{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 8.556149732620321,
  "eval_steps": 400,
  "global_step": 400,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0213903743315508,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 1.8558,
      "step": 1
    },
    {
      "epoch": 0.21390374331550802,
      "grad_norm": 0.0,
      "learning_rate": 0.0,
      "loss": 2.0957,
      "step": 10
    },
    {
      "epoch": 0.42780748663101603,
      "grad_norm": 63.96761703491211,
      "learning_rate": 8e-08,
      "loss": 2.1274,
      "step": 20
    },
    {
      "epoch": 0.6417112299465241,
      "grad_norm": 56.0494270324707,
      "learning_rate": 4.4e-07,
      "loss": 2.0513,
      "step": 30
    },
    {
      "epoch": 0.8556149732620321,
      "grad_norm": 31.82117462158203,
      "learning_rate": 8.400000000000001e-07,
      "loss": 1.6275,
      "step": 40
    },
    {
      "epoch": 1.0695187165775402,
      "grad_norm": 27.546764373779297,
      "learning_rate": 1.2400000000000002e-06,
      "loss": 1.3922,
      "step": 50
    },
    {
      "epoch": 1.2834224598930482,
      "grad_norm": 27.145185470581055,
      "learning_rate": 1.6400000000000002e-06,
      "loss": 1.0424,
      "step": 60
    },
    {
      "epoch": 1.4973262032085561,
      "grad_norm": 33.02227020263672,
      "learning_rate": 2.04e-06,
      "loss": 1.0434,
      "step": 70
    },
    {
      "epoch": 1.7112299465240641,
      "grad_norm": 23.329740524291992,
      "learning_rate": 2.4400000000000004e-06,
      "loss": 1.0585,
      "step": 80
    },
    {
      "epoch": 1.9251336898395723,
      "grad_norm": 26.408071517944336,
      "learning_rate": 2.84e-06,
      "loss": 0.8849,
      "step": 90
    },
    {
      "epoch": 2.1390374331550803,
      "grad_norm": 17.790225982666016,
      "learning_rate": 3.2400000000000003e-06,
      "loss": 0.5427,
      "step": 100
    },
    {
      "epoch": 2.3529411764705883,
      "grad_norm": 29.846942901611328,
      "learning_rate": 3.6400000000000003e-06,
      "loss": 0.2784,
      "step": 110
    },
    {
      "epoch": 2.5668449197860963,
      "grad_norm": 20.77630043029785,
      "learning_rate": 4.04e-06,
      "loss": 0.2569,
      "step": 120
    },
    {
      "epoch": 2.7807486631016043,
      "grad_norm": 33.25271987915039,
      "learning_rate": 4.440000000000001e-06,
      "loss": 0.1836,
      "step": 130
    },
    {
      "epoch": 2.9946524064171123,
      "grad_norm": 66.23503875732422,
      "learning_rate": 4.84e-06,
      "loss": 0.3042,
      "step": 140
    },
    {
      "epoch": 3.2085561497326203,
      "grad_norm": 4.618898868560791,
      "learning_rate": 5.240000000000001e-06,
      "loss": 0.0455,
      "step": 150
    },
    {
      "epoch": 3.4224598930481283,
      "grad_norm": 5.856906890869141,
      "learning_rate": 5.64e-06,
      "loss": 0.0558,
      "step": 160
    },
    {
      "epoch": 3.6363636363636362,
      "grad_norm": 25.529407501220703,
      "learning_rate": 6.040000000000001e-06,
      "loss": 0.0835,
      "step": 170
    },
    {
      "epoch": 3.8502673796791442,
      "grad_norm": 16.971477508544922,
      "learning_rate": 6.440000000000001e-06,
      "loss": 0.1126,
      "step": 180
    },
    {
      "epoch": 4.064171122994653,
      "grad_norm": 9.28547191619873,
      "learning_rate": 6.8400000000000014e-06,
      "loss": 0.0838,
      "step": 190
    },
    {
      "epoch": 4.278074866310161,
      "grad_norm": 17.296798706054688,
      "learning_rate": 7.24e-06,
      "loss": 0.0518,
      "step": 200
    },
    {
      "epoch": 4.491978609625669,
      "grad_norm": 12.538177490234375,
      "learning_rate": 7.640000000000001e-06,
      "loss": 0.0532,
      "step": 210
    },
    {
      "epoch": 4.705882352941177,
      "grad_norm": 24.446659088134766,
      "learning_rate": 8.040000000000001e-06,
      "loss": 0.1583,
      "step": 220
    },
    {
      "epoch": 4.919786096256685,
      "grad_norm": 25.139781951904297,
      "learning_rate": 8.44e-06,
      "loss": 0.0894,
      "step": 230
    },
    {
      "epoch": 5.133689839572193,
      "grad_norm": 2.361607074737549,
      "learning_rate": 8.84e-06,
      "loss": 0.0531,
      "step": 240
    },
    {
      "epoch": 5.347593582887701,
      "grad_norm": 4.768627643585205,
      "learning_rate": 9.240000000000001e-06,
      "loss": 0.0664,
      "step": 250
    },
    {
      "epoch": 5.561497326203209,
      "grad_norm": 37.02785873413086,
      "learning_rate": 9.640000000000001e-06,
      "loss": 0.1502,
      "step": 260
    },
    {
      "epoch": 5.775401069518717,
      "grad_norm": 48.693763732910156,
      "learning_rate": 1e-05,
      "loss": 0.1953,
      "step": 270
    },
    {
      "epoch": 5.989304812834225,
      "grad_norm": 37.84030532836914,
      "learning_rate": 1e-05,
      "loss": 0.1806,
      "step": 280
    },
    {
      "epoch": 6.2032085561497325,
      "grad_norm": 39.74201965332031,
      "learning_rate": 1e-05,
      "loss": 0.0866,
      "step": 290
    },
    {
      "epoch": 6.4171122994652405,
      "grad_norm": 7.8511834144592285,
      "learning_rate": 1e-05,
      "loss": 0.0994,
      "step": 300
    },
    {
      "epoch": 6.6310160427807485,
      "grad_norm": 54.63271713256836,
      "learning_rate": 1e-05,
      "loss": 0.1712,
      "step": 310
    },
    {
      "epoch": 6.8449197860962565,
      "grad_norm": 44.596153259277344,
      "learning_rate": 1e-05,
      "loss": 0.1442,
      "step": 320
    },
    {
      "epoch": 7.0588235294117645,
      "grad_norm": 5.094964504241943,
      "learning_rate": 1e-05,
      "loss": 0.0526,
      "step": 330
    },
    {
      "epoch": 7.2727272727272725,
      "grad_norm": 12.109665870666504,
      "learning_rate": 1e-05,
      "loss": 0.03,
      "step": 340
    },
    {
      "epoch": 7.4866310160427805,
      "grad_norm": 34.3682975769043,
      "learning_rate": 1e-05,
      "loss": 0.0759,
      "step": 350
    },
    {
      "epoch": 7.7005347593582885,
      "grad_norm": 2.3397929668426514,
      "learning_rate": 1e-05,
      "loss": 0.0685,
      "step": 360
    },
    {
      "epoch": 7.9144385026737964,
      "grad_norm": 21.006542205810547,
      "learning_rate": 1e-05,
      "loss": 0.0637,
      "step": 370
    },
    {
      "epoch": 8.128342245989305,
      "grad_norm": 2.5418567657470703,
      "learning_rate": 1e-05,
      "loss": 0.057,
      "step": 380
    },
    {
      "epoch": 8.342245989304812,
      "grad_norm": 18.59604263305664,
      "learning_rate": 1e-05,
      "loss": 0.1096,
      "step": 390
    },
    {
      "epoch": 8.556149732620321,
      "grad_norm": 52.85743713378906,
      "learning_rate": 1e-05,
      "loss": 0.1422,
      "step": 400
    },
    {
      "epoch": 8.556149732620321,
      "eval_accuracy": 0.4,
      "eval_loss": 4.6875,
      "eval_runtime": 0.8724,
      "eval_samples_per_second": 11.462,
      "eval_steps_per_second": 1.146,
      "step": 400
    }
  ],
  "logging_steps": 10,
  "max_steps": 2500,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 55,
  "save_steps": 400,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 3.3017478812532736e+17,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}