{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0949667616334283,
  "eval_steps": 25,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.003798670465337132,
      "grad_norm": 5.763856410980225,
      "learning_rate": 3.3333333333333335e-05,
      "loss": 1.3805,
      "step": 1
    },
    {
      "epoch": 0.003798670465337132,
      "eval_loss": 1.6539767980575562,
      "eval_runtime": 46.0435,
      "eval_samples_per_second": 4.822,
      "eval_steps_per_second": 2.411,
      "step": 1
    },
    {
      "epoch": 0.007597340930674264,
      "grad_norm": 10.064556121826172,
      "learning_rate": 6.666666666666667e-05,
      "loss": 1.3331,
      "step": 2
    },
    {
      "epoch": 0.011396011396011397,
      "grad_norm": 4.493223190307617,
      "learning_rate": 0.0001,
      "loss": 1.2743,
      "step": 3
    },
    {
      "epoch": 0.015194681861348529,
      "grad_norm": 2.946624755859375,
      "learning_rate": 9.99524110790929e-05,
      "loss": 0.8182,
      "step": 4
    },
    {
      "epoch": 0.01899335232668566,
      "grad_norm": 2.3877036571502686,
      "learning_rate": 9.980973490458728e-05,
      "loss": 0.4942,
      "step": 5
    },
    {
      "epoch": 0.022792022792022793,
      "grad_norm": 2.079784631729126,
      "learning_rate": 9.957224306869053e-05,
      "loss": 0.3639,
      "step": 6
    },
    {
      "epoch": 0.026590693257359924,
      "grad_norm": 2.2234725952148438,
      "learning_rate": 9.924038765061042e-05,
      "loss": 0.2986,
      "step": 7
    },
    {
      "epoch": 0.030389363722697058,
      "grad_norm": 2.4654929637908936,
      "learning_rate": 9.881480035599667e-05,
      "loss": 0.3149,
      "step": 8
    },
    {
      "epoch": 0.03418803418803419,
      "grad_norm": 1.5854908227920532,
      "learning_rate": 9.829629131445342e-05,
      "loss": 0.2439,
      "step": 9
    },
    {
      "epoch": 0.03798670465337132,
      "grad_norm": 1.5591164827346802,
      "learning_rate": 9.768584753741134e-05,
      "loss": 0.2072,
      "step": 10
    },
    {
      "epoch": 0.04178537511870845,
      "grad_norm": 1.7570960521697998,
      "learning_rate": 9.698463103929542e-05,
      "loss": 0.2455,
      "step": 11
    },
    {
      "epoch": 0.045584045584045586,
      "grad_norm": 1.3588300943374634,
      "learning_rate": 9.619397662556435e-05,
      "loss": 0.2317,
      "step": 12
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 1.2992509603500366,
      "learning_rate": 9.53153893518325e-05,
      "loss": 0.2435,
      "step": 13
    },
    {
      "epoch": 0.05318138651471985,
      "grad_norm": 1.2096527814865112,
      "learning_rate": 9.435054165891109e-05,
      "loss": 0.1905,
      "step": 14
    },
    {
      "epoch": 0.05698005698005698,
      "grad_norm": 1.542781114578247,
      "learning_rate": 9.330127018922194e-05,
      "loss": 0.2319,
      "step": 15
    },
    {
      "epoch": 0.060778727445394115,
      "grad_norm": 1.497053861618042,
      "learning_rate": 9.21695722906443e-05,
      "loss": 0.2579,
      "step": 16
    },
    {
      "epoch": 0.06457739791073125,
      "grad_norm": 0.8226407766342163,
      "learning_rate": 9.09576022144496e-05,
      "loss": 0.1359,
      "step": 17
    },
    {
      "epoch": 0.06837606837606838,
      "grad_norm": 1.5668431520462036,
      "learning_rate": 8.966766701456177e-05,
      "loss": 0.196,
      "step": 18
    },
    {
      "epoch": 0.0721747388414055,
      "grad_norm": 0.9736147522926331,
      "learning_rate": 8.83022221559489e-05,
      "loss": 0.147,
      "step": 19
    },
    {
      "epoch": 0.07597340930674264,
      "grad_norm": 1.0604015588760376,
      "learning_rate": 8.68638668405062e-05,
      "loss": 0.157,
      "step": 20
    },
    {
      "epoch": 0.07977207977207977,
      "grad_norm": 1.4285651445388794,
      "learning_rate": 8.535533905932738e-05,
      "loss": 0.1586,
      "step": 21
    },
    {
      "epoch": 0.0835707502374169,
      "grad_norm": 1.30019211769104,
      "learning_rate": 8.377951038078302e-05,
      "loss": 0.1612,
      "step": 22
    },
    {
      "epoch": 0.08736942070275404,
      "grad_norm": 1.120355248451233,
      "learning_rate": 8.213938048432697e-05,
      "loss": 0.1544,
      "step": 23
    },
    {
      "epoch": 0.09116809116809117,
      "grad_norm": 1.0541555881500244,
      "learning_rate": 8.043807145043604e-05,
      "loss": 0.177,
      "step": 24
    },
    {
      "epoch": 0.0949667616334283,
      "grad_norm": 4.731549263000488,
      "learning_rate": 7.86788218175523e-05,
      "loss": 0.1304,
      "step": 25
    },
    {
      "epoch": 0.0949667616334283,
      "eval_loss": 0.13617277145385742,
      "eval_runtime": 46.0992,
      "eval_samples_per_second": 4.816,
      "eval_steps_per_second": 2.408,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 75,
  "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": 4.1446136610816e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}