{
  "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": 1.2421875,
      "learning_rate": 0.0001,
      "loss": 4.5193,
      "step": 5
    },
    {
      "epoch": 0.01119507416736636,
      "grad_norm": 0.68359375,
      "learning_rate": 0.0001,
      "loss": 2.8387,
      "step": 10
    },
    {
      "epoch": 0.016792611251049538,
      "grad_norm": 0.484375,
      "learning_rate": 0.0001,
      "loss": 2.1966,
      "step": 15
    },
    {
      "epoch": 0.02239014833473272,
      "grad_norm": 0.51953125,
      "learning_rate": 0.0001,
      "loss": 2.0024,
      "step": 20
    },
    {
      "epoch": 0.027987685418415897,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001,
      "loss": 1.7735,
      "step": 25
    },
    {
      "epoch": 0.033585222502099076,
      "grad_norm": 0.263671875,
      "learning_rate": 0.0001,
      "loss": 1.6781,
      "step": 30
    },
    {
      "epoch": 0.039182759585782254,
      "grad_norm": 0.291015625,
      "learning_rate": 0.0001,
      "loss": 1.6619,
      "step": 35
    },
    {
      "epoch": 0.04478029666946544,
      "grad_norm": 0.3125,
      "learning_rate": 0.0001,
      "loss": 1.6361,
      "step": 40
    },
    {
      "epoch": 0.05037783375314862,
      "grad_norm": 0.298828125,
      "learning_rate": 0.0001,
      "loss": 1.6153,
      "step": 45
    },
    {
      "epoch": 0.055975370836831795,
      "grad_norm": 0.306640625,
      "learning_rate": 0.0001,
      "loss": 1.5201,
      "step": 50
    },
    {
      "epoch": 0.06157290792051497,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001,
      "loss": 1.5211,
      "step": 55
    },
    {
      "epoch": 0.06717044500419815,
      "grad_norm": 0.2392578125,
      "learning_rate": 0.0001,
      "loss": 1.5359,
      "step": 60
    },
    {
      "epoch": 0.07276798208788134,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001,
      "loss": 1.5686,
      "step": 65
    },
    {
      "epoch": 0.07836551917156451,
      "grad_norm": 0.255859375,
      "learning_rate": 0.0001,
      "loss": 1.5732,
      "step": 70
    },
    {
      "epoch": 0.08396305625524769,
      "grad_norm": 0.244140625,
      "learning_rate": 0.0001,
      "loss": 1.5958,
      "step": 75
    },
    {
      "epoch": 0.08956059333893088,
      "grad_norm": 0.25390625,
      "learning_rate": 0.0001,
      "loss": 1.5006,
      "step": 80
    },
    {
      "epoch": 0.09515813042261405,
      "grad_norm": 0.2890625,
      "learning_rate": 0.0001,
      "loss": 1.5051,
      "step": 85
    },
    {
      "epoch": 0.10075566750629723,
      "grad_norm": 0.314453125,
      "learning_rate": 0.0001,
      "loss": 1.5649,
      "step": 90
    },
    {
      "epoch": 0.1063532045899804,
      "grad_norm": 0.263671875,
      "learning_rate": 0.0001,
      "loss": 1.5,
      "step": 95
    },
    {
      "epoch": 0.11195074167366359,
      "grad_norm": 0.310546875,
      "learning_rate": 0.0001,
      "loss": 1.4951,
      "step": 100
    },
    {
      "epoch": 0.11754827875734676,
      "grad_norm": 0.2412109375,
      "learning_rate": 0.0001,
      "loss": 1.5258,
      "step": 105
    },
    {
      "epoch": 0.12314581584102995,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.0001,
      "loss": 1.556,
      "step": 110
    },
    {
      "epoch": 0.12874335292471312,
      "grad_norm": 0.1982421875,
      "learning_rate": 0.0001,
      "loss": 1.5306,
      "step": 115
    },
    {
      "epoch": 0.1343408900083963,
      "grad_norm": 0.203125,
      "learning_rate": 0.0001,
      "loss": 1.4242,
      "step": 120
    },
    {
      "epoch": 0.1399384270920795,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.0001,
      "loss": 1.4403,
      "step": 125
    },
    {
      "epoch": 0.14553596417576267,
      "grad_norm": 0.2265625,
      "learning_rate": 0.0001,
      "loss": 1.4604,
      "step": 130
    },
    {
      "epoch": 0.15113350125944586,
      "grad_norm": 0.2275390625,
      "learning_rate": 0.0001,
      "loss": 1.5809,
      "step": 135
    },
    {
      "epoch": 0.15673103834312901,
      "grad_norm": 0.2421875,
      "learning_rate": 0.0001,
      "loss": 1.4282,
      "step": 140
    },
    {
      "epoch": 0.1623285754268122,
      "grad_norm": 0.228515625,
      "learning_rate": 0.0001,
      "loss": 1.5452,
      "step": 145
    },
    {
      "epoch": 0.16792611251049538,
      "grad_norm": 0.359375,
      "learning_rate": 0.0001,
      "loss": 1.3127,
      "step": 150
    },
    {
      "epoch": 0.17352364959417857,
      "grad_norm": 0.46875,
      "learning_rate": 0.0001,
      "loss": 1.5287,
      "step": 155
    },
    {
      "epoch": 0.17912118667786175,
      "grad_norm": 0.28515625,
      "learning_rate": 0.0001,
      "loss": 1.5197,
      "step": 160
    },
    {
      "epoch": 0.1847187237615449,
      "grad_norm": 0.201171875,
      "learning_rate": 0.0001,
      "loss": 1.5512,
      "step": 165
    },
    {
      "epoch": 0.1903162608452281,
      "grad_norm": 0.2490234375,
      "learning_rate": 0.0001,
      "loss": 1.4973,
      "step": 170
    },
    {
      "epoch": 0.19591379792891128,
      "grad_norm": 0.220703125,
      "learning_rate": 0.0001,
      "loss": 1.503,
      "step": 175
    },
    {
      "epoch": 0.20151133501259447,
      "grad_norm": 0.2080078125,
      "learning_rate": 0.0001,
      "loss": 1.4571,
      "step": 180
    },
    {
      "epoch": 0.20710887209627762,
      "grad_norm": 0.2119140625,
      "learning_rate": 0.0001,
      "loss": 1.5066,
      "step": 185
    },
    {
      "epoch": 0.2127064091799608,
      "grad_norm": 0.2470703125,
      "learning_rate": 0.0001,
      "loss": 1.42,
      "step": 190
    },
    {
      "epoch": 0.218303946263644,
      "grad_norm": 0.2275390625,
      "learning_rate": 0.0001,
      "loss": 1.4306,
      "step": 195
    },
    {
      "epoch": 0.22390148334732718,
      "grad_norm": 0.357421875,
      "learning_rate": 0.0001,
      "loss": 1.3198,
      "step": 200
    },
    {
      "epoch": 0.22949902043101036,
      "grad_norm": 0.2109375,
      "learning_rate": 0.0001,
      "loss": 1.4567,
      "step": 205
    },
    {
      "epoch": 0.23509655751469352,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001,
      "loss": 1.5331,
      "step": 210
    },
    {
      "epoch": 0.2406940945983767,
      "grad_norm": 0.2392578125,
      "learning_rate": 0.0001,
      "loss": 1.4561,
      "step": 215
    },
    {
      "epoch": 0.2462916316820599,
      "grad_norm": 0.263671875,
      "learning_rate": 0.0001,
      "loss": 1.5067,
      "step": 220
    },
    {
      "epoch": 0.2518891687657431,
      "grad_norm": 0.21875,
      "learning_rate": 0.0001,
      "loss": 1.5058,
      "step": 225
    },
    {
      "epoch": 0.25748670584942623,
      "grad_norm": 0.2333984375,
      "learning_rate": 0.0001,
      "loss": 1.5166,
      "step": 230
    },
    {
      "epoch": 0.26308424293310945,
      "grad_norm": 0.2060546875,
      "learning_rate": 0.0001,
      "loss": 1.5097,
      "step": 235
    },
    {
      "epoch": 0.2686817800167926,
      "grad_norm": 0.1982421875,
      "learning_rate": 0.0001,
      "loss": 1.5102,
      "step": 240
    },
    {
      "epoch": 0.2742793171004758,
      "grad_norm": 0.216796875,
      "learning_rate": 0.0001,
      "loss": 1.4113,
      "step": 245
    },
    {
      "epoch": 0.279876854184159,
      "grad_norm": 0.279296875,
      "learning_rate": 0.0001,
      "loss": 1.3356,
      "step": 250
    },
    {
      "epoch": 0.28547439126784213,
      "grad_norm": 0.25,
      "learning_rate": 0.0001,
      "loss": 1.4804,
      "step": 255
    },
    {
      "epoch": 0.29107192835152534,
      "grad_norm": 0.2236328125,
      "learning_rate": 0.0001,
      "loss": 1.5235,
      "step": 260
    },
    {
      "epoch": 0.2966694654352085,
      "grad_norm": 0.23828125,
      "learning_rate": 0.0001,
      "loss": 1.5687,
      "step": 265
    },
    {
      "epoch": 0.3022670025188917,
      "grad_norm": 0.220703125,
      "learning_rate": 0.0001,
      "loss": 1.4548,
      "step": 270
    },
    {
      "epoch": 0.30786453960257487,
      "grad_norm": 0.2041015625,
      "learning_rate": 0.0001,
      "loss": 1.5667,
      "step": 275
    },
    {
      "epoch": 0.31346207668625803,
      "grad_norm": 0.2060546875,
      "learning_rate": 0.0001,
      "loss": 1.4787,
      "step": 280
    },
    {
      "epoch": 0.31905961376994124,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.0001,
      "loss": 1.4374,
      "step": 285
    },
    {
      "epoch": 0.3246571508536244,
      "grad_norm": 0.2138671875,
      "learning_rate": 0.0001,
      "loss": 1.5262,
      "step": 290
    },
    {
      "epoch": 0.3302546879373076,
      "grad_norm": 0.26953125,
      "learning_rate": 0.0001,
      "loss": 1.4109,
      "step": 295
    },
    {
      "epoch": 0.33585222502099077,
      "grad_norm": 0.37890625,
      "learning_rate": 0.0001,
      "loss": 1.307,
      "step": 300
    },
    {
      "epoch": 0.3414497621046739,
      "grad_norm": 0.3671875,
      "learning_rate": 0.0001,
      "loss": 1.4678,
      "step": 305
    },
    {
      "epoch": 0.34704729918835714,
      "grad_norm": 0.244140625,
      "learning_rate": 0.0001,
      "loss": 1.5243,
      "step": 310
    },
    {
      "epoch": 0.3526448362720403,
      "grad_norm": 0.23828125,
      "learning_rate": 0.0001,
      "loss": 1.4596,
      "step": 315
    },
    {
      "epoch": 0.3582423733557235,
      "grad_norm": 0.19921875,
      "learning_rate": 0.0001,
      "loss": 1.4231,
      "step": 320
    },
    {
      "epoch": 0.36383991043940667,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001,
      "loss": 1.4536,
      "step": 325
    },
    {
      "epoch": 0.3694374475230898,
      "grad_norm": 0.18359375,
      "learning_rate": 0.0001,
      "loss": 1.4464,
      "step": 330
    },
    {
      "epoch": 0.37503498460677304,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.0001,
      "loss": 1.4785,
      "step": 335
    },
    {
      "epoch": 0.3806325216904562,
      "grad_norm": 0.2294921875,
      "learning_rate": 0.0001,
      "loss": 1.4717,
      "step": 340
    },
    {
      "epoch": 0.38623005877413935,
      "grad_norm": 0.2197265625,
      "learning_rate": 0.0001,
      "loss": 1.3935,
      "step": 345
    },
    {
      "epoch": 0.39182759585782256,
      "grad_norm": 0.2734375,
      "learning_rate": 0.0001,
      "loss": 1.3039,
      "step": 350
    },
    {
      "epoch": 0.3974251329415057,
      "grad_norm": 0.490234375,
      "learning_rate": 0.0001,
      "loss": 1.3593,
      "step": 355
    },
    {
      "epoch": 0.40302267002518893,
      "grad_norm": 0.2294921875,
      "learning_rate": 0.0001,
      "loss": 1.5417,
      "step": 360
    },
    {
      "epoch": 0.4086202071088721,
      "grad_norm": 0.251953125,
      "learning_rate": 0.0001,
      "loss": 1.4483,
      "step": 365
    },
    {
      "epoch": 0.41421774419255525,
      "grad_norm": 0.328125,
      "learning_rate": 0.0001,
      "loss": 1.5291,
      "step": 370
    },
    {
      "epoch": 0.41981528127623846,
      "grad_norm": 0.2216796875,
      "learning_rate": 0.0001,
      "loss": 1.4624,
      "step": 375
    },
    {
      "epoch": 0.4254128183599216,
      "grad_norm": 0.1845703125,
      "learning_rate": 0.0001,
      "loss": 1.3895,
      "step": 380
    },
    {
      "epoch": 0.43101035544360483,
      "grad_norm": 0.1943359375,
      "learning_rate": 0.0001,
      "loss": 1.3898,
      "step": 385
    },
    {
      "epoch": 0.436607892527288,
      "grad_norm": 0.1904296875,
      "learning_rate": 0.0001,
      "loss": 1.4392,
      "step": 390
    },
    {
      "epoch": 0.44220542961097115,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001,
      "loss": 1.3673,
      "step": 395
    },
    {
      "epoch": 0.44780296669465436,
      "grad_norm": 0.296875,
      "learning_rate": 0.0001,
      "loss": 1.2251,
      "step": 400
    },
    {
      "epoch": 0.4534005037783375,
      "grad_norm": 0.234375,
      "learning_rate": 0.0001,
      "loss": 1.4745,
      "step": 405
    },
    {
      "epoch": 0.45899804086202073,
      "grad_norm": 0.314453125,
      "learning_rate": 0.0001,
      "loss": 1.4641,
      "step": 410
    },
    {
      "epoch": 0.4645955779457039,
      "grad_norm": 0.220703125,
      "learning_rate": 0.0001,
      "loss": 1.447,
      "step": 415
    },
    {
      "epoch": 0.47019311502938704,
      "grad_norm": 0.212890625,
      "learning_rate": 0.0001,
      "loss": 1.4333,
      "step": 420
    },
    {
      "epoch": 0.47579065211307026,
      "grad_norm": 0.203125,
      "learning_rate": 0.0001,
      "loss": 1.4172,
      "step": 425
    },
    {
      "epoch": 0.4813881891967534,
      "grad_norm": 0.265625,
      "learning_rate": 0.0001,
      "loss": 1.5103,
      "step": 430
    },
    {
      "epoch": 0.4869857262804366,
      "grad_norm": 0.2255859375,
      "learning_rate": 0.0001,
      "loss": 1.5454,
      "step": 435
    },
    {
      "epoch": 0.4925832633641198,
      "grad_norm": 0.2138671875,
      "learning_rate": 0.0001,
      "loss": 1.3954,
      "step": 440
    },
    {
      "epoch": 0.49818080044780294,
      "grad_norm": 0.2177734375,
      "learning_rate": 0.0001,
      "loss": 1.3549,
      "step": 445
    },
    {
      "epoch": 0.5037783375314862,
      "grad_norm": 0.3046875,
      "learning_rate": 0.0001,
      "loss": 1.3045,
      "step": 450
    },
    {
      "epoch": 0.5037783375314862,
      "step": 450,
      "total_flos": 4.334613097500672e+17,
      "train_loss": 1.541747768190172,
      "train_runtime": 17912.5916,
      "train_samples_per_second": 1.608,
      "train_steps_per_second": 0.025
    }
  ],
  "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
}