{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.012,
  "eval_steps": 500,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0004,
      "grad_norm": 0.14046324789524078,
      "learning_rate": 0.0,
      "loss": 1.3922,
      "step": 1
    },
    {
      "epoch": 0.0008,
      "grad_norm": 0.17429180443286896,
      "learning_rate": 4e-05,
      "loss": 1.4108,
      "step": 2
    },
    {
      "epoch": 0.0012,
      "grad_norm": 0.18312247097492218,
      "learning_rate": 8e-05,
      "loss": 1.3525,
      "step": 3
    },
    {
      "epoch": 0.0016,
      "grad_norm": 0.2110716551542282,
      "learning_rate": 0.00012,
      "loss": 1.3662,
      "step": 4
    },
    {
      "epoch": 0.002,
      "grad_norm": 0.1712651401758194,
      "learning_rate": 0.00016,
      "loss": 1.4026,
      "step": 5
    },
    {
      "epoch": 0.0024,
      "grad_norm": 0.1721387505531311,
      "learning_rate": 0.0002,
      "loss": 1.3036,
      "step": 6
    },
    {
      "epoch": 0.0028,
      "grad_norm": 0.146767720580101,
      "learning_rate": 0.000192,
      "loss": 1.2262,
      "step": 7
    },
    {
      "epoch": 0.0032,
      "grad_norm": 0.1462695449590683,
      "learning_rate": 0.00018400000000000003,
      "loss": 1.1611,
      "step": 8
    },
    {
      "epoch": 0.0036,
      "grad_norm": 0.22634515166282654,
      "learning_rate": 0.00017600000000000002,
      "loss": 1.1031,
      "step": 9
    },
    {
      "epoch": 0.004,
      "grad_norm": 0.16959479451179504,
      "learning_rate": 0.000168,
      "loss": 1.0576,
      "step": 10
    },
    {
      "epoch": 0.0044,
      "grad_norm": 0.15298032760620117,
      "learning_rate": 0.00016,
      "loss": 1.0452,
      "step": 11
    },
    {
      "epoch": 0.0048,
      "grad_norm": 0.1880827248096466,
      "learning_rate": 0.000152,
      "loss": 0.9791,
      "step": 12
    },
    {
      "epoch": 0.0052,
      "grad_norm": 0.16587546467781067,
      "learning_rate": 0.000144,
      "loss": 1.0639,
      "step": 13
    },
    {
      "epoch": 0.0056,
      "grad_norm": 0.1673472821712494,
      "learning_rate": 0.00013600000000000003,
      "loss": 1.0612,
      "step": 14
    },
    {
      "epoch": 0.006,
      "grad_norm": 0.1644534170627594,
      "learning_rate": 0.00012800000000000002,
      "loss": 1.0584,
      "step": 15
    },
    {
      "epoch": 0.0064,
      "grad_norm": 0.168317511677742,
      "learning_rate": 0.00012,
      "loss": 1.0348,
      "step": 16
    },
    {
      "epoch": 0.0068,
      "grad_norm": 0.2933410704135895,
      "learning_rate": 0.00011200000000000001,
      "loss": 1.0254,
      "step": 17
    },
    {
      "epoch": 0.0072,
      "grad_norm": 0.16315768659114838,
      "learning_rate": 0.00010400000000000001,
      "loss": 1.0078,
      "step": 18
    },
    {
      "epoch": 0.0076,
      "grad_norm": 0.17154046893119812,
      "learning_rate": 9.6e-05,
      "loss": 1.0626,
      "step": 19
    },
    {
      "epoch": 0.008,
      "grad_norm": 0.2063586413860321,
      "learning_rate": 8.800000000000001e-05,
      "loss": 1.1072,
      "step": 20
    },
    {
      "epoch": 0.0084,
      "grad_norm": 0.1720573604106903,
      "learning_rate": 8e-05,
      "loss": 0.9562,
      "step": 21
    },
    {
      "epoch": 0.0088,
      "grad_norm": 0.15085603296756744,
      "learning_rate": 7.2e-05,
      "loss": 0.9819,
      "step": 22
    },
    {
      "epoch": 0.0092,
      "grad_norm": 0.16576017439365387,
      "learning_rate": 6.400000000000001e-05,
      "loss": 0.9569,
      "step": 23
    },
    {
      "epoch": 0.0096,
      "grad_norm": 0.15237872302532196,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.0633,
      "step": 24
    },
    {
      "epoch": 0.01,
      "grad_norm": 0.16275323927402496,
      "learning_rate": 4.8e-05,
      "loss": 1.0202,
      "step": 25
    },
    {
      "epoch": 0.0104,
      "grad_norm": 0.1494642049074173,
      "learning_rate": 4e-05,
      "loss": 0.9842,
      "step": 26
    },
    {
      "epoch": 0.0108,
      "grad_norm": 0.14561104774475098,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 0.9534,
      "step": 27
    },
    {
      "epoch": 0.0112,
      "grad_norm": 0.1298287808895111,
      "learning_rate": 2.4e-05,
      "loss": 0.8834,
      "step": 28
    },
    {
      "epoch": 0.0116,
      "grad_norm": 0.15824304521083832,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 0.9824,
      "step": 29
    },
    {
      "epoch": 0.012,
      "grad_norm": 0.1302255243062973,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.9466,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "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": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 8.690976238834483e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}