{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.09876543209876543,
  "eval_steps": 500,
  "global_step": 36,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0027434842249657062,
      "grad_norm": 0.3216973543167114,
      "learning_rate": 2.0000000000000003e-06,
      "loss": 2.039,
      "step": 1
    },
    {
      "epoch": 0.0054869684499314125,
      "grad_norm": 0.3218615651130676,
      "learning_rate": 4.000000000000001e-06,
      "loss": 2.063,
      "step": 2
    },
    {
      "epoch": 0.00823045267489712,
      "grad_norm": 0.3071180582046509,
      "learning_rate": 6e-06,
      "loss": 2.0298,
      "step": 3
    },
    {
      "epoch": 0.010973936899862825,
      "grad_norm": 0.30708086490631104,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.9489,
      "step": 4
    },
    {
      "epoch": 0.013717421124828532,
      "grad_norm": 0.31064078211784363,
      "learning_rate": 1e-05,
      "loss": 2.0401,
      "step": 5
    },
    {
      "epoch": 0.01646090534979424,
      "grad_norm": 0.35925883054733276,
      "learning_rate": 1.2e-05,
      "loss": 2.0963,
      "step": 6
    },
    {
      "epoch": 0.019204389574759947,
      "grad_norm": 0.3267571032047272,
      "learning_rate": 1.4000000000000001e-05,
      "loss": 2.0252,
      "step": 7
    },
    {
      "epoch": 0.02194787379972565,
      "grad_norm": 0.30728623270988464,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 2.0108,
      "step": 8
    },
    {
      "epoch": 0.024691358024691357,
      "grad_norm": 0.2928607761859894,
      "learning_rate": 1.8e-05,
      "loss": 1.9542,
      "step": 9
    },
    {
      "epoch": 0.027434842249657063,
      "grad_norm": 0.30577352643013,
      "learning_rate": 2e-05,
      "loss": 2.017,
      "step": 10
    },
    {
      "epoch": 0.03017832647462277,
      "grad_norm": 0.3024803102016449,
      "learning_rate": 2.2000000000000003e-05,
      "loss": 1.982,
      "step": 11
    },
    {
      "epoch": 0.03292181069958848,
      "grad_norm": 0.28839072585105896,
      "learning_rate": 2.4e-05,
      "loss": 1.9217,
      "step": 12
    },
    {
      "epoch": 0.03566529492455418,
      "grad_norm": 0.2843893766403198,
      "learning_rate": 2.6000000000000002e-05,
      "loss": 1.9608,
      "step": 13
    },
    {
      "epoch": 0.038408779149519894,
      "grad_norm": 0.2703002095222473,
      "learning_rate": 2.8000000000000003e-05,
      "loss": 1.9696,
      "step": 14
    },
    {
      "epoch": 0.0411522633744856,
      "grad_norm": 0.24636265635490417,
      "learning_rate": 3e-05,
      "loss": 1.8818,
      "step": 15
    },
    {
      "epoch": 0.0438957475994513,
      "grad_norm": 0.2405432015657425,
      "learning_rate": 3.2000000000000005e-05,
      "loss": 1.975,
      "step": 16
    },
    {
      "epoch": 0.04663923182441701,
      "grad_norm": 0.24582137167453766,
      "learning_rate": 3.4000000000000007e-05,
      "loss": 1.923,
      "step": 17
    },
    {
      "epoch": 0.04938271604938271,
      "grad_norm": 0.2504767179489136,
      "learning_rate": 3.6e-05,
      "loss": 1.9781,
      "step": 18
    },
    {
      "epoch": 0.05212620027434842,
      "grad_norm": 0.2394665777683258,
      "learning_rate": 3.8e-05,
      "loss": 1.8959,
      "step": 19
    },
    {
      "epoch": 0.05486968449931413,
      "grad_norm": 0.24969030916690826,
      "learning_rate": 4e-05,
      "loss": 1.855,
      "step": 20
    },
    {
      "epoch": 0.05761316872427984,
      "grad_norm": 0.2694351077079773,
      "learning_rate": 4.2e-05,
      "loss": 1.9602,
      "step": 21
    },
    {
      "epoch": 0.06035665294924554,
      "grad_norm": 0.25622957944869995,
      "learning_rate": 4.4000000000000006e-05,
      "loss": 1.8208,
      "step": 22
    },
    {
      "epoch": 0.06310013717421124,
      "grad_norm": 0.24535588920116425,
      "learning_rate": 4.600000000000001e-05,
      "loss": 1.7967,
      "step": 23
    },
    {
      "epoch": 0.06584362139917696,
      "grad_norm": 0.2737885117530823,
      "learning_rate": 4.8e-05,
      "loss": 1.7841,
      "step": 24
    },
    {
      "epoch": 0.06858710562414266,
      "grad_norm": 0.2646300196647644,
      "learning_rate": 5e-05,
      "loss": 1.7744,
      "step": 25
    },
    {
      "epoch": 0.07133058984910837,
      "grad_norm": 0.2676407992839813,
      "learning_rate": 5.2000000000000004e-05,
      "loss": 1.7359,
      "step": 26
    },
    {
      "epoch": 0.07407407407407407,
      "grad_norm": 0.2649776041507721,
      "learning_rate": 5.4000000000000005e-05,
      "loss": 1.7205,
      "step": 27
    },
    {
      "epoch": 0.07681755829903979,
      "grad_norm": 0.296818345785141,
      "learning_rate": 5.6000000000000006e-05,
      "loss": 1.696,
      "step": 28
    },
    {
      "epoch": 0.07956104252400549,
      "grad_norm": 0.31905728578567505,
      "learning_rate": 5.8e-05,
      "loss": 1.7261,
      "step": 29
    },
    {
      "epoch": 0.0823045267489712,
      "grad_norm": 0.4174517095088959,
      "learning_rate": 6e-05,
      "loss": 1.6451,
      "step": 30
    },
    {
      "epoch": 0.0850480109739369,
      "grad_norm": 0.4545894265174866,
      "learning_rate": 6.2e-05,
      "loss": 1.5867,
      "step": 31
    },
    {
      "epoch": 0.0877914951989026,
      "grad_norm": 0.45722702145576477,
      "learning_rate": 6.400000000000001e-05,
      "loss": 1.5184,
      "step": 32
    },
    {
      "epoch": 0.09053497942386832,
      "grad_norm": 0.4953472316265106,
      "learning_rate": 6.6e-05,
      "loss": 1.4793,
      "step": 33
    },
    {
      "epoch": 0.09327846364883402,
      "grad_norm": 0.5516601800918579,
      "learning_rate": 6.800000000000001e-05,
      "loss": 1.4967,
      "step": 34
    },
    {
      "epoch": 0.09602194787379972,
      "grad_norm": 0.5295405983924866,
      "learning_rate": 7e-05,
      "loss": 1.4445,
      "step": 35
    },
    {
      "epoch": 0.09876543209876543,
      "grad_norm": 0.3918333351612091,
      "learning_rate": 7.2e-05,
      "loss": 1.3956,
      "step": 36
    }
  ],
  "logging_steps": 1,
  "max_steps": 364,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 1,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.029250509239255e+17,
  "train_batch_size": 16,
  "trial_name": null,
  "trial_params": null
}