{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 2.3597225544128198,
  "eval_steps": 500,
  "global_step": 1232,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.09567089213106912,
      "grad_norm": 79.64751434326172,
      "learning_rate": 2.5e-06,
      "loss": 10.5359,
      "step": 50
    },
    {
      "epoch": 0.19134178426213824,
      "grad_norm": 57.142730712890625,
      "learning_rate": 5e-06,
      "loss": 9.4534,
      "step": 100
    },
    {
      "epoch": 0.2870126763932074,
      "grad_norm": 56.33840560913086,
      "learning_rate": 7.5e-06,
      "loss": 8.7762,
      "step": 150
    },
    {
      "epoch": 0.3826835685242765,
      "grad_norm": 48.39895248413086,
      "learning_rate": 1e-05,
      "loss": 8.0812,
      "step": 200
    },
    {
      "epoch": 0.4783544606553456,
      "grad_norm": 51.66913604736328,
      "learning_rate": 1.25e-05,
      "loss": 7.4712,
      "step": 250
    },
    {
      "epoch": 0.5740253527864148,
      "grad_norm": 39.3389778137207,
      "learning_rate": 1.5e-05,
      "loss": 6.9249,
      "step": 300
    },
    {
      "epoch": 0.6696962449174838,
      "grad_norm": 42.176029205322266,
      "learning_rate": 1.7500000000000002e-05,
      "loss": 6.3373,
      "step": 350
    },
    {
      "epoch": 0.765367137048553,
      "grad_norm": 27.88520622253418,
      "learning_rate": 2e-05,
      "loss": 5.8156,
      "step": 400
    },
    {
      "epoch": 0.8610380291796221,
      "grad_norm": 27.722829818725586,
      "learning_rate": 2.2499999999999998e-05,
      "loss": 5.362,
      "step": 450
    },
    {
      "epoch": 0.9567089213106912,
      "grad_norm": 28.680429458618164,
      "learning_rate": 2.5e-05,
      "loss": 5.0434,
      "step": 500
    },
    {
      "epoch": 0.9988041138483617,
      "eval_accuracy": 0.0,
      "eval_loss": 8.436083793640137,
      "eval_normalizer": 94012.0,
      "eval_runtime": 81.5272,
      "eval_samples_per_second": 655.695,
      "eval_steps_per_second": 1.288,
      "step": 522
    },
    {
      "epoch": 1.0535756995933987,
      "grad_norm": 25.760271072387695,
      "learning_rate": 2.75e-05,
      "loss": 4.8276,
      "step": 550
    },
    {
      "epoch": 1.1492465917244679,
      "grad_norm": 27.668893814086914,
      "learning_rate": 3e-05,
      "loss": 4.6499,
      "step": 600
    },
    {
      "epoch": 1.244917483855537,
      "grad_norm": 27.842025756835938,
      "learning_rate": 3.2500000000000004e-05,
      "loss": 4.4827,
      "step": 650
    },
    {
      "epoch": 1.3405883759866062,
      "grad_norm": 30.099782943725586,
      "learning_rate": 3.5000000000000004e-05,
      "loss": 4.3643,
      "step": 700
    },
    {
      "epoch": 1.4362592681176751,
      "grad_norm": 33.141204833984375,
      "learning_rate": 3.75e-05,
      "loss": 4.2279,
      "step": 750
    },
    {
      "epoch": 1.5319301602487443,
      "grad_norm": 37.47197723388672,
      "learning_rate": 4e-05,
      "loss": 4.1339,
      "step": 800
    },
    {
      "epoch": 1.6276010523798135,
      "grad_norm": 34.994571685791016,
      "learning_rate": 4.25e-05,
      "loss": 4.0134,
      "step": 850
    },
    {
      "epoch": 1.7232719445108826,
      "grad_norm": 29.075597763061523,
      "learning_rate": 4.4999999999999996e-05,
      "loss": 3.9216,
      "step": 900
    },
    {
      "epoch": 1.8189428366419516,
      "grad_norm": 31.81198501586914,
      "learning_rate": 4.75e-05,
      "loss": 3.8193,
      "step": 950
    },
    {
      "epoch": 1.9146137287730207,
      "grad_norm": 33.48542785644531,
      "learning_rate": 5e-05,
      "loss": 3.7218,
      "step": 1000
    },
    {
      "epoch": 1.9988041138483617,
      "eval_accuracy": 0.0,
      "eval_loss": 8.203332901000977,
      "eval_normalizer": 93558.0,
      "eval_runtime": 83.028,
      "eval_samples_per_second": 643.843,
      "eval_steps_per_second": 1.265,
      "step": 1044
    },
    {
      "epoch": 2.0114805070557282,
      "grad_norm": 84.52313232421875,
      "learning_rate": 5.25e-05,
      "loss": 4.1746,
      "step": 1050
    },
    {
      "epoch": 2.1071513991867974,
      "grad_norm": 32.48819351196289,
      "learning_rate": 5.5e-05,
      "loss": 6.9906,
      "step": 1100
    },
    {
      "epoch": 2.2028222913178666,
      "grad_norm": 20.257213592529297,
      "learning_rate": 5.75e-05,
      "loss": 6.1631,
      "step": 1150
    },
    {
      "epoch": 2.2984931834489357,
      "grad_norm": 20.544626235961914,
      "learning_rate": 6e-05,
      "loss": 5.787,
      "step": 1200
    },
    {
      "epoch": 2.3597225544128198,
      "eval_accuracy": 0.0,
      "eval_loss": 6.199265480041504,
      "eval_normalizer": 94216.0,
      "eval_runtime": 83.3702,
      "eval_samples_per_second": 641.201,
      "eval_steps_per_second": 1.259,
      "step": 1232
    }
  ],
  "logging_steps": 50,
  "max_steps": 5220,
  "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": false
      },
      "attributes": {}
    }
  },
  "total_flos": 7.555390113439814e+16,
  "train_batch_size": 128,
  "trial_name": null,
  "trial_params": null
}