{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 10,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.020151133501259445,
      "grad_norm": 286.0,
      "learning_rate": 0.0,
      "loss": 6.3323,
      "step": 1
    },
    {
      "epoch": 0.04030226700251889,
      "grad_norm": 294.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 6.9278,
      "step": 2
    },
    {
      "epoch": 0.060453400503778336,
      "grad_norm": 258.0,
      "learning_rate": 4.000000000000001e-06,
      "loss": 6.5878,
      "step": 3
    },
    {
      "epoch": 0.08060453400503778,
      "grad_norm": 236.0,
      "learning_rate": 6e-06,
      "loss": 4.9359,
      "step": 4
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 98.5,
      "learning_rate": 8.000000000000001e-06,
      "loss": 3.6571,
      "step": 5
    },
    {
      "epoch": 0.12090680100755667,
      "grad_norm": 71.5,
      "learning_rate": 1e-05,
      "loss": 2.9318,
      "step": 6
    },
    {
      "epoch": 0.14105793450881612,
      "grad_norm": 40.25,
      "learning_rate": 9.777777777777779e-06,
      "loss": 2.16,
      "step": 7
    },
    {
      "epoch": 0.16120906801007556,
      "grad_norm": 40.75,
      "learning_rate": 9.555555555555556e-06,
      "loss": 2.028,
      "step": 8
    },
    {
      "epoch": 0.181360201511335,
      "grad_norm": 39.75,
      "learning_rate": 9.333333333333334e-06,
      "loss": 1.6548,
      "step": 9
    },
    {
      "epoch": 0.20151133501259447,
      "grad_norm": 35.75,
      "learning_rate": 9.111111111111112e-06,
      "loss": 2.1349,
      "step": 10
    },
    {
      "epoch": 0.20151133501259447,
      "eval_loss": 1.6403069496154785,
      "eval_model_preparation_time": 0.0199,
      "eval_runtime": 2.5723,
      "eval_samples_per_second": 36.931,
      "eval_steps_per_second": 18.66,
      "step": 10
    },
    {
      "epoch": 0.2216624685138539,
      "grad_norm": 50.0,
      "learning_rate": 8.888888888888888e-06,
      "loss": 1.2909,
      "step": 11
    },
    {
      "epoch": 0.24181360201511334,
      "grad_norm": 30.0,
      "learning_rate": 8.666666666666668e-06,
      "loss": 1.2002,
      "step": 12
    },
    {
      "epoch": 0.2619647355163728,
      "grad_norm": 25.25,
      "learning_rate": 8.444444444444446e-06,
      "loss": 1.1529,
      "step": 13
    },
    {
      "epoch": 0.28211586901763225,
      "grad_norm": 28.5,
      "learning_rate": 8.222222222222222e-06,
      "loss": 1.436,
      "step": 14
    },
    {
      "epoch": 0.3022670025188917,
      "grad_norm": 21.5,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.1747,
      "step": 15
    },
    {
      "epoch": 0.3224181360201511,
      "grad_norm": 25.25,
      "learning_rate": 7.77777777777778e-06,
      "loss": 1.2486,
      "step": 16
    },
    {
      "epoch": 0.3425692695214106,
      "grad_norm": 29.125,
      "learning_rate": 7.555555555555556e-06,
      "loss": 1.3699,
      "step": 17
    },
    {
      "epoch": 0.36272040302267,
      "grad_norm": 28.625,
      "learning_rate": 7.333333333333333e-06,
      "loss": 1.0368,
      "step": 18
    },
    {
      "epoch": 0.38287153652392947,
      "grad_norm": 31.25,
      "learning_rate": 7.111111111111112e-06,
      "loss": 1.7601,
      "step": 19
    },
    {
      "epoch": 0.40302267002518893,
      "grad_norm": 27.125,
      "learning_rate": 6.88888888888889e-06,
      "loss": 1.0943,
      "step": 20
    },
    {
      "epoch": 0.40302267002518893,
      "eval_loss": 1.2779872417449951,
      "eval_model_preparation_time": 0.0199,
      "eval_runtime": 2.5465,
      "eval_samples_per_second": 37.305,
      "eval_steps_per_second": 18.849,
      "step": 20
    },
    {
      "epoch": 0.42317380352644834,
      "grad_norm": 29.0,
      "learning_rate": 6.666666666666667e-06,
      "loss": 1.1963,
      "step": 21
    },
    {
      "epoch": 0.4433249370277078,
      "grad_norm": 20.625,
      "learning_rate": 6.444444444444445e-06,
      "loss": 0.8011,
      "step": 22
    },
    {
      "epoch": 0.4634760705289673,
      "grad_norm": 26.625,
      "learning_rate": 6.222222222222223e-06,
      "loss": 0.9265,
      "step": 23
    },
    {
      "epoch": 0.4836272040302267,
      "grad_norm": 26.375,
      "learning_rate": 6e-06,
      "loss": 0.9816,
      "step": 24
    },
    {
      "epoch": 0.5037783375314862,
      "grad_norm": 27.25,
      "learning_rate": 5.777777777777778e-06,
      "loss": 1.1287,
      "step": 25
    },
    {
      "epoch": 0.5239294710327456,
      "grad_norm": 22.75,
      "learning_rate": 5.555555555555557e-06,
      "loss": 1.031,
      "step": 26
    },
    {
      "epoch": 0.5440806045340051,
      "grad_norm": 28.25,
      "learning_rate": 5.333333333333334e-06,
      "loss": 1.184,
      "step": 27
    },
    {
      "epoch": 0.5642317380352645,
      "grad_norm": 20.5,
      "learning_rate": 5.1111111111111115e-06,
      "loss": 0.9292,
      "step": 28
    },
    {
      "epoch": 0.5843828715365239,
      "grad_norm": 27.75,
      "learning_rate": 4.888888888888889e-06,
      "loss": 0.9952,
      "step": 29
    },
    {
      "epoch": 0.6045340050377834,
      "grad_norm": 21.125,
      "learning_rate": 4.666666666666667e-06,
      "loss": 0.886,
      "step": 30
    },
    {
      "epoch": 0.6045340050377834,
      "eval_loss": 1.2436152696609497,
      "eval_model_preparation_time": 0.0199,
      "eval_runtime": 2.7811,
      "eval_samples_per_second": 34.159,
      "eval_steps_per_second": 17.259,
      "step": 30
    },
    {
      "epoch": 0.6246851385390428,
      "grad_norm": 22.625,
      "learning_rate": 4.444444444444444e-06,
      "loss": 0.9749,
      "step": 31
    },
    {
      "epoch": 0.6448362720403022,
      "grad_norm": 17.0,
      "learning_rate": 4.222222222222223e-06,
      "loss": 0.8473,
      "step": 32
    },
    {
      "epoch": 0.6649874055415617,
      "grad_norm": 25.125,
      "learning_rate": 4.000000000000001e-06,
      "loss": 0.928,
      "step": 33
    },
    {
      "epoch": 0.6851385390428212,
      "grad_norm": 38.25,
      "learning_rate": 3.777777777777778e-06,
      "loss": 1.1706,
      "step": 34
    },
    {
      "epoch": 0.7052896725440806,
      "grad_norm": 15.75,
      "learning_rate": 3.555555555555556e-06,
      "loss": 0.6605,
      "step": 35
    },
    {
      "epoch": 0.72544080604534,
      "grad_norm": 22.875,
      "learning_rate": 3.3333333333333333e-06,
      "loss": 0.9448,
      "step": 36
    },
    {
      "epoch": 0.7455919395465995,
      "grad_norm": 16.25,
      "learning_rate": 3.1111111111111116e-06,
      "loss": 0.8088,
      "step": 37
    },
    {
      "epoch": 0.7657430730478589,
      "grad_norm": 15.5625,
      "learning_rate": 2.888888888888889e-06,
      "loss": 0.7572,
      "step": 38
    },
    {
      "epoch": 0.7858942065491183,
      "grad_norm": 28.75,
      "learning_rate": 2.666666666666667e-06,
      "loss": 0.9594,
      "step": 39
    },
    {
      "epoch": 0.8060453400503779,
      "grad_norm": 20.375,
      "learning_rate": 2.4444444444444447e-06,
      "loss": 0.7057,
      "step": 40
    },
    {
      "epoch": 0.8060453400503779,
      "eval_loss": 1.194969892501831,
      "eval_model_preparation_time": 0.0199,
      "eval_runtime": 2.4247,
      "eval_samples_per_second": 39.181,
      "eval_steps_per_second": 19.797,
      "step": 40
    },
    {
      "epoch": 0.8261964735516373,
      "grad_norm": 20.375,
      "learning_rate": 2.222222222222222e-06,
      "loss": 1.032,
      "step": 41
    },
    {
      "epoch": 0.8463476070528967,
      "grad_norm": 24.0,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 0.9994,
      "step": 42
    },
    {
      "epoch": 0.8664987405541562,
      "grad_norm": 25.625,
      "learning_rate": 1.777777777777778e-06,
      "loss": 0.7317,
      "step": 43
    },
    {
      "epoch": 0.8866498740554156,
      "grad_norm": 21.5,
      "learning_rate": 1.5555555555555558e-06,
      "loss": 1.0102,
      "step": 44
    },
    {
      "epoch": 0.906801007556675,
      "grad_norm": 23.125,
      "learning_rate": 1.3333333333333334e-06,
      "loss": 0.9164,
      "step": 45
    },
    {
      "epoch": 0.9269521410579346,
      "grad_norm": 18.375,
      "learning_rate": 1.111111111111111e-06,
      "loss": 0.8684,
      "step": 46
    },
    {
      "epoch": 0.947103274559194,
      "grad_norm": 16.75,
      "learning_rate": 8.88888888888889e-07,
      "loss": 0.8164,
      "step": 47
    },
    {
      "epoch": 0.9672544080604534,
      "grad_norm": 29.0,
      "learning_rate": 6.666666666666667e-07,
      "loss": 1.2547,
      "step": 48
    },
    {
      "epoch": 0.9874055415617129,
      "grad_norm": 19.5,
      "learning_rate": 4.444444444444445e-07,
      "loss": 0.7327,
      "step": 49
    },
    {
      "epoch": 1.0,
      "grad_norm": 26.875,
      "learning_rate": 2.2222222222222224e-07,
      "loss": 1.0369,
      "step": 50
    },
    {
      "epoch": 1.0,
      "eval_loss": 1.154162883758545,
      "eval_model_preparation_time": 0.0199,
      "eval_runtime": 2.5588,
      "eval_samples_per_second": 37.127,
      "eval_steps_per_second": 18.759,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1842168632426496.0,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}