{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.929233772571987,
  "eval_steps": 50,
  "global_step": 1280,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.3904343582235237,
      "grad_norm": 316011.5625,
      "learning_rate": 9.609375e-05,
      "loss": 14505.3388,
      "step": 50
    },
    {
      "epoch": 0.3904343582235237,
      "eval_runtime": 19.78,
      "eval_samples_per_second": 21.84,
      "eval_steps_per_second": 5.46,
      "step": 50
    },
    {
      "epoch": 0.7808687164470474,
      "grad_norm": 484251.53125,
      "learning_rate": 9.21875e-05,
      "loss": 4453.3172,
      "step": 100
    },
    {
      "epoch": 0.7808687164470474,
      "eval_runtime": 19.7737,
      "eval_samples_per_second": 21.847,
      "eval_steps_per_second": 5.462,
      "step": 100
    },
    {
      "epoch": 1.16398243045388,
      "grad_norm": 502497.4375,
      "learning_rate": 8.828125000000001e-05,
      "loss": 3495.4003,
      "step": 150
    },
    {
      "epoch": 1.16398243045388,
      "eval_runtime": 19.7678,
      "eval_samples_per_second": 21.854,
      "eval_steps_per_second": 5.463,
      "step": 150
    },
    {
      "epoch": 1.5544167886774036,
      "grad_norm": 733164.8125,
      "learning_rate": 8.4375e-05,
      "loss": 3503.1944,
      "step": 200
    },
    {
      "epoch": 1.5544167886774036,
      "eval_runtime": 19.8051,
      "eval_samples_per_second": 21.813,
      "eval_steps_per_second": 5.453,
      "step": 200
    },
    {
      "epoch": 1.9448511469009273,
      "grad_norm": 385944.6875,
      "learning_rate": 8.046875e-05,
      "loss": 2722.6881,
      "step": 250
    },
    {
      "epoch": 1.9448511469009273,
      "eval_runtime": 19.7807,
      "eval_samples_per_second": 21.839,
      "eval_steps_per_second": 5.46,
      "step": 250
    },
    {
      "epoch": 2.32796486090776,
      "grad_norm": 331782.8125,
      "learning_rate": 7.65625e-05,
      "loss": 2230.8694,
      "step": 300
    },
    {
      "epoch": 2.32796486090776,
      "eval_runtime": 19.7643,
      "eval_samples_per_second": 21.858,
      "eval_steps_per_second": 5.464,
      "step": 300
    },
    {
      "epoch": 2.7183992191312836,
      "grad_norm": 321584.84375,
      "learning_rate": 7.265625000000001e-05,
      "loss": 1869.6005,
      "step": 350
    },
    {
      "epoch": 2.7183992191312836,
      "eval_runtime": 19.7383,
      "eval_samples_per_second": 21.886,
      "eval_steps_per_second": 5.472,
      "step": 350
    },
    {
      "epoch": 3.101512933138116,
      "grad_norm": 535160.875,
      "learning_rate": 6.875e-05,
      "loss": 1711.6647,
      "step": 400
    },
    {
      "epoch": 3.101512933138116,
      "eval_runtime": 19.7699,
      "eval_samples_per_second": 21.851,
      "eval_steps_per_second": 5.463,
      "step": 400
    },
    {
      "epoch": 3.49194729136164,
      "grad_norm": 411710.09375,
      "learning_rate": 6.484375e-05,
      "loss": 1542.0261,
      "step": 450
    },
    {
      "epoch": 3.49194729136164,
      "eval_runtime": 19.7891,
      "eval_samples_per_second": 21.83,
      "eval_steps_per_second": 5.458,
      "step": 450
    },
    {
      "epoch": 3.8823816495851635,
      "grad_norm": 426711.1875,
      "learning_rate": 6.0937500000000004e-05,
      "loss": 1512.678,
      "step": 500
    },
    {
      "epoch": 3.8823816495851635,
      "eval_runtime": 19.7847,
      "eval_samples_per_second": 21.835,
      "eval_steps_per_second": 5.459,
      "step": 500
    },
    {
      "epoch": 4.265495363591996,
      "grad_norm": 605412.375,
      "learning_rate": 5.703125e-05,
      "loss": 1325.2478,
      "step": 550
    },
    {
      "epoch": 4.265495363591996,
      "eval_runtime": 19.7746,
      "eval_samples_per_second": 21.846,
      "eval_steps_per_second": 5.462,
      "step": 550
    },
    {
      "epoch": 4.65592972181552,
      "grad_norm": 409170.1875,
      "learning_rate": 5.3125000000000004e-05,
      "loss": 1282.363,
      "step": 600
    },
    {
      "epoch": 4.65592972181552,
      "eval_runtime": 19.7404,
      "eval_samples_per_second": 21.884,
      "eval_steps_per_second": 5.471,
      "step": 600
    },
    {
      "epoch": 5.039043435822352,
      "grad_norm": 328730.40625,
      "learning_rate": 4.921875e-05,
      "loss": 971.7115,
      "step": 650
    },
    {
      "epoch": 5.039043435822352,
      "eval_runtime": 19.734,
      "eval_samples_per_second": 21.891,
      "eval_steps_per_second": 5.473,
      "step": 650
    },
    {
      "epoch": 5.4294777940458765,
      "grad_norm": 145752.921875,
      "learning_rate": 4.5312500000000004e-05,
      "loss": 901.4456,
      "step": 700
    },
    {
      "epoch": 5.4294777940458765,
      "eval_runtime": 19.7781,
      "eval_samples_per_second": 21.842,
      "eval_steps_per_second": 5.461,
      "step": 700
    },
    {
      "epoch": 5.819912152269399,
      "grad_norm": 190886.453125,
      "learning_rate": 4.140625e-05,
      "loss": 991.2295,
      "step": 750
    },
    {
      "epoch": 5.819912152269399,
      "eval_runtime": 19.7898,
      "eval_samples_per_second": 21.829,
      "eval_steps_per_second": 5.457,
      "step": 750
    },
    {
      "epoch": 6.203025866276232,
      "grad_norm": 195982.890625,
      "learning_rate": 3.7500000000000003e-05,
      "loss": 829.7355,
      "step": 800
    },
    {
      "epoch": 6.203025866276232,
      "eval_runtime": 19.7721,
      "eval_samples_per_second": 21.849,
      "eval_steps_per_second": 5.462,
      "step": 800
    },
    {
      "epoch": 6.593460224499756,
      "grad_norm": 427655.71875,
      "learning_rate": 3.359375e-05,
      "loss": 684.6569,
      "step": 850
    },
    {
      "epoch": 6.593460224499756,
      "eval_runtime": 19.7731,
      "eval_samples_per_second": 21.848,
      "eval_steps_per_second": 5.462,
      "step": 850
    },
    {
      "epoch": 6.98389458272328,
      "grad_norm": 516619.03125,
      "learning_rate": 2.96875e-05,
      "loss": 778.275,
      "step": 900
    },
    {
      "epoch": 6.98389458272328,
      "eval_runtime": 19.7592,
      "eval_samples_per_second": 21.863,
      "eval_steps_per_second": 5.466,
      "step": 900
    },
    {
      "epoch": 7.367008296730113,
      "grad_norm": 240667.90625,
      "learning_rate": 2.578125e-05,
      "loss": 658.1772,
      "step": 950
    },
    {
      "epoch": 7.367008296730113,
      "eval_runtime": 19.7525,
      "eval_samples_per_second": 21.871,
      "eval_steps_per_second": 5.468,
      "step": 950
    },
    {
      "epoch": 7.7574426549536355,
      "grad_norm": 319554.6875,
      "learning_rate": 2.1875e-05,
      "loss": 457.791,
      "step": 1000
    },
    {
      "epoch": 7.7574426549536355,
      "eval_runtime": 19.8005,
      "eval_samples_per_second": 21.818,
      "eval_steps_per_second": 5.454,
      "step": 1000
    },
    {
      "epoch": 8.140556368960468,
      "grad_norm": 406190.0625,
      "learning_rate": 1.796875e-05,
      "loss": 536.1774,
      "step": 1050
    },
    {
      "epoch": 8.140556368960468,
      "eval_runtime": 19.767,
      "eval_samples_per_second": 21.855,
      "eval_steps_per_second": 5.464,
      "step": 1050
    },
    {
      "epoch": 8.530990727183992,
      "grad_norm": 325491.78125,
      "learning_rate": 1.4062500000000001e-05,
      "loss": 373.9504,
      "step": 1100
    },
    {
      "epoch": 8.530990727183992,
      "eval_runtime": 19.7611,
      "eval_samples_per_second": 21.861,
      "eval_steps_per_second": 5.465,
      "step": 1100
    },
    {
      "epoch": 8.921425085407517,
      "grad_norm": 98692.546875,
      "learning_rate": 1.0156250000000001e-05,
      "loss": 313.6299,
      "step": 1150
    },
    {
      "epoch": 8.921425085407517,
      "eval_runtime": 19.766,
      "eval_samples_per_second": 21.856,
      "eval_steps_per_second": 5.464,
      "step": 1150
    },
    {
      "epoch": 9.304538799414349,
      "grad_norm": 154307.0,
      "learning_rate": 6.25e-06,
      "loss": 275.3413,
      "step": 1200
    },
    {
      "epoch": 9.304538799414349,
      "eval_runtime": 19.7645,
      "eval_samples_per_second": 21.857,
      "eval_steps_per_second": 5.464,
      "step": 1200
    },
    {
      "epoch": 9.694973157637872,
      "grad_norm": 77167.2265625,
      "learning_rate": 2.3437500000000002e-06,
      "loss": 241.9685,
      "step": 1250
    },
    {
      "epoch": 9.694973157637872,
      "eval_runtime": 19.7657,
      "eval_samples_per_second": 21.856,
      "eval_steps_per_second": 5.464,
      "step": 1250
    }
  ],
  "logging_steps": 50,
  "max_steps": 1280,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "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": 0.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}