{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.5486284289276808,
  "eval_steps": 500,
  "global_step": 550,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0113314447592068,
      "grad_norm": 4.46875,
      "learning_rate": 3.6000000000000003e-06,
      "loss": 0.5448,
      "step": 10
    },
    {
      "epoch": 0.0226628895184136,
      "grad_norm": 0.74609375,
      "learning_rate": 7.600000000000001e-06,
      "loss": 0.4594,
      "step": 20
    },
    {
      "epoch": 0.0339943342776204,
      "grad_norm": 0.380859375,
      "learning_rate": 1.16e-05,
      "loss": 0.3953,
      "step": 30
    },
    {
      "epoch": 0.0453257790368272,
      "grad_norm": 0.31640625,
      "learning_rate": 1.5600000000000003e-05,
      "loss": 0.3695,
      "step": 40
    },
    {
      "epoch": 0.056657223796033995,
      "grad_norm": 0.2314453125,
      "learning_rate": 1.9600000000000002e-05,
      "loss": 0.3366,
      "step": 50
    },
    {
      "epoch": 0.0679886685552408,
      "grad_norm": 0.21484375,
      "learning_rate": 1.9998642592088543e-05,
      "loss": 0.3204,
      "step": 60
    },
    {
      "epoch": 0.07932011331444759,
      "grad_norm": 0.2060546875,
      "learning_rate": 1.9993950790937545e-05,
      "loss": 0.3231,
      "step": 70
    },
    {
      "epoch": 0.0906515580736544,
      "grad_norm": 0.2236328125,
      "learning_rate": 1.9985909410557404e-05,
      "loss": 0.3127,
      "step": 80
    },
    {
      "epoch": 0.10198300283286119,
      "grad_norm": 0.21875,
      "learning_rate": 1.9974521146102535e-05,
      "loss": 0.3033,
      "step": 90
    },
    {
      "epoch": 0.11331444759206799,
      "grad_norm": 0.267578125,
      "learning_rate": 1.9959789814471278e-05,
      "loss": 0.2907,
      "step": 100
    },
    {
      "epoch": 0.12464589235127478,
      "grad_norm": 0.24609375,
      "learning_rate": 1.9941720353026582e-05,
      "loss": 0.2941,
      "step": 110
    },
    {
      "epoch": 0.1359773371104816,
      "grad_norm": 0.2236328125,
      "learning_rate": 1.9920318817941234e-05,
      "loss": 0.2844,
      "step": 120
    },
    {
      "epoch": 0.14730878186968838,
      "grad_norm": 0.23828125,
      "learning_rate": 1.9895592382168036e-05,
      "loss": 0.2801,
      "step": 130
    },
    {
      "epoch": 0.15864022662889518,
      "grad_norm": 0.2294921875,
      "learning_rate": 1.986754933303574e-05,
      "loss": 0.2805,
      "step": 140
    },
    {
      "epoch": 0.16997167138810199,
      "grad_norm": 0.2177734375,
      "learning_rate": 1.983619906947144e-05,
      "loss": 0.2706,
      "step": 150
    },
    {
      "epoch": 0.1813031161473088,
      "grad_norm": 0.240234375,
      "learning_rate": 1.980155209885043e-05,
      "loss": 0.2756,
      "step": 160
    },
    {
      "epoch": 0.19263456090651557,
      "grad_norm": 0.232421875,
      "learning_rate": 1.9763620033474552e-05,
      "loss": 0.2713,
      "step": 170
    },
    {
      "epoch": 0.20396600566572237,
      "grad_norm": 0.2470703125,
      "learning_rate": 1.9722415586680204e-05,
      "loss": 0.2675,
      "step": 180
    },
    {
      "epoch": 0.21529745042492918,
      "grad_norm": 0.236328125,
      "learning_rate": 1.9677952568577316e-05,
      "loss": 0.2574,
      "step": 190
    },
    {
      "epoch": 0.22662889518413598,
      "grad_norm": 0.259765625,
      "learning_rate": 1.9630245881420764e-05,
      "loss": 0.2636,
      "step": 200
    },
    {
      "epoch": 0.23796033994334279,
      "grad_norm": 0.26953125,
      "learning_rate": 1.957931151461572e-05,
      "loss": 0.2614,
      "step": 210
    },
    {
      "epoch": 0.24929178470254956,
      "grad_norm": 0.271484375,
      "learning_rate": 1.9525166539358608e-05,
      "loss": 0.2548,
      "step": 220
    },
    {
      "epoch": 0.26062322946175637,
      "grad_norm": 0.2412109375,
      "learning_rate": 1.946782910291554e-05,
      "loss": 0.2532,
      "step": 230
    },
    {
      "epoch": 0.2719546742209632,
      "grad_norm": 0.271484375,
      "learning_rate": 1.9407318422540057e-05,
      "loss": 0.2545,
      "step": 240
    },
    {
      "epoch": 0.28328611898017,
      "grad_norm": 0.267578125,
      "learning_rate": 1.9343654779032244e-05,
      "loss": 0.251,
      "step": 250
    },
    {
      "epoch": 0.2593516209476309,
      "grad_norm": 0.29296875,
      "learning_rate": 1.944186059309318e-05,
      "loss": 0.2362,
      "step": 260
    },
    {
      "epoch": 0.26932668329177056,
      "grad_norm": 0.31640625,
      "learning_rate": 1.93877370638343e-05,
      "loss": 0.2377,
      "step": 270
    },
    {
      "epoch": 0.2793017456359102,
      "grad_norm": 0.3125,
      "learning_rate": 1.9331191872025963e-05,
      "loss": 0.2346,
      "step": 280
    },
    {
      "epoch": 0.2892768079800499,
      "grad_norm": 0.400390625,
      "learning_rate": 1.927223960407727e-05,
      "loss": 0.233,
      "step": 290
    },
    {
      "epoch": 0.29925187032418954,
      "grad_norm": 0.337890625,
      "learning_rate": 1.921089546732717e-05,
      "loss": 0.23,
      "step": 300
    },
    {
      "epoch": 0.3092269326683292,
      "grad_norm": 0.31640625,
      "learning_rate": 1.9147175286121577e-05,
      "loss": 0.2345,
      "step": 310
    },
    {
      "epoch": 0.3192019950124688,
      "grad_norm": 0.298828125,
      "learning_rate": 1.90810954977313e-05,
      "loss": 0.2325,
      "step": 320
    },
    {
      "epoch": 0.32917705735660846,
      "grad_norm": 0.3359375,
      "learning_rate": 1.9012673148111908e-05,
      "loss": 0.2322,
      "step": 330
    },
    {
      "epoch": 0.33915211970074816,
      "grad_norm": 0.298828125,
      "learning_rate": 1.8941925887506527e-05,
      "loss": 0.2257,
      "step": 340
    },
    {
      "epoch": 0.3491271820448878,
      "grad_norm": 0.31640625,
      "learning_rate": 1.8868871965892794e-05,
      "loss": 0.2273,
      "step": 350
    },
    {
      "epoch": 0.35910224438902744,
      "grad_norm": 0.400390625,
      "learning_rate": 1.879353022827509e-05,
      "loss": 0.2272,
      "step": 360
    },
    {
      "epoch": 0.3690773067331671,
      "grad_norm": 0.3515625,
      "learning_rate": 1.8715920109823266e-05,
      "loss": 0.2223,
      "step": 370
    },
    {
      "epoch": 0.3790523690773067,
      "grad_norm": 0.33203125,
      "learning_rate": 1.8636061630859157e-05,
      "loss": 0.2175,
      "step": 380
    },
    {
      "epoch": 0.38902743142144636,
      "grad_norm": 0.345703125,
      "learning_rate": 1.855397539169214e-05,
      "loss": 0.2175,
      "step": 390
    },
    {
      "epoch": 0.39900249376558605,
      "grad_norm": 0.4140625,
      "learning_rate": 1.846968256730504e-05,
      "loss": 0.2146,
      "step": 400
    },
    {
      "epoch": 0.4089775561097257,
      "grad_norm": 0.330078125,
      "learning_rate": 1.838320490189187e-05,
      "loss": 0.2127,
      "step": 410
    },
    {
      "epoch": 0.41895261845386533,
      "grad_norm": 0.35546875,
      "learning_rate": 1.8294564703248668e-05,
      "loss": 0.207,
      "step": 420
    },
    {
      "epoch": 0.428927680798005,
      "grad_norm": 0.365234375,
      "learning_rate": 1.8203784837018985e-05,
      "loss": 0.2025,
      "step": 430
    },
    {
      "epoch": 0.4389027431421446,
      "grad_norm": 0.390625,
      "learning_rate": 1.8110888720795453e-05,
      "loss": 0.203,
      "step": 440
    },
    {
      "epoch": 0.4488778054862843,
      "grad_norm": 0.365234375,
      "learning_rate": 1.8015900318078976e-05,
      "loss": 0.2026,
      "step": 450
    },
    {
      "epoch": 0.45885286783042395,
      "grad_norm": 0.345703125,
      "learning_rate": 1.791884413209711e-05,
      "loss": 0.194,
      "step": 460
    },
    {
      "epoch": 0.4688279301745636,
      "grad_norm": 0.388671875,
      "learning_rate": 1.7819745199483196e-05,
      "loss": 0.1938,
      "step": 470
    },
    {
      "epoch": 0.47880299251870323,
      "grad_norm": 0.380859375,
      "learning_rate": 1.7718629083817914e-05,
      "loss": 0.1981,
      "step": 480
    },
    {
      "epoch": 0.48877805486284287,
      "grad_norm": 0.330078125,
      "learning_rate": 1.7615521869034887e-05,
      "loss": 0.1939,
      "step": 490
    },
    {
      "epoch": 0.49875311720698257,
      "grad_norm": 0.365234375,
      "learning_rate": 1.751045015269207e-05,
      "loss": 0.1874,
      "step": 500
    },
    {
      "epoch": 0.5087281795511222,
      "grad_norm": 0.38671875,
      "learning_rate": 1.740344103911063e-05,
      "loss": 0.1947,
      "step": 510
    },
    {
      "epoch": 0.5187032418952618,
      "grad_norm": 0.400390625,
      "learning_rate": 1.7294522132383137e-05,
      "loss": 0.1927,
      "step": 520
    },
    {
      "epoch": 0.5286783042394015,
      "grad_norm": 0.40234375,
      "learning_rate": 1.7183721529252762e-05,
      "loss": 0.1879,
      "step": 530
    },
    {
      "epoch": 0.5386533665835411,
      "grad_norm": 0.43359375,
      "learning_rate": 1.7071067811865477e-05,
      "loss": 0.1899,
      "step": 540
    },
    {
      "epoch": 0.5486284289276808,
      "grad_norm": 0.408203125,
      "learning_rate": 1.6956590040396975e-05,
      "loss": 0.1791,
      "step": 550
    }
  ],
  "logging_steps": 10,
  "max_steps": 2006,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 50,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 8.7337702045947e+18,
  "train_batch_size": 25,
  "trial_name": null,
  "trial_params": null
}