{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0022476961114857273,
  "eval_steps": 9,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 8.990784445942908e-05,
      "grad_norm": 15.35192584991455,
      "learning_rate": 1e-05,
      "loss": 12.6326,
      "step": 1
    },
    {
      "epoch": 8.990784445942908e-05,
      "eval_loss": 12.586104393005371,
      "eval_runtime": 276.5266,
      "eval_samples_per_second": 33.874,
      "eval_steps_per_second": 4.235,
      "step": 1
    },
    {
      "epoch": 0.00017981568891885816,
      "grad_norm": 16.091136932373047,
      "learning_rate": 2e-05,
      "loss": 12.5988,
      "step": 2
    },
    {
      "epoch": 0.00026972353337828726,
      "grad_norm": 14.455317497253418,
      "learning_rate": 3e-05,
      "loss": 12.5276,
      "step": 3
    },
    {
      "epoch": 0.0003596313778377163,
      "grad_norm": 15.562151908874512,
      "learning_rate": 4e-05,
      "loss": 12.5544,
      "step": 4
    },
    {
      "epoch": 0.0004495392222971454,
      "grad_norm": 13.742938995361328,
      "learning_rate": 5e-05,
      "loss": 12.5895,
      "step": 5
    },
    {
      "epoch": 0.0005394470667565745,
      "grad_norm": 14.714332580566406,
      "learning_rate": 6e-05,
      "loss": 12.6172,
      "step": 6
    },
    {
      "epoch": 0.0006293549112160036,
      "grad_norm": 11.049238204956055,
      "learning_rate": 7e-05,
      "loss": 12.4842,
      "step": 7
    },
    {
      "epoch": 0.0007192627556754326,
      "grad_norm": 13.16402816772461,
      "learning_rate": 8e-05,
      "loss": 12.302,
      "step": 8
    },
    {
      "epoch": 0.0008091706001348617,
      "grad_norm": 12.623836517333984,
      "learning_rate": 9e-05,
      "loss": 12.2529,
      "step": 9
    },
    {
      "epoch": 0.0008091706001348617,
      "eval_loss": 12.082995414733887,
      "eval_runtime": 277.7717,
      "eval_samples_per_second": 33.722,
      "eval_steps_per_second": 4.216,
      "step": 9
    },
    {
      "epoch": 0.0008990784445942908,
      "grad_norm": 10.00021743774414,
      "learning_rate": 0.0001,
      "loss": 12.0075,
      "step": 10
    },
    {
      "epoch": 0.0009889862890537198,
      "grad_norm": 9.958125114440918,
      "learning_rate": 9.99695413509548e-05,
      "loss": 11.9523,
      "step": 11
    },
    {
      "epoch": 0.001078894133513149,
      "grad_norm": 10.316842079162598,
      "learning_rate": 9.987820251299122e-05,
      "loss": 11.8709,
      "step": 12
    },
    {
      "epoch": 0.001168801977972578,
      "grad_norm": 10.072561264038086,
      "learning_rate": 9.972609476841367e-05,
      "loss": 11.7194,
      "step": 13
    },
    {
      "epoch": 0.0012587098224320073,
      "grad_norm": 9.017184257507324,
      "learning_rate": 9.951340343707852e-05,
      "loss": 11.5661,
      "step": 14
    },
    {
      "epoch": 0.0013486176668914363,
      "grad_norm": 8.668551445007324,
      "learning_rate": 9.924038765061042e-05,
      "loss": 11.4991,
      "step": 15
    },
    {
      "epoch": 0.0014385255113508653,
      "grad_norm": 8.481941223144531,
      "learning_rate": 9.890738003669029e-05,
      "loss": 11.3203,
      "step": 16
    },
    {
      "epoch": 0.0015284333558102945,
      "grad_norm": 7.682249546051025,
      "learning_rate": 9.851478631379982e-05,
      "loss": 11.2815,
      "step": 17
    },
    {
      "epoch": 0.0016183412002697235,
      "grad_norm": 7.486232280731201,
      "learning_rate": 9.806308479691595e-05,
      "loss": 11.1782,
      "step": 18
    },
    {
      "epoch": 0.0016183412002697235,
      "eval_loss": 11.049551010131836,
      "eval_runtime": 277.8127,
      "eval_samples_per_second": 33.717,
      "eval_steps_per_second": 4.215,
      "step": 18
    },
    {
      "epoch": 0.0017082490447291527,
      "grad_norm": 7.089673042297363,
      "learning_rate": 9.755282581475769e-05,
      "loss": 10.9657,
      "step": 19
    },
    {
      "epoch": 0.0017981568891885817,
      "grad_norm": 6.506858825683594,
      "learning_rate": 9.698463103929542e-05,
      "loss": 10.9544,
      "step": 20
    },
    {
      "epoch": 0.001888064733648011,
      "grad_norm": 6.114770412445068,
      "learning_rate": 9.635919272833938e-05,
      "loss": 10.8534,
      "step": 21
    },
    {
      "epoch": 0.0019779725781074397,
      "grad_norm": 5.774037837982178,
      "learning_rate": 9.567727288213005e-05,
      "loss": 10.7668,
      "step": 22
    },
    {
      "epoch": 0.002067880422566869,
      "grad_norm": 5.377146244049072,
      "learning_rate": 9.493970231495835e-05,
      "loss": 10.7447,
      "step": 23
    },
    {
      "epoch": 0.002157788267026298,
      "grad_norm": 4.897111892700195,
      "learning_rate": 9.414737964294636e-05,
      "loss": 10.5888,
      "step": 24
    },
    {
      "epoch": 0.0022476961114857273,
      "grad_norm": 4.556328773498535,
      "learning_rate": 9.330127018922194e-05,
      "loss": 10.5711,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 100,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 13303264837632.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}