{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.03422899195618689,
  "eval_steps": 500,
  "global_step": 25,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0013691596782474755,
      "grad_norm": 3.442312002182007,
      "learning_rate": 0.0001,
      "loss": 2.1747,
      "step": 1
    },
    {
      "epoch": 0.002738319356494951,
      "grad_norm": 3.3342490196228027,
      "learning_rate": 0.0002,
      "loss": 2.0423,
      "step": 2
    },
    {
      "epoch": 0.004107479034742427,
      "grad_norm": 2.533416986465454,
      "learning_rate": 0.00019978589232386035,
      "loss": 1.6375,
      "step": 3
    },
    {
      "epoch": 0.005476638712989902,
      "grad_norm": 1.5912055969238281,
      "learning_rate": 0.00019914448613738106,
      "loss": 0.9787,
      "step": 4
    },
    {
      "epoch": 0.006845798391237378,
      "grad_norm": 1.6528733968734741,
      "learning_rate": 0.00019807852804032305,
      "loss": 1.1491,
      "step": 5
    },
    {
      "epoch": 0.008214958069484853,
      "grad_norm": 2.063443422317505,
      "learning_rate": 0.00019659258262890683,
      "loss": 1.0858,
      "step": 6
    },
    {
      "epoch": 0.009584117747732329,
      "grad_norm": 2.0438201427459717,
      "learning_rate": 0.0001946930129495106,
      "loss": 0.9206,
      "step": 7
    },
    {
      "epoch": 0.010953277425979804,
      "grad_norm": 1.7179049253463745,
      "learning_rate": 0.0001923879532511287,
      "loss": 0.9812,
      "step": 8
    },
    {
      "epoch": 0.01232243710422728,
      "grad_norm": 1.064609408378601,
      "learning_rate": 0.00018968727415326884,
      "loss": 1.097,
      "step": 9
    },
    {
      "epoch": 0.013691596782474755,
      "grad_norm": 1.3474338054656982,
      "learning_rate": 0.00018660254037844388,
      "loss": 1.0998,
      "step": 10
    },
    {
      "epoch": 0.015060756460722231,
      "grad_norm": 0.9349080920219421,
      "learning_rate": 0.00018314696123025454,
      "loss": 0.7325,
      "step": 11
    },
    {
      "epoch": 0.016429916138969707,
      "grad_norm": 1.1312912702560425,
      "learning_rate": 0.00017933533402912354,
      "loss": 1.0285,
      "step": 12
    },
    {
      "epoch": 0.017799075817217184,
      "grad_norm": 1.008134126663208,
      "learning_rate": 0.00017518398074789775,
      "loss": 0.7593,
      "step": 13
    },
    {
      "epoch": 0.019168235495464658,
      "grad_norm": 0.9038427472114563,
      "learning_rate": 0.00017071067811865476,
      "loss": 0.7422,
      "step": 14
    },
    {
      "epoch": 0.020537395173712135,
      "grad_norm": 1.281387448310852,
      "learning_rate": 0.00016593458151000688,
      "loss": 0.8447,
      "step": 15
    },
    {
      "epoch": 0.02190655485195961,
      "grad_norm": 0.9998169541358948,
      "learning_rate": 0.00016087614290087208,
      "loss": 0.8007,
      "step": 16
    },
    {
      "epoch": 0.023275714530207086,
      "grad_norm": 0.9114604592323303,
      "learning_rate": 0.00015555702330196023,
      "loss": 0.8013,
      "step": 17
    },
    {
      "epoch": 0.02464487420845456,
      "grad_norm": 1.1608867645263672,
      "learning_rate": 0.00015000000000000001,
      "loss": 1.0643,
      "step": 18
    },
    {
      "epoch": 0.026014033886702037,
      "grad_norm": 1.2039852142333984,
      "learning_rate": 0.00014422886902190014,
      "loss": 0.8865,
      "step": 19
    },
    {
      "epoch": 0.02738319356494951,
      "grad_norm": 0.898479700088501,
      "learning_rate": 0.000138268343236509,
      "loss": 0.619,
      "step": 20
    },
    {
      "epoch": 0.028752353243196988,
      "grad_norm": 1.2546143531799316,
      "learning_rate": 0.00013214394653031616,
      "loss": 0.9154,
      "step": 21
    },
    {
      "epoch": 0.030121512921444462,
      "grad_norm": 0.962232232093811,
      "learning_rate": 0.00012588190451025207,
      "loss": 0.7535,
      "step": 22
    },
    {
      "epoch": 0.03149067259969194,
      "grad_norm": 1.122208595275879,
      "learning_rate": 0.00011950903220161285,
      "loss": 0.8251,
      "step": 23
    },
    {
      "epoch": 0.03285983227793941,
      "grad_norm": 1.0500138998031616,
      "learning_rate": 0.00011305261922200519,
      "loss": 0.8844,
      "step": 24
    },
    {
      "epoch": 0.03422899195618689,
      "grad_norm": 1.0177123546600342,
      "learning_rate": 0.00010654031292301432,
      "loss": 1.0503,
      "step": 25
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "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": 3.83447180771328e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}