{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9900990099009901,
  "eval_steps": 7,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.039603960396039604,
      "grad_norm": 0.2005040943622589,
      "learning_rate": 0.0001,
      "loss": 1.222,
      "step": 1
    },
    {
      "epoch": 0.039603960396039604,
      "eval_loss": 1.2184828519821167,
      "eval_runtime": 135.46,
      "eval_samples_per_second": 7.412,
      "eval_steps_per_second": 0.93,
      "step": 1
    },
    {
      "epoch": 0.07920792079207921,
      "grad_norm": 0.19737568497657776,
      "learning_rate": 0.0002,
      "loss": 1.2035,
      "step": 2
    },
    {
      "epoch": 0.1188118811881188,
      "grad_norm": 0.22430424392223358,
      "learning_rate": 0.00019978589232386035,
      "loss": 1.2364,
      "step": 3
    },
    {
      "epoch": 0.15841584158415842,
      "grad_norm": 0.3319801986217499,
      "learning_rate": 0.00019914448613738106,
      "loss": 1.1084,
      "step": 4
    },
    {
      "epoch": 0.19801980198019803,
      "grad_norm": 0.2900150418281555,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.0104,
      "step": 5
    },
    {
      "epoch": 0.2376237623762376,
      "grad_norm": 0.3314291834831238,
      "learning_rate": 0.00019659258262890683,
      "loss": 0.9168,
      "step": 6
    },
    {
      "epoch": 0.27722772277227725,
      "grad_norm": 0.4147993326187134,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.9168,
      "step": 7
    },
    {
      "epoch": 0.27722772277227725,
      "eval_loss": 0.8507946729660034,
      "eval_runtime": 135.7758,
      "eval_samples_per_second": 7.395,
      "eval_steps_per_second": 0.928,
      "step": 7
    },
    {
      "epoch": 0.31683168316831684,
      "grad_norm": 0.32303664088249207,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.8745,
      "step": 8
    },
    {
      "epoch": 0.3564356435643564,
      "grad_norm": 0.19321317970752716,
      "learning_rate": 0.00018968727415326884,
      "loss": 0.8174,
      "step": 9
    },
    {
      "epoch": 0.39603960396039606,
      "grad_norm": 0.18172240257263184,
      "learning_rate": 0.00018660254037844388,
      "loss": 0.8014,
      "step": 10
    },
    {
      "epoch": 0.43564356435643564,
      "grad_norm": 0.13811971247196198,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.7884,
      "step": 11
    },
    {
      "epoch": 0.4752475247524752,
      "grad_norm": 0.13254143297672272,
      "learning_rate": 0.00017933533402912354,
      "loss": 0.7617,
      "step": 12
    },
    {
      "epoch": 0.5148514851485149,
      "grad_norm": 0.10325208306312561,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.7857,
      "step": 13
    },
    {
      "epoch": 0.5544554455445545,
      "grad_norm": 0.08808338642120361,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.7745,
      "step": 14
    },
    {
      "epoch": 0.5544554455445545,
      "eval_loss": 0.7478359937667847,
      "eval_runtime": 135.6094,
      "eval_samples_per_second": 7.404,
      "eval_steps_per_second": 0.929,
      "step": 14
    },
    {
      "epoch": 0.594059405940594,
      "grad_norm": 0.0986776053905487,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.7461,
      "step": 15
    },
    {
      "epoch": 0.6336633663366337,
      "grad_norm": 0.1371486485004425,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.7296,
      "step": 16
    },
    {
      "epoch": 0.6732673267326733,
      "grad_norm": 0.12637566030025482,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.776,
      "step": 17
    },
    {
      "epoch": 0.7128712871287128,
      "grad_norm": 0.09393499791622162,
      "learning_rate": 0.00015000000000000001,
      "loss": 0.7159,
      "step": 18
    },
    {
      "epoch": 0.7524752475247525,
      "grad_norm": 0.07980824261903763,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.7219,
      "step": 19
    },
    {
      "epoch": 0.7920792079207921,
      "grad_norm": 0.07864726334810257,
      "learning_rate": 0.000138268343236509,
      "loss": 0.7282,
      "step": 20
    },
    {
      "epoch": 0.8316831683168316,
      "grad_norm": 0.08049978315830231,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.7129,
      "step": 21
    },
    {
      "epoch": 0.8316831683168316,
      "eval_loss": 0.713334321975708,
      "eval_runtime": 135.7568,
      "eval_samples_per_second": 7.396,
      "eval_steps_per_second": 0.928,
      "step": 21
    },
    {
      "epoch": 0.8712871287128713,
      "grad_norm": 0.07534715533256531,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.7116,
      "step": 22
    },
    {
      "epoch": 0.9108910891089109,
      "grad_norm": 0.07699955999851227,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.7159,
      "step": 23
    },
    {
      "epoch": 0.9504950495049505,
      "grad_norm": 0.09450427442789078,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.7165,
      "step": 24
    },
    {
      "epoch": 0.9900990099009901,
      "grad_norm": 0.08074381202459335,
      "learning_rate": 0.00010654031292301432,
      "loss": 0.6931,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "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": 1.492020904329216e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}