{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5263157894736842,
  "eval_steps": 500,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.013157894736842105,
      "grad_norm": 0.29758667945861816,
      "learning_rate": 0.00049,
      "loss": 2.2376,
      "step": 5
    },
    {
      "epoch": 0.02631578947368421,
      "grad_norm": 0.22196123003959656,
      "learning_rate": 0.0004775,
      "loss": 1.9277,
      "step": 10
    },
    {
      "epoch": 0.039473684210526314,
      "grad_norm": 0.2114119827747345,
      "learning_rate": 0.000465,
      "loss": 1.825,
      "step": 15
    },
    {
      "epoch": 0.05263157894736842,
      "grad_norm": 0.3481071889400482,
      "learning_rate": 0.00045250000000000005,
      "loss": 1.6025,
      "step": 20
    },
    {
      "epoch": 0.06578947368421052,
      "grad_norm": 0.22427237033843994,
      "learning_rate": 0.00044,
      "loss": 1.879,
      "step": 25
    },
    {
      "epoch": 0.07894736842105263,
      "grad_norm": 0.40945950150489807,
      "learning_rate": 0.0004275,
      "loss": 1.8997,
      "step": 30
    },
    {
      "epoch": 0.09210526315789473,
      "grad_norm": 0.19926413893699646,
      "learning_rate": 0.000415,
      "loss": 1.7553,
      "step": 35
    },
    {
      "epoch": 0.10526315789473684,
      "grad_norm": 0.19860610365867615,
      "learning_rate": 0.0004025,
      "loss": 1.6122,
      "step": 40
    },
    {
      "epoch": 0.11842105263157894,
      "grad_norm": 0.2695777714252472,
      "learning_rate": 0.00039000000000000005,
      "loss": 1.7543,
      "step": 45
    },
    {
      "epoch": 0.13157894736842105,
      "grad_norm": 0.16942498087882996,
      "learning_rate": 0.0003775,
      "loss": 1.789,
      "step": 50
    },
    {
      "epoch": 0.14473684210526316,
      "grad_norm": 0.20437906682491302,
      "learning_rate": 0.000365,
      "loss": 1.9185,
      "step": 55
    },
    {
      "epoch": 0.15789473684210525,
      "grad_norm": 0.23559698462486267,
      "learning_rate": 0.0003525,
      "loss": 1.7316,
      "step": 60
    },
    {
      "epoch": 0.17105263157894737,
      "grad_norm": 0.20673207938671112,
      "learning_rate": 0.00034,
      "loss": 1.7895,
      "step": 65
    },
    {
      "epoch": 0.18421052631578946,
      "grad_norm": 0.19694335758686066,
      "learning_rate": 0.00032750000000000005,
      "loss": 1.6532,
      "step": 70
    },
    {
      "epoch": 0.19736842105263158,
      "grad_norm": 0.308459997177124,
      "learning_rate": 0.000315,
      "loss": 1.8113,
      "step": 75
    },
    {
      "epoch": 0.21052631578947367,
      "grad_norm": 0.23931701481342316,
      "learning_rate": 0.0003025,
      "loss": 1.9647,
      "step": 80
    },
    {
      "epoch": 0.2236842105263158,
      "grad_norm": 0.3195277750492096,
      "learning_rate": 0.00029,
      "loss": 1.6484,
      "step": 85
    },
    {
      "epoch": 0.23684210526315788,
      "grad_norm": 0.2581469416618347,
      "learning_rate": 0.0002775,
      "loss": 1.8056,
      "step": 90
    },
    {
      "epoch": 0.25,
      "grad_norm": 0.21418361365795135,
      "learning_rate": 0.00026500000000000004,
      "loss": 1.6111,
      "step": 95
    },
    {
      "epoch": 0.2631578947368421,
      "grad_norm": 0.2666741609573364,
      "learning_rate": 0.0002525,
      "loss": 1.8763,
      "step": 100
    },
    {
      "epoch": 0.27631578947368424,
      "grad_norm": 0.2849399745464325,
      "learning_rate": 0.00024,
      "loss": 1.6717,
      "step": 105
    },
    {
      "epoch": 0.2894736842105263,
      "grad_norm": 0.4305271804332733,
      "learning_rate": 0.0002275,
      "loss": 1.9686,
      "step": 110
    },
    {
      "epoch": 0.3026315789473684,
      "grad_norm": 0.2307509481906891,
      "learning_rate": 0.000215,
      "loss": 1.7055,
      "step": 115
    },
    {
      "epoch": 0.3157894736842105,
      "grad_norm": 0.2147100567817688,
      "learning_rate": 0.00020250000000000002,
      "loss": 1.5492,
      "step": 120
    },
    {
      "epoch": 0.32894736842105265,
      "grad_norm": 0.301596462726593,
      "learning_rate": 0.00019,
      "loss": 1.6773,
      "step": 125
    },
    {
      "epoch": 0.34210526315789475,
      "grad_norm": 0.23740164935588837,
      "learning_rate": 0.0001775,
      "loss": 1.6153,
      "step": 130
    },
    {
      "epoch": 0.35526315789473684,
      "grad_norm": 0.5926236510276794,
      "learning_rate": 0.000165,
      "loss": 1.5491,
      "step": 135
    },
    {
      "epoch": 0.3684210526315789,
      "grad_norm": 0.31152641773223877,
      "learning_rate": 0.0001525,
      "loss": 1.5888,
      "step": 140
    },
    {
      "epoch": 0.3815789473684211,
      "grad_norm": 0.29370665550231934,
      "learning_rate": 0.00014000000000000001,
      "loss": 1.4578,
      "step": 145
    },
    {
      "epoch": 0.39473684210526316,
      "grad_norm": 0.4238162040710449,
      "learning_rate": 0.0001275,
      "loss": 1.6124,
      "step": 150
    },
    {
      "epoch": 0.40789473684210525,
      "grad_norm": 0.17060554027557373,
      "learning_rate": 0.000115,
      "loss": 1.4683,
      "step": 155
    },
    {
      "epoch": 0.42105263157894735,
      "grad_norm": 0.2400592416524887,
      "learning_rate": 0.0001025,
      "loss": 1.594,
      "step": 160
    },
    {
      "epoch": 0.4342105263157895,
      "grad_norm": 0.2850854694843292,
      "learning_rate": 8.999999999999999e-05,
      "loss": 1.5918,
      "step": 165
    },
    {
      "epoch": 0.4473684210526316,
      "grad_norm": 0.26509717106819153,
      "learning_rate": 7.75e-05,
      "loss": 1.6568,
      "step": 170
    },
    {
      "epoch": 0.4605263157894737,
      "grad_norm": 0.2525962293148041,
      "learning_rate": 6.500000000000001e-05,
      "loss": 1.5518,
      "step": 175
    },
    {
      "epoch": 0.47368421052631576,
      "grad_norm": 0.3045089542865753,
      "learning_rate": 5.25e-05,
      "loss": 1.527,
      "step": 180
    },
    {
      "epoch": 0.4868421052631579,
      "grad_norm": 0.25709375739097595,
      "learning_rate": 4e-05,
      "loss": 1.344,
      "step": 185
    },
    {
      "epoch": 0.5,
      "grad_norm": 0.3316431939601898,
      "learning_rate": 2.75e-05,
      "loss": 1.9208,
      "step": 190
    },
    {
      "epoch": 0.5131578947368421,
      "grad_norm": 0.23111386597156525,
      "learning_rate": 1.5e-05,
      "loss": 1.3025,
      "step": 195
    },
    {
      "epoch": 0.5263157894736842,
      "grad_norm": 0.2982702851295471,
      "learning_rate": 2.5e-06,
      "loss": 1.6718,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 200,
  "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": 3.101511345913528e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}