{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.06668700620355875,
  "eval_steps": 500,
  "global_step": 2500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 2.66748024814235e-05,
      "grad_norm": 3.8722002506256104,
      "learning_rate": 0.0,
      "loss": 0.5003,
      "step": 1
    },
    {
      "epoch": 0.0026674802481423503,
      "grad_norm": 3.6500043869018555,
      "learning_rate": 8.25e-09,
      "loss": 0.4412,
      "step": 100
    },
    {
      "epoch": 0.0053349604962847005,
      "grad_norm": 3.9299707412719727,
      "learning_rate": 1.658333333333333e-08,
      "loss": 0.4411,
      "step": 200
    },
    {
      "epoch": 0.00800244074442705,
      "grad_norm": 5.91644287109375,
      "learning_rate": 2.4916666666666665e-08,
      "loss": 0.4481,
      "step": 300
    },
    {
      "epoch": 0.010669920992569401,
      "grad_norm": 4.572421550750732,
      "learning_rate": 3.325e-08,
      "loss": 0.4476,
      "step": 400
    },
    {
      "epoch": 0.01333740124071175,
      "grad_norm": 3.8618998527526855,
      "learning_rate": 4.158333333333333e-08,
      "loss": 0.4377,
      "step": 500
    },
    {
      "epoch": 0.0160048814888541,
      "grad_norm": 4.088321208953857,
      "learning_rate": 4.991666666666666e-08,
      "loss": 0.4317,
      "step": 600
    },
    {
      "epoch": 0.018672361736996452,
      "grad_norm": 4.604540824890137,
      "learning_rate": 5.825e-08,
      "loss": 0.4063,
      "step": 700
    },
    {
      "epoch": 0.021339841985138802,
      "grad_norm": 4.912314414978027,
      "learning_rate": 6.658333333333332e-08,
      "loss": 0.3927,
      "step": 800
    },
    {
      "epoch": 0.024007322233281152,
      "grad_norm": 7.348450660705566,
      "learning_rate": 7.491666666666667e-08,
      "loss": 0.3712,
      "step": 900
    },
    {
      "epoch": 0.0266748024814235,
      "grad_norm": 4.6706061363220215,
      "learning_rate": 8.325e-08,
      "loss": 0.3559,
      "step": 1000
    },
    {
      "epoch": 0.02934228272956585,
      "grad_norm": 2.785581350326538,
      "learning_rate": 9.158333333333334e-08,
      "loss": 0.331,
      "step": 1100
    },
    {
      "epoch": 0.0320097629777082,
      "grad_norm": 2.7393457889556885,
      "learning_rate": 9.991666666666666e-08,
      "loss": 0.3123,
      "step": 1200
    },
    {
      "epoch": 0.03467724322585055,
      "grad_norm": 4.026894569396973,
      "learning_rate": 1.0824999999999999e-07,
      "loss": 0.2969,
      "step": 1300
    },
    {
      "epoch": 0.037344723473992904,
      "grad_norm": 2.8775548934936523,
      "learning_rate": 1.1658333333333332e-07,
      "loss": 0.281,
      "step": 1400
    },
    {
      "epoch": 0.04001220372213525,
      "grad_norm": 2.1844277381896973,
      "learning_rate": 1.2491666666666666e-07,
      "loss": 0.2793,
      "step": 1500
    },
    {
      "epoch": 0.042679683970277604,
      "grad_norm": 2.770414113998413,
      "learning_rate": 1.3325e-07,
      "loss": 0.2749,
      "step": 1600
    },
    {
      "epoch": 0.04534716421841995,
      "grad_norm": 3.1216094493865967,
      "learning_rate": 1.4158333333333332e-07,
      "loss": 0.254,
      "step": 1700
    },
    {
      "epoch": 0.048014644466562305,
      "grad_norm": 2.497659206390381,
      "learning_rate": 1.4991666666666666e-07,
      "loss": 0.2494,
      "step": 1800
    },
    {
      "epoch": 0.05068212471470465,
      "grad_norm": 2.0535426139831543,
      "learning_rate": 1.5825e-07,
      "loss": 0.2555,
      "step": 1900
    },
    {
      "epoch": 0.053349604962847,
      "grad_norm": 1.760150671005249,
      "learning_rate": 1.6658333333333332e-07,
      "loss": 0.2248,
      "step": 2000
    },
    {
      "epoch": 0.05601708521098935,
      "grad_norm": 2.8502137660980225,
      "learning_rate": 1.7491666666666666e-07,
      "loss": 0.225,
      "step": 2100
    },
    {
      "epoch": 0.0586845654591317,
      "grad_norm": 2.776670455932617,
      "learning_rate": 1.8324999999999998e-07,
      "loss": 0.2246,
      "step": 2200
    },
    {
      "epoch": 0.06135204570727405,
      "grad_norm": 2.368945598602295,
      "learning_rate": 1.9158333333333332e-07,
      "loss": 0.2167,
      "step": 2300
    },
    {
      "epoch": 0.0640195259554164,
      "grad_norm": 1.504767656326294,
      "learning_rate": 1.9991666666666666e-07,
      "loss": 0.2231,
      "step": 2400
    },
    {
      "epoch": 0.06668700620355875,
      "grad_norm": 2.272890329360962,
      "learning_rate": 2.0824999999999998e-07,
      "loss": 0.2023,
      "step": 2500
    }
  ],
  "logging_steps": 100,
  "max_steps": 60000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 2500,
  "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": 2,
  "trial_name": null,
  "trial_params": null
}