{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.002399996160006144,
  "eval_steps": 200000,
  "global_step": 1500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0001599997440004096,
      "grad_norm": 84.32501983642578,
      "learning_rate": 3.103950336794611e-08,
      "loss": 10.8792,
      "step": 100
    },
    {
      "epoch": 0.0003199994880008192,
      "grad_norm": 60.63747024536133,
      "learning_rate": 6.303899137613798e-08,
      "loss": 10.9284,
      "step": 200
    },
    {
      "epoch": 0.00047999923200122877,
      "grad_norm": 55.71075439453125,
      "learning_rate": 9.503847938432986e-08,
      "loss": 10.6466,
      "step": 300
    },
    {
      "epoch": 0.0006399989760016384,
      "grad_norm": 57.63307189941406,
      "learning_rate": 1.2703796739252173e-07,
      "loss": 10.841,
      "step": 400
    },
    {
      "epoch": 0.000799998720002048,
      "grad_norm": 89.1032485961914,
      "learning_rate": 1.590374554007136e-07,
      "loss": 10.8094,
      "step": 500
    },
    {
      "epoch": 0.0009599984640024575,
      "grad_norm": 57.2479362487793,
      "learning_rate": 1.9103694340890547e-07,
      "loss": 10.4323,
      "step": 600
    },
    {
      "epoch": 0.0011199982080028672,
      "grad_norm": 51.17530059814453,
      "learning_rate": 2.2303643141709733e-07,
      "loss": 10.3032,
      "step": 700
    },
    {
      "epoch": 0.0012799979520032767,
      "grad_norm": 60.76409912109375,
      "learning_rate": 2.550359194252892e-07,
      "loss": 10.4006,
      "step": 800
    },
    {
      "epoch": 0.0014399976960036865,
      "grad_norm": 67.00859069824219,
      "learning_rate": 2.870354074334811e-07,
      "loss": 10.4743,
      "step": 900
    },
    {
      "epoch": 0.001599997440004096,
      "grad_norm": 68.4343032836914,
      "learning_rate": 3.19034895441673e-07,
      "loss": 10.2334,
      "step": 1000
    },
    {
      "epoch": 0.0017599971840045055,
      "grad_norm": 48.704105377197266,
      "learning_rate": 3.510343834498648e-07,
      "loss": 10.0135,
      "step": 1100
    },
    {
      "epoch": 0.001919996928004915,
      "grad_norm": 45.30134963989258,
      "learning_rate": 3.830338714580567e-07,
      "loss": 9.7874,
      "step": 1200
    },
    {
      "epoch": 0.002079996672005325,
      "grad_norm": 84.56024169921875,
      "learning_rate": 4.150333594662486e-07,
      "loss": 9.7419,
      "step": 1300
    },
    {
      "epoch": 0.0022399964160057344,
      "grad_norm": 45.73213195800781,
      "learning_rate": 4.470328474744404e-07,
      "loss": 9.7412,
      "step": 1400
    },
    {
      "epoch": 0.002399996160006144,
      "grad_norm": 50.21996307373047,
      "learning_rate": 4.790323354826324e-07,
      "loss": 9.4585,
      "step": 1500
    }
  ],
  "logging_steps": 100,
  "max_steps": 625001,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}