{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.9280742459396751,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02320185614849188,
      "grad_norm": 26.745355095184312,
      "learning_rate": 5e-07,
      "loss": 1.6569,
      "step": 5
    },
    {
      "epoch": 0.04640371229698376,
      "grad_norm": 13.080188660738868,
      "learning_rate": 1e-06,
      "loss": 1.5099,
      "step": 10
    },
    {
      "epoch": 0.06960556844547564,
      "grad_norm": 7.775505635686351,
      "learning_rate": 9.998470286265414e-07,
      "loss": 1.2782,
      "step": 15
    },
    {
      "epoch": 0.09280742459396751,
      "grad_norm": 6.492859712313467,
      "learning_rate": 9.993882081071305e-07,
      "loss": 1.2359,
      "step": 20
    },
    {
      "epoch": 0.11600928074245939,
      "grad_norm": 5.355551984540261,
      "learning_rate": 9.986238191873872e-07,
      "loss": 1.204,
      "step": 25
    },
    {
      "epoch": 0.13921113689095127,
      "grad_norm": 5.125393165293572,
      "learning_rate": 9.975543295858033e-07,
      "loss": 1.1627,
      "step": 30
    },
    {
      "epoch": 0.16241299303944315,
      "grad_norm": 4.710071299991241,
      "learning_rate": 9.961803937075514e-07,
      "loss": 1.1463,
      "step": 35
    },
    {
      "epoch": 0.18561484918793503,
      "grad_norm": 5.029376799191572,
      "learning_rate": 9.945028522440653e-07,
      "loss": 1.1394,
      "step": 40
    },
    {
      "epoch": 0.2088167053364269,
      "grad_norm": 4.763291242870039,
      "learning_rate": 9.925227316586314e-07,
      "loss": 1.1371,
      "step": 45
    },
    {
      "epoch": 0.23201856148491878,
      "grad_norm": 4.903033982523367,
      "learning_rate": 9.902412435583125e-07,
      "loss": 1.1181,
      "step": 50
    },
    {
      "epoch": 0.23201856148491878,
      "eval_loss": 1.1214605569839478,
      "eval_runtime": 105.8329,
      "eval_samples_per_second": 57.912,
      "eval_steps_per_second": 0.907,
      "step": 50
    },
    {
      "epoch": 0.2552204176334107,
      "grad_norm": 4.785575700738186,
      "learning_rate": 9.876597839525813e-07,
      "loss": 1.1163,
      "step": 55
    },
    {
      "epoch": 0.27842227378190254,
      "grad_norm": 4.600727000401806,
      "learning_rate": 9.847799323991233e-07,
      "loss": 1.1232,
      "step": 60
    },
    {
      "epoch": 0.30162412993039445,
      "grad_norm": 4.8200416840356315,
      "learning_rate": 9.816034510373285e-07,
      "loss": 1.125,
      "step": 65
    },
    {
      "epoch": 0.3248259860788863,
      "grad_norm": 4.958997518359378,
      "learning_rate": 9.781322835100637e-07,
      "loss": 1.108,
      "step": 70
    },
    {
      "epoch": 0.3480278422273782,
      "grad_norm": 4.883541365508776,
      "learning_rate": 9.743685537743856e-07,
      "loss": 1.106,
      "step": 75
    },
    {
      "epoch": 0.37122969837587005,
      "grad_norm": 4.973507458353338,
      "learning_rate": 9.70314564801922e-07,
      "loss": 1.0973,
      "step": 80
    },
    {
      "epoch": 0.39443155452436196,
      "grad_norm": 4.704415990191669,
      "learning_rate": 9.659727971697173e-07,
      "loss": 1.0964,
      "step": 85
    },
    {
      "epoch": 0.4176334106728538,
      "grad_norm": 4.759885977268913,
      "learning_rate": 9.613459075424033e-07,
      "loss": 1.0956,
      "step": 90
    },
    {
      "epoch": 0.4408352668213457,
      "grad_norm": 4.868535908803129,
      "learning_rate": 9.564367270466245e-07,
      "loss": 1.0787,
      "step": 95
    },
    {
      "epoch": 0.46403712296983757,
      "grad_norm": 5.180286116736628,
      "learning_rate": 9.51248259538713e-07,
      "loss": 1.0765,
      "step": 100
    },
    {
      "epoch": 0.46403712296983757,
      "eval_loss": 1.0775035619735718,
      "eval_runtime": 105.5293,
      "eval_samples_per_second": 58.079,
      "eval_steps_per_second": 0.91,
      "step": 100
    },
    {
      "epoch": 0.4872389791183295,
      "grad_norm": 5.290465762761348,
      "learning_rate": 9.457836797666721e-07,
      "loss": 1.0903,
      "step": 105
    },
    {
      "epoch": 0.5104408352668214,
      "grad_norm": 4.81291157554945,
      "learning_rate": 9.400463314275941e-07,
      "loss": 1.0697,
      "step": 110
    },
    {
      "epoch": 0.5336426914153132,
      "grad_norm": 4.914554202012043,
      "learning_rate": 9.340397251217008e-07,
      "loss": 1.0668,
      "step": 115
    },
    {
      "epoch": 0.5568445475638051,
      "grad_norm": 5.240457841494325,
      "learning_rate": 9.27767536204258e-07,
      "loss": 1.0676,
      "step": 120
    },
    {
      "epoch": 0.580046403712297,
      "grad_norm": 4.957459385263701,
      "learning_rate": 9.212336025366787e-07,
      "loss": 1.0746,
      "step": 125
    },
    {
      "epoch": 0.6032482598607889,
      "grad_norm": 5.29032668711839,
      "learning_rate": 9.144419221381918e-07,
      "loss": 1.0724,
      "step": 130
    },
    {
      "epoch": 0.6264501160092807,
      "grad_norm": 4.908560953587426,
      "learning_rate": 9.073966507395121e-07,
      "loss": 1.0745,
      "step": 135
    },
    {
      "epoch": 0.6496519721577726,
      "grad_norm": 4.912842113728852,
      "learning_rate": 9.001020992400085e-07,
      "loss": 1.0559,
      "step": 140
    },
    {
      "epoch": 0.6728538283062645,
      "grad_norm": 5.088585906783296,
      "learning_rate": 8.925627310699274e-07,
      "loss": 1.0705,
      "step": 145
    },
    {
      "epoch": 0.6960556844547564,
      "grad_norm": 5.140684832177941,
      "learning_rate": 8.84783159459285e-07,
      "loss": 1.0639,
      "step": 150
    },
    {
      "epoch": 0.6960556844547564,
      "eval_loss": 1.0501643419265747,
      "eval_runtime": 105.4561,
      "eval_samples_per_second": 58.119,
      "eval_steps_per_second": 0.91,
      "step": 150
    },
    {
      "epoch": 0.7192575406032483,
      "grad_norm": 5.311257433234373,
      "learning_rate": 8.767681446150976e-07,
      "loss": 1.0472,
      "step": 155
    },
    {
      "epoch": 0.7424593967517401,
      "grad_norm": 5.091539509688025,
      "learning_rate": 8.68522590808682e-07,
      "loss": 1.0645,
      "step": 160
    },
    {
      "epoch": 0.765661252900232,
      "grad_norm": 5.132013982763288,
      "learning_rate": 8.600515433748001e-07,
      "loss": 1.0416,
      "step": 165
    },
    {
      "epoch": 0.7888631090487239,
      "grad_norm": 4.753354098230195,
      "learning_rate": 8.51360185624495e-07,
      "loss": 1.0478,
      "step": 170
    },
    {
      "epoch": 0.8120649651972158,
      "grad_norm": 5.029473978539478,
      "learning_rate": 8.424538356734956e-07,
      "loss": 1.0383,
      "step": 175
    },
    {
      "epoch": 0.8352668213457076,
      "grad_norm": 4.9588553004593345,
      "learning_rate": 8.333379431881397e-07,
      "loss": 1.0342,
      "step": 180
    },
    {
      "epoch": 0.8584686774941995,
      "grad_norm": 5.234591483099779,
      "learning_rate": 8.240180860508026e-07,
      "loss": 1.0413,
      "step": 185
    },
    {
      "epoch": 0.8816705336426914,
      "grad_norm": 5.121566469508508,
      "learning_rate": 8.144999669468713e-07,
      "loss": 1.0264,
      "step": 190
    },
    {
      "epoch": 0.9048723897911833,
      "grad_norm": 5.0479045768726305,
      "learning_rate": 8.047894098753539e-07,
      "loss": 1.028,
      "step": 195
    },
    {
      "epoch": 0.9280742459396751,
      "grad_norm": 5.0838098259091185,
      "learning_rate": 7.948923565852597e-07,
      "loss": 1.0308,
      "step": 200
    },
    {
      "epoch": 0.9280742459396751,
      "eval_loss": 1.0281875133514404,
      "eval_runtime": 105.8568,
      "eval_samples_per_second": 57.899,
      "eval_steps_per_second": 0.907,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 645,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 100,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1179056703799296.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}