{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.2,
  "eval_steps": 50,
  "global_step": 200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.005,
      "grad_norm": 1.859375,
      "learning_rate": 7.999999999999999e-05,
      "loss": 2.9596134185791017,
      "step": 5
    },
    {
      "epoch": 0.01,
      "grad_norm": 2.375,
      "learning_rate": 0.00017999999999999998,
      "loss": 3.0003786087036133,
      "step": 10
    },
    {
      "epoch": 0.015,
      "grad_norm": 14.75,
      "learning_rate": 0.00028,
      "loss": 2.946580696105957,
      "step": 15
    },
    {
      "epoch": 0.02,
      "grad_norm": 1.2421875,
      "learning_rate": 0.0003,
      "loss": 2.9287084579467773,
      "step": 20
    },
    {
      "epoch": 0.025,
      "grad_norm": 3.296875,
      "learning_rate": 0.0003,
      "loss": 2.8551090240478514,
      "step": 25
    },
    {
      "epoch": 0.03,
      "grad_norm": 1.5546875,
      "learning_rate": 0.0003,
      "loss": 2.8845558166503906,
      "step": 30
    },
    {
      "epoch": 0.035,
      "grad_norm": 1.03125,
      "learning_rate": 0.0003,
      "loss": 2.8326595306396483,
      "step": 35
    },
    {
      "epoch": 0.04,
      "grad_norm": 5.03125,
      "learning_rate": 0.0003,
      "loss": 2.844678497314453,
      "step": 40
    },
    {
      "epoch": 0.045,
      "grad_norm": 2.046875,
      "learning_rate": 0.0003,
      "loss": 2.828007125854492,
      "step": 45
    },
    {
      "epoch": 0.05,
      "grad_norm": 9.25,
      "learning_rate": 0.0003,
      "loss": 2.8197803497314453,
      "step": 50
    },
    {
      "epoch": 0.05,
      "eval_loss": 3.1455771923065186,
      "eval_runtime": 6.8102,
      "eval_samples_per_second": 5.433,
      "eval_steps_per_second": 2.79,
      "step": 50
    },
    {
      "epoch": 0.055,
      "grad_norm": 1.6171875,
      "learning_rate": 0.0003,
      "loss": 2.797296714782715,
      "step": 55
    },
    {
      "epoch": 0.06,
      "grad_norm": 1.90625,
      "learning_rate": 0.0003,
      "loss": 2.7909267425537108,
      "step": 60
    },
    {
      "epoch": 0.065,
      "grad_norm": 0.66796875,
      "learning_rate": 0.0003,
      "loss": 2.7826940536499025,
      "step": 65
    },
    {
      "epoch": 0.07,
      "grad_norm": 1.1640625,
      "learning_rate": 0.0003,
      "loss": 2.8065961837768554,
      "step": 70
    },
    {
      "epoch": 0.075,
      "grad_norm": 0.61328125,
      "learning_rate": 0.0003,
      "loss": 2.8089221954345702,
      "step": 75
    },
    {
      "epoch": 0.08,
      "grad_norm": 2.21875,
      "learning_rate": 0.0003,
      "loss": 2.7947248458862304,
      "step": 80
    },
    {
      "epoch": 0.085,
      "grad_norm": 0.7890625,
      "learning_rate": 0.0003,
      "loss": 2.7826770782470702,
      "step": 85
    },
    {
      "epoch": 0.09,
      "grad_norm": 26.5,
      "learning_rate": 0.0003,
      "loss": 2.7801084518432617,
      "step": 90
    },
    {
      "epoch": 0.095,
      "grad_norm": 1.2734375,
      "learning_rate": 0.0003,
      "loss": 2.748321533203125,
      "step": 95
    },
    {
      "epoch": 0.1,
      "grad_norm": 0.341796875,
      "learning_rate": 0.0003,
      "loss": 2.7878595352172852,
      "step": 100
    },
    {
      "epoch": 0.1,
      "eval_loss": 3.1193559169769287,
      "eval_runtime": 6.6531,
      "eval_samples_per_second": 5.561,
      "eval_steps_per_second": 2.856,
      "step": 100
    },
    {
      "epoch": 0.105,
      "grad_norm": 1.078125,
      "learning_rate": 0.0003,
      "loss": 2.785268211364746,
      "step": 105
    },
    {
      "epoch": 0.11,
      "grad_norm": 0.890625,
      "learning_rate": 0.0003,
      "loss": 2.725397491455078,
      "step": 110
    },
    {
      "epoch": 0.115,
      "grad_norm": 2.84375,
      "learning_rate": 0.0003,
      "loss": 2.7376623153686523,
      "step": 115
    },
    {
      "epoch": 0.12,
      "grad_norm": 2.421875,
      "learning_rate": 0.0003,
      "loss": 2.758837127685547,
      "step": 120
    },
    {
      "epoch": 0.125,
      "grad_norm": 1.828125,
      "learning_rate": 0.0003,
      "loss": 2.768202018737793,
      "step": 125
    },
    {
      "epoch": 0.13,
      "grad_norm": 0.3515625,
      "learning_rate": 0.0003,
      "loss": 2.7715227127075197,
      "step": 130
    },
    {
      "epoch": 0.135,
      "grad_norm": 0.5,
      "learning_rate": 0.0003,
      "loss": 2.7676155090332033,
      "step": 135
    },
    {
      "epoch": 0.14,
      "grad_norm": 0.83203125,
      "learning_rate": 0.0003,
      "loss": 2.739817428588867,
      "step": 140
    },
    {
      "epoch": 0.145,
      "grad_norm": 0.66796875,
      "learning_rate": 0.0003,
      "loss": 2.740823745727539,
      "step": 145
    },
    {
      "epoch": 0.15,
      "grad_norm": 12.5,
      "learning_rate": 0.0003,
      "loss": 2.754258728027344,
      "step": 150
    },
    {
      "epoch": 0.15,
      "eval_loss": 3.1168980598449707,
      "eval_runtime": 6.6806,
      "eval_samples_per_second": 5.538,
      "eval_steps_per_second": 2.844,
      "step": 150
    },
    {
      "epoch": 0.155,
      "grad_norm": 2.359375,
      "learning_rate": 0.0003,
      "loss": 2.713482475280762,
      "step": 155
    },
    {
      "epoch": 0.16,
      "grad_norm": 2.265625,
      "learning_rate": 0.0003,
      "loss": 2.7810474395751954,
      "step": 160
    },
    {
      "epoch": 0.165,
      "grad_norm": 0.5625,
      "learning_rate": 0.0003,
      "loss": 2.758929443359375,
      "step": 165
    },
    {
      "epoch": 0.17,
      "grad_norm": 1.6015625,
      "learning_rate": 0.0003,
      "loss": 2.7030134201049805,
      "step": 170
    },
    {
      "epoch": 0.175,
      "grad_norm": 0.74609375,
      "learning_rate": 0.0003,
      "loss": 2.7331872940063477,
      "step": 175
    },
    {
      "epoch": 0.18,
      "grad_norm": 2.5,
      "learning_rate": 0.0003,
      "loss": 2.7181303024291994,
      "step": 180
    },
    {
      "epoch": 0.185,
      "grad_norm": 0.53515625,
      "learning_rate": 0.0003,
      "loss": 2.7308780670166017,
      "step": 185
    },
    {
      "epoch": 0.19,
      "grad_norm": 3.875,
      "learning_rate": 0.0003,
      "loss": 2.7536849975585938,
      "step": 190
    },
    {
      "epoch": 0.195,
      "grad_norm": 0.361328125,
      "learning_rate": 0.0003,
      "loss": 2.71515007019043,
      "step": 195
    },
    {
      "epoch": 0.2,
      "grad_norm": 0.408203125,
      "learning_rate": 0.0003,
      "loss": 2.712385559082031,
      "step": 200
    },
    {
      "epoch": 0.2,
      "eval_loss": 3.117068290710449,
      "eval_runtime": 6.7047,
      "eval_samples_per_second": 5.519,
      "eval_steps_per_second": 2.834,
      "step": 200
    }
  ],
  "logging_steps": 5,
  "max_steps": 1000,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 9223372036854775807,
  "save_steps": 200,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 5.79830248636416e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}