{
  "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": 1504.0633544921875,
      "learning_rate": 1.25e-05,
      "loss": 50577.664,
      "step": 500
    },
    {
      "epoch": 0.09010632546404758,
      "grad_norm": 4176.2333984375,
      "learning_rate": 2.5e-05,
      "loss": 956.2112,
      "step": 1000
    },
    {
      "epoch": 0.13515948819607138,
      "grad_norm": 4970.99951171875,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 782.5375,
      "step": 1500
    },
    {
      "epoch": 0.18021265092809516,
      "grad_norm": 2413.134521484375,
      "learning_rate": 5e-05,
      "loss": 689.6987,
      "step": 2000
    },
    {
      "epoch": 0.22526581366011894,
      "grad_norm": 5042.96044921875,
      "learning_rate": 4.990486745229364e-05,
      "loss": 584.8549,
      "step": 2500
    },
    {
      "epoch": 0.27031897639214275,
      "grad_norm": 4070.779541015625,
      "learning_rate": 4.962019382530521e-05,
      "loss": 517.2255,
      "step": 3000
    },
    {
      "epoch": 0.3153721391241665,
      "grad_norm": 3235.265625,
      "learning_rate": 4.914814565722671e-05,
      "loss": 481.8345,
      "step": 3500
    },
    {
      "epoch": 0.3604253018561903,
      "grad_norm": 3092.599853515625,
      "learning_rate": 4.849231551964771e-05,
      "loss": 440.7662,
      "step": 4000
    },
    {
      "epoch": 0.40547846458821407,
      "grad_norm": 2103.07470703125,
      "learning_rate": 4.765769467591625e-05,
      "loss": 431.5163,
      "step": 4500
    },
    {
      "epoch": 0.4505316273202379,
      "grad_norm": 4784.69677734375,
      "learning_rate": 4.665063509461097e-05,
      "loss": 412.511,
      "step": 5000
    },
    {
      "epoch": 0.4955847900522617,
      "grad_norm": 2093.876220703125,
      "learning_rate": 4.54788011072248e-05,
      "loss": 403.5441,
      "step": 5500
    },
    {
      "epoch": 0.5406379527842855,
      "grad_norm": 2614.074951171875,
      "learning_rate": 4.415111107797445e-05,
      "loss": 393.1005,
      "step": 6000
    },
    {
      "epoch": 0.5856911155163093,
      "grad_norm": 2555.35009765625,
      "learning_rate": 4.267766952966369e-05,
      "loss": 386.7879,
      "step": 6500
    },
    {
      "epoch": 0.630744278248333,
      "grad_norm": 1973.346923828125,
      "learning_rate": 4.1069690242163484e-05,
      "loss": 377.9793,
      "step": 7000
    },
    {
      "epoch": 0.6757974409803568,
      "grad_norm": 2326.179443359375,
      "learning_rate": 3.933941090877615e-05,
      "loss": 368.5712,
      "step": 7500
    },
    {
      "epoch": 0.7208506037123806,
      "grad_norm": 2329.2734375,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 362.9063,
      "step": 8000
    },
    {
      "epoch": 0.7659037664444044,
      "grad_norm": 2288.851806640625,
      "learning_rate": 3.556545654351749e-05,
      "loss": 356.2086,
      "step": 8500
    },
    {
      "epoch": 0.8109569291764281,
      "grad_norm": 1827.595458984375,
      "learning_rate": 3.355050358314172e-05,
      "loss": 348.2401,
      "step": 9000
    },
    {
      "epoch": 0.856010091908452,
      "grad_norm": 2932.881103515625,
      "learning_rate": 3.147047612756302e-05,
      "loss": 348.9446,
      "step": 9500
    },
    {
      "epoch": 0.9010632546404758,
      "grad_norm": 2461.783447265625,
      "learning_rate": 2.9341204441673266e-05,
      "loss": 346.5127,
      "step": 10000
    },
    {
      "epoch": 0.9461164173724995,
      "grad_norm": 2421.28662109375,
      "learning_rate": 2.717889356869146e-05,
      "loss": 344.7176,
      "step": 10500
    },
    {
      "epoch": 0.9911695801045234,
      "grad_norm": 1982.3907470703125,
      "learning_rate": 2.5e-05,
      "loss": 337.3412,
      "step": 11000
    },
    {
      "epoch": 1.0,
      "eval_loss": 313.6606750488281,
      "eval_runtime": 287.9712,
      "eval_samples_per_second": 34.253,
      "eval_steps_per_second": 4.282,
      "step": 11098
    },
    {
      "epoch": 1.0362227428365471,
      "grad_norm": 2792.6796875,
      "learning_rate": 2.2821106431308544e-05,
      "loss": 334.3391,
      "step": 11500
    },
    {
      "epoch": 1.081275905568571,
      "grad_norm": 1987.4095458984375,
      "learning_rate": 2.0658795558326743e-05,
      "loss": 322.6437,
      "step": 12000
    },
    {
      "epoch": 1.1263290683005946,
      "grad_norm": 2908.916748046875,
      "learning_rate": 1.852952387243698e-05,
      "loss": 315.7919,
      "step": 12500
    },
    {
      "epoch": 1.1713822310326185,
      "grad_norm": 2517.258056640625,
      "learning_rate": 1.6449496416858284e-05,
      "loss": 318.9125,
      "step": 13000
    },
    {
      "epoch": 1.2164353937646424,
      "grad_norm": 2682.38720703125,
      "learning_rate": 1.443454345648252e-05,
      "loss": 319.5607,
      "step": 13500
    },
    {
      "epoch": 1.261488556496666,
      "grad_norm": 2938.4580078125,
      "learning_rate": 1.2500000000000006e-05,
      "loss": 315.3093,
      "step": 14000
    },
    {
      "epoch": 1.30654171922869,
      "grad_norm": 2178.617919921875,
      "learning_rate": 1.0660589091223855e-05,
      "loss": 310.6303,
      "step": 14500
    },
    {
      "epoch": 1.3515948819607138,
      "grad_norm": 2113.363037109375,
      "learning_rate": 8.930309757836517e-06,
      "loss": 312.9181,
      "step": 15000
    },
    {
      "epoch": 1.3966480446927374,
      "grad_norm": 1653.667724609375,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 309.9157,
      "step": 15500
    },
    {
      "epoch": 1.4417012074247613,
      "grad_norm": 1915.794921875,
      "learning_rate": 5.848888922025553e-06,
      "loss": 306.6258,
      "step": 16000
    },
    {
      "epoch": 1.4867543701567851,
      "grad_norm": 2332.58447265625,
      "learning_rate": 4.521198892775203e-06,
      "loss": 305.0456,
      "step": 16500
    },
    {
      "epoch": 1.5318075328888088,
      "grad_norm": 2958.545166015625,
      "learning_rate": 3.3493649053890326e-06,
      "loss": 308.7233,
      "step": 17000
    },
    {
      "epoch": 1.5768606956208324,
      "grad_norm": 2622.941650390625,
      "learning_rate": 2.3423053240837515e-06,
      "loss": 305.4986,
      "step": 17500
    },
    {
      "epoch": 1.6219138583528565,
      "grad_norm": 2132.97265625,
      "learning_rate": 1.5076844803522922e-06,
      "loss": 308.1588,
      "step": 18000
    },
    {
      "epoch": 1.6669670210848802,
      "grad_norm": 2630.685791015625,
      "learning_rate": 8.51854342773295e-07,
      "loss": 299.4269,
      "step": 18500
    },
    {
      "epoch": 1.7120201838169038,
      "grad_norm": 3238.62158203125,
      "learning_rate": 3.7980617469479953e-07,
      "loss": 303.9314,
      "step": 19000
    },
    {
      "epoch": 1.7570733465489279,
      "grad_norm": 2097.742431640625,
      "learning_rate": 9.513254770636137e-08,
      "loss": 307.2666,
      "step": 19500
    },
    {
      "epoch": 1.8021265092809515,
      "grad_norm": 2517.14990234375,
      "learning_rate": 0.0,
      "loss": 304.3546,
      "step": 20000
    }
  ],
  "logging_steps": 500,
  "max_steps": 20000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 2,
  "save_steps": 10000,
  "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
}