{
  "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": 4470.23388671875,
      "learning_rate": 1.25e-05,
      "loss": 17941.426,
      "step": 500
    },
    {
      "epoch": 0.09010632546404758,
      "grad_norm": 2147.42724609375,
      "learning_rate": 2.5e-05,
      "loss": 684.2933,
      "step": 1000
    },
    {
      "epoch": 0.13515948819607138,
      "grad_norm": 5162.5986328125,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 536.4867,
      "step": 1500
    },
    {
      "epoch": 0.18021265092809516,
      "grad_norm": 3121.87646484375,
      "learning_rate": 5e-05,
      "loss": 434.1654,
      "step": 2000
    },
    {
      "epoch": 0.22526581366011894,
      "grad_norm": 3676.3232421875,
      "learning_rate": 4.990486745229364e-05,
      "loss": 386.8585,
      "step": 2500
    },
    {
      "epoch": 0.27031897639214275,
      "grad_norm": 7765.45458984375,
      "learning_rate": 4.962019382530521e-05,
      "loss": 335.3436,
      "step": 3000
    },
    {
      "epoch": 0.3153721391241665,
      "grad_norm": 2876.93701171875,
      "learning_rate": 4.914814565722671e-05,
      "loss": 322.3182,
      "step": 3500
    },
    {
      "epoch": 0.3604253018561903,
      "grad_norm": 0.0,
      "learning_rate": 4.849231551964771e-05,
      "loss": 293.0514,
      "step": 4000
    },
    {
      "epoch": 0.40547846458821407,
      "grad_norm": 2518.416259765625,
      "learning_rate": 4.765769467591625e-05,
      "loss": 269.1285,
      "step": 4500
    },
    {
      "epoch": 0.4505316273202379,
      "grad_norm": 3044.99853515625,
      "learning_rate": 4.665063509461097e-05,
      "loss": 277.6437,
      "step": 5000
    },
    {
      "epoch": 0.4955847900522617,
      "grad_norm": 2915.5595703125,
      "learning_rate": 4.54788011072248e-05,
      "loss": 258.6959,
      "step": 5500
    },
    {
      "epoch": 0.5406379527842855,
      "grad_norm": 0.0,
      "learning_rate": 4.415111107797445e-05,
      "loss": 260.6136,
      "step": 6000
    },
    {
      "epoch": 0.5856911155163093,
      "grad_norm": 3373.0654296875,
      "learning_rate": 4.267766952966369e-05,
      "loss": 250.7846,
      "step": 6500
    },
    {
      "epoch": 0.630744278248333,
      "grad_norm": 2416.063232421875,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 240.0419,
      "step": 7000
    },
    {
      "epoch": 0.6757974409803568,
      "grad_norm": 3405.637451171875,
      "learning_rate": 3.933941090877615e-05,
      "loss": 242.7395,
      "step": 7500
    },
    {
      "epoch": 0.7208506037123806,
      "grad_norm": 0.0,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 236.5273,
      "step": 8000
    },
    {
      "epoch": 0.7659037664444044,
      "grad_norm": 2412.057861328125,
      "learning_rate": 3.556545654351749e-05,
      "loss": 225.7031,
      "step": 8500
    },
    {
      "epoch": 0.8109569291764281,
      "grad_norm": 8866.654296875,
      "learning_rate": 3.355050358314172e-05,
      "loss": 232.8072,
      "step": 9000
    },
    {
      "epoch": 0.856010091908452,
      "grad_norm": 2159.58642578125,
      "learning_rate": 3.147047612756302e-05,
      "loss": 228.5174,
      "step": 9500
    },
    {
      "epoch": 0.9010632546404758,
      "grad_norm": 3101.438720703125,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 226.6102,
      "step": 10000
    },
    {
      "epoch": 0.9461164173724995,
      "grad_norm": 2370.216552734375,
      "learning_rate": 2.717889356869146e-05,
      "loss": 221.0378,
      "step": 10500
    },
    {
      "epoch": 0.9911695801045234,
      "grad_norm": 1607.97900390625,
      "learning_rate": 2.5e-05,
      "loss": 208.4827,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_loss": 237.83326721191406,
      "eval_runtime": 242.6406,
      "eval_samples_per_second": 40.657,
      "eval_steps_per_second": 5.086,
      "step": 11098
    },
    {
      "epoch": 1.0362227428365471,
      "grad_norm": 1659.910400390625,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 202.1607,
      "step": 11500
    },
    {
      "epoch": 1.081275905568571,
      "grad_norm": 1811.052001953125,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 198.4596,
      "step": 12000
    },
    {
      "epoch": 1.1263290683005946,
      "grad_norm": 4330.6376953125,
      "learning_rate": 1.852952387243698e-05,
      "loss": 194.4083,
      "step": 12500
    },
    {
      "epoch": 1.1713822310326185,
      "grad_norm": 2148.2275390625,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 196.8616,
      "step": 13000
    },
    {
      "epoch": 1.2164353937646424,
      "grad_norm": 2007.6566162109375,
      "learning_rate": 1.443454345648252e-05,
      "loss": 193.8067,
      "step": 13500
    },
    {
      "epoch": 1.261488556496666,
      "grad_norm": 1964.06884765625,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 189.0563,
      "step": 14000
    },
    {
      "epoch": 1.30654171922869,
      "grad_norm": 2146.515625,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 187.8685,
      "step": 14500
    },
    {
      "epoch": 1.3515948819607138,
      "grad_norm": 0.0,
      "learning_rate": 8.930309757836517e-06,
      "loss": 191.7554,
      "step": 15000
    },
    {
      "epoch": 1.3966480446927374,
      "grad_norm": 2082.637451171875,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 186.9572,
      "step": 15500
    },
    {
      "epoch": 1.4417012074247613,
      "grad_norm": 3713.958984375,
      "learning_rate": 5.848888922025553e-06,
      "loss": 187.3405,
      "step": 16000
    },
    {
      "epoch": 1.4867543701567851,
      "grad_norm": 3464.310302734375,
      "learning_rate": 4.521198892775203e-06,
      "loss": 184.6902,
      "step": 16500
    },
    {
      "epoch": 1.5318075328888088,
      "grad_norm": 2287.31494140625,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 185.3727,
      "step": 17000
    },
    {
      "epoch": 1.5768606956208324,
      "grad_norm": 2169.33544921875,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 189.5521,
      "step": 17500
    },
    {
      "epoch": 1.6219138583528565,
      "grad_norm": 4489.81787109375,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 186.5204,
      "step": 18000
    },
    {
      "epoch": 1.6669670210848802,
      "grad_norm": 2658.7236328125,
      "learning_rate": 8.51854342773295e-07,
      "loss": 178.6977,
      "step": 18500
    },
    {
      "epoch": 1.7120201838169038,
      "grad_norm": 2208.738037109375,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 179.4614,
      "step": 19000
    },
    {
      "epoch": 1.7570733465489279,
      "grad_norm": 5405.3544921875,
      "learning_rate": 9.513254770636137e-08,
      "loss": 179.7739,
      "step": 19500
    },
    {
      "epoch": 1.8021265092809515,
      "grad_norm": 2117.037353515625,
      "learning_rate": 0.0,
      "loss": 178.2009,
      "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
}