{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.984709480122324,
  "eval_steps": 500,
  "global_step": 366,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.08154943934760449,
      "grad_norm": 0.9675019979476929,
      "learning_rate": 2.702702702702703e-05,
      "loss": 0.3194,
      "step": 10
    },
    {
      "epoch": 0.16309887869520898,
      "grad_norm": 0.8973706364631653,
      "learning_rate": 5.405405405405406e-05,
      "loss": 0.2554,
      "step": 20
    },
    {
      "epoch": 0.24464831804281345,
      "grad_norm": 1.1754801273345947,
      "learning_rate": 8.108108108108109e-05,
      "loss": 0.268,
      "step": 30
    },
    {
      "epoch": 0.32619775739041795,
      "grad_norm": 0.7706596255302429,
      "learning_rate": 9.997948550797227e-05,
      "loss": 0.2453,
      "step": 40
    },
    {
      "epoch": 0.4077471967380224,
      "grad_norm": 0.9513430595397949,
      "learning_rate": 9.961525153583327e-05,
      "loss": 0.2863,
      "step": 50
    },
    {
      "epoch": 0.4892966360856269,
      "grad_norm": 1.0345094203948975,
      "learning_rate": 9.879896064123961e-05,
      "loss": 0.2919,
      "step": 60
    },
    {
      "epoch": 0.5708460754332314,
      "grad_norm": 0.8420723676681519,
      "learning_rate": 9.753805025397779e-05,
      "loss": 0.2996,
      "step": 70
    },
    {
      "epoch": 0.6523955147808359,
      "grad_norm": 0.6143088936805725,
      "learning_rate": 9.584400884284545e-05,
      "loss": 0.2602,
      "step": 80
    },
    {
      "epoch": 0.7339449541284404,
      "grad_norm": 0.9206684231758118,
      "learning_rate": 9.373227124134888e-05,
      "loss": 0.2537,
      "step": 90
    },
    {
      "epoch": 0.8154943934760448,
      "grad_norm": 0.9815739393234253,
      "learning_rate": 9.122207801708802e-05,
      "loss": 0.2704,
      "step": 100
    },
    {
      "epoch": 0.8970438328236493,
      "grad_norm": 0.6698834896087646,
      "learning_rate": 8.833630016614976e-05,
      "loss": 0.2736,
      "step": 110
    },
    {
      "epoch": 0.9785932721712538,
      "grad_norm": 0.8576629161834717,
      "learning_rate": 8.510123072976239e-05,
      "loss": 0.2774,
      "step": 120
    },
    {
      "epoch": 1.0601427115188584,
      "grad_norm": 0.5907473564147949,
      "learning_rate": 8.154634523184388e-05,
      "loss": 0.245,
      "step": 130
    },
    {
      "epoch": 1.1416921508664628,
      "grad_norm": 0.9188482761383057,
      "learning_rate": 7.770403312015721e-05,
      "loss": 0.2726,
      "step": 140
    },
    {
      "epoch": 1.2232415902140672,
      "grad_norm": 0.6934948563575745,
      "learning_rate": 7.360930265797935e-05,
      "loss": 0.196,
      "step": 150
    },
    {
      "epoch": 1.3047910295616718,
      "grad_norm": 0.6566444635391235,
      "learning_rate": 6.929946195508932e-05,
      "loss": 0.2178,
      "step": 160
    },
    {
      "epoch": 1.3863404689092762,
      "grad_norm": 0.7326809167861938,
      "learning_rate": 6.481377904428171e-05,
      "loss": 0.1964,
      "step": 170
    },
    {
      "epoch": 1.4678899082568808,
      "grad_norm": 0.6168932914733887,
      "learning_rate": 6.019312410053286e-05,
      "loss": 0.1984,
      "step": 180
    },
    {
      "epoch": 1.5494393476044852,
      "grad_norm": 1.0814765691757202,
      "learning_rate": 5.547959706265068e-05,
      "loss": 0.2158,
      "step": 190
    },
    {
      "epoch": 1.6309887869520896,
      "grad_norm": 0.892710268497467,
      "learning_rate": 5.0716144050239375e-05,
      "loss": 0.1935,
      "step": 200
    },
    {
      "epoch": 1.7125382262996942,
      "grad_norm": 0.5259914398193359,
      "learning_rate": 4.594616607090028e-05,
      "loss": 0.217,
      "step": 210
    },
    {
      "epoch": 1.7940876656472988,
      "grad_norm": 0.8986033797264099,
      "learning_rate": 4.121312358283463e-05,
      "loss": 0.1994,
      "step": 220
    },
    {
      "epoch": 1.8756371049949032,
      "grad_norm": 0.8425778746604919,
      "learning_rate": 3.656014051577713e-05,
      "loss": 0.2021,
      "step": 230
    },
    {
      "epoch": 1.9571865443425076,
      "grad_norm": 0.7094092965126038,
      "learning_rate": 3.202961135812437e-05,
      "loss": 0.201,
      "step": 240
    },
    {
      "epoch": 2.038735983690112,
      "grad_norm": 0.6760769486427307,
      "learning_rate": 2.7662814890184818e-05,
      "loss": 0.1843,
      "step": 250
    },
    {
      "epoch": 2.120285423037717,
      "grad_norm": 0.7410211563110352,
      "learning_rate": 2.3499538082923606e-05,
      "loss": 0.1573,
      "step": 260
    },
    {
      "epoch": 2.2018348623853212,
      "grad_norm": 0.8644802570343018,
      "learning_rate": 1.9577713588953795e-05,
      "loss": 0.1533,
      "step": 270
    },
    {
      "epoch": 2.2833843017329256,
      "grad_norm": 0.8199602365493774,
      "learning_rate": 1.5933074128684332e-05,
      "loss": 0.1864,
      "step": 280
    },
    {
      "epoch": 2.36493374108053,
      "grad_norm": 0.832036018371582,
      "learning_rate": 1.2598826920598772e-05,
      "loss": 0.1508,
      "step": 290
    },
    {
      "epoch": 2.4464831804281344,
      "grad_norm": 0.7652586102485657,
      "learning_rate": 9.605351122011309e-06,
      "loss": 0.1421,
      "step": 300
    },
    {
      "epoch": 2.528032619775739,
      "grad_norm": 0.7681753635406494,
      "learning_rate": 6.979921036993042e-06,
      "loss": 0.1749,
      "step": 310
    },
    {
      "epoch": 2.6095820591233436,
      "grad_norm": 1.117201566696167,
      "learning_rate": 4.746457613389904e-06,
      "loss": 0.1707,
      "step": 320
    },
    {
      "epoch": 2.691131498470948,
      "grad_norm": 0.7108331918716431,
      "learning_rate": 2.925310493105099e-06,
      "loss": 0.1529,
      "step": 330
    },
    {
      "epoch": 2.7726809378185524,
      "grad_norm": 0.7729602456092834,
      "learning_rate": 1.5330726014397668e-06,
      "loss": 0.1463,
      "step": 340
    },
    {
      "epoch": 2.8542303771661572,
      "grad_norm": 0.8554747104644775,
      "learning_rate": 5.824289648152126e-07,
      "loss": 0.1573,
      "step": 350
    },
    {
      "epoch": 2.9357798165137616,
      "grad_norm": 0.96407550573349,
      "learning_rate": 8.204113433559201e-08,
      "loss": 0.1395,
      "step": 360
    },
    {
      "epoch": 2.984709480122324,
      "step": 366,
      "total_flos": 7989808469360640.0,
      "train_loss": 0.21511392222076167,
      "train_runtime": 5218.8385,
      "train_samples_per_second": 0.564,
      "train_steps_per_second": 0.07
    }
  ],
  "logging_steps": 10,
  "max_steps": 366,
  "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": 7989808469360640.0,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}