{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5037783375314862,
  "eval_steps": 500,
  "global_step": 450,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00559753708368318,
      "grad_norm": 0.8359375,
      "learning_rate": 0.0001,
      "loss": 5.5483,
      "step": 5
    },
    {
      "epoch": 0.01119507416736636,
      "grad_norm": 0.55078125,
      "learning_rate": 0.0001,
      "loss": 4.1635,
      "step": 10
    },
    {
      "epoch": 0.016792611251049538,
      "grad_norm": 0.54296875,
      "learning_rate": 0.0001,
      "loss": 3.2229,
      "step": 15
    },
    {
      "epoch": 0.02239014833473272,
      "grad_norm": 0.376953125,
      "learning_rate": 0.0001,
      "loss": 2.8432,
      "step": 20
    },
    {
      "epoch": 0.027987685418415897,
      "grad_norm": 0.462890625,
      "learning_rate": 0.0001,
      "loss": 2.6705,
      "step": 25
    },
    {
      "epoch": 0.033585222502099076,
      "grad_norm": 0.5234375,
      "learning_rate": 0.0001,
      "loss": 2.3014,
      "step": 30
    },
    {
      "epoch": 0.039182759585782254,
      "grad_norm": 0.318359375,
      "learning_rate": 0.0001,
      "loss": 1.8735,
      "step": 35
    },
    {
      "epoch": 0.04478029666946544,
      "grad_norm": 0.2578125,
      "learning_rate": 0.0001,
      "loss": 1.6909,
      "step": 40
    },
    {
      "epoch": 0.05037783375314862,
      "grad_norm": 0.2158203125,
      "learning_rate": 0.0001,
      "loss": 1.6512,
      "step": 45
    },
    {
      "epoch": 0.055975370836831795,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0001,
      "loss": 1.5669,
      "step": 50
    },
    {
      "epoch": 0.06157290792051497,
      "grad_norm": 0.2333984375,
      "learning_rate": 0.0001,
      "loss": 1.5499,
      "step": 55
    },
    {
      "epoch": 0.06717044500419815,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.0001,
      "loss": 1.557,
      "step": 60
    },
    {
      "epoch": 0.07276798208788134,
      "grad_norm": 0.1748046875,
      "learning_rate": 0.0001,
      "loss": 1.5974,
      "step": 65
    },
    {
      "epoch": 0.07836551917156451,
      "grad_norm": 0.173828125,
      "learning_rate": 0.0001,
      "loss": 1.6001,
      "step": 70
    },
    {
      "epoch": 0.08396305625524769,
      "grad_norm": 0.171875,
      "learning_rate": 0.0001,
      "loss": 1.6237,
      "step": 75
    },
    {
      "epoch": 0.08956059333893088,
      "grad_norm": 0.2578125,
      "learning_rate": 0.0001,
      "loss": 1.5338,
      "step": 80
    },
    {
      "epoch": 0.09515813042261405,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001,
      "loss": 1.53,
      "step": 85
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001,
      "loss": 1.5943,
      "step": 90
    },
    {
      "epoch": 0.1063532045899804,
      "grad_norm": 0.240234375,
      "learning_rate": 0.0001,
      "loss": 1.5289,
      "step": 95
    },
    {
      "epoch": 0.11195074167366359,
      "grad_norm": 0.283203125,
      "learning_rate": 0.0001,
      "loss": 1.5258,
      "step": 100
    },
    {
      "epoch": 0.11754827875734676,
      "grad_norm": 0.1708984375,
      "learning_rate": 0.0001,
      "loss": 1.5399,
      "step": 105
    },
    {
      "epoch": 0.12314581584102995,
      "grad_norm": 0.2001953125,
      "learning_rate": 0.0001,
      "loss": 1.5737,
      "step": 110
    },
    {
      "epoch": 0.12874335292471312,
      "grad_norm": 0.1630859375,
      "learning_rate": 0.0001,
      "loss": 1.5441,
      "step": 115
    },
    {
      "epoch": 0.1343408900083963,
      "grad_norm": 0.19140625,
      "learning_rate": 0.0001,
      "loss": 1.4422,
      "step": 120
    },
    {
      "epoch": 0.1399384270920795,
      "grad_norm": 0.203125,
      "learning_rate": 0.0001,
      "loss": 1.452,
      "step": 125
    },
    {
      "epoch": 0.14553596417576267,
      "grad_norm": 0.2353515625,
      "learning_rate": 0.0001,
      "loss": 1.4814,
      "step": 130
    },
    {
      "epoch": 0.15113350125944586,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001,
      "loss": 1.5935,
      "step": 135
    },
    {
      "epoch": 0.15673103834312901,
      "grad_norm": 0.1884765625,
      "learning_rate": 0.0001,
      "loss": 1.444,
      "step": 140
    },
    {
      "epoch": 0.1623285754268122,
      "grad_norm": 0.18359375,
      "learning_rate": 0.0001,
      "loss": 1.5664,
      "step": 145
    },
    {
      "epoch": 0.16792611251049538,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0001,
      "loss": 1.3374,
      "step": 150
    },
    {
      "epoch": 0.17352364959417857,
      "grad_norm": 0.380859375,
      "learning_rate": 0.0001,
      "loss": 1.551,
      "step": 155
    },
    {
      "epoch": 0.17912118667786175,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0001,
      "loss": 1.5344,
      "step": 160
    },
    {
      "epoch": 0.1847187237615449,
      "grad_norm": 0.216796875,
      "learning_rate": 0.0001,
      "loss": 1.5554,
      "step": 165
    },
    {
      "epoch": 0.1903162608452281,
      "grad_norm": 0.1806640625,
      "learning_rate": 0.0001,
      "loss": 1.5077,
      "step": 170
    },
    {
      "epoch": 0.19591379792891128,
      "grad_norm": 0.18359375,
      "learning_rate": 0.0001,
      "loss": 1.5209,
      "step": 175
    },
    {
      "epoch": 0.20151133501259447,
      "grad_norm": 0.2001953125,
      "learning_rate": 0.0001,
      "loss": 1.4717,
      "step": 180
    },
    {
      "epoch": 0.20710887209627762,
      "grad_norm": 0.19921875,
      "learning_rate": 0.0001,
      "loss": 1.5203,
      "step": 185
    },
    {
      "epoch": 0.2127064091799608,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.0001,
      "loss": 1.4326,
      "step": 190
    },
    {
      "epoch": 0.218303946263644,
      "grad_norm": 0.203125,
      "learning_rate": 0.0001,
      "loss": 1.4371,
      "step": 195
    },
    {
      "epoch": 0.22390148334732718,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001,
      "loss": 1.3296,
      "step": 200
    },
    {
      "epoch": 0.22949902043101036,
      "grad_norm": 0.5234375,
      "learning_rate": 0.0001,
      "loss": 1.4735,
      "step": 205
    },
    {
      "epoch": 0.23509655751469352,
      "grad_norm": 0.20703125,
      "learning_rate": 0.0001,
      "loss": 1.5329,
      "step": 210
    },
    {
      "epoch": 0.2406940945983767,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.0001,
      "loss": 1.4673,
      "step": 215
    },
    {
      "epoch": 0.2462916316820599,
      "grad_norm": 0.203125,
      "learning_rate": 0.0001,
      "loss": 1.5117,
      "step": 220
    },
    {
      "epoch": 0.2518891687657431,
      "grad_norm": 0.1953125,
      "learning_rate": 0.0001,
      "loss": 1.5133,
      "step": 225
    },
    {
      "epoch": 0.25748670584942623,
      "grad_norm": 0.267578125,
      "learning_rate": 0.0001,
      "loss": 1.5302,
      "step": 230
    },
    {
      "epoch": 0.26308424293310945,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0001,
      "loss": 1.52,
      "step": 235
    },
    {
      "epoch": 0.2686817800167926,
      "grad_norm": 0.1875,
      "learning_rate": 0.0001,
      "loss": 1.52,
      "step": 240
    },
    {
      "epoch": 0.2742793171004758,
      "grad_norm": 0.193359375,
      "learning_rate": 0.0001,
      "loss": 1.4227,
      "step": 245
    },
    {
      "epoch": 0.279876854184159,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0001,
      "loss": 1.3521,
      "step": 250
    },
    {
      "epoch": 0.28547439126784213,
      "grad_norm": 0.2080078125,
      "learning_rate": 0.0001,
      "loss": 1.4912,
      "step": 255
    },
    {
      "epoch": 0.29107192835152534,
      "grad_norm": 0.23046875,
      "learning_rate": 0.0001,
      "loss": 1.5325,
      "step": 260
    },
    {
      "epoch": 0.2966694654352085,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001,
      "loss": 1.5691,
      "step": 265
    },
    {
      "epoch": 0.3022670025188917,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.0001,
      "loss": 1.4568,
      "step": 270
    },
    {
      "epoch": 0.30786453960257487,
      "grad_norm": 0.240234375,
      "learning_rate": 0.0001,
      "loss": 1.5762,
      "step": 275
    },
    {
      "epoch": 0.31346207668625803,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001,
      "loss": 1.4846,
      "step": 280
    },
    {
      "epoch": 0.31905961376994124,
      "grad_norm": 0.2041015625,
      "learning_rate": 0.0001,
      "loss": 1.4436,
      "step": 285
    },
    {
      "epoch": 0.3246571508536244,
      "grad_norm": 0.1875,
      "learning_rate": 0.0001,
      "loss": 1.5297,
      "step": 290
    },
    {
      "epoch": 0.3302546879373076,
      "grad_norm": 0.216796875,
      "learning_rate": 0.0001,
      "loss": 1.4201,
      "step": 295
    },
    {
      "epoch": 0.33585222502099077,
      "grad_norm": 0.353515625,
      "learning_rate": 0.0001,
      "loss": 1.3166,
      "step": 300
    },
    {
      "epoch": 0.3414497621046739,
      "grad_norm": 0.357421875,
      "learning_rate": 0.0001,
      "loss": 1.4785,
      "step": 305
    },
    {
      "epoch": 0.34704729918835714,
      "grad_norm": 0.30859375,
      "learning_rate": 0.0001,
      "loss": 1.5302,
      "step": 310
    },
    {
      "epoch": 0.3526448362720403,
      "grad_norm": 0.201171875,
      "learning_rate": 0.0001,
      "loss": 1.4568,
      "step": 315
    },
    {
      "epoch": 0.3582423733557235,
      "grad_norm": 0.2275390625,
      "learning_rate": 0.0001,
      "loss": 1.4256,
      "step": 320
    },
    {
      "epoch": 0.36383991043940667,
      "grad_norm": 0.34375,
      "learning_rate": 0.0001,
      "loss": 1.4523,
      "step": 325
    },
    {
      "epoch": 0.3694374475230898,
      "grad_norm": 0.1787109375,
      "learning_rate": 0.0001,
      "loss": 1.4466,
      "step": 330
    },
    {
      "epoch": 0.37503498460677304,
      "grad_norm": 0.1982421875,
      "learning_rate": 0.0001,
      "loss": 1.4772,
      "step": 335
    },
    {
      "epoch": 0.3806325216904562,
      "grad_norm": 0.2197265625,
      "learning_rate": 0.0001,
      "loss": 1.4707,
      "step": 340
    },
    {
      "epoch": 0.38623005877413935,
      "grad_norm": 0.2158203125,
      "learning_rate": 0.0001,
      "loss": 1.3964,
      "step": 345
    },
    {
      "epoch": 0.39182759585782256,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001,
      "loss": 1.3211,
      "step": 350
    },
    {
      "epoch": 0.3974251329415057,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0001,
      "loss": 1.3659,
      "step": 355
    },
    {
      "epoch": 0.40302267002518893,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0001,
      "loss": 1.5411,
      "step": 360
    },
    {
      "epoch": 0.4086202071088721,
      "grad_norm": 0.2431640625,
      "learning_rate": 0.0001,
      "loss": 1.4501,
      "step": 365
    },
    {
      "epoch": 0.41421774419255525,
      "grad_norm": 0.2021484375,
      "learning_rate": 0.0001,
      "loss": 1.5281,
      "step": 370
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 0.234375,
      "learning_rate": 0.0001,
      "loss": 1.458,
      "step": 375
    },
    {
      "epoch": 0.4254128183599216,
      "grad_norm": 0.201171875,
      "learning_rate": 0.0001,
      "loss": 1.3954,
      "step": 380
    },
    {
      "epoch": 0.43101035544360483,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0001,
      "loss": 1.394,
      "step": 385
    },
    {
      "epoch": 0.436607892527288,
      "grad_norm": 0.2041015625,
      "learning_rate": 0.0001,
      "loss": 1.4369,
      "step": 390
    },
    {
      "epoch": 0.44220542961097115,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001,
      "loss": 1.3687,
      "step": 395
    },
    {
      "epoch": 0.44780296669465436,
      "grad_norm": 0.29296875,
      "learning_rate": 0.0001,
      "loss": 1.2293,
      "step": 400
    },
    {
      "epoch": 0.4534005037783375,
      "grad_norm": 0.287109375,
      "learning_rate": 0.0001,
      "loss": 1.4791,
      "step": 405
    },
    {
      "epoch": 0.45899804086202073,
      "grad_norm": 0.5546875,
      "learning_rate": 0.0001,
      "loss": 1.464,
      "step": 410
    },
    {
      "epoch": 0.4645955779457039,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001,
      "loss": 1.4523,
      "step": 415
    },
    {
      "epoch": 0.47019311502938704,
      "grad_norm": 0.2373046875,
      "learning_rate": 0.0001,
      "loss": 1.4332,
      "step": 420
    },
    {
      "epoch": 0.47579065211307026,
      "grad_norm": 0.19921875,
      "learning_rate": 0.0001,
      "loss": 1.4185,
      "step": 425
    },
    {
      "epoch": 0.4813881891967534,
      "grad_norm": 0.322265625,
      "learning_rate": 0.0001,
      "loss": 1.5112,
      "step": 430
    },
    {
      "epoch": 0.4869857262804366,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.0001,
      "loss": 1.5503,
      "step": 435
    },
    {
      "epoch": 0.4925832633641198,
      "grad_norm": 0.2421875,
      "learning_rate": 0.0001,
      "loss": 1.3926,
      "step": 440
    },
    {
      "epoch": 0.49818080044780294,
      "grad_norm": 0.232421875,
      "learning_rate": 0.0001,
      "loss": 1.3562,
      "step": 445
    },
    {
      "epoch": 0.5037783375314862,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0001,
      "loss": 1.3121,
      "step": 450
    },
    {
      "epoch": 0.5037783375314862,
      "step": 450,
      "total_flos": 4.334613097500672e+17,
      "train_loss": 1.6184998904334174,
      "train_runtime": 20544.5242,
      "train_samples_per_second": 1.402,
      "train_steps_per_second": 0.022
    }
  ],
  "logging_steps": 5,
  "max_steps": 450,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 90,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 4.334613097500672e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}