{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.1,
  "eval_steps": 100,
  "global_step": 500,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.002,
      "grad_norm": 366.0,
      "learning_rate": 1.7999999999999997e-05,
      "loss": 3.335772705078125,
      "step": 10
    },
    {
      "epoch": 0.004,
      "grad_norm": 76.0,
      "learning_rate": 3.8e-05,
      "loss": 3.325016403198242,
      "step": 20
    },
    {
      "epoch": 0.006,
      "grad_norm": 426.0,
      "learning_rate": 5.7999999999999994e-05,
      "loss": 3.355701446533203,
      "step": 30
    },
    {
      "epoch": 0.008,
      "grad_norm": 194.0,
      "learning_rate": 7.8e-05,
      "loss": 3.3106155395507812,
      "step": 40
    },
    {
      "epoch": 0.01,
      "grad_norm": 712.0,
      "learning_rate": 9.799999999999998e-05,
      "loss": 3.270039367675781,
      "step": 50
    },
    {
      "epoch": 0.012,
      "grad_norm": 164.0,
      "learning_rate": 0.00011799999999999998,
      "loss": 3.2886486053466797,
      "step": 60
    },
    {
      "epoch": 0.014,
      "grad_norm": 162.0,
      "learning_rate": 0.000138,
      "loss": 3.2564620971679688,
      "step": 70
    },
    {
      "epoch": 0.016,
      "grad_norm": 234.0,
      "learning_rate": 0.00015799999999999996,
      "loss": 3.267023468017578,
      "step": 80
    },
    {
      "epoch": 0.018,
      "grad_norm": 1536.0,
      "learning_rate": 0.000178,
      "loss": 3.231563949584961,
      "step": 90
    },
    {
      "epoch": 0.02,
      "grad_norm": 39.5,
      "learning_rate": 0.000198,
      "loss": 3.2340599060058595,
      "step": 100
    },
    {
      "epoch": 0.02,
      "eval_loss": 3.491870403289795,
      "eval_runtime": 4.5004,
      "eval_samples_per_second": 66.216,
      "eval_steps_per_second": 3.777,
      "step": 100
    },
    {
      "epoch": 0.022,
      "grad_norm": 23.0,
      "learning_rate": 0.00021799999999999999,
      "loss": 3.20191650390625,
      "step": 110
    },
    {
      "epoch": 0.024,
      "grad_norm": 32.0,
      "learning_rate": 0.00023799999999999998,
      "loss": 3.2040287017822267,
      "step": 120
    },
    {
      "epoch": 0.026,
      "grad_norm": 136.0,
      "learning_rate": 0.000258,
      "loss": 3.1589597702026366,
      "step": 130
    },
    {
      "epoch": 0.028,
      "grad_norm": 238.0,
      "learning_rate": 0.000278,
      "loss": 3.150320625305176,
      "step": 140
    },
    {
      "epoch": 0.03,
      "grad_norm": 540.0,
      "learning_rate": 0.000298,
      "loss": 3.172740364074707,
      "step": 150
    },
    {
      "epoch": 0.032,
      "grad_norm": 58.0,
      "learning_rate": 0.0003,
      "loss": 3.149807167053223,
      "step": 160
    },
    {
      "epoch": 0.034,
      "grad_norm": 196.0,
      "learning_rate": 0.0003,
      "loss": 3.169495391845703,
      "step": 170
    },
    {
      "epoch": 0.036,
      "grad_norm": 444.0,
      "learning_rate": 0.0003,
      "loss": 3.1639734268188477,
      "step": 180
    },
    {
      "epoch": 0.038,
      "grad_norm": 378.0,
      "learning_rate": 0.0003,
      "loss": 3.221640777587891,
      "step": 190
    },
    {
      "epoch": 0.04,
      "grad_norm": 2272.0,
      "learning_rate": 0.0003,
      "loss": 3.1916147232055665,
      "step": 200
    },
    {
      "epoch": 0.04,
      "eval_loss": 3.4648807048797607,
      "eval_runtime": 4.3534,
      "eval_samples_per_second": 68.452,
      "eval_steps_per_second": 3.905,
      "step": 200
    },
    {
      "epoch": 0.042,
      "grad_norm": 520.0,
      "learning_rate": 0.0003,
      "loss": 3.1814949035644533,
      "step": 210
    },
    {
      "epoch": 0.044,
      "grad_norm": 87.0,
      "learning_rate": 0.0003,
      "loss": 3.1746402740478517,
      "step": 220
    },
    {
      "epoch": 0.046,
      "grad_norm": 39.0,
      "learning_rate": 0.0003,
      "loss": 3.172597885131836,
      "step": 230
    },
    {
      "epoch": 0.048,
      "grad_norm": 50.5,
      "learning_rate": 0.0003,
      "loss": 3.1576799392700194,
      "step": 240
    },
    {
      "epoch": 0.05,
      "grad_norm": 29.0,
      "learning_rate": 0.0003,
      "loss": 3.1418006896972654,
      "step": 250
    },
    {
      "epoch": 0.052,
      "grad_norm": 50.5,
      "learning_rate": 0.0003,
      "loss": 3.1035797119140627,
      "step": 260
    },
    {
      "epoch": 0.054,
      "grad_norm": 568.0,
      "learning_rate": 0.0003,
      "loss": 3.095198059082031,
      "step": 270
    },
    {
      "epoch": 0.056,
      "grad_norm": 15.5625,
      "learning_rate": 0.0003,
      "loss": 3.079079818725586,
      "step": 280
    },
    {
      "epoch": 0.058,
      "grad_norm": 17.625,
      "learning_rate": 0.0003,
      "loss": 3.060195732116699,
      "step": 290
    },
    {
      "epoch": 0.06,
      "grad_norm": 56.25,
      "learning_rate": 0.0003,
      "loss": 3.0736625671386717,
      "step": 300
    },
    {
      "epoch": 0.06,
      "eval_loss": 3.349555015563965,
      "eval_runtime": 4.3918,
      "eval_samples_per_second": 67.854,
      "eval_steps_per_second": 3.871,
      "step": 300
    },
    {
      "epoch": 0.062,
      "grad_norm": 432.0,
      "learning_rate": 0.0003,
      "loss": 3.0508825302124025,
      "step": 310
    },
    {
      "epoch": 0.064,
      "grad_norm": 6.28125,
      "learning_rate": 0.0003,
      "loss": 3.021405792236328,
      "step": 320
    },
    {
      "epoch": 0.066,
      "grad_norm": 161.0,
      "learning_rate": 0.0003,
      "loss": 3.011042022705078,
      "step": 330
    },
    {
      "epoch": 0.068,
      "grad_norm": 29.625,
      "learning_rate": 0.0003,
      "loss": 2.9988969802856444,
      "step": 340
    },
    {
      "epoch": 0.07,
      "grad_norm": 24.625,
      "learning_rate": 0.0003,
      "loss": 2.9939882278442385,
      "step": 350
    },
    {
      "epoch": 0.072,
      "grad_norm": 61.0,
      "learning_rate": 0.0003,
      "loss": 2.979990768432617,
      "step": 360
    },
    {
      "epoch": 0.074,
      "grad_norm": 13.6875,
      "learning_rate": 0.0003,
      "loss": 2.9845876693725586,
      "step": 370
    },
    {
      "epoch": 0.076,
      "grad_norm": 280.0,
      "learning_rate": 0.0003,
      "loss": 2.975000762939453,
      "step": 380
    },
    {
      "epoch": 0.078,
      "grad_norm": 21.125,
      "learning_rate": 0.0003,
      "loss": 2.958791732788086,
      "step": 390
    },
    {
      "epoch": 0.08,
      "grad_norm": 12.8125,
      "learning_rate": 0.0003,
      "loss": 2.956746482849121,
      "step": 400
    },
    {
      "epoch": 0.08,
      "eval_loss": 3.2549893856048584,
      "eval_runtime": 4.4045,
      "eval_samples_per_second": 67.658,
      "eval_steps_per_second": 3.86,
      "step": 400
    },
    {
      "epoch": 0.082,
      "grad_norm": 314.0,
      "learning_rate": 0.0003,
      "loss": 2.9515405654907227,
      "step": 410
    },
    {
      "epoch": 0.084,
      "grad_norm": 2.125,
      "learning_rate": 0.0003,
      "loss": 2.910631561279297,
      "step": 420
    },
    {
      "epoch": 0.086,
      "grad_norm": 24.75,
      "learning_rate": 0.0003,
      "loss": 2.8589399337768553,
      "step": 430
    },
    {
      "epoch": 0.088,
      "grad_norm": 3.78125,
      "learning_rate": 0.0003,
      "loss": 2.844576835632324,
      "step": 440
    },
    {
      "epoch": 0.09,
      "grad_norm": 1.6171875,
      "learning_rate": 0.0003,
      "loss": 2.7850717544555663,
      "step": 450
    },
    {
      "epoch": 0.092,
      "grad_norm": 6.5625,
      "learning_rate": 0.0003,
      "loss": 2.7605606079101563,
      "step": 460
    },
    {
      "epoch": 0.094,
      "grad_norm": 12.5625,
      "learning_rate": 0.0003,
      "loss": 2.747697639465332,
      "step": 470
    },
    {
      "epoch": 0.096,
      "grad_norm": 0.7734375,
      "learning_rate": 0.0003,
      "loss": 2.7024419784545897,
      "step": 480
    },
    {
      "epoch": 0.098,
      "grad_norm": 0.55078125,
      "learning_rate": 0.0003,
      "loss": 2.727059173583984,
      "step": 490
    },
    {
      "epoch": 0.1,
      "grad_norm": 1.3046875,
      "learning_rate": 0.0003,
      "loss": 2.688610076904297,
      "step": 500
    },
    {
      "epoch": 0.1,
      "eval_loss": 3.0536108016967773,
      "eval_runtime": 4.4183,
      "eval_samples_per_second": 67.447,
      "eval_steps_per_second": 3.848,
      "step": 500
    }
  ],
  "logging_steps": 10,
  "max_steps": 5000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 500,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 1.63077257428992e+17,
  "train_batch_size": 18,
  "trial_name": null,
  "trial_params": null
}