{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 1.8021265092809515,
  "eval_steps": 500,
  "global_step": 20000,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.04505316273202379,
      "grad_norm": 2773.720458984375,
      "learning_rate": 1.25e-05,
      "loss": 2160.937,
      "step": 500
    },
    {
      "epoch": 0.09010632546404758,
      "grad_norm": 2222.2841796875,
      "learning_rate": 2.5e-05,
      "loss": 607.2575,
      "step": 1000
    },
    {
      "epoch": 0.13515948819607138,
      "grad_norm": 2238.150146484375,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 567.5459,
      "step": 1500
    },
    {
      "epoch": 0.18021265092809516,
      "grad_norm": 2031.3114013671875,
      "learning_rate": 5e-05,
      "loss": 555.2621,
      "step": 2000
    },
    {
      "epoch": 0.22526581366011894,
      "grad_norm": 1727.6153564453125,
      "learning_rate": 4.990486745229364e-05,
      "loss": 530.0263,
      "step": 2500
    },
    {
      "epoch": 0.27031897639214275,
      "grad_norm": 4237.337890625,
      "learning_rate": 4.962019382530521e-05,
      "loss": 518.2249,
      "step": 3000
    },
    {
      "epoch": 0.3153721391241665,
      "grad_norm": 2440.982177734375,
      "learning_rate": 4.914814565722671e-05,
      "loss": 515.6068,
      "step": 3500
    },
    {
      "epoch": 0.3604253018561903,
      "grad_norm": 1709.0987548828125,
      "learning_rate": 4.849231551964771e-05,
      "loss": 492.0353,
      "step": 4000
    },
    {
      "epoch": 0.40547846458821407,
      "grad_norm": 2613.7958984375,
      "learning_rate": 4.765769467591625e-05,
      "loss": 493.8408,
      "step": 4500
    },
    {
      "epoch": 0.4505316273202379,
      "grad_norm": 1762.2047119140625,
      "learning_rate": 4.665063509461097e-05,
      "loss": 484.2692,
      "step": 5000
    },
    {
      "epoch": 0.4955847900522617,
      "grad_norm": 2041.5257568359375,
      "learning_rate": 4.54788011072248e-05,
      "loss": 482.6173,
      "step": 5500
    },
    {
      "epoch": 0.5406379527842855,
      "grad_norm": 1927.1434326171875,
      "learning_rate": 4.415111107797445e-05,
      "loss": 474.6368,
      "step": 6000
    },
    {
      "epoch": 0.5856911155163093,
      "grad_norm": 1960.3173828125,
      "learning_rate": 4.267766952966369e-05,
      "loss": 465.6196,
      "step": 6500
    },
    {
      "epoch": 0.630744278248333,
      "grad_norm": 1922.5286865234375,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 462.0098,
      "step": 7000
    },
    {
      "epoch": 0.6757974409803568,
      "grad_norm": 2714.07177734375,
      "learning_rate": 3.933941090877615e-05,
      "loss": 459.0566,
      "step": 7500
    },
    {
      "epoch": 0.7208506037123806,
      "grad_norm": 3798.8544921875,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 456.6062,
      "step": 8000
    },
    {
      "epoch": 0.7659037664444044,
      "grad_norm": 2949.78564453125,
      "learning_rate": 3.556545654351749e-05,
      "loss": 450.5293,
      "step": 8500
    },
    {
      "epoch": 0.8109569291764281,
      "grad_norm": 3772.734130859375,
      "learning_rate": 3.355050358314172e-05,
      "loss": 449.1692,
      "step": 9000
    },
    {
      "epoch": 0.856010091908452,
      "grad_norm": 3372.73828125,
      "learning_rate": 3.147047612756302e-05,
      "loss": 439.0725,
      "step": 9500
    },
    {
      "epoch": 0.9010632546404758,
      "grad_norm": 3328.4609375,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 440.5102,
      "step": 10000
    },
    {
      "epoch": 0.9461164173724995,
      "grad_norm": 2040.6248779296875,
      "learning_rate": 2.717889356869146e-05,
      "loss": 437.5615,
      "step": 10500
    },
    {
      "epoch": 0.9911695801045234,
      "grad_norm": 1969.1085205078125,
      "learning_rate": 2.5e-05,
      "loss": 428.4736,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_loss": 408.4035339355469,
      "eval_runtime": 101.091,
      "eval_samples_per_second": 97.585,
      "eval_steps_per_second": 12.207,
      "step": 11098
    },
    {
      "epoch": 1.0362227428365471,
      "grad_norm": 5208.33203125,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 419.041,
      "step": 11500
    },
    {
      "epoch": 1.081275905568571,
      "grad_norm": 1830.0736083984375,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 412.06,
      "step": 12000
    },
    {
      "epoch": 1.1263290683005946,
      "grad_norm": 1650.867919921875,
      "learning_rate": 1.852952387243698e-05,
      "loss": 411.9837,
      "step": 12500
    },
    {
      "epoch": 1.1713822310326185,
      "grad_norm": 2066.202880859375,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 414.626,
      "step": 13000
    },
    {
      "epoch": 1.2164353937646424,
      "grad_norm": 3917.142578125,
      "learning_rate": 1.443454345648252e-05,
      "loss": 409.7331,
      "step": 13500
    },
    {
      "epoch": 1.261488556496666,
      "grad_norm": 2366.1328125,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 397.0079,
      "step": 14000
    },
    {
      "epoch": 1.30654171922869,
      "grad_norm": 2070.89697265625,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 402.8564,
      "step": 14500
    },
    {
      "epoch": 1.3515948819607138,
      "grad_norm": 1930.0994873046875,
      "learning_rate": 8.930309757836517e-06,
      "loss": 396.2593,
      "step": 15000
    },
    {
      "epoch": 1.3966480446927374,
      "grad_norm": 4285.21630859375,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 403.2037,
      "step": 15500
    },
    {
      "epoch": 1.4417012074247613,
      "grad_norm": 2037.2159423828125,
      "learning_rate": 5.848888922025553e-06,
      "loss": 397.7643,
      "step": 16000
    },
    {
      "epoch": 1.4867543701567851,
      "grad_norm": 2373.021484375,
      "learning_rate": 4.521198892775203e-06,
      "loss": 399.0661,
      "step": 16500
    },
    {
      "epoch": 1.5318075328888088,
      "grad_norm": 1866.4925537109375,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 399.666,
      "step": 17000
    },
    {
      "epoch": 1.5768606956208324,
      "grad_norm": 1536.1265869140625,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 396.0931,
      "step": 17500
    },
    {
      "epoch": 1.6219138583528565,
      "grad_norm": 2335.9306640625,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 394.8895,
      "step": 18000
    },
    {
      "epoch": 1.6669670210848802,
      "grad_norm": 1966.092041015625,
      "learning_rate": 8.51854342773295e-07,
      "loss": 400.0806,
      "step": 18500
    },
    {
      "epoch": 1.7120201838169038,
      "grad_norm": 1782.7061767578125,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 395.8506,
      "step": 19000
    },
    {
      "epoch": 1.7570733465489279,
      "grad_norm": 2151.033203125,
      "learning_rate": 9.513254770636137e-08,
      "loss": 390.219,
      "step": 19500
    },
    {
      "epoch": 1.8021265092809515,
      "grad_norm": 2529.850341796875,
      "learning_rate": 0.0,
      "loss": 391.8754,
      "step": 20000
    }
  ],
  "logging_steps": 500,
  "max_steps": 20000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 5000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 0.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}