{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 500,
  "global_step": 215,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.023255813953488372,
      "grad_norm": 0.42513933777809143,
      "learning_rate": 2e-05,
      "loss": 1.4281,
      "step": 5
    },
    {
      "epoch": 0.046511627906976744,
      "grad_norm": 0.2810695171356201,
      "learning_rate": 2e-05,
      "loss": 1.3645,
      "step": 10
    },
    {
      "epoch": 0.06976744186046512,
      "grad_norm": 0.3605867028236389,
      "learning_rate": 2e-05,
      "loss": 1.3975,
      "step": 15
    },
    {
      "epoch": 0.09302325581395349,
      "grad_norm": 0.26210489869117737,
      "learning_rate": 2e-05,
      "loss": 1.2299,
      "step": 20
    },
    {
      "epoch": 0.11627906976744186,
      "grad_norm": 0.2155284434556961,
      "learning_rate": 2e-05,
      "loss": 1.1918,
      "step": 25
    },
    {
      "epoch": 0.13953488372093023,
      "grad_norm": 0.28256216645240784,
      "learning_rate": 2e-05,
      "loss": 1.2193,
      "step": 30
    },
    {
      "epoch": 0.16279069767441862,
      "grad_norm": 0.24989347159862518,
      "learning_rate": 2e-05,
      "loss": 1.2496,
      "step": 35
    },
    {
      "epoch": 0.18604651162790697,
      "grad_norm": 0.20540378987789154,
      "learning_rate": 2e-05,
      "loss": 1.0645,
      "step": 40
    },
    {
      "epoch": 0.20930232558139536,
      "grad_norm": 0.28998884558677673,
      "learning_rate": 2e-05,
      "loss": 1.1089,
      "step": 45
    },
    {
      "epoch": 0.23255813953488372,
      "grad_norm": 0.3626082241535187,
      "learning_rate": 2e-05,
      "loss": 1.2453,
      "step": 50
    },
    {
      "epoch": 0.2558139534883721,
      "grad_norm": 0.2234840840101242,
      "learning_rate": 2e-05,
      "loss": 1.1233,
      "step": 55
    },
    {
      "epoch": 0.27906976744186046,
      "grad_norm": 0.20808465778827667,
      "learning_rate": 2e-05,
      "loss": 1.089,
      "step": 60
    },
    {
      "epoch": 0.3023255813953488,
      "grad_norm": 0.31903448700904846,
      "learning_rate": 2e-05,
      "loss": 1.176,
      "step": 65
    },
    {
      "epoch": 0.32558139534883723,
      "grad_norm": 0.2401343584060669,
      "learning_rate": 2e-05,
      "loss": 1.1098,
      "step": 70
    },
    {
      "epoch": 0.3488372093023256,
      "grad_norm": 0.2063365876674652,
      "learning_rate": 2e-05,
      "loss": 1.105,
      "step": 75
    },
    {
      "epoch": 0.37209302325581395,
      "grad_norm": 0.3152436912059784,
      "learning_rate": 2e-05,
      "loss": 1.0867,
      "step": 80
    },
    {
      "epoch": 0.3953488372093023,
      "grad_norm": 0.28349247574806213,
      "learning_rate": 2e-05,
      "loss": 1.2119,
      "step": 85
    },
    {
      "epoch": 0.4186046511627907,
      "grad_norm": 0.21781769394874573,
      "learning_rate": 2e-05,
      "loss": 1.0341,
      "step": 90
    },
    {
      "epoch": 0.4418604651162791,
      "grad_norm": 0.2972399890422821,
      "learning_rate": 2e-05,
      "loss": 1.0487,
      "step": 95
    },
    {
      "epoch": 0.46511627906976744,
      "grad_norm": 0.3430672883987427,
      "learning_rate": 2e-05,
      "loss": 1.1891,
      "step": 100
    },
    {
      "epoch": 0.4883720930232558,
      "grad_norm": 0.24118821322917938,
      "learning_rate": 2e-05,
      "loss": 1.0056,
      "step": 105
    },
    {
      "epoch": 0.5116279069767442,
      "grad_norm": 0.23012392222881317,
      "learning_rate": 2e-05,
      "loss": 1.0166,
      "step": 110
    },
    {
      "epoch": 0.5348837209302325,
      "grad_norm": 0.41410136222839355,
      "learning_rate": 2e-05,
      "loss": 1.1573,
      "step": 115
    },
    {
      "epoch": 0.5581395348837209,
      "grad_norm": 0.25534236431121826,
      "learning_rate": 2e-05,
      "loss": 1.091,
      "step": 120
    },
    {
      "epoch": 0.5813953488372093,
      "grad_norm": 0.33041778206825256,
      "learning_rate": 2e-05,
      "loss": 1.0053,
      "step": 125
    },
    {
      "epoch": 0.6046511627906976,
      "grad_norm": 0.3311578333377838,
      "learning_rate": 2e-05,
      "loss": 1.0512,
      "step": 130
    },
    {
      "epoch": 0.627906976744186,
      "grad_norm": 0.3010158836841583,
      "learning_rate": 2e-05,
      "loss": 1.1523,
      "step": 135
    },
    {
      "epoch": 0.6511627906976745,
      "grad_norm": 0.2367880493402481,
      "learning_rate": 2e-05,
      "loss": 0.9708,
      "step": 140
    },
    {
      "epoch": 0.6744186046511628,
      "grad_norm": 0.30969762802124023,
      "learning_rate": 2e-05,
      "loss": 1.0445,
      "step": 145
    },
    {
      "epoch": 0.6976744186046512,
      "grad_norm": 0.43711283802986145,
      "learning_rate": 2e-05,
      "loss": 1.1745,
      "step": 150
    },
    {
      "epoch": 0.7209302325581395,
      "grad_norm": 0.27942749857902527,
      "learning_rate": 2e-05,
      "loss": 1.004,
      "step": 155
    },
    {
      "epoch": 0.7441860465116279,
      "grad_norm": 0.2938617467880249,
      "learning_rate": 2e-05,
      "loss": 1.041,
      "step": 160
    },
    {
      "epoch": 0.7674418604651163,
      "grad_norm": 0.3397826552391052,
      "learning_rate": 2e-05,
      "loss": 1.0989,
      "step": 165
    },
    {
      "epoch": 0.7906976744186046,
      "grad_norm": 0.2756069302558899,
      "learning_rate": 2e-05,
      "loss": 1.049,
      "step": 170
    },
    {
      "epoch": 0.813953488372093,
      "grad_norm": 0.2508189380168915,
      "learning_rate": 2e-05,
      "loss": 0.9834,
      "step": 175
    },
    {
      "epoch": 0.8372093023255814,
      "grad_norm": 0.34858086705207825,
      "learning_rate": 2e-05,
      "loss": 1.0219,
      "step": 180
    },
    {
      "epoch": 0.8604651162790697,
      "grad_norm": 0.30454790592193604,
      "learning_rate": 2e-05,
      "loss": 1.1379,
      "step": 185
    },
    {
      "epoch": 0.8837209302325582,
      "grad_norm": 0.2674161195755005,
      "learning_rate": 2e-05,
      "loss": 1.0125,
      "step": 190
    },
    {
      "epoch": 0.9069767441860465,
      "grad_norm": 0.3410373330116272,
      "learning_rate": 2e-05,
      "loss": 0.9154,
      "step": 195
    },
    {
      "epoch": 0.9302325581395349,
      "grad_norm": 0.3718777298927307,
      "learning_rate": 2e-05,
      "loss": 1.1459,
      "step": 200
    },
    {
      "epoch": 0.9534883720930233,
      "grad_norm": 0.2812870740890503,
      "learning_rate": 2e-05,
      "loss": 0.9306,
      "step": 205
    },
    {
      "epoch": 0.9767441860465116,
      "grad_norm": 0.30063411593437195,
      "learning_rate": 2e-05,
      "loss": 0.9894,
      "step": 210
    },
    {
      "epoch": 1.0,
      "grad_norm": 0.3839293122291565,
      "learning_rate": 2e-05,
      "loss": 1.0635,
      "step": 215
    }
  ],
  "logging_steps": 5,
  "max_steps": 215,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 99999,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3.502029231221637e+17,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}