{
  "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": 0.6597224473953247,
      "learning_rate": 0.003,
      "loss": 6.157908325195312,
      "step": 100
    },
    {
      "epoch": 0.082389289392379,
      "grad_norm": 0.6448944211006165,
      "learning_rate": 0.003,
      "loss": 4.372836303710938,
      "step": 200
    },
    {
      "epoch": 0.12358393408856849,
      "grad_norm": 0.6967822909355164,
      "learning_rate": 0.003,
      "loss": 3.6461520385742188,
      "step": 300
    },
    {
      "epoch": 0.164778578784758,
      "grad_norm": 0.41282591223716736,
      "learning_rate": 0.003,
      "loss": 3.4010238647460938,
      "step": 400
    },
    {
      "epoch": 0.2059732234809475,
      "grad_norm": 0.3191543221473694,
      "learning_rate": 0.003,
      "loss": 3.2758245849609375,
      "step": 500
    },
    {
      "epoch": 0.2059732234809475,
      "eval_loss": 3.237875461578369,
      "eval_runtime": 8.2925,
      "eval_samples_per_second": 387.096,
      "eval_steps_per_second": 48.477,
      "step": 500
    },
    {
      "epoch": 0.24716786817713698,
      "grad_norm": 0.3816635310649872,
      "learning_rate": 0.003,
      "loss": 3.1946185302734373,
      "step": 600
    },
    {
      "epoch": 0.2883625128733265,
      "grad_norm": 0.4032311737537384,
      "learning_rate": 0.003,
      "loss": 3.121783447265625,
      "step": 700
    },
    {
      "epoch": 0.329557157569516,
      "grad_norm": 0.30259284377098083,
      "learning_rate": 0.003,
      "loss": 3.067249450683594,
      "step": 800
    },
    {
      "epoch": 0.3707518022657055,
      "grad_norm": 0.2819083034992218,
      "learning_rate": 0.003,
      "loss": 3.027862854003906,
      "step": 900
    },
    {
      "epoch": 0.411946446961895,
      "grad_norm": 0.2758381962776184,
      "learning_rate": 0.003,
      "loss": 2.99330078125,
      "step": 1000
    },
    {
      "epoch": 0.411946446961895,
      "eval_loss": 2.9818687438964844,
      "eval_runtime": 8.8898,
      "eval_samples_per_second": 361.088,
      "eval_steps_per_second": 45.22,
      "step": 1000
    },
    {
      "epoch": 0.45314109165808447,
      "grad_norm": 0.2729312479496002,
      "learning_rate": 0.003,
      "loss": 2.961981201171875,
      "step": 1100
    },
    {
      "epoch": 0.49433573635427397,
      "grad_norm": 0.2777229845523834,
      "learning_rate": 0.003,
      "loss": 2.935169982910156,
      "step": 1200
    },
    {
      "epoch": 0.5355303810504635,
      "grad_norm": 0.24782100319862366,
      "learning_rate": 0.003,
      "loss": 2.91510009765625,
      "step": 1300
    },
    {
      "epoch": 0.576725025746653,
      "grad_norm": 0.23335237801074982,
      "learning_rate": 0.003,
      "loss": 2.8987603759765626,
      "step": 1400
    },
    {
      "epoch": 0.6179196704428425,
      "grad_norm": 0.3017883896827698,
      "learning_rate": 0.003,
      "loss": 2.8854364013671874,
      "step": 1500
    },
    {
      "epoch": 0.6179196704428425,
      "eval_loss": 2.8901753425598145,
      "eval_runtime": 9.372,
      "eval_samples_per_second": 342.508,
      "eval_steps_per_second": 42.894,
      "step": 1500
    },
    {
      "epoch": 0.659114315139032,
      "grad_norm": 0.27505359053611755,
      "learning_rate": 0.003,
      "loss": 2.8680685424804686,
      "step": 1600
    },
    {
      "epoch": 0.7003089598352215,
      "grad_norm": 0.28313618898391724,
      "learning_rate": 0.003,
      "loss": 2.8546218872070312,
      "step": 1700
    },
    {
      "epoch": 0.741503604531411,
      "grad_norm": 0.2307853400707245,
      "learning_rate": 0.003,
      "loss": 2.8439126586914063,
      "step": 1800
    },
    {
      "epoch": 0.7826982492276005,
      "grad_norm": 0.24696213006973267,
      "learning_rate": 0.003,
      "loss": 2.8371237182617186,
      "step": 1900
    },
    {
      "epoch": 0.82389289392379,
      "grad_norm": 0.29832541942596436,
      "learning_rate": 0.002899325557098001,
      "loss": 2.82598876953125,
      "step": 2000
    },
    {
      "epoch": 0.82389289392379,
      "eval_loss": 2.8335654735565186,
      "eval_runtime": 7.8752,
      "eval_samples_per_second": 407.609,
      "eval_steps_per_second": 51.046,
      "step": 2000
    },
    {
      "epoch": 0.8650875386199794,
      "grad_norm": 0.21801859140396118,
      "learning_rate": 0.0022915870802995226,
      "loss": 2.809080810546875,
      "step": 2100
    },
    {
      "epoch": 0.9062821833161689,
      "grad_norm": 0.18502108752727509,
      "learning_rate": 0.0013644373889485982,
      "loss": 2.78666015625,
      "step": 2200
    },
    {
      "epoch": 0.9474768280123584,
      "grad_norm": 0.18302616477012634,
      "learning_rate": 0.0004919882091667163,
      "loss": 2.760544738769531,
      "step": 2300
    },
    {
      "epoch": 0.9886714727085479,
      "grad_norm": 0.13551127910614014,
      "learning_rate": 2.6279207952956684e-05,
      "loss": 2.7378546142578126,
      "step": 2400
    },
    {
      "epoch": 1.0,
      "eval_loss": 2.7432973384857178,
      "eval_runtime": 8.3832,
      "eval_samples_per_second": 382.911,
      "eval_steps_per_second": 47.953,
      "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
}