{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0256,
  "eval_steps": 1000,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.00064,
      "grad_norm": 1.2594444751739502,
      "learning_rate": 3.840409643695328e-08,
      "loss": 0.7238,
      "step": 10
    },
    {
      "epoch": 0.00128,
      "grad_norm": 1.3807746171951294,
      "learning_rate": 8.10753147002347e-08,
      "loss": 0.7178,
      "step": 20
    },
    {
      "epoch": 0.00192,
      "grad_norm": 0.9590708613395691,
      "learning_rate": 1.2374653296351612e-07,
      "loss": 0.7106,
      "step": 30
    },
    {
      "epoch": 0.00256,
      "grad_norm": 1.2128362655639648,
      "learning_rate": 1.6641775122679754e-07,
      "loss": 0.72,
      "step": 40
    },
    {
      "epoch": 0.0032,
      "grad_norm": 1.0866276025772095,
      "learning_rate": 2.0908896949007894e-07,
      "loss": 0.7108,
      "step": 50
    },
    {
      "epoch": 0.00384,
      "grad_norm": 1.6984202861785889,
      "learning_rate": 2.517601877533604e-07,
      "loss": 0.7149,
      "step": 60
    },
    {
      "epoch": 0.00448,
      "grad_norm": 1.249053716659546,
      "learning_rate": 2.944314060166418e-07,
      "loss": 0.7243,
      "step": 70
    },
    {
      "epoch": 0.00512,
      "grad_norm": 1.8781795501708984,
      "learning_rate": 3.371026242799232e-07,
      "loss": 0.7138,
      "step": 80
    },
    {
      "epoch": 0.00576,
      "grad_norm": 2.162505626678467,
      "learning_rate": 3.7977384254320464e-07,
      "loss": 0.7117,
      "step": 90
    },
    {
      "epoch": 0.0064,
      "grad_norm": 1.0761003494262695,
      "learning_rate": 4.22445060806486e-07,
      "loss": 0.7121,
      "step": 100
    },
    {
      "epoch": 0.00704,
      "grad_norm": 2.104625940322876,
      "learning_rate": 4.651162790697675e-07,
      "loss": 0.7157,
      "step": 110
    },
    {
      "epoch": 0.00768,
      "grad_norm": 1.6532983779907227,
      "learning_rate": 5.077874973330489e-07,
      "loss": 0.7175,
      "step": 120
    },
    {
      "epoch": 0.00832,
      "grad_norm": 1.094260334968567,
      "learning_rate": 5.504587155963304e-07,
      "loss": 0.7142,
      "step": 130
    },
    {
      "epoch": 0.00896,
      "grad_norm": 1.7268928289413452,
      "learning_rate": 5.931299338596117e-07,
      "loss": 0.717,
      "step": 140
    },
    {
      "epoch": 0.0096,
      "grad_norm": 2.225884199142456,
      "learning_rate": 6.358011521228932e-07,
      "loss": 0.7144,
      "step": 150
    },
    {
      "epoch": 0.01024,
      "grad_norm": 1.7743901014328003,
      "learning_rate": 6.784723703861745e-07,
      "loss": 0.7127,
      "step": 160
    },
    {
      "epoch": 0.01088,
      "grad_norm": 1.1327497959136963,
      "learning_rate": 7.21143588649456e-07,
      "loss": 0.7148,
      "step": 170
    },
    {
      "epoch": 0.01152,
      "grad_norm": 1.9613993167877197,
      "learning_rate": 7.638148069127374e-07,
      "loss": 0.711,
      "step": 180
    },
    {
      "epoch": 0.01216,
      "grad_norm": 1.4991788864135742,
      "learning_rate": 8.064860251760189e-07,
      "loss": 0.713,
      "step": 190
    },
    {
      "epoch": 0.0128,
      "grad_norm": 1.3405441045761108,
      "learning_rate": 8.491572434393003e-07,
      "loss": 0.7142,
      "step": 200
    },
    {
      "epoch": 0.01344,
      "grad_norm": 1.8038678169250488,
      "learning_rate": 8.918284617025817e-07,
      "loss": 0.7067,
      "step": 210
    },
    {
      "epoch": 0.01408,
      "grad_norm": 1.2749669551849365,
      "learning_rate": 9.344996799658632e-07,
      "loss": 0.7133,
      "step": 220
    },
    {
      "epoch": 0.01472,
      "grad_norm": 1.858957052230835,
      "learning_rate": 9.771708982291445e-07,
      "loss": 0.7093,
      "step": 230
    },
    {
      "epoch": 0.01536,
      "grad_norm": 1.1406413316726685,
      "learning_rate": 1.0198421164924258e-06,
      "loss": 0.7163,
      "step": 240
    },
    {
      "epoch": 0.016,
      "grad_norm": 1.3233072757720947,
      "learning_rate": 1.0625133347557074e-06,
      "loss": 0.7152,
      "step": 250
    },
    {
      "epoch": 0.01664,
      "grad_norm": 2.3287241458892822,
      "learning_rate": 1.1051845530189888e-06,
      "loss": 0.712,
      "step": 260
    },
    {
      "epoch": 0.01728,
      "grad_norm": 1.6007124185562134,
      "learning_rate": 1.1478557712822702e-06,
      "loss": 0.711,
      "step": 270
    },
    {
      "epoch": 0.01792,
      "grad_norm": 1.5458295345306396,
      "learning_rate": 1.1905269895455517e-06,
      "loss": 0.7107,
      "step": 280
    },
    {
      "epoch": 0.01856,
      "grad_norm": 1.6052477359771729,
      "learning_rate": 1.233198207808833e-06,
      "loss": 0.7142,
      "step": 290
    },
    {
      "epoch": 0.0192,
      "grad_norm": 1.7393243312835693,
      "learning_rate": 1.2758694260721145e-06,
      "loss": 0.7126,
      "step": 300
    },
    {
      "epoch": 0.01984,
      "grad_norm": 1.3717942237854004,
      "learning_rate": 1.318540644335396e-06,
      "loss": 0.7053,
      "step": 310
    },
    {
      "epoch": 0.02048,
      "grad_norm": 1.41959810256958,
      "learning_rate": 1.3612118625986772e-06,
      "loss": 0.7011,
      "step": 320
    },
    {
      "epoch": 0.02112,
      "grad_norm": 1.365114450454712,
      "learning_rate": 1.4038830808619588e-06,
      "loss": 0.707,
      "step": 330
    },
    {
      "epoch": 0.02176,
      "grad_norm": 1.775238037109375,
      "learning_rate": 1.4465542991252401e-06,
      "loss": 0.7148,
      "step": 340
    },
    {
      "epoch": 0.0224,
      "grad_norm": 2.691812753677368,
      "learning_rate": 1.4892255173885215e-06,
      "loss": 0.6986,
      "step": 350
    },
    {
      "epoch": 0.02304,
      "grad_norm": 1.2819510698318481,
      "learning_rate": 1.531896735651803e-06,
      "loss": 0.7029,
      "step": 360
    },
    {
      "epoch": 0.02368,
      "grad_norm": 1.1647347211837769,
      "learning_rate": 1.5745679539150842e-06,
      "loss": 0.7108,
      "step": 370
    },
    {
      "epoch": 0.02432,
      "grad_norm": 0.9920722246170044,
      "learning_rate": 1.6172391721783658e-06,
      "loss": 0.706,
      "step": 380
    },
    {
      "epoch": 0.02496,
      "grad_norm": 1.785387396812439,
      "learning_rate": 1.6599103904416472e-06,
      "loss": 0.7048,
      "step": 390
    },
    {
      "epoch": 0.0256,
      "grad_norm": 1.7709925174713135,
      "learning_rate": 1.7025816087049288e-06,
      "loss": 0.7035,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 46875,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 200,
  "stateful_callbacks": {
    "EarlyStoppingCallback": {
      "args": {
        "early_stopping_patience": 3,
        "early_stopping_threshold": 0.0
      },
      "attributes": {
        "early_stopping_patience_counter": 0
      }
    },
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3366473064449280.0,
  "train_batch_size": 32,
  "trial_name": null,
  "trial_params": null
}