{
  "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": 0.467864453792572,
      "learning_rate": 0.003,
      "loss": 6.407201538085937,
      "step": 100
    },
    {
      "epoch": 0.082389289392379,
      "grad_norm": 0.4472709596157074,
      "learning_rate": 0.003,
      "loss": 5.041720581054688,
      "step": 200
    },
    {
      "epoch": 0.12358393408856849,
      "grad_norm": 0.48611021041870117,
      "learning_rate": 0.003,
      "loss": 4.333825988769531,
      "step": 300
    },
    {
      "epoch": 0.164778578784758,
      "grad_norm": 0.406901091337204,
      "learning_rate": 0.003,
      "loss": 4.042262573242187,
      "step": 400
    },
    {
      "epoch": 0.2059732234809475,
      "grad_norm": 0.33796098828315735,
      "learning_rate": 0.003,
      "loss": 3.9043743896484373,
      "step": 500
    },
    {
      "epoch": 0.2059732234809475,
      "eval_loss": 3.865790843963623,
      "eval_runtime": 8.0265,
      "eval_samples_per_second": 399.925,
      "eval_steps_per_second": 50.084,
      "step": 500
    },
    {
      "epoch": 0.24716786817713698,
      "grad_norm": 0.4365800619125366,
      "learning_rate": 0.003,
      "loss": 3.8237649536132814,
      "step": 600
    },
    {
      "epoch": 0.2883625128733265,
      "grad_norm": 0.28054454922676086,
      "learning_rate": 0.003,
      "loss": 3.764461669921875,
      "step": 700
    },
    {
      "epoch": 0.329557157569516,
      "grad_norm": 0.29116520285606384,
      "learning_rate": 0.003,
      "loss": 3.7118209838867187,
      "step": 800
    },
    {
      "epoch": 0.3707518022657055,
      "grad_norm": 0.3120614290237427,
      "learning_rate": 0.003,
      "loss": 3.6665850830078126,
      "step": 900
    },
    {
      "epoch": 0.411946446961895,
      "grad_norm": 0.2823605239391327,
      "learning_rate": 0.003,
      "loss": 3.6290557861328123,
      "step": 1000
    },
    {
      "epoch": 0.411946446961895,
      "eval_loss": 3.618884801864624,
      "eval_runtime": 7.522,
      "eval_samples_per_second": 426.746,
      "eval_steps_per_second": 53.443,
      "step": 1000
    },
    {
      "epoch": 0.45314109165808447,
      "grad_norm": 0.32250627875328064,
      "learning_rate": 0.003,
      "loss": 3.5978604125976563,
      "step": 1100
    },
    {
      "epoch": 0.49433573635427397,
      "grad_norm": 0.25370901823043823,
      "learning_rate": 0.003,
      "loss": 3.5753305053710935,
      "step": 1200
    },
    {
      "epoch": 0.5355303810504635,
      "grad_norm": 0.27662038803100586,
      "learning_rate": 0.003,
      "loss": 3.553804626464844,
      "step": 1300
    },
    {
      "epoch": 0.576725025746653,
      "grad_norm": 0.2849913537502289,
      "learning_rate": 0.003,
      "loss": 3.5376666259765623,
      "step": 1400
    },
    {
      "epoch": 0.6179196704428425,
      "grad_norm": 0.2572985291481018,
      "learning_rate": 0.003,
      "loss": 3.5211285400390624,
      "step": 1500
    },
    {
      "epoch": 0.6179196704428425,
      "eval_loss": 3.521266460418701,
      "eval_runtime": 8.3868,
      "eval_samples_per_second": 382.744,
      "eval_steps_per_second": 47.932,
      "step": 1500
    },
    {
      "epoch": 0.659114315139032,
      "grad_norm": 0.21017690002918243,
      "learning_rate": 0.003,
      "loss": 3.5094705200195313,
      "step": 1600
    },
    {
      "epoch": 0.7003089598352215,
      "grad_norm": 0.2542063891887665,
      "learning_rate": 0.003,
      "loss": 3.4962704467773436,
      "step": 1700
    },
    {
      "epoch": 0.741503604531411,
      "grad_norm": 0.22395335137844086,
      "learning_rate": 0.003,
      "loss": 3.485750427246094,
      "step": 1800
    },
    {
      "epoch": 0.7826982492276005,
      "grad_norm": 0.27532121539115906,
      "learning_rate": 0.003,
      "loss": 3.4784066772460935,
      "step": 1900
    },
    {
      "epoch": 0.82389289392379,
      "grad_norm": 0.22537492215633392,
      "learning_rate": 0.002899325557098001,
      "loss": 3.4674105834960938,
      "step": 2000
    },
    {
      "epoch": 0.82389289392379,
      "eval_loss": 3.4714837074279785,
      "eval_runtime": 7.2122,
      "eval_samples_per_second": 445.079,
      "eval_steps_per_second": 55.739,
      "step": 2000
    },
    {
      "epoch": 0.8650875386199794,
      "grad_norm": 0.18755502998828888,
      "learning_rate": 0.0022915870802995226,
      "loss": 3.4546932983398437,
      "step": 2100
    },
    {
      "epoch": 0.9062821833161689,
      "grad_norm": 0.17484472692012787,
      "learning_rate": 0.0013644373889485982,
      "loss": 3.42761962890625,
      "step": 2200
    },
    {
      "epoch": 0.9474768280123584,
      "grad_norm": 0.1623256355524063,
      "learning_rate": 0.0004919882091667163,
      "loss": 3.4039578247070312,
      "step": 2300
    },
    {
      "epoch": 0.9886714727085479,
      "grad_norm": 0.1342345029115677,
      "learning_rate": 2.6279207952956684e-05,
      "loss": 3.3823727416992186,
      "step": 2400
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.383687973022461,
      "eval_runtime": 11.5434,
      "eval_samples_per_second": 278.081,
      "eval_steps_per_second": 34.825,
      "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
}