{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1978021978021978,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.006593406593406593,
      "grad_norm": 0.8349836468696594,
      "learning_rate": 0.0,
      "loss": 0.9434,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 0.8700987696647644,
      "learning_rate": 4e-05,
      "loss": 0.9905,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 0.9241365194320679,
      "learning_rate": 8e-05,
      "loss": 0.9438,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 0.9019892811775208,
      "learning_rate": 0.00012,
      "loss": 0.9216,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 0.8872910141944885,
      "learning_rate": 0.00016,
      "loss": 0.9374,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 0.5874530076980591,
      "learning_rate": 0.0002,
      "loss": 0.7673,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 0.5062956809997559,
      "learning_rate": 0.00019955654101995565,
      "loss": 0.8011,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 0.5953829288482666,
      "learning_rate": 0.00019911308203991133,
      "loss": 0.8455,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 0.5616072416305542,
      "learning_rate": 0.00019866962305986697,
      "loss": 0.8265,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.49180087447166443,
      "learning_rate": 0.00019822616407982261,
      "loss": 0.8561,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 0.42030951380729675,
      "learning_rate": 0.00019778270509977829,
      "loss": 0.8796,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.3004567325115204,
      "learning_rate": 0.00019733924611973393,
      "loss": 0.8636,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.2698984444141388,
      "learning_rate": 0.0001968957871396896,
      "loss": 0.718,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.25445133447647095,
      "learning_rate": 0.00019645232815964525,
      "loss": 0.7235,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.22418756783008575,
      "learning_rate": 0.00019600886917960092,
      "loss": 0.688,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.2096303105354309,
      "learning_rate": 0.00019556541019955653,
      "loss": 0.7267,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.3029191195964813,
      "learning_rate": 0.0001951219512195122,
      "loss": 0.7763,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.2644464075565338,
      "learning_rate": 0.00019467849223946785,
      "loss": 0.7618,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.2536560893058777,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.7999,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.24718916416168213,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.752,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.2625150680541992,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.736,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.32164040207862854,
      "learning_rate": 0.00019290465631929045,
      "loss": 0.7043,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3981449604034424,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.7057,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3817313015460968,
      "learning_rate": 0.00019201773835920177,
      "loss": 0.7413,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.29256680607795715,
      "learning_rate": 0.00019157427937915744,
      "loss": 0.693,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.27523350715637207,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.6474,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.23511967062950134,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.6519,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.2961374819278717,
      "learning_rate": 0.0001902439024390244,
      "loss": 0.6426,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.2760772407054901,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.7388,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.2285313606262207,
      "learning_rate": 0.00018935698447893572,
      "loss": 0.7756,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 456,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 15,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.3848851187376128e+16,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}