{
  "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": 2.0722603797912598,
      "learning_rate": 0.0,
      "loss": 3.2131,
      "step": 1
    },
    {
      "epoch": 0.013186813186813187,
      "grad_norm": 1.6677350997924805,
      "learning_rate": 4e-05,
      "loss": 2.5554,
      "step": 2
    },
    {
      "epoch": 0.01978021978021978,
      "grad_norm": 1.6039100885391235,
      "learning_rate": 8e-05,
      "loss": 2.6951,
      "step": 3
    },
    {
      "epoch": 0.026373626373626374,
      "grad_norm": 1.6277270317077637,
      "learning_rate": 0.00012,
      "loss": 2.9003,
      "step": 4
    },
    {
      "epoch": 0.03296703296703297,
      "grad_norm": 2.0207111835479736,
      "learning_rate": 0.00016,
      "loss": 2.6989,
      "step": 5
    },
    {
      "epoch": 0.03956043956043956,
      "grad_norm": 2.6012003421783447,
      "learning_rate": 0.0002,
      "loss": 2.2728,
      "step": 6
    },
    {
      "epoch": 0.046153846153846156,
      "grad_norm": 2.338730812072754,
      "learning_rate": 0.00019955654101995565,
      "loss": 1.7083,
      "step": 7
    },
    {
      "epoch": 0.05274725274725275,
      "grad_norm": 2.3853142261505127,
      "learning_rate": 0.00019911308203991133,
      "loss": 1.5367,
      "step": 8
    },
    {
      "epoch": 0.05934065934065934,
      "grad_norm": 1.1683852672576904,
      "learning_rate": 0.00019866962305986697,
      "loss": 1.2907,
      "step": 9
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.9153192639350891,
      "learning_rate": 0.00019822616407982261,
      "loss": 1.16,
      "step": 10
    },
    {
      "epoch": 0.07252747252747253,
      "grad_norm": 1.4894245862960815,
      "learning_rate": 0.00019778270509977829,
      "loss": 1.5419,
      "step": 11
    },
    {
      "epoch": 0.07912087912087912,
      "grad_norm": 0.8791560530662537,
      "learning_rate": 0.00019733924611973393,
      "loss": 1.323,
      "step": 12
    },
    {
      "epoch": 0.08571428571428572,
      "grad_norm": 0.5337121486663818,
      "learning_rate": 0.0001968957871396896,
      "loss": 1.1458,
      "step": 13
    },
    {
      "epoch": 0.09230769230769231,
      "grad_norm": 0.5149000883102417,
      "learning_rate": 0.00019645232815964525,
      "loss": 1.0808,
      "step": 14
    },
    {
      "epoch": 0.0989010989010989,
      "grad_norm": 0.4778643846511841,
      "learning_rate": 0.00019600886917960092,
      "loss": 1.088,
      "step": 15
    },
    {
      "epoch": 0.1054945054945055,
      "grad_norm": 0.47255033254623413,
      "learning_rate": 0.00019556541019955653,
      "loss": 1.0745,
      "step": 16
    },
    {
      "epoch": 0.11208791208791209,
      "grad_norm": 0.43144354224205017,
      "learning_rate": 0.0001951219512195122,
      "loss": 1.2685,
      "step": 17
    },
    {
      "epoch": 0.11868131868131868,
      "grad_norm": 0.38666868209838867,
      "learning_rate": 0.00019467849223946785,
      "loss": 1.0754,
      "step": 18
    },
    {
      "epoch": 0.12527472527472527,
      "grad_norm": 0.38462671637535095,
      "learning_rate": 0.00019423503325942352,
      "loss": 0.9311,
      "step": 19
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.35871055722236633,
      "learning_rate": 0.00019379157427937917,
      "loss": 0.95,
      "step": 20
    },
    {
      "epoch": 0.13846153846153847,
      "grad_norm": 0.43639278411865234,
      "learning_rate": 0.00019334811529933484,
      "loss": 0.9915,
      "step": 21
    },
    {
      "epoch": 0.14505494505494507,
      "grad_norm": 0.3904358446598053,
      "learning_rate": 0.00019290465631929045,
      "loss": 1.0229,
      "step": 22
    },
    {
      "epoch": 0.15164835164835164,
      "grad_norm": 0.3931411802768707,
      "learning_rate": 0.00019246119733924613,
      "loss": 0.897,
      "step": 23
    },
    {
      "epoch": 0.15824175824175823,
      "grad_norm": 0.3906334340572357,
      "learning_rate": 0.00019201773835920177,
      "loss": 1.0983,
      "step": 24
    },
    {
      "epoch": 0.16483516483516483,
      "grad_norm": 0.3786067068576813,
      "learning_rate": 0.00019157427937915744,
      "loss": 1.0237,
      "step": 25
    },
    {
      "epoch": 0.17142857142857143,
      "grad_norm": 0.36092478036880493,
      "learning_rate": 0.00019113082039911309,
      "loss": 0.9729,
      "step": 26
    },
    {
      "epoch": 0.17802197802197803,
      "grad_norm": 0.27863427996635437,
      "learning_rate": 0.00019068736141906876,
      "loss": 0.9565,
      "step": 27
    },
    {
      "epoch": 0.18461538461538463,
      "grad_norm": 0.30928313732147217,
      "learning_rate": 0.0001902439024390244,
      "loss": 1.0746,
      "step": 28
    },
    {
      "epoch": 0.1912087912087912,
      "grad_norm": 0.3250511586666107,
      "learning_rate": 0.00018980044345898005,
      "loss": 0.9843,
      "step": 29
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.30846866965293884,
      "learning_rate": 0.00018935698447893572,
      "loss": 1.0582,
      "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": 4901350956564480.0,
  "train_batch_size": 22,
  "trial_name": null,
  "trial_params": null
}