{
  "best_metric": null,
  "best_model_checkpoint": null,
  "epoch": 0.049714143673875215,
  "eval_steps": 13,
  "global_step": 50,
  "is_hyper_param_search": false,
  "is_local_process_zero": true,
  "is_world_process_zero": true,
  "log_history": [
    {
      "epoch": 0.0009942828734775043,
      "grad_norm": 1.0767807960510254,
      "learning_rate": 5e-06,
      "loss": 1.4767,
      "step": 1
    },
    {
      "epoch": 0.0009942828734775043,
      "eval_loss": 1.4993078708648682,
      "eval_runtime": 34.2272,
      "eval_samples_per_second": 12.388,
      "eval_steps_per_second": 6.194,
      "step": 1
    },
    {
      "epoch": 0.0019885657469550086,
      "grad_norm": 1.241318702697754,
      "learning_rate": 1e-05,
      "loss": 1.2547,
      "step": 2
    },
    {
      "epoch": 0.002982848620432513,
      "grad_norm": 1.0247488021850586,
      "learning_rate": 1.5e-05,
      "loss": 1.2667,
      "step": 3
    },
    {
      "epoch": 0.003977131493910017,
      "grad_norm": 1.1591644287109375,
      "learning_rate": 2e-05,
      "loss": 1.4027,
      "step": 4
    },
    {
      "epoch": 0.004971414367387522,
      "grad_norm": 1.1431999206542969,
      "learning_rate": 2.5e-05,
      "loss": 1.5309,
      "step": 5
    },
    {
      "epoch": 0.005965697240865026,
      "grad_norm": 1.1215442419052124,
      "learning_rate": 3e-05,
      "loss": 1.2735,
      "step": 6
    },
    {
      "epoch": 0.00695998011434253,
      "grad_norm": 1.185957908630371,
      "learning_rate": 3.5e-05,
      "loss": 1.3907,
      "step": 7
    },
    {
      "epoch": 0.007954262987820034,
      "grad_norm": 0.9886231422424316,
      "learning_rate": 4e-05,
      "loss": 1.2722,
      "step": 8
    },
    {
      "epoch": 0.008948545861297539,
      "grad_norm": 1.3221428394317627,
      "learning_rate": 4.5e-05,
      "loss": 1.5192,
      "step": 9
    },
    {
      "epoch": 0.009942828734775044,
      "grad_norm": 1.54436457157135,
      "learning_rate": 5e-05,
      "loss": 1.8312,
      "step": 10
    },
    {
      "epoch": 0.010937111608252548,
      "grad_norm": 1.059188723564148,
      "learning_rate": 4.99229333433282e-05,
      "loss": 1.3039,
      "step": 11
    },
    {
      "epoch": 0.011931394481730051,
      "grad_norm": 1.1226993799209595,
      "learning_rate": 4.9692208514878444e-05,
      "loss": 1.1677,
      "step": 12
    },
    {
      "epoch": 0.012925677355207556,
      "grad_norm": 1.0901505947113037,
      "learning_rate": 4.9309248009941914e-05,
      "loss": 1.2394,
      "step": 13
    },
    {
      "epoch": 0.012925677355207556,
      "eval_loss": 1.2392393350601196,
      "eval_runtime": 34.2682,
      "eval_samples_per_second": 12.373,
      "eval_steps_per_second": 6.186,
      "step": 13
    },
    {
      "epoch": 0.01391996022868506,
      "grad_norm": 0.9254087209701538,
      "learning_rate": 4.877641290737884e-05,
      "loss": 1.7542,
      "step": 14
    },
    {
      "epoch": 0.014914243102162566,
      "grad_norm": 0.6952210068702698,
      "learning_rate": 4.8096988312782174e-05,
      "loss": 1.19,
      "step": 15
    },
    {
      "epoch": 0.01590852597564007,
      "grad_norm": 0.6884624361991882,
      "learning_rate": 4.72751631047092e-05,
      "loss": 1.2885,
      "step": 16
    },
    {
      "epoch": 0.016902808849117573,
      "grad_norm": 0.6651028990745544,
      "learning_rate": 4.6316004108852305e-05,
      "loss": 1.1477,
      "step": 17
    },
    {
      "epoch": 0.017897091722595078,
      "grad_norm": 0.7259565591812134,
      "learning_rate": 4.522542485937369e-05,
      "loss": 1.3021,
      "step": 18
    },
    {
      "epoch": 0.018891374596072583,
      "grad_norm": 0.8364481329917908,
      "learning_rate": 4.401014914000078e-05,
      "loss": 1.3226,
      "step": 19
    },
    {
      "epoch": 0.019885657469550087,
      "grad_norm": 0.6525047421455383,
      "learning_rate": 4.267766952966369e-05,
      "loss": 1.0674,
      "step": 20
    },
    {
      "epoch": 0.020879940343027592,
      "grad_norm": 0.6612785458564758,
      "learning_rate": 4.123620120825459e-05,
      "loss": 1.1099,
      "step": 21
    },
    {
      "epoch": 0.021874223216505097,
      "grad_norm": 0.6104527115821838,
      "learning_rate": 3.969463130731183e-05,
      "loss": 1.1705,
      "step": 22
    },
    {
      "epoch": 0.0228685060899826,
      "grad_norm": 0.6610237956047058,
      "learning_rate": 3.8062464117898724e-05,
      "loss": 1.0519,
      "step": 23
    },
    {
      "epoch": 0.023862788963460103,
      "grad_norm": 0.6938290596008301,
      "learning_rate": 3.634976249348867e-05,
      "loss": 0.9388,
      "step": 24
    },
    {
      "epoch": 0.024857071836937607,
      "grad_norm": 0.6120235919952393,
      "learning_rate": 3.456708580912725e-05,
      "loss": 1.0911,
      "step": 25
    },
    {
      "epoch": 0.025851354710415112,
      "grad_norm": 0.6890453100204468,
      "learning_rate": 3.272542485937369e-05,
      "loss": 0.9741,
      "step": 26
    },
    {
      "epoch": 0.025851354710415112,
      "eval_loss": 1.1278754472732544,
      "eval_runtime": 34.2794,
      "eval_samples_per_second": 12.369,
      "eval_steps_per_second": 6.184,
      "step": 26
    },
    {
      "epoch": 0.026845637583892617,
      "grad_norm": 0.6195194125175476,
      "learning_rate": 3.083613409639764e-05,
      "loss": 1.3244,
      "step": 27
    },
    {
      "epoch": 0.02783992045737012,
      "grad_norm": 0.5792179107666016,
      "learning_rate": 2.8910861626005776e-05,
      "loss": 1.0774,
      "step": 28
    },
    {
      "epoch": 0.028834203330847626,
      "grad_norm": 0.6153373718261719,
      "learning_rate": 2.6961477393196126e-05,
      "loss": 1.4603,
      "step": 29
    },
    {
      "epoch": 0.02982848620432513,
      "grad_norm": 0.5552039742469788,
      "learning_rate": 2.5e-05,
      "loss": 0.9616,
      "step": 30
    },
    {
      "epoch": 0.030822769077802636,
      "grad_norm": 0.6039525270462036,
      "learning_rate": 2.303852260680388e-05,
      "loss": 1.1378,
      "step": 31
    },
    {
      "epoch": 0.03181705195128014,
      "grad_norm": 0.5297777652740479,
      "learning_rate": 2.1089138373994223e-05,
      "loss": 0.9908,
      "step": 32
    },
    {
      "epoch": 0.03281133482475764,
      "grad_norm": 0.6318143606185913,
      "learning_rate": 1.9163865903602374e-05,
      "loss": 1.0829,
      "step": 33
    },
    {
      "epoch": 0.033805617698235146,
      "grad_norm": 0.5691390037536621,
      "learning_rate": 1.7274575140626318e-05,
      "loss": 1.2315,
      "step": 34
    },
    {
      "epoch": 0.03479990057171265,
      "grad_norm": 0.5200899243354797,
      "learning_rate": 1.5432914190872757e-05,
      "loss": 1.0599,
      "step": 35
    },
    {
      "epoch": 0.035794183445190156,
      "grad_norm": 0.4896901249885559,
      "learning_rate": 1.3650237506511331e-05,
      "loss": 1.2254,
      "step": 36
    },
    {
      "epoch": 0.03678846631866766,
      "grad_norm": 0.5189372897148132,
      "learning_rate": 1.1937535882101281e-05,
      "loss": 1.0241,
      "step": 37
    },
    {
      "epoch": 0.037782749192145165,
      "grad_norm": 0.5271244645118713,
      "learning_rate": 1.0305368692688174e-05,
      "loss": 0.9474,
      "step": 38
    },
    {
      "epoch": 0.03877703206562267,
      "grad_norm": 0.5122260451316833,
      "learning_rate": 8.763798791745411e-06,
      "loss": 1.1279,
      "step": 39
    },
    {
      "epoch": 0.03877703206562267,
      "eval_loss": 1.0933287143707275,
      "eval_runtime": 34.2822,
      "eval_samples_per_second": 12.368,
      "eval_steps_per_second": 6.184,
      "step": 39
    },
    {
      "epoch": 0.039771314939100175,
      "grad_norm": 0.5207390785217285,
      "learning_rate": 7.3223304703363135e-06,
      "loss": 0.85,
      "step": 40
    },
    {
      "epoch": 0.04076559781257768,
      "grad_norm": 0.49141305685043335,
      "learning_rate": 5.989850859999227e-06,
      "loss": 0.8256,
      "step": 41
    },
    {
      "epoch": 0.041759880686055184,
      "grad_norm": 0.49803686141967773,
      "learning_rate": 4.7745751406263165e-06,
      "loss": 1.0561,
      "step": 42
    },
    {
      "epoch": 0.04275416355953269,
      "grad_norm": 0.5928795337677002,
      "learning_rate": 3.6839958911476957e-06,
      "loss": 1.0151,
      "step": 43
    },
    {
      "epoch": 0.043748446433010194,
      "grad_norm": 0.4802905023097992,
      "learning_rate": 2.7248368952908053e-06,
      "loss": 0.9441,
      "step": 44
    },
    {
      "epoch": 0.0447427293064877,
      "grad_norm": 0.45927828550338745,
      "learning_rate": 1.9030116872178316e-06,
      "loss": 0.9223,
      "step": 45
    },
    {
      "epoch": 0.0457370121799652,
      "grad_norm": 0.5768618583679199,
      "learning_rate": 1.2235870926211619e-06,
      "loss": 1.1136,
      "step": 46
    },
    {
      "epoch": 0.04673129505344271,
      "grad_norm": 0.6009936332702637,
      "learning_rate": 6.907519900580861e-07,
      "loss": 1.1245,
      "step": 47
    },
    {
      "epoch": 0.047725577926920205,
      "grad_norm": 0.9392962455749512,
      "learning_rate": 3.077914851215585e-07,
      "loss": 1.2505,
      "step": 48
    },
    {
      "epoch": 0.04871986080039771,
      "grad_norm": 0.5324287414550781,
      "learning_rate": 7.706665667180091e-08,
      "loss": 0.8628,
      "step": 49
    },
    {
      "epoch": 0.049714143673875215,
      "grad_norm": 0.4643092751502991,
      "learning_rate": 0.0,
      "loss": 0.9188,
      "step": 50
    }
  ],
  "logging_steps": 1,
  "max_steps": 50,
  "num_input_tokens_seen": 0,
  "num_train_epochs": 1,
  "save_steps": 13,
  "stateful_callbacks": {
    "TrainerControl": {
      "args": {
        "should_epoch_stop": false,
        "should_evaluate": false,
        "should_log": false,
        "should_save": true,
        "should_training_stop": true
      },
      "attributes": {}
    }
  },
  "total_flos": 1.7547965428137984e+16,
  "train_batch_size": 2,
  "trial_name": null,
  "trial_params": null
}