{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 782,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0256,
      "grad_norm": 0.6669269800186157,
      "learning_rate": 1.9e-05,
      "loss": 8.179115295410156,
      "step": 20
    },
    {
      "epoch": 0.0512,
      "grad_norm": 0.5379630327224731,
      "learning_rate": 3.9000000000000006e-05,
      "loss": 8.11802978515625,
      "step": 40
    },
    {
      "epoch": 0.0768,
      "grad_norm": 0.5859383940696716,
      "learning_rate": 5.9e-05,
      "loss": 8.041471862792969,
      "step": 60
    },
    {
      "epoch": 0.1024,
      "grad_norm": 0.6329635381698608,
      "learning_rate": 7.900000000000001e-05,
      "loss": 7.967082977294922,
      "step": 80
    },
    {
      "epoch": 0.128,
      "grad_norm": 0.7737689018249512,
      "learning_rate": 9.900000000000001e-05,
      "loss": 7.894486999511718,
      "step": 100
    },
    {
      "epoch": 0.1536,
      "grad_norm": 1.0059387683868408,
      "learning_rate": 9.721407624633431e-05,
      "loss": 7.814192199707032,
      "step": 120
    },
    {
      "epoch": 0.1792,
      "grad_norm": 0.804948091506958,
      "learning_rate": 9.428152492668623e-05,
      "loss": 7.729258728027344,
      "step": 140
    },
    {
      "epoch": 0.2048,
      "grad_norm": 0.9692172408103943,
      "learning_rate": 9.134897360703812e-05,
      "loss": 7.668946838378906,
      "step": 160
    },
    {
      "epoch": 0.2304,
      "grad_norm": 0.9547553062438965,
      "learning_rate": 8.841642228739004e-05,
      "loss": 7.622274780273438,
      "step": 180
    },
    {
      "epoch": 0.256,
      "grad_norm": 0.6002941727638245,
      "learning_rate": 8.548387096774195e-05,
      "loss": 7.579273986816406,
      "step": 200
    },
    {
      "epoch": 0.2816,
      "grad_norm": 0.8823673725128174,
      "learning_rate": 8.255131964809384e-05,
      "loss": 7.519114685058594,
      "step": 220
    },
    {
      "epoch": 0.3072,
      "grad_norm": 1.0416988134384155,
      "learning_rate": 7.961876832844574e-05,
      "loss": 7.484053039550782,
      "step": 240
    },
    {
      "epoch": 0.3328,
      "grad_norm": 0.735251784324646,
      "learning_rate": 7.668621700879765e-05,
      "loss": 7.443171691894531,
      "step": 260
    },
    {
      "epoch": 0.3584,
      "grad_norm": 1.0857356786727905,
      "learning_rate": 7.375366568914957e-05,
      "loss": 7.403555297851563,
      "step": 280
    },
    {
      "epoch": 0.384,
      "grad_norm": 0.9961302280426025,
      "learning_rate": 7.082111436950148e-05,
      "loss": 7.371603393554688,
      "step": 300
    },
    {
      "epoch": 0.4096,
      "grad_norm": 0.8889548182487488,
      "learning_rate": 6.788856304985338e-05,
      "loss": 7.352679443359375,
      "step": 320
    },
    {
      "epoch": 0.4352,
      "grad_norm": 1.0873897075653076,
      "learning_rate": 6.495601173020527e-05,
      "loss": 7.3021392822265625,
      "step": 340
    },
    {
      "epoch": 0.4608,
      "grad_norm": 0.7345384359359741,
      "learning_rate": 6.202346041055719e-05,
      "loss": 7.2823539733886715,
      "step": 360
    },
    {
      "epoch": 0.4864,
      "grad_norm": 0.6853398084640503,
      "learning_rate": 5.90909090909091e-05,
      "loss": 7.260960388183594,
      "step": 380
    },
    {
      "epoch": 0.512,
      "grad_norm": 0.9110084772109985,
      "learning_rate": 5.6158357771260995e-05,
      "loss": 7.228886413574219,
      "step": 400
    },
    {
      "epoch": 0.5376,
      "grad_norm": 1.127113938331604,
      "learning_rate": 5.32258064516129e-05,
      "loss": 7.202789306640625,
      "step": 420
    },
    {
      "epoch": 0.5632,
      "grad_norm": 0.7524133324623108,
      "learning_rate": 5.029325513196481e-05,
      "loss": 7.181660461425781,
      "step": 440
    },
    {
      "epoch": 0.5888,
      "grad_norm": 0.7863721251487732,
      "learning_rate": 4.736070381231672e-05,
      "loss": 7.178968048095703,
      "step": 460
    },
    {
      "epoch": 0.6144,
      "grad_norm": 0.9041445851325989,
      "learning_rate": 4.442815249266862e-05,
      "loss": 7.156215667724609,
      "step": 480
    },
    {
      "epoch": 0.64,
      "grad_norm": 0.9909660220146179,
      "learning_rate": 4.149560117302053e-05,
      "loss": 7.125262451171875,
      "step": 500
    },
    {
      "epoch": 0.6656,
      "grad_norm": 0.816728949546814,
      "learning_rate": 3.856304985337244e-05,
      "loss": 7.123587036132813,
      "step": 520
    },
    {
      "epoch": 0.6912,
      "grad_norm": 0.8992451429367065,
      "learning_rate": 3.563049853372434e-05,
      "loss": 7.094441223144531,
      "step": 540
    },
    {
      "epoch": 0.7168,
      "grad_norm": 1.083111047744751,
      "learning_rate": 3.269794721407625e-05,
      "loss": 7.08851318359375,
      "step": 560
    },
    {
      "epoch": 0.7424,
      "grad_norm": 0.7089452147483826,
      "learning_rate": 2.9765395894428155e-05,
      "loss": 7.087593841552734,
      "step": 580
    },
    {
      "epoch": 0.768,
      "grad_norm": 0.7186883687973022,
      "learning_rate": 2.683284457478006e-05,
      "loss": 7.07503662109375,
      "step": 600
    },
    {
      "epoch": 0.7936,
      "grad_norm": 0.8105409741401672,
      "learning_rate": 2.3900293255131968e-05,
      "loss": 7.063044738769531,
      "step": 620
    },
    {
      "epoch": 0.8192,
      "grad_norm": 0.6952916979789734,
      "learning_rate": 2.0967741935483873e-05,
      "loss": 7.058567047119141,
      "step": 640
    },
    {
      "epoch": 0.8448,
      "grad_norm": 0.7389153838157654,
      "learning_rate": 1.8035190615835778e-05,
      "loss": 7.051625061035156,
      "step": 660
    },
    {
      "epoch": 0.8704,
      "grad_norm": 0.7044821381568909,
      "learning_rate": 1.5102639296187684e-05,
      "loss": 7.039373779296875,
      "step": 680
    },
    {
      "epoch": 0.896,
      "grad_norm": 0.7552204728126526,
      "learning_rate": 1.217008797653959e-05,
      "loss": 7.039744567871094,
      "step": 700
    },
    {
      "epoch": 0.9216,
      "grad_norm": 0.8664493560791016,
      "learning_rate": 9.237536656891495e-06,
      "loss": 7.020960998535156,
      "step": 720
    },
    {
      "epoch": 0.9472,
      "grad_norm": 0.5861105918884277,
      "learning_rate": 6.304985337243402e-06,
      "loss": 7.012393188476563,
      "step": 740
    },
    {
      "epoch": 0.9728,
      "grad_norm": 0.7869713306427002,
      "learning_rate": 3.372434017595308e-06,
      "loss": 7.024510192871094,
      "step": 760
    },
    {
      "epoch": 0.9984,
      "grad_norm": 0.6115875840187073,
      "learning_rate": 4.3988269794721416e-07,
      "loss": 7.033552551269532,
      "step": 780
    }
  ],
  "logging_steps": 20,
  "max_steps": 782,
  "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": 259881610772480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}