{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.0,
  "eval_steps": 100,
  "global_step": 163,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.030745580322828592,
      "grad_norm": 6.350613102744608,
      "learning_rate": 1.0204081632653061e-07,
      "loss": 6.5284,
      "step": 5
    },
    {
      "epoch": 0.061491160645657184,
      "grad_norm": 5.249984394687515,
      "learning_rate": 2.0408163265306121e-07,
      "loss": 6.4945,
      "step": 10
    },
    {
      "epoch": 0.09223674096848578,
      "grad_norm": 5.352306724137368,
      "learning_rate": 3.0612244897959183e-07,
      "loss": 6.6828,
      "step": 15
    },
    {
      "epoch": 0.12298232129131437,
      "grad_norm": 5.486794769339902,
      "learning_rate": 4.0816326530612243e-07,
      "loss": 6.467,
      "step": 20
    },
    {
      "epoch": 0.15372790161414296,
      "grad_norm": 4.077117426584361,
      "learning_rate": 5.10204081632653e-07,
      "loss": 6.1826,
      "step": 25
    },
    {
      "epoch": 0.18447348193697155,
      "grad_norm": 3.119167144675083,
      "learning_rate": 6.122448979591837e-07,
      "loss": 5.949,
      "step": 30
    },
    {
      "epoch": 0.21521906225980014,
      "grad_norm": 2.6950432819564356,
      "learning_rate": 7.142857142857143e-07,
      "loss": 5.4738,
      "step": 35
    },
    {
      "epoch": 0.24596464258262873,
      "grad_norm": 1.5382799926978608,
      "learning_rate": 8.163265306122449e-07,
      "loss": 5.2285,
      "step": 40
    },
    {
      "epoch": 0.2767102229054573,
      "grad_norm": 1.2825119089431523,
      "learning_rate": 9.183673469387755e-07,
      "loss": 5.0174,
      "step": 45
    },
    {
      "epoch": 0.3074558032282859,
      "grad_norm": 1.14912166210836,
      "learning_rate": 9.99987079628245e-07,
      "loss": 4.7716,
      "step": 50
    },
    {
      "epoch": 0.3382013835511145,
      "grad_norm": 1.285686948508955,
      "learning_rate": 9.995349367260807e-07,
      "loss": 4.5585,
      "step": 55
    },
    {
      "epoch": 0.3689469638739431,
      "grad_norm": 1.054957564577766,
      "learning_rate": 9.984374428250894e-07,
      "loss": 4.3855,
      "step": 60
    },
    {
      "epoch": 0.3996925441967717,
      "grad_norm": 0.9925990274913604,
      "learning_rate": 9.966960157816278e-07,
      "loss": 4.1541,
      "step": 65
    },
    {
      "epoch": 0.4304381245196003,
      "grad_norm": 0.8744404881743455,
      "learning_rate": 9.943129053516174e-07,
      "loss": 4.1257,
      "step": 70
    },
    {
      "epoch": 0.4611837048424289,
      "grad_norm": 0.7463667798296578,
      "learning_rate": 9.91291190284077e-07,
      "loss": 3.8852,
      "step": 75
    },
    {
      "epoch": 0.49192928516525747,
      "grad_norm": 0.7902691532243193,
      "learning_rate": 9.876347743436758e-07,
      "loss": 3.8846,
      "step": 80
    },
    {
      "epoch": 0.5226748654880861,
      "grad_norm": 0.926879835692504,
      "learning_rate": 9.833483812674452e-07,
      "loss": 3.9166,
      "step": 85
    },
    {
      "epoch": 0.5534204458109147,
      "grad_norm": 0.803407155130827,
      "learning_rate": 9.784375486621668e-07,
      "loss": 3.7194,
      "step": 90
    },
    {
      "epoch": 0.5841660261337432,
      "grad_norm": 0.8117888501469026,
      "learning_rate": 9.729086208503173e-07,
      "loss": 3.7475,
      "step": 95
    },
    {
      "epoch": 0.6149116064565718,
      "grad_norm": 0.7821755674358282,
      "learning_rate": 9.66768740673815e-07,
      "loss": 3.6407,
      "step": 100
    },
    {
      "epoch": 0.6149116064565718,
      "eval_loss": NaN,
      "eval_runtime": 349.4965,
      "eval_samples_per_second": 15.285,
      "eval_steps_per_second": 0.956,
      "step": 100
    },
    {
      "epoch": 0.6456571867794004,
      "grad_norm": 0.6822137175921249,
      "learning_rate": 9.600258402661569e-07,
      "loss": 3.6531,
      "step": 105
    },
    {
      "epoch": 0.676402767102229,
      "grad_norm": 0.7500359822402426,
      "learning_rate": 9.526886308048668e-07,
      "loss": 3.6282,
      "step": 110
    },
    {
      "epoch": 0.7071483474250576,
      "grad_norm": 0.8622924385168957,
      "learning_rate": 9.447665912574929e-07,
      "loss": 3.5622,
      "step": 115
    },
    {
      "epoch": 0.7378939277478862,
      "grad_norm": 0.7766220833707687,
      "learning_rate": 9.362699561356956e-07,
      "loss": 3.4787,
      "step": 120
    },
    {
      "epoch": 0.7686395080707148,
      "grad_norm": 0.7590912417940764,
      "learning_rate": 9.272097022732443e-07,
      "loss": 3.4078,
      "step": 125
    },
    {
      "epoch": 0.7993850883935434,
      "grad_norm": 0.822433668441714,
      "learning_rate": 9.175975346450062e-07,
      "loss": 3.3673,
      "step": 130
    },
    {
      "epoch": 0.830130668716372,
      "grad_norm": 0.7129904612641743,
      "learning_rate": 9.074458712452475e-07,
      "loss": 3.4122,
      "step": 135
    },
    {
      "epoch": 0.8608762490392006,
      "grad_norm": 0.8733565752917316,
      "learning_rate": 8.967678270447798e-07,
      "loss": 3.3817,
      "step": 140
    },
    {
      "epoch": 0.8916218293620292,
      "grad_norm": 0.7851319189409072,
      "learning_rate": 8.855771970476833e-07,
      "loss": 3.2653,
      "step": 145
    },
    {
      "epoch": 0.9223674096848578,
      "grad_norm": 0.8962287259777225,
      "learning_rate": 8.738884384694905e-07,
      "loss": 3.3029,
      "step": 150
    },
    {
      "epoch": 0.9531129900076863,
      "grad_norm": 0.9466863901587774,
      "learning_rate": 8.617166520598562e-07,
      "loss": 3.2964,
      "step": 155
    },
    {
      "epoch": 0.9838585703305149,
      "grad_norm": 0.8018084383307482,
      "learning_rate": 8.490775625938451e-07,
      "loss": 3.2516,
      "step": 160
    }
  ],
  "logging_steps": 5,
  "max_steps": 486,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 51242899865600.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}