{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.0495000495000495,
  "eval_steps": 63,
  "global_step": 250,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.000198000198000198,
      "eval_loss": 1.105994701385498,
      "eval_runtime": 178.7554,
      "eval_samples_per_second": 11.899,
      "eval_steps_per_second": 5.952,
      "step": 1
    },
    {
      "epoch": 0.00198000198000198,
      "grad_norm": 1.0253896713256836,
      "learning_rate": 0.00019979453927503364,
      "loss": 4.1623,
      "step": 10
    },
    {
      "epoch": 0.00396000396000396,
      "grad_norm": 1.3080334663391113,
      "learning_rate": 0.00019815591569910654,
      "loss": 3.808,
      "step": 20
    },
    {
      "epoch": 0.00594000594000594,
      "grad_norm": 1.1358824968338013,
      "learning_rate": 0.00019490557470106686,
      "loss": 3.8129,
      "step": 30
    },
    {
      "epoch": 0.00792000792000792,
      "grad_norm": 1.09774649143219,
      "learning_rate": 0.0001900968867902419,
      "loss": 3.6487,
      "step": 40
    },
    {
      "epoch": 0.0099000099000099,
      "grad_norm": 1.8375412225723267,
      "learning_rate": 0.00018380881048918405,
      "loss": 3.9302,
      "step": 50
    },
    {
      "epoch": 0.01188001188001188,
      "grad_norm": 1.5806461572647095,
      "learning_rate": 0.00017614459583691346,
      "loss": 3.7849,
      "step": 60
    },
    {
      "epoch": 0.012474012474012475,
      "eval_loss": 0.8816875219345093,
      "eval_runtime": 178.7559,
      "eval_samples_per_second": 11.899,
      "eval_steps_per_second": 5.952,
      "step": 63
    },
    {
      "epoch": 0.01386001386001386,
      "grad_norm": 1.0627981424331665,
      "learning_rate": 0.0001672300890261317,
      "loss": 3.9733,
      "step": 70
    },
    {
      "epoch": 0.01584001584001584,
      "grad_norm": 1.2830634117126465,
      "learning_rate": 0.00015721166601221698,
      "loss": 3.5916,
      "step": 80
    },
    {
      "epoch": 0.01782001782001782,
      "grad_norm": 1.6237497329711914,
      "learning_rate": 0.00014625382902408356,
      "loss": 3.5255,
      "step": 90
    },
    {
      "epoch": 0.0198000198000198,
      "grad_norm": 0.9424677491188049,
      "learning_rate": 0.00013453650544213076,
      "loss": 3.4469,
      "step": 100
    },
    {
      "epoch": 0.02178002178002178,
      "grad_norm": 1.0363863706588745,
      "learning_rate": 0.00012225209339563145,
      "loss": 3.1657,
      "step": 110
    },
    {
      "epoch": 0.02376002376002376,
      "grad_norm": 1.1030207872390747,
      "learning_rate": 0.00010960230259076818,
      "loss": 3.1192,
      "step": 120
    },
    {
      "epoch": 0.02494802494802495,
      "eval_loss": 0.8477188348770142,
      "eval_runtime": 178.9339,
      "eval_samples_per_second": 11.887,
      "eval_steps_per_second": 5.946,
      "step": 126
    },
    {
      "epoch": 0.02574002574002574,
      "grad_norm": 2.223292350769043,
      "learning_rate": 9.679484224283449e-05,
      "loss": 3.7863,
      "step": 130
    },
    {
      "epoch": 0.02772002772002772,
      "grad_norm": 1.6937029361724854,
      "learning_rate": 8.404001049666211e-05,
      "loss": 3.357,
      "step": 140
    },
    {
      "epoch": 0.0297000297000297,
      "grad_norm": 1.402112603187561,
      "learning_rate": 7.154724133689677e-05,
      "loss": 3.268,
      "step": 150
    },
    {
      "epoch": 0.03168003168003168,
      "grad_norm": 1.8958817720413208,
      "learning_rate": 5.952166568776062e-05,
      "loss": 3.2951,
      "step": 160
    },
    {
      "epoch": 0.03366003366003366,
      "grad_norm": 1.6198538541793823,
      "learning_rate": 4.8160743168947496e-05,
      "loss": 3.3408,
      "step": 170
    },
    {
      "epoch": 0.03564003564003564,
      "grad_norm": 1.636849284172058,
      "learning_rate": 3.7651019814126654e-05,
      "loss": 3.8538,
      "step": 180
    },
    {
      "epoch": 0.037422037422037424,
      "eval_loss": 0.8331639766693115,
      "eval_runtime": 178.779,
      "eval_samples_per_second": 11.897,
      "eval_steps_per_second": 5.951,
      "step": 189
    },
    {
      "epoch": 0.03762003762003762,
      "grad_norm": 1.3049726486206055,
      "learning_rate": 2.8165064990227252e-05,
      "loss": 3.5265,
      "step": 190
    },
    {
      "epoch": 0.0396000396000396,
      "grad_norm": 1.4380872249603271,
      "learning_rate": 1.985863781320435e-05,
      "loss": 3.0763,
      "step": 200
    },
    {
      "epoch": 0.04158004158004158,
      "grad_norm": 1.24958074092865,
      "learning_rate": 1.286812958766106e-05,
      "loss": 3.0707,
      "step": 210
    },
    {
      "epoch": 0.04356004356004356,
      "grad_norm": 2.750286102294922,
      "learning_rate": 7.308324265397836e-06,
      "loss": 2.7011,
      "step": 220
    },
    {
      "epoch": 0.04554004554004554,
      "grad_norm": 1.8265074491500854,
      "learning_rate": 3.270513696097055e-06,
      "loss": 2.7879,
      "step": 230
    },
    {
      "epoch": 0.04752004752004752,
      "grad_norm": 1.098848581314087,
      "learning_rate": 8.209986176753948e-07,
      "loss": 3.438,
      "step": 240
    },
    {
      "epoch": 0.0495000495000495,
      "grad_norm": 1.3819769620895386,
      "learning_rate": 0.0,
      "loss": 2.7865,
      "step": 250
    }
  ],
  "logging_steps": 10,
  "max_steps": 250,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 63,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.2102892407226368e+17,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}