{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.11289867344058707,
  "eval_steps": 9,
  "global_step": 100,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0011289867344058708,
      "eval_loss": 11.095446586608887,
      "eval_runtime": 5.2252,
      "eval_samples_per_second": 142.77,
      "eval_steps_per_second": 35.788,
      "step": 1
    },
    {
      "epoch": 0.003386960203217612,
      "grad_norm": 1.9205418825149536,
      "learning_rate": 3e-05,
      "loss": 44.3861,
      "step": 3
    },
    {
      "epoch": 0.006773920406435224,
      "grad_norm": 2.004185676574707,
      "learning_rate": 6e-05,
      "loss": 44.3659,
      "step": 6
    },
    {
      "epoch": 0.010160880609652836,
      "grad_norm": 2.0670409202575684,
      "learning_rate": 9e-05,
      "loss": 44.3444,
      "step": 9
    },
    {
      "epoch": 0.010160880609652836,
      "eval_loss": 11.07402229309082,
      "eval_runtime": 4.807,
      "eval_samples_per_second": 155.189,
      "eval_steps_per_second": 38.901,
      "step": 9
    },
    {
      "epoch": 0.013547840812870448,
      "grad_norm": 2.8204221725463867,
      "learning_rate": 9.987820251299122e-05,
      "loss": 44.2671,
      "step": 12
    },
    {
      "epoch": 0.01693480101608806,
      "grad_norm": 1.7280925512313843,
      "learning_rate": 9.924038765061042e-05,
      "loss": 44.2078,
      "step": 15
    },
    {
      "epoch": 0.02032176121930567,
      "grad_norm": 1.5682748556137085,
      "learning_rate": 9.806308479691595e-05,
      "loss": 44.1568,
      "step": 18
    },
    {
      "epoch": 0.02032176121930567,
      "eval_loss": 11.031317710876465,
      "eval_runtime": 4.8233,
      "eval_samples_per_second": 154.664,
      "eval_steps_per_second": 38.77,
      "step": 18
    },
    {
      "epoch": 0.023708721422523286,
      "grad_norm": 1.489903211593628,
      "learning_rate": 9.635919272833938e-05,
      "loss": 44.1182,
      "step": 21
    },
    {
      "epoch": 0.027095681625740897,
      "grad_norm": 1.5463424921035767,
      "learning_rate": 9.414737964294636e-05,
      "loss": 44.0264,
      "step": 24
    },
    {
      "epoch": 0.03048264182895851,
      "grad_norm": 1.5844411849975586,
      "learning_rate": 9.145187862775209e-05,
      "loss": 44.0424,
      "step": 27
    },
    {
      "epoch": 0.03048264182895851,
      "eval_loss": 10.998998641967773,
      "eval_runtime": 4.8843,
      "eval_samples_per_second": 152.734,
      "eval_steps_per_second": 38.286,
      "step": 27
    },
    {
      "epoch": 0.03386960203217612,
      "grad_norm": 1.455848217010498,
      "learning_rate": 8.83022221559489e-05,
      "loss": 43.9554,
      "step": 30
    },
    {
      "epoch": 0.03725656223539373,
      "grad_norm": 1.5806920528411865,
      "learning_rate": 8.473291852294987e-05,
      "loss": 43.9434,
      "step": 33
    },
    {
      "epoch": 0.04064352243861134,
      "grad_norm": 1.0965741872787476,
      "learning_rate": 8.07830737662829e-05,
      "loss": 43.9742,
      "step": 36
    },
    {
      "epoch": 0.04064352243861134,
      "eval_loss": 10.9762544631958,
      "eval_runtime": 4.7717,
      "eval_samples_per_second": 156.337,
      "eval_steps_per_second": 39.189,
      "step": 36
    },
    {
      "epoch": 0.04403048264182896,
      "grad_norm": 1.2829879522323608,
      "learning_rate": 7.649596321166024e-05,
      "loss": 43.9071,
      "step": 39
    },
    {
      "epoch": 0.04741744284504657,
      "grad_norm": 1.4857579469680786,
      "learning_rate": 7.191855733945387e-05,
      "loss": 43.8148,
      "step": 42
    },
    {
      "epoch": 0.05080440304826418,
      "grad_norm": 1.1876442432403564,
      "learning_rate": 6.710100716628344e-05,
      "loss": 43.8749,
      "step": 45
    },
    {
      "epoch": 0.05080440304826418,
      "eval_loss": 10.957741737365723,
      "eval_runtime": 4.8157,
      "eval_samples_per_second": 154.911,
      "eval_steps_per_second": 38.832,
      "step": 45
    },
    {
      "epoch": 0.05419136325148179,
      "grad_norm": 1.1559016704559326,
      "learning_rate": 6.209609477998338e-05,
      "loss": 43.9038,
      "step": 48
    },
    {
      "epoch": 0.057578323454699404,
      "grad_norm": 1.2160911560058594,
      "learning_rate": 5.695865504800327e-05,
      "loss": 43.895,
      "step": 51
    },
    {
      "epoch": 0.06096528365791702,
      "grad_norm": 1.068589210510254,
      "learning_rate": 5.174497483512506e-05,
      "loss": 43.795,
      "step": 54
    },
    {
      "epoch": 0.06096528365791702,
      "eval_loss": 10.946942329406738,
      "eval_runtime": 4.8205,
      "eval_samples_per_second": 154.757,
      "eval_steps_per_second": 38.793,
      "step": 54
    },
    {
      "epoch": 0.06435224386113463,
      "grad_norm": 1.0464539527893066,
      "learning_rate": 4.6512176312793736e-05,
      "loss": 43.7855,
      "step": 57
    },
    {
      "epoch": 0.06773920406435224,
      "grad_norm": 1.1093237400054932,
      "learning_rate": 4.131759111665349e-05,
      "loss": 43.7564,
      "step": 60
    },
    {
      "epoch": 0.07112616426756986,
      "grad_norm": 1.0022168159484863,
      "learning_rate": 3.6218132209150045e-05,
      "loss": 43.8452,
      "step": 63
    },
    {
      "epoch": 0.07112616426756986,
      "eval_loss": 10.939535140991211,
      "eval_runtime": 4.8096,
      "eval_samples_per_second": 155.107,
      "eval_steps_per_second": 38.881,
      "step": 63
    },
    {
      "epoch": 0.07451312447078746,
      "grad_norm": 1.0073579549789429,
      "learning_rate": 3.12696703292044e-05,
      "loss": 43.8497,
      "step": 66
    },
    {
      "epoch": 0.07790008467400508,
      "grad_norm": 0.9595133066177368,
      "learning_rate": 2.6526421860705473e-05,
      "loss": 43.7864,
      "step": 69
    },
    {
      "epoch": 0.08128704487722269,
      "grad_norm": 0.95490962266922,
      "learning_rate": 2.2040354826462668e-05,
      "loss": 43.827,
      "step": 72
    },
    {
      "epoch": 0.08128704487722269,
      "eval_loss": 10.936300277709961,
      "eval_runtime": 4.8359,
      "eval_samples_per_second": 154.262,
      "eval_steps_per_second": 38.669,
      "step": 72
    },
    {
      "epoch": 0.0846740050804403,
      "grad_norm": 0.8142202496528625,
      "learning_rate": 1.7860619515673033e-05,
      "loss": 43.7521,
      "step": 75
    },
    {
      "epoch": 0.08806096528365792,
      "grad_norm": 1.1691547632217407,
      "learning_rate": 1.4033009983067452e-05,
      "loss": 43.6878,
      "step": 78
    },
    {
      "epoch": 0.09144792548687553,
      "grad_norm": 0.8926234245300293,
      "learning_rate": 1.0599462319663905e-05,
      "loss": 43.7551,
      "step": 81
    },
    {
      "epoch": 0.09144792548687553,
      "eval_loss": 10.934897422790527,
      "eval_runtime": 4.8264,
      "eval_samples_per_second": 154.567,
      "eval_steps_per_second": 38.745,
      "step": 81
    },
    {
      "epoch": 0.09483488569009314,
      "grad_norm": 1.1671419143676758,
      "learning_rate": 7.597595192178702e-06,
      "loss": 43.788,
      "step": 84
    },
    {
      "epoch": 0.09822184589331075,
      "grad_norm": 0.9878164529800415,
      "learning_rate": 5.060297685041659e-06,
      "loss": 43.8031,
      "step": 87
    },
    {
      "epoch": 0.10160880609652836,
      "grad_norm": 0.9175395965576172,
      "learning_rate": 3.0153689607045845e-06,
      "loss": 43.7536,
      "step": 90
    },
    {
      "epoch": 0.10160880609652836,
      "eval_loss": 10.933818817138672,
      "eval_runtime": 4.9131,
      "eval_samples_per_second": 151.839,
      "eval_steps_per_second": 38.061,
      "step": 90
    },
    {
      "epoch": 0.10499576629974598,
      "grad_norm": 0.8062633275985718,
      "learning_rate": 1.4852136862001764e-06,
      "loss": 43.793,
      "step": 93
    },
    {
      "epoch": 0.10838272650296359,
      "grad_norm": 1.0015171766281128,
      "learning_rate": 4.865965629214819e-07,
      "loss": 43.7244,
      "step": 96
    },
    {
      "epoch": 0.1117696867061812,
      "grad_norm": 1.0298224687576294,
      "learning_rate": 3.04586490452119e-08,
      "loss": 43.7583,
      "step": 99
    },
    {
      "epoch": 0.1117696867061812,
      "eval_loss": 10.933626174926758,
      "eval_runtime": 4.8154,
      "eval_samples_per_second": 154.918,
      "eval_steps_per_second": 38.833,
      "step": 99
    }
  ],
  "logging_steps": 3,
  "max_steps": 100,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 9,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 885239316480.0,
  "train_batch_size": 4,
  "trial_name": null,
  "trial_params": null
}