{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.7473598700243704,
  "eval_steps": 500,
  "global_step": 460,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.016246953696181964,
      "grad_norm": 0.11087504774332047,
      "learning_rate": 0.0002,
      "loss": 1.2851,
      "step": 10
    },
    {
      "epoch": 0.03249390739236393,
      "grad_norm": 0.14227746427059174,
      "learning_rate": 0.0002,
      "loss": 1.1866,
      "step": 20
    },
    {
      "epoch": 0.048740861088545896,
      "grad_norm": 0.15468546748161316,
      "learning_rate": 0.0002,
      "loss": 1.3344,
      "step": 30
    },
    {
      "epoch": 0.06498781478472786,
      "grad_norm": 0.1867746114730835,
      "learning_rate": 0.0002,
      "loss": 1.4973,
      "step": 40
    },
    {
      "epoch": 0.08123476848090982,
      "grad_norm": 0.6773258447647095,
      "learning_rate": 0.0002,
      "loss": 1.7041,
      "step": 50
    },
    {
      "epoch": 0.09748172217709179,
      "grad_norm": 0.09346572309732437,
      "learning_rate": 0.0002,
      "loss": 1.239,
      "step": 60
    },
    {
      "epoch": 0.11372867587327376,
      "grad_norm": 0.11293257027864456,
      "learning_rate": 0.0002,
      "loss": 1.1884,
      "step": 70
    },
    {
      "epoch": 0.12997562956945571,
      "grad_norm": 0.1317419856786728,
      "learning_rate": 0.0002,
      "loss": 1.3503,
      "step": 80
    },
    {
      "epoch": 0.1462225832656377,
      "grad_norm": 0.20818021893501282,
      "learning_rate": 0.0002,
      "loss": 1.505,
      "step": 90
    },
    {
      "epoch": 0.16246953696181965,
      "grad_norm": 0.5995267629623413,
      "learning_rate": 0.0002,
      "loss": 1.7264,
      "step": 100
    },
    {
      "epoch": 0.17871649065800163,
      "grad_norm": 0.10515395551919937,
      "learning_rate": 0.0002,
      "loss": 1.1812,
      "step": 110
    },
    {
      "epoch": 0.19496344435418358,
      "grad_norm": 0.11150451004505157,
      "learning_rate": 0.0002,
      "loss": 1.287,
      "step": 120
    },
    {
      "epoch": 0.21121039805036557,
      "grad_norm": 0.1395130306482315,
      "learning_rate": 0.0002,
      "loss": 1.2411,
      "step": 130
    },
    {
      "epoch": 0.22745735174654752,
      "grad_norm": 0.15016046166419983,
      "learning_rate": 0.0002,
      "loss": 1.4182,
      "step": 140
    },
    {
      "epoch": 0.2437043054427295,
      "grad_norm": 0.4636495113372803,
      "learning_rate": 0.0002,
      "loss": 1.7269,
      "step": 150
    },
    {
      "epoch": 0.25995125913891143,
      "grad_norm": 0.0939592495560646,
      "learning_rate": 0.0002,
      "loss": 1.2139,
      "step": 160
    },
    {
      "epoch": 0.27619821283509344,
      "grad_norm": 0.09509933739900589,
      "learning_rate": 0.0002,
      "loss": 1.1963,
      "step": 170
    },
    {
      "epoch": 0.2924451665312754,
      "grad_norm": 0.1235380694270134,
      "learning_rate": 0.0002,
      "loss": 1.2873,
      "step": 180
    },
    {
      "epoch": 0.30869212022745735,
      "grad_norm": 0.1839320808649063,
      "learning_rate": 0.0002,
      "loss": 1.455,
      "step": 190
    },
    {
      "epoch": 0.3249390739236393,
      "grad_norm": 0.481478750705719,
      "learning_rate": 0.0002,
      "loss": 1.7412,
      "step": 200
    },
    {
      "epoch": 0.3411860276198213,
      "grad_norm": 0.08681885898113251,
      "learning_rate": 0.0002,
      "loss": 1.2474,
      "step": 210
    },
    {
      "epoch": 0.35743298131600326,
      "grad_norm": 0.09558644890785217,
      "learning_rate": 0.0002,
      "loss": 1.2158,
      "step": 220
    },
    {
      "epoch": 0.3736799350121852,
      "grad_norm": 0.12771648168563843,
      "learning_rate": 0.0002,
      "loss": 1.3005,
      "step": 230
    },
    {
      "epoch": 0.38992688870836717,
      "grad_norm": 0.17630507051944733,
      "learning_rate": 0.0002,
      "loss": 1.4772,
      "step": 240
    },
    {
      "epoch": 0.4061738424045491,
      "grad_norm": 0.44942063093185425,
      "learning_rate": 0.0002,
      "loss": 1.6645,
      "step": 250
    },
    {
      "epoch": 0.42242079610073113,
      "grad_norm": 0.09558656066656113,
      "learning_rate": 0.0002,
      "loss": 1.1758,
      "step": 260
    },
    {
      "epoch": 0.4386677497969131,
      "grad_norm": 0.09703896939754486,
      "learning_rate": 0.0002,
      "loss": 1.2423,
      "step": 270
    },
    {
      "epoch": 0.45491470349309504,
      "grad_norm": 0.12717948853969574,
      "learning_rate": 0.0002,
      "loss": 1.3671,
      "step": 280
    },
    {
      "epoch": 0.471161657189277,
      "grad_norm": 0.1827155202627182,
      "learning_rate": 0.0002,
      "loss": 1.5173,
      "step": 290
    },
    {
      "epoch": 0.487408610885459,
      "grad_norm": 0.4099660813808441,
      "learning_rate": 0.0002,
      "loss": 1.6514,
      "step": 300
    },
    {
      "epoch": 0.503655564581641,
      "grad_norm": 0.12756651639938354,
      "learning_rate": 0.0002,
      "loss": 1.1952,
      "step": 310
    },
    {
      "epoch": 0.5199025182778229,
      "grad_norm": 0.09647507965564728,
      "learning_rate": 0.0002,
      "loss": 1.1511,
      "step": 320
    },
    {
      "epoch": 0.5361494719740049,
      "grad_norm": 0.12492221593856812,
      "learning_rate": 0.0002,
      "loss": 1.1778,
      "step": 330
    },
    {
      "epoch": 0.5523964256701869,
      "grad_norm": 0.18637599050998688,
      "learning_rate": 0.0002,
      "loss": 1.4947,
      "step": 340
    },
    {
      "epoch": 0.5686433793663688,
      "grad_norm": 0.5491933226585388,
      "learning_rate": 0.0002,
      "loss": 1.6702,
      "step": 350
    },
    {
      "epoch": 0.5848903330625508,
      "grad_norm": 0.091646708548069,
      "learning_rate": 0.0002,
      "loss": 1.1607,
      "step": 360
    },
    {
      "epoch": 0.6011372867587328,
      "grad_norm": 0.10480837523937225,
      "learning_rate": 0.0002,
      "loss": 1.2112,
      "step": 370
    },
    {
      "epoch": 0.6173842404549147,
      "grad_norm": 0.12856683135032654,
      "learning_rate": 0.0002,
      "loss": 1.2448,
      "step": 380
    },
    {
      "epoch": 0.6336311941510967,
      "grad_norm": 0.221836119890213,
      "learning_rate": 0.0002,
      "loss": 1.471,
      "step": 390
    },
    {
      "epoch": 0.6498781478472786,
      "grad_norm": 0.442389577627182,
      "learning_rate": 0.0002,
      "loss": 1.7765,
      "step": 400
    },
    {
      "epoch": 0.6661251015434606,
      "grad_norm": 0.08752889186143875,
      "learning_rate": 0.0002,
      "loss": 1.2821,
      "step": 410
    },
    {
      "epoch": 0.6823720552396426,
      "grad_norm": 0.10227832943201065,
      "learning_rate": 0.0002,
      "loss": 1.1901,
      "step": 420
    },
    {
      "epoch": 0.6986190089358245,
      "grad_norm": 0.12081281840801239,
      "learning_rate": 0.0002,
      "loss": 1.302,
      "step": 430
    },
    {
      "epoch": 0.7148659626320065,
      "grad_norm": 0.1923910230398178,
      "learning_rate": 0.0002,
      "loss": 1.5397,
      "step": 440
    },
    {
      "epoch": 0.7311129163281884,
      "grad_norm": 0.5226483941078186,
      "learning_rate": 0.0002,
      "loss": 1.6591,
      "step": 450
    },
    {
      "epoch": 0.7473598700243704,
      "grad_norm": 0.09780491888523102,
      "learning_rate": 0.0002,
      "loss": 1.1514,
      "step": 460
    }
  ],
  "logging_steps": 10,
  "max_steps": 500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 10,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.0671426142086758e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}