{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3894862604540026,
  "eval_steps": 1000,
  "global_step": 2000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011947431302270011,
      "grad_norm": 23.375,
      "learning_rate": 2e-06,
      "loss": 2.4074,
      "step": 1
    },
    {
      "epoch": 0.11947431302270012,
      "grad_norm": 0.515625,
      "learning_rate": 0.0002,
      "loss": 0.7151,
      "step": 100
    },
    {
      "epoch": 0.23894862604540024,
      "grad_norm": 0.369140625,
      "learning_rate": 0.0004,
      "loss": 0.4333,
      "step": 200
    },
    {
      "epoch": 0.35842293906810035,
      "grad_norm": 0.361328125,
      "learning_rate": 0.0006,
      "loss": 0.4113,
      "step": 300
    },
    {
      "epoch": 0.4778972520908005,
      "grad_norm": 0.244140625,
      "learning_rate": 0.0008,
      "loss": 0.393,
      "step": 400
    },
    {
      "epoch": 0.5973715651135006,
      "grad_norm": 0.2099609375,
      "learning_rate": 0.001,
      "loss": 0.3857,
      "step": 500
    },
    {
      "epoch": 0.7168458781362007,
      "grad_norm": 0.193359375,
      "learning_rate": 0.0012,
      "loss": 0.3734,
      "step": 600
    },
    {
      "epoch": 0.8363201911589009,
      "grad_norm": 0.1796875,
      "learning_rate": 0.0014,
      "loss": 0.373,
      "step": 700
    },
    {
      "epoch": 0.955794504181601,
      "grad_norm": 0.126953125,
      "learning_rate": 0.0016,
      "loss": 0.3578,
      "step": 800
    },
    {
      "epoch": 1.075268817204301,
      "grad_norm": 0.111328125,
      "learning_rate": 0.0018000000000000002,
      "loss": 0.3473,
      "step": 900
    },
    {
      "epoch": 1.1947431302270013,
      "grad_norm": 0.125,
      "learning_rate": 0.002,
      "loss": 0.3551,
      "step": 1000
    },
    {
      "epoch": 1.3142174432497014,
      "grad_norm": 0.1591796875,
      "learning_rate": 0.0019987165071710528,
      "loss": 0.3466,
      "step": 1100
    },
    {
      "epoch": 1.4336917562724014,
      "grad_norm": 0.099609375,
      "learning_rate": 0.001994869323391895,
      "loss": 0.3251,
      "step": 1200
    },
    {
      "epoch": 1.5531660692951015,
      "grad_norm": 0.10888671875,
      "learning_rate": 0.0019884683243281114,
      "loss": 0.3183,
      "step": 1300
    },
    {
      "epoch": 1.6726403823178018,
      "grad_norm": 0.1337890625,
      "learning_rate": 0.0019795299412524946,
      "loss": 0.3006,
      "step": 1400
    },
    {
      "epoch": 1.7921146953405018,
      "grad_norm": 0.1494140625,
      "learning_rate": 0.001968077118866204,
      "loss": 0.2911,
      "step": 1500
    },
    {
      "epoch": 1.911589008363202,
      "grad_norm": 0.1201171875,
      "learning_rate": 0.001954139256400049,
      "loss": 0.2853,
      "step": 1600
    },
    {
      "epoch": 2.031063321385902,
      "grad_norm": 0.08154296875,
      "learning_rate": 0.0019377521321470807,
      "loss": 0.2585,
      "step": 1700
    },
    {
      "epoch": 2.150537634408602,
      "grad_norm": 0.12890625,
      "learning_rate": 0.0019189578116202307,
      "loss": 0.2611,
      "step": 1800
    },
    {
      "epoch": 2.270011947431302,
      "grad_norm": 0.125,
      "learning_rate": 0.0018978045395707417,
      "loss": 0.2502,
      "step": 1900
    },
    {
      "epoch": 2.3894862604540026,
      "grad_norm": 0.1162109375,
      "learning_rate": 0.0018743466161445822,
      "loss": 0.2455,
      "step": 2000
    }
  ],
  "logging_steps": 100,
  "max_steps": 7200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9,
  "save_steps": 2000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": true,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.830024878686208e+16,
  "train_batch_size": 12,
  "trial_name": null,
  "trial_params": null
}