{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0036247643903146295,
  "eval_steps": 4,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001449905756125852,
      "grad_norm": 68.50080871582031,
      "learning_rate": 1e-05,
      "loss": 10.076,
      "step": 1
    },
    {
      "epoch": 0.0001449905756125852,
      "eval_loss": 9.672462463378906,
      "eval_runtime": 166.7625,
      "eval_samples_per_second": 34.828,
      "eval_steps_per_second": 4.353,
      "step": 1
    },
    {
      "epoch": 0.0002899811512251704,
      "grad_norm": 86.92239379882812,
      "learning_rate": 2e-05,
      "loss": 10.1925,
      "step": 2
    },
    {
      "epoch": 0.00043497172683775554,
      "grad_norm": 57.988224029541016,
      "learning_rate": 3e-05,
      "loss": 8.8292,
      "step": 3
    },
    {
      "epoch": 0.0005799623024503408,
      "grad_norm": 83.44893646240234,
      "learning_rate": 4e-05,
      "loss": 9.1977,
      "step": 4
    },
    {
      "epoch": 0.0005799623024503408,
      "eval_loss": 8.433806419372559,
      "eval_runtime": 166.7306,
      "eval_samples_per_second": 34.835,
      "eval_steps_per_second": 4.354,
      "step": 4
    },
    {
      "epoch": 0.0007249528780629259,
      "grad_norm": 54.48796081542969,
      "learning_rate": 5e-05,
      "loss": 8.61,
      "step": 5
    },
    {
      "epoch": 0.0008699434536755111,
      "grad_norm": 84.71044921875,
      "learning_rate": 6e-05,
      "loss": 7.9657,
      "step": 6
    },
    {
      "epoch": 0.0010149340292880964,
      "grad_norm": 48.630592346191406,
      "learning_rate": 7e-05,
      "loss": 6.8239,
      "step": 7
    },
    {
      "epoch": 0.0011599246049006815,
      "grad_norm": 26.573875427246094,
      "learning_rate": 8e-05,
      "loss": 6.3551,
      "step": 8
    },
    {
      "epoch": 0.0011599246049006815,
      "eval_loss": 5.716758728027344,
      "eval_runtime": 166.7532,
      "eval_samples_per_second": 34.83,
      "eval_steps_per_second": 4.354,
      "step": 8
    },
    {
      "epoch": 0.0013049151805132667,
      "grad_norm": 23.909320831298828,
      "learning_rate": 9e-05,
      "loss": 5.8831,
      "step": 9
    },
    {
      "epoch": 0.0014499057561258518,
      "grad_norm": 42.59280014038086,
      "learning_rate": 0.0001,
      "loss": 5.3481,
      "step": 10
    },
    {
      "epoch": 0.001594896331738437,
      "grad_norm": 33.284767150878906,
      "learning_rate": 9.890738003669029e-05,
      "loss": 4.0478,
      "step": 11
    },
    {
      "epoch": 0.0017398869073510222,
      "grad_norm": 17.203149795532227,
      "learning_rate": 9.567727288213005e-05,
      "loss": 3.4926,
      "step": 12
    },
    {
      "epoch": 0.0017398869073510222,
      "eval_loss": 3.4215242862701416,
      "eval_runtime": 166.8249,
      "eval_samples_per_second": 34.815,
      "eval_steps_per_second": 4.352,
      "step": 12
    },
    {
      "epoch": 0.0018848774829636073,
      "grad_norm": 18.14301109313965,
      "learning_rate": 9.045084971874738e-05,
      "loss": 3.4935,
      "step": 13
    },
    {
      "epoch": 0.0020298680585761927,
      "grad_norm": 15.798501014709473,
      "learning_rate": 8.345653031794292e-05,
      "loss": 3.483,
      "step": 14
    },
    {
      "epoch": 0.002174858634188778,
      "grad_norm": 18.8242130279541,
      "learning_rate": 7.500000000000001e-05,
      "loss": 3.2867,
      "step": 15
    },
    {
      "epoch": 0.002319849209801363,
      "grad_norm": 30.02107048034668,
      "learning_rate": 6.545084971874738e-05,
      "loss": 3.4131,
      "step": 16
    },
    {
      "epoch": 0.002319849209801363,
      "eval_loss": 2.5611982345581055,
      "eval_runtime": 166.7524,
      "eval_samples_per_second": 34.83,
      "eval_steps_per_second": 4.354,
      "step": 16
    },
    {
      "epoch": 0.002464839785413948,
      "grad_norm": 16.698036193847656,
      "learning_rate": 5.522642316338268e-05,
      "loss": 3.2017,
      "step": 17
    },
    {
      "epoch": 0.0026098303610265334,
      "grad_norm": 13.388322830200195,
      "learning_rate": 4.477357683661734e-05,
      "loss": 2.9257,
      "step": 18
    },
    {
      "epoch": 0.0027548209366391185,
      "grad_norm": 13.722065925598145,
      "learning_rate": 3.4549150281252636e-05,
      "loss": 2.552,
      "step": 19
    },
    {
      "epoch": 0.0028998115122517037,
      "grad_norm": 14.578957557678223,
      "learning_rate": 2.500000000000001e-05,
      "loss": 3.4215,
      "step": 20
    },
    {
      "epoch": 0.0028998115122517037,
      "eval_loss": 2.112037420272827,
      "eval_runtime": 166.7887,
      "eval_samples_per_second": 34.823,
      "eval_steps_per_second": 4.353,
      "step": 20
    },
    {
      "epoch": 0.003044802087864289,
      "grad_norm": 16.224952697753906,
      "learning_rate": 1.6543469682057106e-05,
      "loss": 1.946,
      "step": 21
    },
    {
      "epoch": 0.003189792663476874,
      "grad_norm": 13.316004753112793,
      "learning_rate": 9.549150281252633e-06,
      "loss": 1.9954,
      "step": 22
    },
    {
      "epoch": 0.003334783239089459,
      "grad_norm": 12.274697303771973,
      "learning_rate": 4.322727117869951e-06,
      "loss": 3.0554,
      "step": 23
    },
    {
      "epoch": 0.0034797738147020443,
      "grad_norm": 12.169507026672363,
      "learning_rate": 1.0926199633097157e-06,
      "loss": 2.2489,
      "step": 24
    },
    {
      "epoch": 0.0034797738147020443,
      "eval_loss": 2.007943630218506,
      "eval_runtime": 169.3301,
      "eval_samples_per_second": 34.3,
      "eval_steps_per_second": 4.287,
      "step": 24
    },
    {
      "epoch": 0.0036247643903146295,
      "grad_norm": 11.978036880493164,
      "learning_rate": 0.0,
      "loss": 2.6409,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 25,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 25,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 2573421930086400.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}