{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.01860176716788095,
  "eval_steps": 3,
  "global_step": 30,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0006200589055960316,
      "grad_norm": 0.6006524562835693,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.4363,
      "step": 1
    },
    {
      "epoch": 0.0012401178111920632,
      "grad_norm": 0.4452102482318878,
      "learning_rate": 8.000000000000001e-06,
      "loss": 1.1641,
      "step": 2
    },
    {
      "epoch": 0.0018601767167880949,
      "grad_norm": 0.418393075466156,
      "learning_rate": 1.2e-05,
      "loss": 1.0005,
      "step": 3
    },
    {
      "epoch": 0.0018601767167880949,
      "eval_loss": 1.2559138536453247,
      "eval_runtime": 50.2632,
      "eval_samples_per_second": 1.99,
      "eval_steps_per_second": 1.99,
      "step": 3
    },
    {
      "epoch": 0.0024802356223841263,
      "grad_norm": 0.4599858820438385,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.1938,
      "step": 4
    },
    {
      "epoch": 0.0031002945279801583,
      "grad_norm": 0.4313387870788574,
      "learning_rate": 2e-05,
      "loss": 0.9897,
      "step": 5
    },
    {
      "epoch": 0.0037203534335761897,
      "grad_norm": 0.4715091586112976,
      "learning_rate": 1.9200000000000003e-05,
      "loss": 1.1105,
      "step": 6
    },
    {
      "epoch": 0.0037203534335761897,
      "eval_loss": 1.2492942810058594,
      "eval_runtime": 49.6589,
      "eval_samples_per_second": 2.014,
      "eval_steps_per_second": 2.014,
      "step": 6
    },
    {
      "epoch": 0.004340412339172222,
      "grad_norm": 0.4590495824813843,
      "learning_rate": 1.8400000000000003e-05,
      "loss": 1.0824,
      "step": 7
    },
    {
      "epoch": 0.004960471244768253,
      "grad_norm": 0.6232957243919373,
      "learning_rate": 1.76e-05,
      "loss": 1.2176,
      "step": 8
    },
    {
      "epoch": 0.005580530150364285,
      "grad_norm": 0.4820755422115326,
      "learning_rate": 1.6800000000000002e-05,
      "loss": 1.0774,
      "step": 9
    },
    {
      "epoch": 0.005580530150364285,
      "eval_loss": 1.2356064319610596,
      "eval_runtime": 49.9029,
      "eval_samples_per_second": 2.004,
      "eval_steps_per_second": 2.004,
      "step": 9
    },
    {
      "epoch": 0.0062005890559603165,
      "grad_norm": 0.614038348197937,
      "learning_rate": 1.6000000000000003e-05,
      "loss": 1.2989,
      "step": 10
    },
    {
      "epoch": 0.0068206479615563476,
      "grad_norm": 0.5838705897331238,
      "learning_rate": 1.5200000000000002e-05,
      "loss": 1.05,
      "step": 11
    },
    {
      "epoch": 0.0074407068671523795,
      "grad_norm": 0.6922520995140076,
      "learning_rate": 1.4400000000000001e-05,
      "loss": 1.3979,
      "step": 12
    },
    {
      "epoch": 0.0074407068671523795,
      "eval_loss": 1.2183419466018677,
      "eval_runtime": 50.5422,
      "eval_samples_per_second": 1.979,
      "eval_steps_per_second": 1.979,
      "step": 12
    },
    {
      "epoch": 0.008060765772748411,
      "grad_norm": 0.6026104688644409,
      "learning_rate": 1.3600000000000002e-05,
      "loss": 1.1974,
      "step": 13
    },
    {
      "epoch": 0.008680824678344443,
      "grad_norm": 0.46571722626686096,
      "learning_rate": 1.2800000000000001e-05,
      "loss": 0.9946,
      "step": 14
    },
    {
      "epoch": 0.009300883583940475,
      "grad_norm": 0.5651541948318481,
      "learning_rate": 1.2e-05,
      "loss": 1.0568,
      "step": 15
    },
    {
      "epoch": 0.009300883583940475,
      "eval_loss": 1.1998839378356934,
      "eval_runtime": 50.192,
      "eval_samples_per_second": 1.992,
      "eval_steps_per_second": 1.992,
      "step": 15
    },
    {
      "epoch": 0.009920942489536505,
      "grad_norm": 0.4988487958908081,
      "learning_rate": 1.1200000000000001e-05,
      "loss": 0.9318,
      "step": 16
    },
    {
      "epoch": 0.010541001395132537,
      "grad_norm": 0.4823167324066162,
      "learning_rate": 1.04e-05,
      "loss": 1.0622,
      "step": 17
    },
    {
      "epoch": 0.01116106030072857,
      "grad_norm": 0.5371574759483337,
      "learning_rate": 9.600000000000001e-06,
      "loss": 1.0033,
      "step": 18
    },
    {
      "epoch": 0.01116106030072857,
      "eval_loss": 1.1833301782608032,
      "eval_runtime": 50.0653,
      "eval_samples_per_second": 1.997,
      "eval_steps_per_second": 1.997,
      "step": 18
    },
    {
      "epoch": 0.011781119206324601,
      "grad_norm": 0.5795661807060242,
      "learning_rate": 8.8e-06,
      "loss": 0.9854,
      "step": 19
    },
    {
      "epoch": 0.012401178111920633,
      "grad_norm": 0.41762855648994446,
      "learning_rate": 8.000000000000001e-06,
      "loss": 0.8116,
      "step": 20
    },
    {
      "epoch": 0.013021237017516665,
      "grad_norm": 0.6034093499183655,
      "learning_rate": 7.2000000000000005e-06,
      "loss": 1.1081,
      "step": 21
    },
    {
      "epoch": 0.013021237017516665,
      "eval_loss": 1.1694728136062622,
      "eval_runtime": 50.5031,
      "eval_samples_per_second": 1.98,
      "eval_steps_per_second": 1.98,
      "step": 21
    },
    {
      "epoch": 0.013641295923112695,
      "grad_norm": 0.5518467426300049,
      "learning_rate": 6.4000000000000006e-06,
      "loss": 1.0851,
      "step": 22
    },
    {
      "epoch": 0.014261354828708727,
      "grad_norm": 0.7419660687446594,
      "learning_rate": 5.600000000000001e-06,
      "loss": 1.2086,
      "step": 23
    },
    {
      "epoch": 0.014881413734304759,
      "grad_norm": 0.5225710272789001,
      "learning_rate": 4.800000000000001e-06,
      "loss": 1.044,
      "step": 24
    },
    {
      "epoch": 0.014881413734304759,
      "eval_loss": 1.1590291261672974,
      "eval_runtime": 50.214,
      "eval_samples_per_second": 1.991,
      "eval_steps_per_second": 1.991,
      "step": 24
    },
    {
      "epoch": 0.01550147263990079,
      "grad_norm": 0.539212167263031,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.0468,
      "step": 25
    },
    {
      "epoch": 0.016121531545496823,
      "grad_norm": 0.4953361451625824,
      "learning_rate": 3.2000000000000003e-06,
      "loss": 0.9279,
      "step": 26
    },
    {
      "epoch": 0.016741590451092855,
      "grad_norm": 0.4864480793476105,
      "learning_rate": 2.4000000000000003e-06,
      "loss": 0.9413,
      "step": 27
    },
    {
      "epoch": 0.016741590451092855,
      "eval_loss": 1.1525880098342896,
      "eval_runtime": 50.5444,
      "eval_samples_per_second": 1.978,
      "eval_steps_per_second": 1.978,
      "step": 27
    },
    {
      "epoch": 0.017361649356688887,
      "grad_norm": 0.4352854788303375,
      "learning_rate": 1.6000000000000001e-06,
      "loss": 0.8065,
      "step": 28
    },
    {
      "epoch": 0.01798170826228492,
      "grad_norm": 0.5856941342353821,
      "learning_rate": 8.000000000000001e-07,
      "loss": 1.1299,
      "step": 29
    },
    {
      "epoch": 0.01860176716788095,
      "grad_norm": 0.5818368196487427,
      "learning_rate": 0.0,
      "loss": 0.8976,
      "step": 30
    },
    {
      "epoch": 0.01860176716788095,
      "eval_loss": 1.1500217914581299,
      "eval_runtime": 50.2769,
      "eval_samples_per_second": 1.989,
      "eval_steps_per_second": 1.989,
      "step": 30
    }
  ],
  "logging_steps": 1,
  "max_steps": 30,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 3,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 6.438329862521242e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}