{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.9918458117123796,
  "eval_steps": 500,
  "global_step": 504,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.05930318754633061,
      "grad_norm": 1.3802219854574984,
      "learning_rate": 5e-06,
      "loss": 0.7739,
      "step": 10
    },
    {
      "epoch": 0.11860637509266123,
      "grad_norm": 2.733409062302713,
      "learning_rate": 5e-06,
      "loss": 0.7072,
      "step": 20
    },
    {
      "epoch": 0.17790956263899185,
      "grad_norm": 1.3622548058844581,
      "learning_rate": 5e-06,
      "loss": 0.6883,
      "step": 30
    },
    {
      "epoch": 0.23721275018532245,
      "grad_norm": 2.1397210299903042,
      "learning_rate": 5e-06,
      "loss": 0.6653,
      "step": 40
    },
    {
      "epoch": 0.2965159377316531,
      "grad_norm": 1.1868267718380074,
      "learning_rate": 5e-06,
      "loss": 0.6578,
      "step": 50
    },
    {
      "epoch": 0.3558191252779837,
      "grad_norm": 0.768661599042398,
      "learning_rate": 5e-06,
      "loss": 0.6434,
      "step": 60
    },
    {
      "epoch": 0.41512231282431433,
      "grad_norm": 0.929517541921154,
      "learning_rate": 5e-06,
      "loss": 0.6412,
      "step": 70
    },
    {
      "epoch": 0.4744255003706449,
      "grad_norm": 1.0083217759359295,
      "learning_rate": 5e-06,
      "loss": 0.6305,
      "step": 80
    },
    {
      "epoch": 0.5337286879169756,
      "grad_norm": 0.7019920027719391,
      "learning_rate": 5e-06,
      "loss": 0.625,
      "step": 90
    },
    {
      "epoch": 0.5930318754633062,
      "grad_norm": 0.8179786383641104,
      "learning_rate": 5e-06,
      "loss": 0.6186,
      "step": 100
    },
    {
      "epoch": 0.6523350630096367,
      "grad_norm": 1.505043114613733,
      "learning_rate": 5e-06,
      "loss": 0.6109,
      "step": 110
    },
    {
      "epoch": 0.7116382505559674,
      "grad_norm": 0.652990528799698,
      "learning_rate": 5e-06,
      "loss": 0.6174,
      "step": 120
    },
    {
      "epoch": 0.770941438102298,
      "grad_norm": 0.8738270604177748,
      "learning_rate": 5e-06,
      "loss": 0.6099,
      "step": 130
    },
    {
      "epoch": 0.8302446256486287,
      "grad_norm": 0.7482311809054135,
      "learning_rate": 5e-06,
      "loss": 0.6152,
      "step": 140
    },
    {
      "epoch": 0.8895478131949592,
      "grad_norm": 0.5898841945150782,
      "learning_rate": 5e-06,
      "loss": 0.604,
      "step": 150
    },
    {
      "epoch": 0.9488510007412898,
      "grad_norm": 0.5509255300448996,
      "learning_rate": 5e-06,
      "loss": 0.6088,
      "step": 160
    },
    {
      "epoch": 0.9962935507783544,
      "eval_loss": 0.6123025417327881,
      "eval_runtime": 177.7519,
      "eval_samples_per_second": 25.558,
      "eval_steps_per_second": 0.399,
      "step": 168
    },
    {
      "epoch": 1.0096367679762788,
      "grad_norm": 0.5962998315100678,
      "learning_rate": 5e-06,
      "loss": 0.6323,
      "step": 170
    },
    {
      "epoch": 1.0689399555226093,
      "grad_norm": 0.6401517658215825,
      "learning_rate": 5e-06,
      "loss": 0.5587,
      "step": 180
    },
    {
      "epoch": 1.12824314306894,
      "grad_norm": 0.5789193360471795,
      "learning_rate": 5e-06,
      "loss": 0.5532,
      "step": 190
    },
    {
      "epoch": 1.1875463306152705,
      "grad_norm": 0.5007418392739746,
      "learning_rate": 5e-06,
      "loss": 0.5449,
      "step": 200
    },
    {
      "epoch": 1.2468495181616013,
      "grad_norm": 0.742099379670997,
      "learning_rate": 5e-06,
      "loss": 0.5506,
      "step": 210
    },
    {
      "epoch": 1.3061527057079318,
      "grad_norm": 0.6357145205835705,
      "learning_rate": 5e-06,
      "loss": 0.5518,
      "step": 220
    },
    {
      "epoch": 1.3654558932542624,
      "grad_norm": 0.4706954425299361,
      "learning_rate": 5e-06,
      "loss": 0.543,
      "step": 230
    },
    {
      "epoch": 1.424759080800593,
      "grad_norm": 0.6430769844169726,
      "learning_rate": 5e-06,
      "loss": 0.5563,
      "step": 240
    },
    {
      "epoch": 1.4840622683469236,
      "grad_norm": 0.714837022060758,
      "learning_rate": 5e-06,
      "loss": 0.5517,
      "step": 250
    },
    {
      "epoch": 1.5433654558932544,
      "grad_norm": 0.5623788095234329,
      "learning_rate": 5e-06,
      "loss": 0.5512,
      "step": 260
    },
    {
      "epoch": 1.602668643439585,
      "grad_norm": 0.5481074950687667,
      "learning_rate": 5e-06,
      "loss": 0.55,
      "step": 270
    },
    {
      "epoch": 1.6619718309859155,
      "grad_norm": 0.5539378521915824,
      "learning_rate": 5e-06,
      "loss": 0.5472,
      "step": 280
    },
    {
      "epoch": 1.721275018532246,
      "grad_norm": 0.8039356878348214,
      "learning_rate": 5e-06,
      "loss": 0.5451,
      "step": 290
    },
    {
      "epoch": 1.7805782060785766,
      "grad_norm": 0.7791331104006716,
      "learning_rate": 5e-06,
      "loss": 0.5477,
      "step": 300
    },
    {
      "epoch": 1.8398813936249074,
      "grad_norm": 0.6989192286392514,
      "learning_rate": 5e-06,
      "loss": 0.5558,
      "step": 310
    },
    {
      "epoch": 1.899184581171238,
      "grad_norm": 0.5069580060902782,
      "learning_rate": 5e-06,
      "loss": 0.5533,
      "step": 320
    },
    {
      "epoch": 1.9584877687175686,
      "grad_norm": 0.5741926432541444,
      "learning_rate": 5e-06,
      "loss": 0.5487,
      "step": 330
    },
    {
      "epoch": 1.9940696812453669,
      "eval_loss": 0.6003267765045166,
      "eval_runtime": 177.8259,
      "eval_samples_per_second": 25.547,
      "eval_steps_per_second": 0.399,
      "step": 336
    },
    {
      "epoch": 2.0192735359525575,
      "grad_norm": 0.9927432888051317,
      "learning_rate": 5e-06,
      "loss": 0.564,
      "step": 340
    },
    {
      "epoch": 2.078576723498888,
      "grad_norm": 0.7990001146652178,
      "learning_rate": 5e-06,
      "loss": 0.4911,
      "step": 350
    },
    {
      "epoch": 2.1378799110452187,
      "grad_norm": 0.556438381270437,
      "learning_rate": 5e-06,
      "loss": 0.4883,
      "step": 360
    },
    {
      "epoch": 2.1971830985915495,
      "grad_norm": 0.6135178834215755,
      "learning_rate": 5e-06,
      "loss": 0.488,
      "step": 370
    },
    {
      "epoch": 2.25648628613788,
      "grad_norm": 0.5081260960389352,
      "learning_rate": 5e-06,
      "loss": 0.493,
      "step": 380
    },
    {
      "epoch": 2.3157894736842106,
      "grad_norm": 0.68213842322186,
      "learning_rate": 5e-06,
      "loss": 0.4814,
      "step": 390
    },
    {
      "epoch": 2.375092661230541,
      "grad_norm": 0.5560842165539166,
      "learning_rate": 5e-06,
      "loss": 0.4947,
      "step": 400
    },
    {
      "epoch": 2.4343958487768718,
      "grad_norm": 0.561149355084152,
      "learning_rate": 5e-06,
      "loss": 0.4916,
      "step": 410
    },
    {
      "epoch": 2.4936990363232026,
      "grad_norm": 0.534652055102195,
      "learning_rate": 5e-06,
      "loss": 0.4956,
      "step": 420
    },
    {
      "epoch": 2.553002223869533,
      "grad_norm": 0.5766622241099675,
      "learning_rate": 5e-06,
      "loss": 0.494,
      "step": 430
    },
    {
      "epoch": 2.6123054114158637,
      "grad_norm": 0.5664640432180077,
      "learning_rate": 5e-06,
      "loss": 0.4973,
      "step": 440
    },
    {
      "epoch": 2.6716085989621945,
      "grad_norm": 0.5141442287518144,
      "learning_rate": 5e-06,
      "loss": 0.4998,
      "step": 450
    },
    {
      "epoch": 2.730911786508525,
      "grad_norm": 0.622575399798233,
      "learning_rate": 5e-06,
      "loss": 0.4891,
      "step": 460
    },
    {
      "epoch": 2.790214974054855,
      "grad_norm": 0.6328620684014972,
      "learning_rate": 5e-06,
      "loss": 0.5005,
      "step": 470
    },
    {
      "epoch": 2.849518161601186,
      "grad_norm": 0.5410072349219146,
      "learning_rate": 5e-06,
      "loss": 0.4894,
      "step": 480
    },
    {
      "epoch": 2.9088213491475168,
      "grad_norm": 0.6725625016553842,
      "learning_rate": 5e-06,
      "loss": 0.4939,
      "step": 490
    },
    {
      "epoch": 2.968124536693847,
      "grad_norm": 0.6468049088847707,
      "learning_rate": 5e-06,
      "loss": 0.497,
      "step": 500
    },
    {
      "epoch": 2.9918458117123796,
      "eval_loss": 0.6024672985076904,
      "eval_runtime": 178.6347,
      "eval_samples_per_second": 25.432,
      "eval_steps_per_second": 0.397,
      "step": 504
    },
    {
      "epoch": 2.9918458117123796,
      "step": 504,
      "total_flos": 844009392046080.0,
      "train_loss": 0.5635922295706612,
      "train_runtime": 29809.8263,
      "train_samples_per_second": 8.685,
      "train_steps_per_second": 0.017
    }
  ],
  "logging_steps": 10,
  "max_steps": 504,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 3,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 844009392046080.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}