{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 2428,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0411946446961895,
      "grad_norm": 0.5167902112007141,
      "learning_rate": 0.003,
      "loss": 5.962776489257813,
      "step": 100
    },
    {
      "epoch": 0.082389289392379,
      "grad_norm": 0.6578283905982971,
      "learning_rate": 0.003,
      "loss": 4.3772125244140625,
      "step": 200
    },
    {
      "epoch": 0.12358393408856849,
      "grad_norm": 0.7207351326942444,
      "learning_rate": 0.003,
      "loss": 3.604791564941406,
      "step": 300
    },
    {
      "epoch": 0.164778578784758,
      "grad_norm": 0.49143338203430176,
      "learning_rate": 0.003,
      "loss": 3.2285305786132814,
      "step": 400
    },
    {
      "epoch": 0.2059732234809475,
      "grad_norm": 0.5450193881988525,
      "learning_rate": 0.003,
      "loss": 2.997611083984375,
      "step": 500
    },
    {
      "epoch": 0.2059732234809475,
      "eval_loss": 2.9541826248168945,
      "eval_runtime": 8.7168,
      "eval_samples_per_second": 368.256,
      "eval_steps_per_second": 46.118,
      "step": 500
    },
    {
      "epoch": 0.24716786817713698,
      "grad_norm": 0.3710590600967407,
      "learning_rate": 0.003,
      "loss": 2.8572198486328126,
      "step": 600
    },
    {
      "epoch": 0.2883625128733265,
      "grad_norm": 0.43497762084007263,
      "learning_rate": 0.003,
      "loss": 2.7712442016601564,
      "step": 700
    },
    {
      "epoch": 0.329557157569516,
      "grad_norm": 0.44306352734565735,
      "learning_rate": 0.003,
      "loss": 2.7086080932617187,
      "step": 800
    },
    {
      "epoch": 0.3707518022657055,
      "grad_norm": 0.39232972264289856,
      "learning_rate": 0.003,
      "loss": 2.6619219970703125,
      "step": 900
    },
    {
      "epoch": 0.411946446961895,
      "grad_norm": 0.34500154852867126,
      "learning_rate": 0.003,
      "loss": 2.6315206909179687,
      "step": 1000
    },
    {
      "epoch": 0.411946446961895,
      "eval_loss": 2.648106813430786,
      "eval_runtime": 7.4182,
      "eval_samples_per_second": 432.722,
      "eval_steps_per_second": 54.191,
      "step": 1000
    },
    {
      "epoch": 0.45314109165808447,
      "grad_norm": 0.3188333213329315,
      "learning_rate": 0.003,
      "loss": 2.6055862426757814,
      "step": 1100
    },
    {
      "epoch": 0.49433573635427397,
      "grad_norm": 0.29628098011016846,
      "learning_rate": 0.003,
      "loss": 2.5831158447265623,
      "step": 1200
    },
    {
      "epoch": 0.5355303810504635,
      "grad_norm": 0.2794441282749176,
      "learning_rate": 0.003,
      "loss": 2.567415771484375,
      "step": 1300
    },
    {
      "epoch": 0.576725025746653,
      "grad_norm": 0.2878789007663727,
      "learning_rate": 0.003,
      "loss": 2.5535826110839843,
      "step": 1400
    },
    {
      "epoch": 0.6179196704428425,
      "grad_norm": 0.3040012717247009,
      "learning_rate": 0.003,
      "loss": 2.5389122009277343,
      "step": 1500
    },
    {
      "epoch": 0.6179196704428425,
      "eval_loss": 2.558194637298584,
      "eval_runtime": 8.0558,
      "eval_samples_per_second": 398.469,
      "eval_steps_per_second": 49.902,
      "step": 1500
    },
    {
      "epoch": 0.659114315139032,
      "grad_norm": 0.2754426598548889,
      "learning_rate": 0.003,
      "loss": 2.5258233642578123,
      "step": 1600
    },
    {
      "epoch": 0.7003089598352215,
      "grad_norm": 0.2642139196395874,
      "learning_rate": 0.003,
      "loss": 2.5123500061035156,
      "step": 1700
    },
    {
      "epoch": 0.741503604531411,
      "grad_norm": 0.31137749552726746,
      "learning_rate": 0.003,
      "loss": 2.5001824951171874,
      "step": 1800
    },
    {
      "epoch": 0.7826982492276005,
      "grad_norm": 0.2772506773471832,
      "learning_rate": 0.003,
      "loss": 2.4918637084960937,
      "step": 1900
    },
    {
      "epoch": 0.82389289392379,
      "grad_norm": 0.26965758204460144,
      "learning_rate": 0.002899325557098001,
      "loss": 2.4782290649414063,
      "step": 2000
    },
    {
      "epoch": 0.82389289392379,
      "eval_loss": 2.5082216262817383,
      "eval_runtime": 8.1628,
      "eval_samples_per_second": 393.246,
      "eval_steps_per_second": 49.248,
      "step": 2000
    },
    {
      "epoch": 0.8650875386199794,
      "grad_norm": 0.23774883151054382,
      "learning_rate": 0.0022915870802995226,
      "loss": 2.467481842041016,
      "step": 2100
    },
    {
      "epoch": 0.9062821833161689,
      "grad_norm": 0.2045634537935257,
      "learning_rate": 0.0013644373889485982,
      "loss": 2.442911834716797,
      "step": 2200
    },
    {
      "epoch": 0.9474768280123584,
      "grad_norm": 0.20750091969966888,
      "learning_rate": 0.0004919882091667163,
      "loss": 2.410100555419922,
      "step": 2300
    },
    {
      "epoch": 0.9886714727085479,
      "grad_norm": 0.15250912308692932,
      "learning_rate": 2.6279207952956684e-05,
      "loss": 2.3908013916015625,
      "step": 2400
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.4129438400268555,
      "eval_runtime": 8.274,
      "eval_samples_per_second": 387.961,
      "eval_steps_per_second": 48.586,
      "step": 2428
    }
  ],
  "logging_steps": 100,
  "max_steps": 2428,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4331665489920000.0,
  "train_batch_size": 400,
  "trial_name": null,
  "trial_params": null
}