{
  "best_global_step": null,
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.8791208791208791,
  "eval_steps": 500,
  "global_step": 80,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.02197802197802198,
      "grad_norm": 0.3012084364891052,
      "learning_rate": 4.000000000000001e-06,
      "loss": 1.3385181427001953,
      "step": 2
    },
    {
      "epoch": 0.04395604395604396,
      "grad_norm": 0.3726103603839874,
      "learning_rate": 1.2e-05,
      "loss": 1.6271111965179443,
      "step": 4
    },
    {
      "epoch": 0.06593406593406594,
      "grad_norm": 0.2790508568286896,
      "learning_rate": 2e-05,
      "loss": 1.5764275789260864,
      "step": 6
    },
    {
      "epoch": 0.08791208791208792,
      "grad_norm": 0.3855365216732025,
      "learning_rate": 1.9973322836635517e-05,
      "loss": 1.80802583694458,
      "step": 8
    },
    {
      "epoch": 0.10989010989010989,
      "grad_norm": 0.2806936502456665,
      "learning_rate": 1.9893433680751105e-05,
      "loss": 1.352150797843933,
      "step": 10
    },
    {
      "epoch": 0.13186813186813187,
      "grad_norm": 0.3063288629055023,
      "learning_rate": 1.9760758775559275e-05,
      "loss": 1.4385991096496582,
      "step": 12
    },
    {
      "epoch": 0.15384615384615385,
      "grad_norm": 0.25889647006988525,
      "learning_rate": 1.957600599908406e-05,
      "loss": 1.841127634048462,
      "step": 14
    },
    {
      "epoch": 0.17582417582417584,
      "grad_norm": 0.27789703011512756,
      "learning_rate": 1.9340161087325483e-05,
      "loss": 1.497275471687317,
      "step": 16
    },
    {
      "epoch": 0.1978021978021978,
      "grad_norm": 0.3025414049625397,
      "learning_rate": 1.905448237493147e-05,
      "loss": 1.4605973958969116,
      "step": 18
    },
    {
      "epoch": 0.21978021978021978,
      "grad_norm": 0.2801181375980377,
      "learning_rate": 1.872049408143808e-05,
      "loss": 1.3008084297180176,
      "step": 20
    },
    {
      "epoch": 0.24175824175824176,
      "grad_norm": 0.2751348912715912,
      "learning_rate": 1.833997817889878e-05,
      "loss": 1.2773511409759521,
      "step": 22
    },
    {
      "epoch": 0.26373626373626374,
      "grad_norm": 0.38996145129203796,
      "learning_rate": 1.7914964884292543e-05,
      "loss": 1.2179161310195923,
      "step": 24
    },
    {
      "epoch": 0.2857142857142857,
      "grad_norm": 0.8840112090110779,
      "learning_rate": 1.744772182743782e-05,
      "loss": 1.855831503868103,
      "step": 26
    },
    {
      "epoch": 0.3076923076923077,
      "grad_norm": 0.3252807855606079,
      "learning_rate": 1.6940741952206342e-05,
      "loss": 1.5678815841674805,
      "step": 28
    },
    {
      "epoch": 0.32967032967032966,
      "grad_norm": 0.24409082531929016,
      "learning_rate": 1.6396730215588913e-05,
      "loss": 1.2494449615478516,
      "step": 30
    },
    {
      "epoch": 0.3516483516483517,
      "grad_norm": 0.22459135949611664,
      "learning_rate": 1.581858915557953e-05,
      "loss": 1.0519582033157349,
      "step": 32
    },
    {
      "epoch": 0.37362637362637363,
      "grad_norm": 0.3741042912006378,
      "learning_rate": 1.5209403404879305e-05,
      "loss": 1.4155118465423584,
      "step": 34
    },
    {
      "epoch": 0.3956043956043956,
      "grad_norm": 0.31006920337677,
      "learning_rate": 1.4572423233046386e-05,
      "loss": 1.1812822818756104,
      "step": 36
    },
    {
      "epoch": 0.4175824175824176,
      "grad_norm": 3.532601833343506,
      "learning_rate": 1.391104720490156e-05,
      "loss": 1.4337464570999146,
      "step": 38
    },
    {
      "epoch": 0.43956043956043955,
      "grad_norm": 0.626689076423645,
      "learning_rate": 1.3228804047714462e-05,
      "loss": 1.2015326023101807,
      "step": 40
    },
    {
      "epoch": 0.46153846153846156,
      "grad_norm": 0.32571879029273987,
      "learning_rate": 1.2529333823916807e-05,
      "loss": 1.010868787765503,
      "step": 42
    },
    {
      "epoch": 0.4835164835164835,
      "grad_norm": 0.3460634648799896,
      "learning_rate": 1.1816368509794365e-05,
      "loss": 1.3443571329116821,
      "step": 44
    },
    {
      "epoch": 0.5054945054945055,
      "grad_norm": 0.3677666485309601,
      "learning_rate": 1.1093712083778748e-05,
      "loss": 1.189827561378479,
      "step": 46
    },
    {
      "epoch": 0.5274725274725275,
      "grad_norm": 0.4721606969833374,
      "learning_rate": 1.0365220230576592e-05,
      "loss": 1.292205572128296,
      "step": 48
    },
    {
      "epoch": 0.5494505494505495,
      "grad_norm": 0.2631397247314453,
      "learning_rate": 9.634779769423412e-06,
      "loss": 1.4859278202056885,
      "step": 50
    },
    {
      "epoch": 0.5714285714285714,
      "grad_norm": 0.4153558909893036,
      "learning_rate": 8.906287916221259e-06,
      "loss": 1.3328526020050049,
      "step": 52
    },
    {
      "epoch": 0.5934065934065934,
      "grad_norm": 0.44497573375701904,
      "learning_rate": 8.183631490205636e-06,
      "loss": 1.295997142791748,
      "step": 54
    },
    {
      "epoch": 0.6153846153846154,
      "grad_norm": 0.4488207697868347,
      "learning_rate": 7.470666176083193e-06,
      "loss": 1.449225902557373,
      "step": 56
    },
    {
      "epoch": 0.6373626373626373,
      "grad_norm": 0.24774296581745148,
      "learning_rate": 6.771195952285541e-06,
      "loss": 1.4275600910186768,
      "step": 58
    },
    {
      "epoch": 0.6593406593406593,
      "grad_norm": 0.5897124409675598,
      "learning_rate": 6.088952795098442e-06,
      "loss": 1.3049211502075195,
      "step": 60
    },
    {
      "epoch": 0.6813186813186813,
      "grad_norm": 0.442289799451828,
      "learning_rate": 5.427576766953615e-06,
      "loss": 1.2369039058685303,
      "step": 62
    },
    {
      "epoch": 0.7032967032967034,
      "grad_norm": 0.3426021635532379,
      "learning_rate": 4.790596595120699e-06,
      "loss": 1.4170987606048584,
      "step": 64
    },
    {
      "epoch": 0.7252747252747253,
      "grad_norm": 0.4659130573272705,
      "learning_rate": 4.181410844420473e-06,
      "loss": 1.540313959121704,
      "step": 66
    },
    {
      "epoch": 0.7472527472527473,
      "grad_norm": 0.3569144010543823,
      "learning_rate": 3.6032697844110896e-06,
      "loss": 1.1695493459701538,
      "step": 68
    },
    {
      "epoch": 0.7692307692307693,
      "grad_norm": 0.31596097350120544,
      "learning_rate": 3.0592580477936606e-06,
      "loss": 1.2741234302520752,
      "step": 70
    },
    {
      "epoch": 0.7912087912087912,
      "grad_norm": 0.3353954553604126,
      "learning_rate": 2.5522781725621814e-06,
      "loss": 1.2784150838851929,
      "step": 72
    },
    {
      "epoch": 0.8131868131868132,
      "grad_norm": 0.3931275010108948,
      "learning_rate": 2.08503511570746e-06,
      "loss": 1.2940069437026978,
      "step": 74
    },
    {
      "epoch": 0.8351648351648352,
      "grad_norm": 0.3980410695075989,
      "learning_rate": 1.660021821101222e-06,
      "loss": 0.9338208436965942,
      "step": 76
    },
    {
      "epoch": 0.8571428571428571,
      "grad_norm": 0.2409302294254303,
      "learning_rate": 1.279505918561923e-06,
      "loss": 1.3363934755325317,
      "step": 78
    },
    {
      "epoch": 0.8791208791208791,
      "grad_norm": 0.3418237268924713,
      "learning_rate": 9.455176250685338e-07,
      "loss": 1.2735731601715088,
      "step": 80
    }
  ],
  "logging_steps": 2,
  "max_steps": 91,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 20,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": false
      },
      "attributes": {}
    }
  },
  "total_flos": 2.4769785469313664e+16,
  "train_batch_size": 1,
  "trial_name": null,
  "trial_params": null
}