{
  "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": 4495.31298828125,
      "learning_rate": 1.25e-05,
      "loss": 876.4691,
      "step": 500
    },
    {
      "epoch": 0.09010632546404758,
      "grad_norm": 7690.41552734375,
      "learning_rate": 2.5e-05,
      "loss": 552.9783,
      "step": 1000
    },
    {
      "epoch": 0.13515948819607138,
      "grad_norm": 3831.229736328125,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 508.4013,
      "step": 1500
    },
    {
      "epoch": 0.18021265092809516,
      "grad_norm": 2652.883056640625,
      "learning_rate": 5e-05,
      "loss": 493.1244,
      "step": 2000
    },
    {
      "epoch": 0.22526581366011894,
      "grad_norm": 2329.73388671875,
      "learning_rate": 4.990486745229364e-05,
      "loss": 471.2945,
      "step": 2500
    },
    {
      "epoch": 0.27031897639214275,
      "grad_norm": 2660.374267578125,
      "learning_rate": 4.962019382530521e-05,
      "loss": 462.8009,
      "step": 3000
    },
    {
      "epoch": 0.3153721391241665,
      "grad_norm": 2498.203857421875,
      "learning_rate": 4.914814565722671e-05,
      "loss": 446.8442,
      "step": 3500
    },
    {
      "epoch": 0.3604253018561903,
      "grad_norm": 3495.0498046875,
      "learning_rate": 4.849231551964771e-05,
      "loss": 449.2647,
      "step": 4000
    },
    {
      "epoch": 0.40547846458821407,
      "grad_norm": 2064.2861328125,
      "learning_rate": 4.765769467591625e-05,
      "loss": 438.1682,
      "step": 4500
    },
    {
      "epoch": 0.4505316273202379,
      "grad_norm": 2323.6640625,
      "learning_rate": 4.665063509461097e-05,
      "loss": 434.8857,
      "step": 5000
    },
    {
      "epoch": 0.4955847900522617,
      "grad_norm": 3712.401611328125,
      "learning_rate": 4.54788011072248e-05,
      "loss": 426.7452,
      "step": 5500
    },
    {
      "epoch": 0.5406379527842855,
      "grad_norm": 3010.898193359375,
      "learning_rate": 4.415111107797445e-05,
      "loss": 425.659,
      "step": 6000
    },
    {
      "epoch": 0.5856911155163093,
      "grad_norm": 2957.86572265625,
      "learning_rate": 4.267766952966369e-05,
      "loss": 414.4347,
      "step": 6500
    },
    {
      "epoch": 0.630744278248333,
      "grad_norm": 5558.51171875,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 414.9519,
      "step": 7000
    },
    {
      "epoch": 0.6757974409803568,
      "grad_norm": 2855.100341796875,
      "learning_rate": 3.933941090877615e-05,
      "loss": 400.0895,
      "step": 7500
    },
    {
      "epoch": 0.7208506037123806,
      "grad_norm": 6043.2392578125,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 406.6636,
      "step": 8000
    },
    {
      "epoch": 0.7659037664444044,
      "grad_norm": 2479.6162109375,
      "learning_rate": 3.556545654351749e-05,
      "loss": 396.584,
      "step": 8500
    },
    {
      "epoch": 0.8109569291764281,
      "grad_norm": 2344.032958984375,
      "learning_rate": 3.355050358314172e-05,
      "loss": 394.9724,
      "step": 9000
    },
    {
      "epoch": 0.856010091908452,
      "grad_norm": 2779.349853515625,
      "learning_rate": 3.147047612756302e-05,
      "loss": 397.4112,
      "step": 9500
    },
    {
      "epoch": 0.9010632546404758,
      "grad_norm": 2716.18994140625,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 391.9731,
      "step": 10000
    },
    {
      "epoch": 0.9461164173724995,
      "grad_norm": 2225.15673828125,
      "learning_rate": 2.717889356869146e-05,
      "loss": 393.7706,
      "step": 10500
    },
    {
      "epoch": 0.9911695801045234,
      "grad_norm": 1508.1142578125,
      "learning_rate": 2.5e-05,
      "loss": 382.8044,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_loss": 358.9232177734375,
      "eval_runtime": 101.4193,
      "eval_samples_per_second": 97.269,
      "eval_steps_per_second": 12.167,
      "step": 11098
    },
    {
      "epoch": 1.0362227428365471,
      "grad_norm": 2014.6854248046875,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 367.5687,
      "step": 11500
    },
    {
      "epoch": 1.081275905568571,
      "grad_norm": 3775.6591796875,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 359.601,
      "step": 12000
    },
    {
      "epoch": 1.1263290683005946,
      "grad_norm": 5092.62548828125,
      "learning_rate": 1.852952387243698e-05,
      "loss": 363.3713,
      "step": 12500
    },
    {
      "epoch": 1.1713822310326185,
      "grad_norm": 2063.513671875,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 359.5718,
      "step": 13000
    },
    {
      "epoch": 1.2164353937646424,
      "grad_norm": 2899.44091796875,
      "learning_rate": 1.443454345648252e-05,
      "loss": 360.4644,
      "step": 13500
    },
    {
      "epoch": 1.261488556496666,
      "grad_norm": 4710.76123046875,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 361.0999,
      "step": 14000
    },
    {
      "epoch": 1.30654171922869,
      "grad_norm": 2558.06005859375,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 350.5707,
      "step": 14500
    },
    {
      "epoch": 1.3515948819607138,
      "grad_norm": 3802.858642578125,
      "learning_rate": 8.930309757836517e-06,
      "loss": 357.1574,
      "step": 15000
    },
    {
      "epoch": 1.3966480446927374,
      "grad_norm": 2361.53662109375,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 347.2792,
      "step": 15500
    },
    {
      "epoch": 1.4417012074247613,
      "grad_norm": 2280.421630859375,
      "learning_rate": 5.848888922025553e-06,
      "loss": 349.3208,
      "step": 16000
    },
    {
      "epoch": 1.4867543701567851,
      "grad_norm": 2809.066650390625,
      "learning_rate": 4.521198892775203e-06,
      "loss": 353.3406,
      "step": 16500
    },
    {
      "epoch": 1.5318075328888088,
      "grad_norm": 2266.29248046875,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 349.8974,
      "step": 17000
    },
    {
      "epoch": 1.5768606956208324,
      "grad_norm": 2905.138671875,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 342.301,
      "step": 17500
    },
    {
      "epoch": 1.6219138583528565,
      "grad_norm": 2068.38330078125,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 347.1441,
      "step": 18000
    },
    {
      "epoch": 1.6669670210848802,
      "grad_norm": 2976.573486328125,
      "learning_rate": 8.51854342773295e-07,
      "loss": 349.023,
      "step": 18500
    },
    {
      "epoch": 1.7120201838169038,
      "grad_norm": 3883.230712890625,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 356.191,
      "step": 19000
    },
    {
      "epoch": 1.7570733465489279,
      "grad_norm": 1931.0743408203125,
      "learning_rate": 9.513254770636137e-08,
      "loss": 344.1293,
      "step": 19500
    },
    {
      "epoch": 1.8021265092809515,
      "grad_norm": 2924.070556640625,
      "learning_rate": 0.0,
      "loss": 350.3576,
      "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
}