
    {
      "epoch": 0.6666666666666666,
      "grad_norm": 7.841652982224934,
      "learning_rate": 3.019601169804216e-06,
      "loss": 1.0488,
      "step": 300
    },
    {
      "epoch": 0.6666666666666666,
      "eval_loss": 0.9803605675697327,
      "eval_runtime": 60.7186,
      "eval_samples_per_second": 3.294,
      "eval_steps_per_second": 1.647,
      "step": 300
    },
    {
      "epoch": 0.6888888888888889,
      "grad_norm": 7.281050976841964,
      "learning_rate": 2.6697824014873076e-06,
      "loss": 0.9133,
      "step": 310
    },
    {
      "epoch": 0.7111111111111111,
      "grad_norm": 6.658646600809646,
      "learning_rate": 2.333977835991545e-06,
      "loss": 0.9479,
      "step": 320
    },
    {
      "epoch": 0.7333333333333333,
      "grad_norm": 7.225803892629026,
      "learning_rate": 2.0142070414860704e-06,
      "loss": 0.8821,
      "step": 330
    },
    {
      "epoch": 0.7555555555555555,
      "grad_norm": 7.786806287208257,
      "learning_rate": 1.7123931571546826e-06,
      "loss": 0.9153,
      "step": 340
    },
    {
      "epoch": 0.7777777777777778,
      "grad_norm": 8.256368895258337,
      "learning_rate": 1.4303513272105057e-06,
      "loss": 0.9199,
      "step": 350
    },
    {
      "epoch": 0.8,
      "grad_norm": 7.104754957970456,
      "learning_rate": 1.1697777844051105e-06,
      "loss": 0.9247,
      "step": 360
    },
    {
      "epoch": 0.8222222222222222,
      "grad_norm": 7.602287535954527,
      "learning_rate": 9.322396486851626e-07,
      "loss": 1.0121,
      "step": 370
    },
    {
      "epoch": 0.8444444444444444,
      "grad_norm": 9.797458497611096,
      "learning_rate": 7.191655023486682e-07,
      "loss": 0.9738,
      "step": 380
    },
    {
      "epoch": 0.8666666666666667,
      "grad_norm": 8.528164702205238,
      "learning_rate": 5.318367983829393e-07,
      "loss": 0.9269,
      "step": 390
    },
    {
      "epoch": 0.8888888888888888,
      "grad_norm": 7.436992260536332,
      "learning_rate": 3.7138015365554834e-07,
      "loss": 0.8813,
      "step": 400
    },
    {
      "epoch": 0.8888888888888888,
      "eval_loss": 0.9376574754714966,
      "eval_runtime": 60.7157,
      "eval_samples_per_second": 3.294,
      "eval_steps_per_second": 1.647,
      "step": 400
    },
    {
      "epoch": 0.9111111111111111,
      "grad_norm": 8.567154183555127,
      "learning_rate": 2.3876057330792344e-07,
      "loss": 0.9061,
      "step": 410
    },
    {
      "epoch": 0.9333333333333333,
      "grad_norm": 8.918491488632892,
      "learning_rate": 1.3477564710088097e-07,
      "loss": 0.885,
      "step": 420
    },
    {
      "epoch": 0.9555555555555556,
      "grad_norm": 6.711316474301502,
      "learning_rate": 6.005075261595495e-08,
      "loss": 0.8554,
      "step": 430
    },
    {
      "epoch": 0.9777777777777777,
      "grad_norm": 9.83507424831323,
      "learning_rate": 1.5035294161039882e-08,
      "loss": 0.8568,
      "step": 440
    },
    {
      "epoch": 1.0,
      "grad_norm": 7.414930651551686,
      "learning_rate": 0.0,
      "loss": 0.7874,
      "step": 450
    },
    {
      "epoch": 1.0,
      "step": 450,
      "total_flos": 899256483840.0,
      "train_loss": 1.0377891794840495,
      "train_runtime": 1877.5234,
      "train_samples_per_second": 0.959,
      "train_steps_per_second": 0.24
    }
  ],
  "logging_steps": 10,
  "max_steps": 450,
  "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": false,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 899256483840.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}