{
  "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": 0.3926346004009247,
      "learning_rate": 0.003,
      "loss": 6.1603759765625,
      "step": 100
    },
    {
      "epoch": 0.082389289392379,
      "grad_norm": 0.42686447501182556,
      "learning_rate": 0.003,
      "loss": 4.739006652832031,
      "step": 200
    },
    {
      "epoch": 0.12358393408856849,
      "grad_norm": 0.5154397487640381,
      "learning_rate": 0.003,
      "loss": 4.014122314453125,
      "step": 300
    },
    {
      "epoch": 0.164778578784758,
      "grad_norm": 0.44306617975234985,
      "learning_rate": 0.003,
      "loss": 3.695447998046875,
      "step": 400
    },
    {
      "epoch": 0.2059732234809475,
      "grad_norm": 0.5973666310310364,
      "learning_rate": 0.003,
      "loss": 3.546534423828125,
      "step": 500
    },
    {
      "epoch": 0.2059732234809475,
      "eval_loss": 3.5068907737731934,
      "eval_runtime": 8.733,
      "eval_samples_per_second": 367.572,
      "eval_steps_per_second": 46.032,
      "step": 500
    },
    {
      "epoch": 0.24716786817713698,
      "grad_norm": 0.4289214611053467,
      "learning_rate": 0.003,
      "loss": 3.46018798828125,
      "step": 600
    },
    {
      "epoch": 0.2883625128733265,
      "grad_norm": 0.29066139459609985,
      "learning_rate": 0.003,
      "loss": 3.4029681396484377,
      "step": 700
    },
    {
      "epoch": 0.329557157569516,
      "grad_norm": 0.29461681842803955,
      "learning_rate": 0.003,
      "loss": 3.3588226318359373,
      "step": 800
    },
    {
      "epoch": 0.3707518022657055,
      "grad_norm": 0.3961299657821655,
      "learning_rate": 0.003,
      "loss": 3.327505798339844,
      "step": 900
    },
    {
      "epoch": 0.411946446961895,
      "grad_norm": 0.29704517126083374,
      "learning_rate": 0.003,
      "loss": 3.2994342041015625,
      "step": 1000
    },
    {
      "epoch": 0.411946446961895,
      "eval_loss": 3.28598952293396,
      "eval_runtime": 8.6935,
      "eval_samples_per_second": 369.243,
      "eval_steps_per_second": 46.242,
      "step": 1000
    },
    {
      "epoch": 0.45314109165808447,
      "grad_norm": 0.2760719358921051,
      "learning_rate": 0.003,
      "loss": 3.2774252319335937,
      "step": 1100
    },
    {
      "epoch": 0.49433573635427397,
      "grad_norm": 0.2545988857746124,
      "learning_rate": 0.003,
      "loss": 3.2593310546875,
      "step": 1200
    },
    {
      "epoch": 0.5355303810504635,
      "grad_norm": 0.30400964617729187,
      "learning_rate": 0.003,
      "loss": 3.24214599609375,
      "step": 1300
    },
    {
      "epoch": 0.576725025746653,
      "grad_norm": 0.26717409491539,
      "learning_rate": 0.003,
      "loss": 3.2309466552734376,
      "step": 1400
    },
    {
      "epoch": 0.6179196704428425,
      "grad_norm": 0.25934040546417236,
      "learning_rate": 0.003,
      "loss": 3.2188458251953125,
      "step": 1500
    },
    {
      "epoch": 0.6179196704428425,
      "eval_loss": 3.21104097366333,
      "eval_runtime": 8.6622,
      "eval_samples_per_second": 370.574,
      "eval_steps_per_second": 46.408,
      "step": 1500
    },
    {
      "epoch": 0.659114315139032,
      "grad_norm": 0.2686704695224762,
      "learning_rate": 0.003,
      "loss": 3.2066079711914064,
      "step": 1600
    },
    {
      "epoch": 0.7003089598352215,
      "grad_norm": 0.24446773529052734,
      "learning_rate": 0.003,
      "loss": 3.1978436279296876,
      "step": 1700
    },
    {
      "epoch": 0.741503604531411,
      "grad_norm": 0.23034396767616272,
      "learning_rate": 0.003,
      "loss": 3.1878036499023437,
      "step": 1800
    },
    {
      "epoch": 0.7826982492276005,
      "grad_norm": 0.2868192195892334,
      "learning_rate": 0.003,
      "loss": 3.179383544921875,
      "step": 1900
    },
    {
      "epoch": 0.82389289392379,
      "grad_norm": 0.3479514420032501,
      "learning_rate": 0.002899325557098001,
      "loss": 3.1715652465820314,
      "step": 2000
    },
    {
      "epoch": 0.82389289392379,
      "eval_loss": 3.167982816696167,
      "eval_runtime": 9.261,
      "eval_samples_per_second": 346.616,
      "eval_steps_per_second": 43.408,
      "step": 2000
    },
    {
      "epoch": 0.8650875386199794,
      "grad_norm": 0.21624135971069336,
      "learning_rate": 0.0022915870802995226,
      "loss": 3.1575164794921875,
      "step": 2100
    },
    {
      "epoch": 0.9062821833161689,
      "grad_norm": 0.17490530014038086,
      "learning_rate": 0.0013644373889485982,
      "loss": 3.1341757202148437,
      "step": 2200
    },
    {
      "epoch": 0.9474768280123584,
      "grad_norm": 0.15521171689033508,
      "learning_rate": 0.0004919882091667163,
      "loss": 3.109773864746094,
      "step": 2300
    },
    {
      "epoch": 0.9886714727085479,
      "grad_norm": 0.13293710350990295,
      "learning_rate": 2.6279207952956684e-05,
      "loss": 3.0883328247070314,
      "step": 2400
    },
    {
      "epoch": 1.0,
      "eval_loss": 3.0843801498413086,
      "eval_runtime": 11.6143,
      "eval_samples_per_second": 276.384,
      "eval_steps_per_second": 34.613,
      "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
}