{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 9.955832389580975,
  "eval_steps": 500,
  "global_step": 2200,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.22650056625141562,
      "grad_norm": 0.20137609957280783,
      "learning_rate": 1.9545454545454546e-05,
      "loss": 0.5168,
      "step": 50
    },
    {
      "epoch": 0.45300113250283125,
      "grad_norm": 0.2013300670370018,
      "learning_rate": 1.9090909090909094e-05,
      "loss": 0.0128,
      "step": 100
    },
    {
      "epoch": 0.6795016987542469,
      "grad_norm": 0.1948749302407212,
      "learning_rate": 1.8636363636363638e-05,
      "loss": 0.0109,
      "step": 150
    },
    {
      "epoch": 0.9060022650056625,
      "grad_norm": 0.3079769456792249,
      "learning_rate": 1.8181818181818182e-05,
      "loss": 0.01,
      "step": 200
    },
    {
      "epoch": 1.131370328425821,
      "grad_norm": 0.11659573946029254,
      "learning_rate": 1.772727272727273e-05,
      "loss": 0.0085,
      "step": 250
    },
    {
      "epoch": 1.3578708946772367,
      "grad_norm": 0.13647255696510582,
      "learning_rate": 1.7272727272727274e-05,
      "loss": 0.0078,
      "step": 300
    },
    {
      "epoch": 1.5843714609286523,
      "grad_norm": 0.15768432375462818,
      "learning_rate": 1.681818181818182e-05,
      "loss": 0.0071,
      "step": 350
    },
    {
      "epoch": 1.8108720271800678,
      "grad_norm": 0.15847143458299046,
      "learning_rate": 1.6363636363636366e-05,
      "loss": 0.0067,
      "step": 400
    },
    {
      "epoch": 2.0362400906002267,
      "grad_norm": 0.11900826522531659,
      "learning_rate": 1.590909090909091e-05,
      "loss": 0.0058,
      "step": 450
    },
    {
      "epoch": 2.262740656851642,
      "grad_norm": 0.10699758660461905,
      "learning_rate": 1.5454545454545454e-05,
      "loss": 0.0048,
      "step": 500
    },
    {
      "epoch": 2.4892412231030576,
      "grad_norm": 0.11450612536065724,
      "learning_rate": 1.5000000000000002e-05,
      "loss": 0.0047,
      "step": 550
    },
    {
      "epoch": 2.7157417893544733,
      "grad_norm": 0.10941823931426253,
      "learning_rate": 1.4545454545454546e-05,
      "loss": 0.0045,
      "step": 600
    },
    {
      "epoch": 2.942242355605889,
      "grad_norm": 0.09961743857235339,
      "learning_rate": 1.4090909090909092e-05,
      "loss": 0.0043,
      "step": 650
    },
    {
      "epoch": 3.1676104190260475,
      "grad_norm": 0.06304576627604626,
      "learning_rate": 1.3636363636363637e-05,
      "loss": 0.0032,
      "step": 700
    },
    {
      "epoch": 3.394110985277463,
      "grad_norm": 0.06297399681880526,
      "learning_rate": 1.3181818181818183e-05,
      "loss": 0.003,
      "step": 750
    },
    {
      "epoch": 3.620611551528879,
      "grad_norm": 0.13120001367468562,
      "learning_rate": 1.2727272727272728e-05,
      "loss": 0.0031,
      "step": 800
    },
    {
      "epoch": 3.8471121177802945,
      "grad_norm": 0.04418669416229479,
      "learning_rate": 1.2272727272727274e-05,
      "loss": 0.0029,
      "step": 850
    },
    {
      "epoch": 4.072480181200453,
      "grad_norm": 0.05532106994003379,
      "learning_rate": 1.181818181818182e-05,
      "loss": 0.0025,
      "step": 900
    },
    {
      "epoch": 4.298980747451869,
      "grad_norm": 0.08355846714318485,
      "learning_rate": 1.1363636363636366e-05,
      "loss": 0.0018,
      "step": 950
    },
    {
      "epoch": 4.525481313703284,
      "grad_norm": 0.07284205298942517,
      "learning_rate": 1.0909090909090909e-05,
      "loss": 0.0019,
      "step": 1000
    },
    {
      "epoch": 4.7519818799547,
      "grad_norm": 0.05972942958206222,
      "learning_rate": 1.0454545454545455e-05,
      "loss": 0.0019,
      "step": 1050
    },
    {
      "epoch": 4.978482446206115,
      "grad_norm": 0.05179823686976107,
      "learning_rate": 1e-05,
      "loss": 0.0019,
      "step": 1100
    },
    {
      "epoch": 5.203850509626274,
      "grad_norm": 0.033306725978502795,
      "learning_rate": 9.545454545454547e-06,
      "loss": 0.0013,
      "step": 1150
    },
    {
      "epoch": 5.43035107587769,
      "grad_norm": 0.03888214010647136,
      "learning_rate": 9.090909090909091e-06,
      "loss": 0.0012,
      "step": 1200
    },
    {
      "epoch": 5.656851642129105,
      "grad_norm": 0.058395019128899245,
      "learning_rate": 8.636363636363637e-06,
      "loss": 0.0013,
      "step": 1250
    },
    {
      "epoch": 5.883352208380521,
      "grad_norm": 0.04978265891525234,
      "learning_rate": 8.181818181818183e-06,
      "loss": 0.0012,
      "step": 1300
    },
    {
      "epoch": 6.10872027180068,
      "grad_norm": 0.04113959184272897,
      "learning_rate": 7.727272727272727e-06,
      "loss": 0.001,
      "step": 1350
    },
    {
      "epoch": 6.335220838052095,
      "grad_norm": 0.041645693484639534,
      "learning_rate": 7.272727272727273e-06,
      "loss": 0.0007,
      "step": 1400
    },
    {
      "epoch": 6.561721404303511,
      "grad_norm": 0.030508542016332258,
      "learning_rate": 6.818181818181818e-06,
      "loss": 0.0007,
      "step": 1450
    },
    {
      "epoch": 6.788221970554926,
      "grad_norm": 0.025347412197402025,
      "learning_rate": 6.363636363636364e-06,
      "loss": 0.0007,
      "step": 1500
    },
    {
      "epoch": 7.013590033975085,
      "grad_norm": 0.018651988693332962,
      "learning_rate": 5.90909090909091e-06,
      "loss": 0.0007,
      "step": 1550
    },
    {
      "epoch": 7.240090600226501,
      "grad_norm": 0.03230699683397215,
      "learning_rate": 5.4545454545454545e-06,
      "loss": 0.0004,
      "step": 1600
    },
    {
      "epoch": 7.466591166477916,
      "grad_norm": 0.026761393614589048,
      "learning_rate": 5e-06,
      "loss": 0.0004,
      "step": 1650
    },
    {
      "epoch": 7.693091732729332,
      "grad_norm": 0.02236008528962798,
      "learning_rate": 4.5454545454545455e-06,
      "loss": 0.0004,
      "step": 1700
    },
    {
      "epoch": 7.9195922989807475,
      "grad_norm": 0.03305879789661407,
      "learning_rate": 4.0909090909090915e-06,
      "loss": 0.0004,
      "step": 1750
    },
    {
      "epoch": 8.144960362400907,
      "grad_norm": 0.012247868310907491,
      "learning_rate": 3.6363636363636366e-06,
      "loss": 0.0003,
      "step": 1800
    },
    {
      "epoch": 8.371460928652322,
      "grad_norm": 0.007866650598934112,
      "learning_rate": 3.181818181818182e-06,
      "loss": 0.0003,
      "step": 1850
    },
    {
      "epoch": 8.597961494903737,
      "grad_norm": 0.016624244747761457,
      "learning_rate": 2.7272727272727272e-06,
      "loss": 0.0003,
      "step": 1900
    },
    {
      "epoch": 8.824462061155153,
      "grad_norm": 0.010416853885837421,
      "learning_rate": 2.2727272727272728e-06,
      "loss": 0.0002,
      "step": 1950
    },
    {
      "epoch": 9.049830124575312,
      "grad_norm": 0.010283065741774714,
      "learning_rate": 1.8181818181818183e-06,
      "loss": 0.0002,
      "step": 2000
    },
    {
      "epoch": 9.276330690826727,
      "grad_norm": 0.007431975696700639,
      "learning_rate": 1.3636363636363636e-06,
      "loss": 0.0002,
      "step": 2050
    },
    {
      "epoch": 9.502831257078142,
      "grad_norm": 0.009351588366790045,
      "learning_rate": 9.090909090909091e-07,
      "loss": 0.0002,
      "step": 2100
    },
    {
      "epoch": 9.729331823329558,
      "grad_norm": 0.011243245600959548,
      "learning_rate": 4.5454545454545457e-07,
      "loss": 0.0002,
      "step": 2150
    },
    {
      "epoch": 9.955832389580975,
      "grad_norm": 0.010736151595878016,
      "learning_rate": 0.0,
      "loss": 0.0002,
      "step": 2200
    }
  ],
  "logging_steps": 50,
  "max_steps": 2200,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 10,
  "save_steps": 1000,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 3520566698967040.0,
  "train_batch_size": 8,
  "trial_name": null,
  "trial_params": null
}