{
  "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": 0.4298292398452759,
      "learning_rate": 0.003,
      "loss": 6.43610595703125,
      "step": 100
    },
    {
      "epoch": 0.082389289392379,
      "grad_norm": 0.38683682680130005,
      "learning_rate": 0.003,
      "loss": 5.0911407470703125,
      "step": 200
    },
    {
      "epoch": 0.12358393408856849,
      "grad_norm": 0.490421324968338,
      "learning_rate": 0.003,
      "loss": 4.339219055175781,
      "step": 300
    },
    {
      "epoch": 0.164778578784758,
      "grad_norm": 0.474597692489624,
      "learning_rate": 0.003,
      "loss": 4.0295562744140625,
      "step": 400
    },
    {
      "epoch": 0.2059732234809475,
      "grad_norm": 0.36108437180519104,
      "learning_rate": 0.003,
      "loss": 3.8877108764648436,
      "step": 500
    },
    {
      "epoch": 0.2059732234809475,
      "eval_loss": 3.847414255142212,
      "eval_runtime": 7.6229,
      "eval_samples_per_second": 421.1,
      "eval_steps_per_second": 52.736,
      "step": 500
    },
    {
      "epoch": 0.24716786817713698,
      "grad_norm": 0.26368337869644165,
      "learning_rate": 0.003,
      "loss": 3.797254638671875,
      "step": 600
    },
    {
      "epoch": 0.2883625128733265,
      "grad_norm": 0.3213416635990143,
      "learning_rate": 0.003,
      "loss": 3.721222229003906,
      "step": 700
    },
    {
      "epoch": 0.329557157569516,
      "grad_norm": 0.3457011878490448,
      "learning_rate": 0.003,
      "loss": 3.65634033203125,
      "step": 800
    },
    {
      "epoch": 0.3707518022657055,
      "grad_norm": 0.39577925205230713,
      "learning_rate": 0.003,
      "loss": 3.6097821044921874,
      "step": 900
    },
    {
      "epoch": 0.411946446961895,
      "grad_norm": 0.3584425449371338,
      "learning_rate": 0.003,
      "loss": 3.575661926269531,
      "step": 1000
    },
    {
      "epoch": 0.411946446961895,
      "eval_loss": 3.5647435188293457,
      "eval_runtime": 8.2293,
      "eval_samples_per_second": 390.071,
      "eval_steps_per_second": 48.85,
      "step": 1000
    },
    {
      "epoch": 0.45314109165808447,
      "grad_norm": 0.30220553278923035,
      "learning_rate": 0.003,
      "loss": 3.550927734375,
      "step": 1100
    },
    {
      "epoch": 0.49433573635427397,
      "grad_norm": 0.3348575234413147,
      "learning_rate": 0.003,
      "loss": 3.5292623901367186,
      "step": 1200
    },
    {
      "epoch": 0.5355303810504635,
      "grad_norm": 0.33219438791275024,
      "learning_rate": 0.003,
      "loss": 3.5094894409179687,
      "step": 1300
    },
    {
      "epoch": 0.576725025746653,
      "grad_norm": 0.30907726287841797,
      "learning_rate": 0.003,
      "loss": 3.497273254394531,
      "step": 1400
    },
    {
      "epoch": 0.6179196704428425,
      "grad_norm": 0.26499462127685547,
      "learning_rate": 0.003,
      "loss": 3.483502197265625,
      "step": 1500
    },
    {
      "epoch": 0.6179196704428425,
      "eval_loss": 3.479076385498047,
      "eval_runtime": 7.418,
      "eval_samples_per_second": 432.73,
      "eval_steps_per_second": 54.192,
      "step": 1500
    },
    {
      "epoch": 0.659114315139032,
      "grad_norm": 0.32156097888946533,
      "learning_rate": 0.003,
      "loss": 3.469326171875,
      "step": 1600
    },
    {
      "epoch": 0.7003089598352215,
      "grad_norm": 0.2879614531993866,
      "learning_rate": 0.003,
      "loss": 3.4609866333007813,
      "step": 1700
    },
    {
      "epoch": 0.741503604531411,
      "grad_norm": 0.28667426109313965,
      "learning_rate": 0.003,
      "loss": 3.4503070068359376,
      "step": 1800
    },
    {
      "epoch": 0.7826982492276005,
      "grad_norm": 0.24957764148712158,
      "learning_rate": 0.003,
      "loss": 3.439223327636719,
      "step": 1900
    },
    {
      "epoch": 0.82389289392379,
      "grad_norm": 0.2855299115180969,
      "learning_rate": 0.002899325557098001,
      "loss": 3.433879699707031,
      "step": 2000
    },
    {
      "epoch": 0.82389289392379,
      "eval_loss": 3.429241895675659,
      "eval_runtime": 7.6711,
      "eval_samples_per_second": 418.453,
      "eval_steps_per_second": 52.404,
      "step": 2000
    },
    {
      "epoch": 0.8650875386199794,
      "grad_norm": 0.2643311023712158,
      "learning_rate": 0.0022915870802995226,
      "loss": 3.418829040527344,
      "step": 2100
    },
    {
      "epoch": 0.9062821833161689,
      "grad_norm": 0.2072380781173706,
      "learning_rate": 0.0013644373889485982,
      "loss": 3.397191162109375,
      "step": 2200
    },
    {
      "epoch": 0.9474768280123584,
      "grad_norm": 0.16420814394950867,
      "learning_rate": 0.0004919882091667163,
      "loss": 3.369662170410156,
      "step": 2300
    },
    {
      "epoch": 0.9886714727085479,
      "grad_norm": 0.14552220702171326,
      "learning_rate": 2.6279207952956684e-05,
      "loss": 3.347156982421875,
      "step": 2400
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.3448657989501953,
      "eval_runtime": 8.6287,
      "eval_samples_per_second": 372.013,
      "eval_steps_per_second": 46.589,
      "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
}