{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.15728036043415933,
  "eval_steps": 1,
  "global_step": 15,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.010485357362277289,
      "grad_norm": 498.0,
      "learning_rate": 0.0,
      "loss": 1.6033425331115723,
      "step": 1
    },
    {
      "epoch": 0.020970714724554577,
      "grad_norm": 139.0,
      "learning_rate": 4e-08,
      "loss": 1.5843058824539185,
      "step": 2
    },
    {
      "epoch": 0.03145607208683186,
      "grad_norm": 158.0,
      "learning_rate": 8e-08,
      "loss": 1.624650239944458,
      "step": 3
    },
    {
      "epoch": 0.041941429449109155,
      "grad_norm": 201.0,
      "learning_rate": 1.2000000000000002e-07,
      "loss": 1.5930713415145874,
      "step": 4
    },
    {
      "epoch": 0.05242678681138644,
      "grad_norm": 1392.0,
      "learning_rate": 1.6e-07,
      "loss": 1.6284583806991577,
      "step": 5
    },
    {
      "epoch": 0.06291214417366373,
      "grad_norm": 644.0,
      "learning_rate": 2.0000000000000002e-07,
      "loss": 1.5755040645599365,
      "step": 6
    },
    {
      "epoch": 0.07339750153594102,
      "grad_norm": 358.0,
      "learning_rate": 2.4000000000000003e-07,
      "loss": 1.5862637758255005,
      "step": 7
    },
    {
      "epoch": 0.08388285889821831,
      "grad_norm": 1012.0,
      "learning_rate": 2.8e-07,
      "loss": 1.6306817531585693,
      "step": 8
    },
    {
      "epoch": 0.0943682162604956,
      "grad_norm": 187.0,
      "learning_rate": 3.2e-07,
      "loss": 1.5844253301620483,
      "step": 9
    },
    {
      "epoch": 0.10485357362277288,
      "grad_norm": 342.0,
      "learning_rate": 3.6e-07,
      "loss": 1.5895334482192993,
      "step": 10
    },
    {
      "epoch": 0.11533893098505017,
      "grad_norm": 816.0,
      "learning_rate": 4.0000000000000003e-07,
      "loss": 1.5861637592315674,
      "step": 11
    },
    {
      "epoch": 0.12582428834732745,
      "grad_norm": 260.0,
      "learning_rate": 4.4e-07,
      "loss": 1.57806396484375,
      "step": 12
    },
    {
      "epoch": 0.13630964570960474,
      "grad_norm": 326.0,
      "learning_rate": 4.800000000000001e-07,
      "loss": 1.5836868286132812,
      "step": 13
    },
    {
      "epoch": 0.14679500307188204,
      "grad_norm": 668.0,
      "learning_rate": 5.2e-07,
      "loss": 1.5597259998321533,
      "step": 14
    },
    {
      "epoch": 0.15728036043415933,
      "grad_norm": 256.0,
      "learning_rate": 5.6e-07,
      "loss": 1.5852601528167725,
      "step": 15
    }
  ],
  "logging_steps": 1,
  "max_steps": 96,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 5,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.401811487798067e+17,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}